International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme <p>The International Journal of Maritime Engineering (IJME) provides a forum for the reporting and discussion on technical and scientific issues associated with the design and construction of marine vessels. Contributions in the form of papers and notes, together with a discussion on published papers are welcomed.</p> <p>The IJME is published four times a year as the Transactions of The Royal Institution of Naval Architects and is available on subscription to members, and non-members.</p> <p>ISSN: 1479-8751</p> <p> </p> en-US info@unibuckinghampress.com (University of Buckingham Press) Christian.muller@legendtimesgroup.co.uk (Christian Muller) Fri, 13 Nov 2026 18:24:11 +0000 OJS 3.3.0.13 http://blogs.law.harvard.edu/tech/rss 60 Design of Latency-Optimized Task Offloading in Underwater Wireless Sensor Network with Blockchain-Based Energy Trading for 6G Edge Networks https://www.intmaritimeengineering.org/index.php/ijme/article/view/2009 <p>Efficient data transmission in Underwater Wireless Sensor Networks (UWSNs) using the 6G edge communication is vital for battery-operated devices. This paper presents a cooperative transmission strategy using an Unmanned Vehicle to collect sensory data and recharge sensor nodes for data transmission. This study introduces a UWSN with Blockchain-Based Energy Trading and Fairness based Power Allocation (UWBEFP) that combines secure energy management, intelligent routing, and efficient relay selection. The Channel and Energy Consumption Model evaluate communication costs and energy use through acoustic propagation, signal-to-noise analysis, and energy estimation. The Computation Model facilitates distributed processing among sensors, UAVs, and edge clouds, minimizing service latency and computational costs through task segmentation and offloading. A KNN Model enhances sensor classification and clustering, while Euclidean distance clustering improves cluster-head selection and reduces communication energy consumption. A Blockchain-Supported Energy Trading mechanism enables decentralized peer-to-peer energy exchange via smart contracts and Proof-of-Stake validation. A Fairness-Based Power Allocation (FPA) technique performs effective task offloading process to reduce the latency occurrence and balances resource use among relay nodes based on energy costs and levels. An optimized relay selection process enhances communication reliability and network lifetime by reducing transmission power while maintaining the required Bit Error Probability. A D2D Authentication Process ensures secure communication through digital signatures, session-key encryption, and reinforcement learning-assisted routing. The performance analysis is packet delivery ratio, route discovery frequency, routing control overhead, end-to-end average delay, energy efficiency, throughput, and energy consumption. Through this process the communication quality 6G edge network is enhanced which it performs underwater data transmission.</p> N. Mohana Priya, Dr. M. Venkata Pavan Kumar, Thota Balaji, Dr. T. V. Sai Krishna, Dr. P Madhavi, Dr. Masthan Rao Kale Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2009 Fri, 13 Nov 2026 00:00:00 +0000 Optimized Power Flow and Efficient Load Sharing in DC Microgrid Systems https://www.intmaritimeengineering.org/index.php/ijme/article/view/2010 <p>Existing power management strategies for interconnected DC microgrids often face limitations such as poor adaptability to nonlinear dynamics, inefficient handling of renewable intermittency, and slow convergence of optimization-based controllers, which hinder stable bidirectional power sharing and voltage regulation. To address these gaps, this work proposes an Adaptive Neuro-Fuzzy Inference System with Dingo Optimizer (ANFIS-DO) for intelligent power flow management in DC microgrids integrating PV generation, battery energy storage, and a Dual Active Bridge (DAB) converter. The PV subsystem with MPPT and boost converter maximizes energy harvesting under variable irradiance, while the DAB ensures efficient bidirectional transfer and voltage stability. ANFIS models complex nonlinear relationships among inputs such as bus voltage error, power mismatch, PV variation, state of charge, and duty cycle to generate optimized control signals. The Dingo Optimizer fine-tunes ANFIS parameters by mimicking encircling, hunting, and attacking behaviors, thus balancing exploration and exploitation for faster convergence. Simulation results validate that ANFIS-DO achieves minimal tracking errors (RMSE 0.08 kW), balanced grid load sharing (48% vs. 44%), and superior computational efficiency (1.8 s, 65 iterations), consistently outperforming Firefly Algorithm (FFA) and Whale Optimization Algorithm (WOA), thereby establishing its effectiveness in adaptive, stable, and reliable DC microgrid power management.</p> Charivil Sojy Rajan, Mabel Ebenezer Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2010 Fri, 13 Nov 2026 00:00:00 +0000 Pharmachain: Blockchain-Based Framework for Efficient Counterfeit Drug Detection and Recall https://www.intmaritimeengineering.org/index.php/ijme/article/view/2011 <p>This paper has introduced PharmaChain framework, which aims to improve counterfeit drug detection and drug recalls in the pharmaceutical supply chain. The framework leverages Ethereum, smart contracts and Interplanetary File System, to manage drug lifecycle phases manufacturing, quality control, complaint handling, fault testing and return and disposal. Using the Ethereum test network, a real-time implementation of the system is demonstrated with metrics at the various operational stages. From experiments, the throughput and latency of the framework against batch sizes are comparatively tested, and results show the system’s average latency was 0.06 seconds and throughput was 152.5 TPS, when processing a single transaction. At a batch size of 50, the framework was still able to function with an average latency of 1.93 seconds and throughput at 10.1 TPS. The implications of the PharmaChain framework point to its efficacy in improving the pharmaceutical supply chain by providing an immutable and transparent setting with built-in drug recall automation. In addition, this research emphasizes the scalability and adaptability potential of the proposed system without compromising the system-level data privacy and security.</p> Boddu Venkateswarlu, Malaya Dutta Borah, Naresh BabuMuppalaneni Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2011 Fri, 13 Nov 2026 00:00:00 +0000 Design of Sub-Threshold Adders Using Schmitt Trigger Logic for Ultra-Low-Power Applications https://www.intmaritimeengineering.org/index.php/ijme/article/view/2012 <p>Interest in sub-threshold computing has increased due to the growing need for ultra-low-power portabledevices and the spike in need for self-powered or energy-harvesting systems. However, due to their reduced supply voltage, these circuits face challenges, making them susceptible to noise and process variations. Schmitt trigger (ST) logic-based design is an effective strategy to reinforce the reliability of circuits in noisy situations by improving noise margin and lowering leakage current. In this work different adders, such as the Weinberger and Ling adders, can be created using ST logic in subthreshold region and these adders offer less power consumption and delay. These adders utilize parallel architecture which minimizes the overall processing delay and in addition with that the ling adder adopts a Pseudo-carry logic which lessensthe circuit complexity. This reduction in logic stages allows for the fastest computation of the final carry relative to other VLSI adder implementations.</p> Lakshmi Barla, Dr. M. Hema, K. Babulu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2012 Fri, 13 Nov 2026 00:00:00 +0000 Wearable Biosensor Fusion with AI for Continuous Psychological Stress Monitoring https://www.intmaritimeengineering.org/index.php/ijme/article/view/2013 <p>This study’s primary goal is to quantitatively assess how wearable technologiessuch as smartwatches, biosensor wristbands, sports GPS trackers, and electromyographic sensorsaffect key physiological and psychological metrics, including heart rate, Heart Rate Variability (HRV), recovery rate, psychological stress levels, and stress management skills in professional Chinese tennis players. To address these issues a new model is developed Hybrid Multitask Deep Learning for Psychological Stress Detection (HMDL-PSD) model utilizes wearable sensor data to identify stress and emotions. Physiological signals were collected from fifteen subjects using the Empatica E4 wristband and RespiBAN chest belt. The Stress Detection Process involves data preparation, normalization, and deep learning training optimized for edge deployment using TensorFlow Lite.Sliding window techniques extract features from time-domain, frequency-domain, and nonlinear signals. The DL Classification module uses 1D Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM), Transformer, Autoencoder, and Random Forest (RF) to identify temporal and complex patterns.Fusion Mechanisms use rulebased switching, Hidden Markov Model (HMM) fusion, and Online-HMM adaptation for physiological state description, with Bayesian filtering for reliable estimation under uncertainty.Advanced regularization improves generalization, while the Bayesian Uncertainty module evaluates confidence using variational inference and Monte Carlo Dropout (MCD). The Explainability Protocol enhances fairness through counterfactual analysis, meta-gating, and SHAP.Cortisol analysis validates efficacy in detecting stress-related hormonal changes. The experimental result is accuracy, precision, recall, F1-Score, HMDL-PSD calibration error, confusion matrix for stress, HMDL-PSD selective prediction.</p> Dr. B. Ranga Swamy, V. Sunkari, Dr. Masthan Rao Kale, Dr. J V S Arundathi, Dr. Ch. Bhavani, Dr. CM Suvarna Varma, Dr. Sindhe Phani Kumar Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2013 Fri, 13 Nov 2026 00:00:00 +0000 Brand Building Through CSR: A Case Study on Tata Group of Companies https://www.intmaritimeengineering.org/index.php/ijme/article/view/2014 <p>Business is no longer about buying and selling products and services without considering the market it operates. Modern responsible companies are shifting their focus to sustainability by developing a more comprehensive set of working goals than profit alone. CSR is gaining wide acceptance in the global market and is considered an integral tool to win competitors against numerous companies. It has now evolved to a status of the profession with an enormous opportunity to which the world is looking up. Effective CSR helps organizations balance economic, environmental, and social imperatives and build their brand’s image. In addition, it also promotes accountability, and transparency amongst all the stakeholders by meeting their expectations. Being India’s one of the most trusted brands and a visionary leader, Tata focuses on building the nation by supporting the public and not just profit-making. They are also keen on providing the best quality products and having a sound relationship with all the stakeholders. Empathy is the key to their actions, which contributed to their success and huge reputation for years. The group Tata has captured our minds through their consistent efforts and is a great model for several companies to follow. This is what makes them different compared to the rest. The data is collected through primary and secondary sources to get an insight into the various CSR Activities, growth patterns, and their role in Tata’s brand building. The researcher has collected the primary data from 115 responses through a common survey, and secondary data from the financial year 2014–2015 –2022–2023. In addition, the researcher has used Carrol’s Pyramid of CSR, and the stakeholder theory to better understand the concept. Further, the Chi-Square test has been used to analyze the primary data. The graphical representation of the major responses derived from the common survey has also been included for clarity. The acceptance the Tata group has in society makes this paper interesting and their correlation with the CSR activities and societal development by promoting sustainability makes it relevant.</p> Shwetha. A. Kumar, Dr. N. V. Sreedharan Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2014 Fri, 13 Nov 2026 00:00:00 +0000 The Application of AI/ML and IIoT to Predictive Maintenance https://www.intmaritimeengineering.org/index.php/ijme/article/view/2015 <p>Predictive maintenance has emerged as a critical approach to industrial automation, particularly as a part of the Industrial Internet of Things (IIoT) where real-time monitoring and smart analytics are key to reducing downtime and maximizing operational performance. The fault-tolerant predictive maintenance framework of air compressors based on probabilistic Hidden Markov Model (HMM) combined with IIoT-based sensor data is introduced in this paper. In the suggested model, these parameters are critical variables that are monitored to identify any onset of degradation and thus predict possible failures: vibration, temperature, pressure, acoustic signals and motor current. The system identifies the compressor conditions in six operational states (S<sub>0</sub>–S<sub>5</sub>), which makes it possible to dynamically make decisions and plan maintenance activities. The comparative performance examination demonstrates that the suggested HMM model has higher accuracy (96.3%), precision (95.6%), and recall (94.9%) in contrast to conventional approaches, Random Forest (93.1%), and LSTM (95.2%) models. It also gives a better lead time to failure identification (7.8 hours), 22.4 percent downtime reduction, and 18.7 percent maintenance cost savings. The uncertainty quantification and Remaining Useful Life (RUL) estimation are also considered in the model, which can ensure its robustness in face of sensor anomalies. The study proves that the application of machine learning, together with the IIoT infrastructure, enables a significant enhancement of predictive maintenance of industrial air compressor systems in order to ensure a higher level of reliability, a reduction of operational<br />costs, and more intelligent asset management.</p> Satish Naikare, Aparna Bannore Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2015 Fri, 13 Nov 2026 00:00:00 +0000 Stacking-Based Hybrid Deep Learning Framework for Dental Cavity Detection https://www.intmaritimeengineering.org/index.php/ijme/article/view/2016 <p>Dental cavity detection plays a vital role in preventive dentistry and early diagnosis of oral diseases. Manual identification of caries from dental images is often subjective and prone to human error, which necessitates the development of automated and intelligent detection systems. In this work, a hybrid stacking-based framework is proposed that combines deep convolutional features from EfficientNetB0 with handcrafted descriptors such as Histogram of Oriented Gradients (HOG) and color moments. The extracted features are normalized, reduced through Principal Component Analysis (PCA), and classified using a multi-level stacking ensemble integrating XG Boost, Light GBM, Random For-est, and Support Vector Machine (SVM) base learners, with a logistic regression meta-classifier for final decision fusion. The model was evaluated on the publicly available Kaggle Dental Cavity dataset, achieving an Area Under the ROC Curve (AUC) of 0.938 and an Average Precision (AP) score of 0.9287, indicating excellent discriminative performance. Class-wise evaluation demonstrated a high recall of 95% for the cavity class and a precision of 93% for the no-cavity class, reflecting the model’s robustness in minimizing both false negatives and false positives. These results confirm that the proposed hybrid stacking approach effectively leverages complementary feature representations, providing a reliable and clinically meaningful solution for automated dental cavity detection.</p> Gosula Suresh, Maneswar Rahang, J. Suresh Kumar Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2016 Fri, 13 Nov 2026 00:00:00 +0000 Enhanced Early Detection of Thyroid Abnormalities Using a Deep Learning Model: A Sequential CNN Approach https://www.intmaritimeengineering.org/index.php/ijme/article/view/2017 <p>This research emphasizes on development of novel methodology for effective early detection of thyroid abnormalities nodules using machine learning and deep learning methods. Accordingly the proposed system employed a hybrid approach namely a sequential convolutional neural network (SCNN) to automate feature extraction and focus on detecting thyroid abnormalities. Further, advanced sequential model algorithms were employed to distinguish benign from malignant morphology using ultrasound images. The models performance was assessed using ultrasound and CT scan images from a dataset containing grayscale US and CT scan images. The outcomes of experiments on medical images datasets, featuring both diseased and normal thyroids, demonstrated classification and diagnostic accuracy between 95% and 99%, underscoring its significant clinical utility. In addition, this novel procedure yield better precision and sensitivity of 97.4%, and 83.1% respectively witnessing robust classifying images for benign or malignant.</p> Pavithra S, Naveen Kumar J.R Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2017 Fri, 13 Nov 2026 00:00:00 +0000 Lescnnet: A Sequence-Guided Convolutional Framework for High-Accuracy Skin Cancer Recognition https://www.intmaritimeengineering.org/index.php/ijme/article/view/2018 <p>Early and reliable identification of malignant skin lesions remains a central challenge in dermatological practice,<br />particularly when visual differences between benign and cancerous tissues are subtle and evolve over time. While<br />conventional convolutional neural networks have shown promise in dermoscopic image analysis, they often treat each image as an isolated sample, overlooking the progressive and structured nature of lesion appearance. To address this limitation, this study presents LesCNNet, a sequence-guided convolutional framework designed to capture both spatial detail and sequential lesion behavior for improved skin cancer recognition.LesCNNet integrates deep convolutional feature extraction with a sequence modeling mechanism that learns how lesion characteristics change across ordered image representations. Instead of relying solely on static texture and color cues, the proposed architecture encodes the continuity and variation of lesion patterns, enabling more stable and discriminative feature learning. The framework is further enhanced through adaptive feature fusion and optimized training strategies to reduce overfitting and improve generalization across diverse skin types and imaging conditions.The proposed model is evaluated on publicly available dermoscopic datasets widely used in skin cancer research. Extensive experiments demonstrate that LesCNNet consistently outperforms conventional CNN-based classifiers and recent deep learning approaches in terms of accuracy, sensitivity, specificity, and F1-score. The results indicate that incorporating sequence-guided learning significantly improves the model’s ability to distinguish malignant lesions from visually similar benign cases, particularly in early-stage and lowcontrast scenarios.The findings suggest that LesCNNet provides a reliable and clinically meaningful tool for automated skin cancer screening. By combining spatial feature learning with sequence-aware modeling, the proposed framework offers a more realistic representation of lesion characteristics, supporting dermatologists in early diagnosis and reducing<br />the risk of misclassification. This work contributes a robust and scalable deep learning solution that moves automated dermatological analysis closer to real-world clinical deployment.</p> Ramesh Nadagoudar, Dr. Jithendra P R Nayak Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2018 Fri, 13 Nov 2026 00:00:00 +0000 A Cross-Modal Neural Architecture for Real-Time Deepfake Detection to Mitigate Misinformation https://www.intmaritimeengineering.org/index.php/ijme/article/view/2019 <p>Deepfake content is spreading quickly online, making it hard to know what’s real. Because of this, we need strong tools that can detect fake images, audio, and videos. In this study, we created a three-step deep learning system that can check all three types of data. In the first step, we used an EfficientNet model to detect fake images. This model is good at noticing tiny details that reveal if an image is fake. After training it with a Kaggle dataset, it reached an accuracy of 95.56%. The second step focuses on fake audio. We have used CNN model to build it which helps the system understand patterns in sound and related facial features. This model was trained on the DEEP-VOICE dataset and achieved 98.5% accuracy.The third step looks at fake videos. In this model we have combinedEfficientNet with an LSTM and a Random Forest classifier. This model helps in both audio and video frames to reach the accuracy of 95.56%. Finally, we combined all three models into one application that can check images, audio, and video in real time. Overall shows that by using multimodel it helps the deep fake to detect the in all the forms.</p> Mallikarjun Gachchannavar, Naveen Kumar J. R. Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2019 Fri, 13 Nov 2026 00:00:00 +0000 Examination of Organizational Support and Environmental Competition on Transformational Leadership for Intrapreneurial Behaviour for Green Human Resource Management https://www.intmaritimeengineering.org/index.php/ijme/article/view/2020 <p>In the evolving landscape of sustainable organizational practices, Green Human Resource Management (GHRM) has<br />emerged as a strategic mechanism to foster both environmental stewardship and organizational effectiveness. By integrating environmentally oriented HR practices—including green recruitment and selection, green training and development, green performance management, and green reward systems—organizations can cultivate employees’ perceptions of strong organizational support. This study examines the influence of organizational support and environmental competition on transformational leadership and their combined effects on intrapreneurial behaviour, with a particular focus on the role of Green Human Resource Management (GHRM) practices. Grounded in leadership and organizational support theories, the study proposes an integrated conceptual framework in which GHRM enhances perceived organizational support, thereby fostering transformational leadership behaviours that stimulate employee intrapreneurship. A quantitative research design was employed using survey data collected from employees across diverse organizational contexts, and the hypothesized relationships were tested using Structural Equation Modeling (SEM). The measurement model was validated through Confirmatory Factor Analysis, demonstrating strong reliability, convergent validity, and discriminant validity. The structural model exhibited excellent fit indices, confirming the robustness of the proposed architecture. The results indicate that GHRM practices have a strong positive effect on perceived organizational support (β = 0.61, p &lt; 0.001), which significantly enhances transformational leadership behaviours (β = 0.58, p &lt; 0.001). Environmental competition also positively influences transformational leadership (β = 0.46, p &lt; 0.001), highlighting the role of external pressures in shaping leadership styles. Transformational leadership was found to be the strongest predictor of intrapreneurial behaviour (β = 0.63, p &lt; 0.001), while organizational support also exerted a direct positive effect (β = 0.41, p &lt; 0.001). Mediation analysis revealed significant indirect effects of organizational support (β = 0.37, p &lt; 0.001) and environmental competition (β = 0.29, p &lt; 0.001) on intrapreneurial behaviour through transformational leadership. The model explained 38% of the variance in organizational support, 52% in transformational leadership, and 61% in intrapreneurial behaviour, demonstrating substantial explanatory power. Overall, the findings underscore the critical role of integrating GHRM practices with transformational leadership to stimulate intrapreneurial behaviour and achieve sustainable competitive advantage.</p> M Sowjanya, Madireddi SSV Srikumar Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2020 Fri, 13 Nov 2026 00:00:00 +0000 Multi-Modal Emotion Recognition Using Ensemble Deep Learning and DeepNet Model https://www.intmaritimeengineering.org/index.php/ijme/article/view/2021 <p>Human speech signals are a vital source for determining human emotions. Classic datasets of human speech signals can be explored for many applications in healthcare, gaming, and advertisement domains. Emotion recognition using Deep Learning (DL) algorithms can facilitate the assessment of well-informed decision-making. Existing DL algorithms have limitations in their predictive performance as they do not leverage feature engineering in their approach. In this work, we propose a novel DeepNet Base Audio Emotion Recognition Framework to achieve automation in the identification of human emotions by means of supervised learning to enhance predictive performance. Proposed DeepNet incorporates algorithms namely the DeepNet Base Audio Emotion Recognition Framework algorithm to efficiently identify features having discriminative capability and Recognition (DeepNet) algorithm which uses Multi-Layer Perceptron for automatic emotion recognition. DeepNet algorithms are trained on the RAVDESS dataset for empirical study which has a broad collection of distinct natural human emotions such as angry, neutral, disgust, fear, surprise, sad, and happiness. Further, a web-application is designed to recognize human emotion based on the saved DeepNet model. Results from the application suggest that the DeepNet algorithm outperformed standard algorithms such as Bi-LSTM and Ensemble Model-D tested on the same dataset. Bi-LSTM process the data forward and backwards using Bi-directional layers from input to output. Whereas the ensemble models built various assorted base model, but fails to interpret generalization type error, Bi-LSTM achieves an accuracy of 81.53%, while the Ensemble Model-D reaches 85.22%. The performance efficiency of the proposed DeepNet algorithm-based DeepNet model has 88.9% better predictive performance than the conventional<br />existing algorithm.</p> Shaik Abdul Khalandar Basha, Ramesh P S Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2021 Fri, 13 Nov 2026 00:00:00 +0000 A Deep Feature–Based Dynamic Hand Gesture Recognition Framework for Word and Sentence Formation Using Mediapipe https://www.intmaritimeengineering.org/index.php/ijme/article/view/2022 <p>Individuals who are deaf or experience difficulties with hearing and speech predominantly rely on sign language as their medium to communicate, which is not universally comprehended leading to obstacles in achieving effective communication. Advances in deep learning technologies in recent years have enabled the development of systems intended to autonomously interpret gestures in sign language and translate them into spoken language. This paper introduces a system built on deep learning methodologies for recognizing sign language. It uses long short-term memory (LSTM) architecture to distinguish and classify hand gestures which are static and dynamic. The system is divided into three primary components, including dataset collection, neural network assessment, and sign detection component that encompasses hand gesture extraction and sign language classification. The project was divided into two major phases: Static Sign Recognition and Dynamic Sign Recognition. During the static phase, a fully original dataset comprising 120,000 images was created for 24 alphabets (A–Z excluding J and Z). Each image was then treated through two custom-designed filters: silhouette extraction and finger detection, carried out using MediaPipe for precise annotation and cropping on its own. The training of the static model happened with custom-designed CNN applied on the data to achieve accuracies of 94% (finger detection), 89% (silhouette), and 91% (combined). In the dynamic phase, signs with movement were captured using MediaPipe landmarks and registered as NumPy arrays (CSV and .NPY) files. Hand and facial keypoints were stored at every frame for temporal learning. This phase included one-hand, two-hand, and hand-with-face categories. The whole system achieved 15–20 FPS real-time inference on CPU alone. While the static signs and single-handed dynamic signs were performing very well, the accuracy of complex two-handed and face-assisted gestures suffered due to scarcity and noise in the data. The results provide a very good baseline to improve upon for the future using deep temporal networks like LSTM or 3D CNNs.</p> Siddangouda Hosamani, Dr. Jithendra P. R. Nayak Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2022 Fri, 13 Nov 2026 00:00:00 +0000 Institutional and Contingency Perspectives on HR Auditing: Evidence from the Indian It Industry https://www.intmaritimeengineering.org/index.php/ijme/article/view/2023 <p>Human Resource Auditing and Disclosure Systems (HRADS) are increasingly recognized as vital mechanisms for<br />enhancing accountability, compliance, and strategic alignment in organizations. This study investigates the determinants and consequences of HRADS adoption in the Indian IT sector by integrating Institutional Theory and Contingency Theory. Drawing on survey data from 300 respondents across multiple departments, the study employs structural equation modeling to test thirteen hypotheses, supplemented with ANOVA and mediation analyses. The results demonstrate that top management support, HRIS maturity, auditor competence, resource availability, and external forces such as regulatory mandates and client pressures significantly influence HRADS adoption, scope, and impact. Further, certifications, data privacy readiness, and a culture of organizational learning strengthen audit depth and effectiveness. Interaction effects, including remote work intensity and client certification pressures, also exhibit significant influence. ANOVA results reveal notable departmental differences in HRADS adoption (F = 5.92, <em>p</em> &lt; 0.001), underscoring the heterogeneous implementation of audit practices. Mediation analysis confirms that audit scope serves as a critical conduit linking data privacy readiness to organizational impact, validated through bootstrapped indirect effects. Collectively, these findings highlight that HR audits extend beyond internal governance mechanisms, functioning as institutional responses to legitimacy pressures while also serving as contingent tools for aligning strategy with context-specific organizational needs. The study contributes to both theory and practice by providing an integrative perspective on HR auditing, offering implications for regulators, practitioners, and policymakers aiming to strengthen human resource governance in dynamic, compliance-driven environments.</p> Tagore S V K Batta, Dr. Venkateswarlu Chandu, Dr. P. Akthar, Dr. M. Thyagaraju, Dr. K. Pradeep Reddy Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2023 Fri, 13 Nov 2026 00:00:00 +0000 A DevSecOps-Driven Hybrid Reinforcement Learning and Swarm Intelligence for Secured Communication in Unmanned Vehicles to Everything (V2E) Framework https://www.intmaritimeengineering.org/index.php/ijme/article/view/2024 <p>Multi Unmanned Aerial Vehicles (MUAVs) networks, often referred to as Flying Ad Hoc Networks (FANETs), are<br />increasingly employed in applications such as disaster management, surveillance, and precision agriculture due to their flexibility and rapid deployment capabilities. However, the highly dynamic topology, limited energy resources, and vulnerability to security threats pose significant challenges to reliable and secure communication. To address these issues, this paper proposes a DevSecOps-driven hybrid framework that integrates topology-aware Q-learning, deep reinforcement learning, and swarm intelligence for secure and adaptive communication in multi-UAV networks. The proposed framework combines Q-learning-based path selection with Topology-Aware Reinforcement Learning for Decision Making (TARL-DM) to enable intelligent routing and dynamic adaptation to network changes. Additionally, a Swarm Intelligence-based Adaptive Communication (SIAC) module is incorporated to optimize cooperative behavior among UAVs, improving network scalability. To ensure continuous security and system robustness, a DevSecOps framework is integrated, enabling real-time monitoring, threat detection, and secure deployment of updates. The system is modelled using a multi-UAV network model, incorporating realistic mobility patterns, data generation processes, and transmission delay considerations. The proposed hybrid approach enhances communication reliability, reduces latency, and improves adaptability under dynamic network conditions while maintaining strong security guarantees. The performance of the proposed framework was evaluated using key metrics, including mission time, system utility, packet delivery ratio (PDR), end-to-end (E2E) delay, variation with speed, energy consumption, coverage rate, outage probability, and routing overhead, with results presented through comprehensive analytical charts. This work demonstrates that the integration of reinforcement learning, swarm intelligence, and DevSecOps principles provides a scalable and secure solution for nextgeneration UAV communication systems.</p> Dr. B.H.V.V.S.R.K.K. Pavan, Jyothirmai Kanchanapally, A. Sreenivasa Rao, K.N.S.K. Santhosh, Dr. U. Srilakshmi, Papolu Balakrishna Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2024 Fri, 13 Nov 2026 00:00:00 +0000 Secure Data Science Model with Cryptographic Techniques for Cybersecurity Risk Mitigation via Machine Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2025 <p>The rapid expansion of the Industrial Internet of Things (IIoT) has introduced complex cyber security challenges,<br />necessitating intelligent and privacy-preserving intrusion detection solutions. This paper presents an Intelligent Digital Twin-based Federated Learning (IDT-FL) framework that employs probabilistic feature computation and distributed model training for secure and efficient cyber attack detection. The framework incorporates information gain-based probabilistic feature ranking, adaptive local model updates, and global aggregation to enhance detection accuracy while maintaining data locality. Extensive experiments on benchmark datasets—CICIDS2017, N-BaIoT, and ToN_IoT—demonstrate that IDT-FL consistently outperforms conventional Federated Averaging and centralized DNN models. Specifically, IDT-FL achieves an average accuracy of 95.0%, F1-score of 94.9%, and latency as low as 20.1 ms across datasets, with reduced communication overhead (average 32.9 MB) and faster convergence (average 40 rounds). In comparison, traditional federated models report lower accuracy (avg. 91.9%) and higher latency (avg. 25.5 ms). The proposed IDT-FL framework not only ensures high detection precision but also optimizes network efficiency and scalability, making it a viable solution for real-time and distributed cyberattack detection in IIoT-enabled Cyber-Physical Systems.</p> M.S.B. Phridviraj, Radhika Rajoju, Shivakumar Nangunuri, R. Govardhan Reddy, Jamuna Rani K Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2025 Fri, 13 Nov 2026 00:00:00 +0000 Optimization of Visual Identity of Wuyi Mountain Cultural Heritage Brand Based on the Kano Model https://www.intmaritimeengineering.org/index.php/ijme/article/view/2026 <p>As a World Cultural and Natural Heritage site, Wuyishan’s brand visual identity system (VI) plays a crucial role in<br />showcasing its cultural value and attracting tourists. This paper takes user perception as its starting point, and based on the three-level cultural theory model, extracts three dimensions—functional experience, visual foundation, and cultural symbols—to construct an analytical framework. An empirical study is conducted using a questionnaire survey combined with the Kano model. The results reveal the priority of different user needs in VI optimization and verify the applicability and effectiveness of the Kano model in optimizing the VI of cultural heritage brands. Furthermore, this research provides new paths and references for Wuyishan’s cultural dissemination and tourism brand building in the new era. </p> QinQiuli, Shahriman Zainal Abidin, ZhaoXiaoJie, ChenMi, Wang XI Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2026 Fri, 13 Nov 2026 00:00:00 +0000 A Multivariate Statistical Analysis of Environmental Compliance Under IMO Regulations: Integrating Socio-Legal Dynamics in Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2027 <p><strong>Background and Aims</strong>: The implementation of the International Maritime Organisation’s (IMO) <em>IMO 2020 </em>sulfur cap and subsequent regulatory amendments to <em>MARPOL Annexe VI</em> have markedly reshaped environmental compliance behaviour across the global shipping industry, directly influencing air quality and operational practices. <em>IMO 2020</em> reduced the permitted sulfur content in marine fuel from 3.5 % to 0.5 % outside emission control areas, with even stricter limits within designated zones, driving widespread adoption of very low sulfur fuel oil and emission control technologies.<br /><strong>Methodology</strong>: This study develops a <strong>multivariate statistical model</strong> to quantify the determinants of compliance with IMO environmental standards and to evaluate associated socio-legal outcomes across global shipping fleets. Using empirical datasets—such as average fuel sulfur content (falling from ~3.03 % in 2019 to ~0.25 % by 2022) and observed noncompliance rates (5 of 78 ships exceeding the sulfur limit in open ocean measurements)—we apply <em>panel regressions</em> and <em>logistic models</em> to relate compliance levels with operator characteristics (e.g., flag state, vessel age), port state control rigour, and legal enforcement practices.<br /><strong>Findings</strong>: Findings reveal statistically significant correlations between robust enforcement regimes and higher compliance rates, alongside notable socio-legal disparities tied to flag-of-convenience registrations, which are associated with higher incidences of non-compliance.<br /><strong>Novelty and Implication</strong>: The research‘s <strong>novel contribution</strong> lies in its integrated socio-legal–mathematical framework that transcends traditional engineering assessments of emissions, offering policy-relevant insights into <em>how regulatory design and enforcement mechanisms interact with maritime socio-economic structures</em> to influence environmental outcomes. Implications include evidence-based recommendations for strengthening port state control practices, harmonising international compliance monitoring, and aligning maritime law with statistical indicators of environmental performance.</p> Dr. Joydeb Patra, Dr. Itishree Panda, Dr. Sthitadhi Das, Dr. M. I. Khan, Dr. Molay Kumar Ruidas Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2027 Fri, 13 Nov 2026 00:00:00 +0000 Securing Medical WSN: A Comprehensive Approach to Data Transmission in the Healthcare Landscape https://www.intmaritimeengineering.org/index.php/ijme/article/view/2028 <p>The term WSN has been in use in the realms of transdisciplinary research. A novel the concept of a method to collect and store heterogeneous and patient-sensitive medical data is a way to go. medical wireless sensor net. The aim of this paper will be to present a secure transmission approach to the data gathering in the Medical WSN (M-WSN). This is done in three steps. technique: symmetric key generation, discontinuous multi-path transmission and user authentication. The first stage of the system is to install a gateway that would give access to the cloud data servers. The second step is to create the secret keys which make the message random. Data fragmentation and uploading to the server constitutes the third step. The evaluation was done on the basis of opinion that the proposed standard is useful in reducing response time and delay in case of medical information is being posted up and downloaded on the server.</p> Dr. Naresh Kumar Bhagavatham, Dr. B. Malathi, P. V. V. S. D Nagendrudu, M K Prakash, Mohana Prasad M, Sriharsha Vikruthi, Dr. V T Ram Pavan Kumar, T. Kishore Babu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2028 Fri, 13 Nov 2026 00:00:00 +0000 Blockchain Network Slices in 5C C-RAN for Resource Allocation with Optimized Model https://www.intmaritimeengineering.org/index.php/ijme/article/view/2029 <p>C-RAN centralizes the baseband processing functions in data centers, making it possible to achieve greater flexibility<br />and efficiency in the deployment of 5G networks. In C-RAN, network slicing refers to the practice of creating multiple<br />virtual, end-to-end networks within a shared physical infrastructure. These slices are isolated and can be customized with distinct quality of service (QoS), bandwidth, latency, and other parameters tailored to the unique needs of the services they support. Efficient allocation and management of network resources for different slices are complex tasks. Network operators need to ensure that resources like computing, storage, and bandwidth are allocated appropriately to meet the service requirements of each slice. Hence, this paper proposed a novel BOEgRA (Blockchain Optimized Edge Computing Resource Allocation), for the dynamic resource allocation and network slicing in 5G Cloud Radio Access Networks (C-RAN). The proposed BOEgRA model incorporates blockchain technology within the edge computing model of the C-RAN. Additionally, BOEgRA comprises of the Whale Optimized Game theory model to enable efficient and adaptable resource management. Network slicing, which provides customized virtual slices for different service requirements, is seamlessly integrated into the model, facilitating the creation of multiple network slices. The model’s infrastructure components, including Base Stations and Remote Radio Heads, continuously evolve to cater to changing network demands. Security, billing, monitoring, and Quality of Service (QoS) are prioritized. Simulation analysis stated that the BOEgRA model serves as an innovative and adaptable solution for network slicing and resource allocation in the dynamic 5G C-RAN environment.</p> Praveena Vaddiboina, Dr. Babburu Kiran Mai, Dr. Ramarakula Madhu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2029 Fri, 13 Nov 2026 00:00:00 +0000 The Role of Artificial Intelligence in Reshaping Consumer Behavior and Market Dynamics in the Digital Economy https://www.intmaritimeengineering.org/index.php/ijme/article/view/2030 <p>Artificial Intelligence (AI) is a transformative technology in the digital economy, enabling businesses to analyze consumer behavior and enhance marketing strategies. The primary drawbacks of these social media platforms are lower data quality and a lack of advanced analytics to meet end users’ requirements. For that purpose, this article develops a novel computational model to analyze digital marketing trends using Machine Learning (ML) and Deep Learning (DL) techniques. The proposed methodology begins with a computational data model for efficient data collection and preprocessing steps, including sentiment labeling, geospatial analysis, ground-truth validation, and data augmentation. A hybrid classification approach is employed, integrating traditional ML models such as Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and Multi-layer Perceptron (MLP) with deep learning models, including a CNN-LSTM architecture and the DeepNAO framework. The hybrid design enables effective extraction and improves classification accuracy. The model simulation, Pythsimulation, and the analysis parameters (including loss, accuracy, and precision) for both calculation models. Among the considered models, the DeepNAO model performs best in terms of accuracy and precision, offering optimized strategies for the competitive digital product market.</p> Anfeng Liu, Yongchao Wu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2030 Fri, 13 Nov 2026 00:00:00 +0000 UPQC Intelligent Adaptive Optimization Model for the Reactive Power Compensation https://www.intmaritimeengineering.org/index.php/ijme/article/view/2031 <p>This paper presents a proposed Intelligent Optimized Second-Order Unified Power Quality Conditioner (IO-SO-UPQC) for reactive power compensation, voltage regulation, and harmonic mitigation in modern distribution networks. The system integrates a hierarchical control structure comprising an inner second-order derivative-based UPQC control layer, a fuzzy adaptive layer for dynamic gain adjustment, and a global optimization layer using Second-Order Sea-Gull Optimization (SO-SGO) for real-time tuning of controller gains. The series and shunt converters work synergistically to compensate voltage sags, swells, and reactive power variations, while the fuzzy logic layer adjusts the proportional, integral, and derivative gains based on instantaneous error and its rate of change. Simulation results under linear, nonlinear, unbalanced, and sudden load variations show that the proposed IO-SO-UPQC reduces reactive power error from 0.45 kVAR to 0.12 kVAR, voltage deviation from 2% to 0.5%, and total harmonic distortion (THD) from 4.5% to 1.8%, while improving settling time from 35 ms to 15 ms. These results demonstrate superior transient response and robust real-time power quality improvement compared to conventional PI-controlled UPQCs.</p> G. Sujatha , S. Venkata Padmavathi Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2031 Fri, 13 Nov 2026 00:00:00 +0000 Transformer-Based Object Detection with Privacy-Preserving Federated Learning and Collaborative Edge Computing https://www.intmaritimeengineering.org/index.php/ijme/article/view/2032 <p>This research introduces a pioneering hybrid framework designed to address the dual challenges of data privacy and<br />resource-limited deployment in Transformer-based object detection systems. The proposed system leverages the<br />combined strengths of Federated Learning (FL) for decentralized, privacy-preserving training and Collaborative Edge<br />Computing for efficient distributed inference. By applying this framework to three leading object detection models—<br />DETR, RT-DETR, and Faster R-CNN—we perform an exhaustive evaluation, demonstrating that our approach delivers<br />a notable trade-off between performance, privacy, and scalability. Our results show 286 mAP for DETR, 380 mAP for<br />Faster R-CNN, and 546 mAP for RT-DETR on COCO validation sets, while simultaneously achieving 95.3% reduction<br />in communication overhead relative to centralized training. Notably, Strong Differential Privacy (ε = 1.0) offers 90%<br />privacy protection at the cost of only a 3% accuracy drop. The framework is scalable up to 10 distributed clients,<br />ensuring robust privacy-preserving performance in real-world settings. Additionally, our approach offers superior<br />fault tolerance through component-level decomposition in inference pipelines, which facilitates continuous operation despite partial system failures. The scalable hybrid architecture is detailed through a three-layer design comprising a Coordination Layer, Collaboration Layer, and Edge Layer, fostering a seamless integration of FL and edge computing for diverse object detection applications. This work makes significant contributions to the privacy and efficiency of AI systems, with practical implications for industries dealing with sensitive data. Our framework provides a blueprint for deploying high-performance object detection models in privacy-sensitive, resource-constrained environments, marking a significant step towards distributed, privacy-aware AI systems that combine cutting-edge performance with real-world deployability.</p> Sukumar Babu Bandarupalli, Dr. V. Suryanarayana Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2032 Fri, 13 Nov 2026 00:00:00 +0000 A Hybrid Feature Extraction and Machine Learning Framework for Multiclass Medical Image Classification https://www.intmaritimeengineering.org/index.php/ijme/article/view/2033 <p>In this paper, we present a systematic hybrid handcrafted feature extraction framework for medical image classification based on the integration of frequency-domain, statistical, texture and distribution-based descriptors in a single architecture. First, grayscale images are preprocessed to fixed resolution 128 × 128 pixels and normalized in the range [0, 1]. A two-dimensional DCT is subsequently employed to obtain frequency-domain coefficients that are vectorized and decomposed based on Benford’s law in order to encapsulate statistical characteristics found within the frequency plane. Simultaneously, compact global intensity and texture characteristics are obtained by first-order statistical features, Local Binary Pattern (LBP) descriptors, Gray-Level Co-occurrence Matrix (GLCM) features and normalized intensity histograms. Andrews curve embedding is applied to the Benford, statistical, LBP, and GLCM descriptors to represent higher-order feature interactions. All extracted descriptors are then stacked together as a compact feature vector, which is processed using feature-scaling and mutual-information based-feature selection techniques. An Extreme Gradient Boosting (XGBoost) model then classifies the resulting representation. A representation produced using an Extreme Gradient Boosting (XGBoost) model is then used to classify the exposure. The introduced approach provides an effective, simple to interpret and discriminative representation that can be directly used for accurate disease classification from medical images by designing image representations leveraging intermodal complementary image attributes. Experimental results demonstrated that the proposed multiclass COVID–Normal–Pneumonia chest X-ray classification framework achieved 93.74% accuracy, 96.07% macro precision, 86.40% macro sensitivity, 98.83% macro specificity, and 90.51% macro F1-score on COVID-19 Radiography Database. Comparative analysis confirmed competitive performance with improved specificity and reliable multiclass disease discrimination capability.</p> Attili Venkata Ramana, Kalli Srinivasa Nageswara Prasad, P. Swetha, Peram Prashanthi, V. Sravan Kiran Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2033 Fri, 13 Nov 2026 00:00:00 +0000 Leveraging Artificial Intelligence to Enhance Efficiency and Decision-Making in the Digital Economy https://www.intmaritimeengineering.org/index.php/ijme/article/view/2034 <p>Artificial Intelligence (AI) is increasingly used in the digital economy to enhance company intelligence, customer<br />engagement, operational efficiency, and decision-making. Here, a novel model, namely Intelligent Multiple Social<br />Network-based Media Analytics with Sentiment Analysis and Susceptible–Infected Model (ITMSSI), is developed. At<br />the initial stage, the proposed model processes businesstransaction records, consumer interaction data, enterprise digital transformation indicators, and digital platform activities, which are examples of digital economy datasets collected and preprocessed. Latent Dirichlet Allocation (LDA) is used in AI-based topic modeling to find emerging market opportunities, consumer preferences, and business trends. Kernel Density Estimation (KDE) and Standard Deviational Ellipse (SDE) are used to assess data distribution and market activity trends. A Digital Economy Utilization Index (DEUI) is formulated to quantify the effectiveness of the digital economy. To predict the growth of the digital economy and facilitate wise decision-making, an AI-based predictive modeling framework is utilized. The simulation is performed in the Python tool, and the analysis is calculated for network models such as the Twitch social network, the ego-gplus network, the GitHub social network, and the large Twitch network, as well as the sentimental score. This analysis shows the improvement of the proposed ITMSSI model compared with earlier models, such as AICSM, ASGHM, and SIMID.</p> Zhaokai Chen, Yongchao Wu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2034 Fri, 13 Nov 2026 00:00:00 +0000 Factors Influencing Consumers’ Behavioural Intention and Their Actual Behaviour in Buying Jewellery Online: An Explorative Study https://www.intmaritimeengineering.org/index.php/ijme/article/view/2035 <p>The rapid growth of e-commerce has transformed consumer buying behavior, particularly in the jewellery market, where online shopping is becoming increasingly popular. This study investigates the factors influencing consumers’ behavioral intention and actual behavior in purchasing jewellery online. Using perceived usefulness (PU) and perceived ease of use (PEOU) as key determinants, the study examines how these factors shape consumer attitudes, which in turn affect behavioral intention and actual purchase behavior. The results from hypothesis testing show that perceived usefulness significantly influences attitude (β = 0.521, p &lt; 0.001), perceived ease of use significantly influences attitude (β = 0.475, p &lt; 0.001) and perceived usefulness (β = 0.589, p &lt; 0.001), and attitude strongly impacts behavioral intention (β = 0.642, p &lt; 0.001), which in turn positively affects actual buying behavior (β = 0.598, p &lt; 0.001). These findings highlight the importance of designing online jewellery platforms that are easy to use, functionally beneficial, and trustworthy to enhance consumer engagement and increase purchases. The study contributes to the literature on online consumer behavior and provides practical guidance for e-commerce managers in the digital jewellery sector.</p> Ram Kiran K, Dr Sunil Kumar M S Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2035 Fri, 13 Nov 2026 00:00:00 +0000 Multi-Scale ODE-Based Continuous Feature Extraction for Retinal Disease Classification Using Fundus Images https://www.intmaritimeengineering.org/index.php/ijme/article/view/2036 <p>The automated diagnosis of retinal diseases from fundus images has attracted a lot of attention due to the increasing prevalence of vision-threatening ocular disorders and shortcomings associated with manual clinical screening. However, multiclass classification of retinal diseases is inherently difficult due to inter-class similarities, changing illumination conditions, low-contrast structures in the retina and computationally expedient models are preferred. In this paper, a new deep learning framework is proposed to classify multiclass retinal diseases based on fundus images. In order to enhance the ability in effectively resulting a desired output for retinal feature representation, this research presents a method that integrates multi-scale feature extraction with an ODE-based learning strategy. The framework automatically learns hierarchical retinal representations from raw fundus images using CNN and multi-scale ODE modules, thereby avoiding hand-crafted feature engineering and enabling end-to-end disease classification. Experiments are performed on the publicly available Eye Disease Image Dataset which consists of images related to multiple categories of retinal diseases. Various preprocessing, data augmentation and feature scaling techniques were incorporated in the pipeline to ensure robustness and generalization. The proposed framework was developed and evaluated for the classification of 10 retinal disease categories using retinal fundus images from the Eye Disease Image Dataset (EDID). The proposed ODE based approach successfully classifies multi-class retinal disease, and the experimental results confirm its performance. Under this framework, ODE-driven feature evolution is used to gradually update the representation of the retinal image by modeling how edges, textures, shapes and pathological patterns in fundus images change over time. The method achieved a classification accuracy of 86.40% and macro precision, sensitivity, F1-score, specificity and balanced accuracy were measured as 87.92%, 88.62%, 88.24%, 98.41% and 88.61%, respectively. Furthermore, three levels of visualization analysis are provided, including ODE feature vector visualization, ODE overlay and Grad-CAM interpretability analysis, and suspicious region localization. The visualizations corroborate that the proposed method achieves a balance of separation of discriminative pathological features while maintaining interpretability, accuracy and accurate localization making it applicable for robust retinal disease diagnosis.</p> <p> </p> Sandhya Kanoujia, P. Karuppanan Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2036 Fri, 13 Nov 2026 00:00:00 +0000 Deep Learning Prediction and Optimization for Management of Cloud-Based Services in Enterprises https://www.intmaritimeengineering.org/index.php/ijme/article/view/2037 <p>Cloud-based services in enterprises refer to the use of remote servers hosted on the internet to store, manage, and process data, rather than relying on local servers or personal computers. Enterprise Cooperation Projects (SECPs) play a vital role in bridging the gap between academic theory and practical industry applications, fostering meaningful collaborations between educational institutions and businesses. This paper proposes a novel approach to enhance the prediction and optimization of SECPs using the Particle SeaHorse Optimization Decision Tree (PSODT) algorithm. The PSODT algorithm combines the adaptive optimization capabilities of Particle Swarm Optimization (PSO) with the decision-making power of Decision Trees to effectively classify project outcomes and predict performance indicators. Through a series of experiments and analyses, we evaluate the algorithm’s classification accuracy, precision, recall, and computational efficiency. The results demonstrate that the PSODT algorithm achieves high accuracy in predicting project outcomes, with precision, recall, and F1 score values consistently exceeding 96%. Specifically, the accuracy ranges from 96.8% to 97.5%, precision from 96.8% to 97.8%, recall from 96.5% to 97.5%, and F1 score from 96.8% to 97.5%. Furthermore, the algorithm balances predictive accuracy with computational efficiency, with computational times ranging from 120 to 150 seconds across experiments.</p> Dr. K. S. R. M. Elia Thagaram, Dr. J. S. V. Gopala Sarma, Dr. P. Akthar, Dr. Venkateswarlu Chandu, Dr. K. Pradeep Reddy, Dr. Krati Kulshrestha, Ankam Dhilli Babu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2037 Fri, 13 Nov 2026 00:00:00 +0000 Artificial Intelligence–Driven Decision Support Systems for Enhancing Sustainable Crop Productivity https://www.intmaritimeengineering.org/index.php/ijme/article/view/2038 <p>Climate variability, pressure on available resources and increasing demands on food further erode efficacious agricultural systems that require intelligent and adaptive decision-making systems. Artificial intelligence (AI) has become an offering with potential to complement all types of information to integrate into actionable insights (data-driven agricultural management). In this research, empirical research and analytical modeling are applied to discuss the importance of AI-driven decision support systems (DSS) in enhancing the sustainable crop productivity. The study utilizes multi-season field observations, agro- meteorolog data, soil health metrics, remote sensing data, and management records of farmers in the variety of agro-climatic regions. The machine learning models were used to assist with the key farming decisions in terms of forecasting yields, when to irrigate, identifying pests and diseases, and optimization of nutrients. The traditional standard statistical measures of accuracy were to determine model performance, whereas the sustainability performance was measured in terms of the stability of yields, water-use efficiency, and input optimization measures. The findings indicate that AI-powered DSS are associated with a high level of accuracy in decision-making in comparison to traditional methods of advisory, which results in better performance of crops, less wastage of resources, and environmental stress reduction. The results also indicate that the situational calibration, the trustworthiness of the data and the participation of farmers are significant parameters determining whether the systems will work or not. This work can add to the existing literature on AI-based decision frameworks and on the agronomic and sustainability advantages of AI-supported frameworks by empirically showing these benefits. The study highlights the future of AI-based DSS as a strategic mechanism of promoting resilient, resource-efficient, and sustainable agricultural production systems.</p> Dr. S. , Dr. T. Kamaleshwar, Dr. D. Rajalakshmi, T. Karthikeyan, Jayaraj R Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2038 Fri, 13 Nov 2026 00:00:00 +0000 Hyb_MDM-QCNN: Construction of Hybrid Multiscale Dilated MobileNet and Quantum-Inspired Convolutional Neural Network Architecture for Brain Tumor Classification Form MRI Images https://www.intmaritimeengineering.org/index.php/ijme/article/view/2061 <p>Brain tumors’ heterogeneous histology and unpredictable clinical course make them a major healthcare concern. They range from slow-growing benign tumors to aggressive malignancies in sensitive anatomical regions. The pathophysiology of these conditions must be well defined for customized therapy. AI methods for brain tumor segmentation and detection are commonly utilized for segmentation and detection, but the lack of generalizable results precludes medical practitioners from adopting them for diagnosis. Magnetic Resonance Imaging dominates research, although Positron Emission Tomography and Computed Tomography lack open-access datasets.This research introduces a unique hybrid architecture that combines Multiscale Dilated MobileNet with a Quantum-inspired Convolutional Neural Network (Hyb_MDMQCNN) to improve spatial and contextual feature extraction while maintaining model efficiency. Many experiments on Br35H and kaggle brain tumor MRI datasets.</p> Subhashini K, Dr. J. Thangakumar Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2061 Fri, 13 Nov 2026 00:00:00 +0000 A Novel Deep Learning Approach for Tropical Cyclone Path Prediction Based on LSTM-BiLSTM https://www.intmaritimeengineering.org/index.php/ijme/article/view/2062 <p>Under global climate change, the frequency of typhoons and their strong wind, heavy rain, and storm surge increase, seriously threatening the life and property of human society. However, traditional tropical cyclone track prediction methods have difficulties in processing large amounts of complex data in terms of prediction efficiency and accuracy. Recently, deep learning methods have shown a potential capability to process complex data efficiently and accurately. In this paper, we propose a novel data-driven approach based on combination of Long Short Term Memory + Bidirectional Long short Term Memory (LSTM-BiLSTM) models to forecast tropical cyclone landing locations using the historical tropical cyclone tracks and various meteorological attributes. The features obtained from Finite Volume Method (FVM) is given to LSTM-BiLSTM. It is noted that FVM is integrated with a three-dimensional conservation of energy paradigm showcasing its effectiveness in capturing vital atmospheric and oceanic interactions. The model is trained on a real-world tropical cyclone dataset from the years 2007–2017. Through a comparison with existing forecasting methods, the results verified that our proposed model performed around 97% of accuracy, 93% of precision, 98% of recall, 2.66 e<sup>–2</sup> of error with 190.9 seconds of elapsed time for testing.</p> S. Karthikeyan, M. Kannan Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2062 Fri, 13 Nov 2026 00:00:00 +0000 GIC-Net: AI-Driven Green IoT-CAN Bus Networks for Sustainable Energy Management with Optimization and Data Compression https://www.intmaritimeengineering.org/index.php/ijme/article/view/2063 <p>The rapid expansion of Internet of Things (IoT) applications has significantly increased energy consumption and network complexity, so that it becomes very essential for the development of efficient and sustainable communication. This paper proposes GIC-Net, an Artificial Intelligence (AI)-driven Green IoT-CAN Bus network designed for sustainable energy management through intelligent optimization and data compression techniques. The proposed framework integrates a Green IoT network model with dynamic cluster-based architecture with cluster head selection, cluster member management, and sleep scheduling to enhance energy efficiency. Additionally, an IoT-CAN Bus communication layer is developed to enable reliable, low-latency data transmission, supported by optimized data collection and compression mechanisms to reduce bandwidth and storage overhead.To further improve system performance, AI-driven optimization algorithms are employed for adaptive decision-making, while a comprehensive energy model is formulated to evaluate energy consumption, residual energy, and system lifetime. The proposed approach is validated through extensive simulations, considering key performance metrics such as cluster head selection efficiency, number of alive nodes, energy consumption, delay, packet delivery ratio, and total system energy.</p> Thirumavalavasethurayar P., Dr. T. Ravi Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2063 Fri, 13 Nov 2026 00:00:00 +0000 A Design for Digital Twin Based IDS System Using Split Learning Predictive Maintenance in Internet of Things Related Smart Manufacturing Systems https://www.intmaritimeengineering.org/index.php/ijme/article/view/2064 <p>The Internet of Industrial Things (IIoTs) is rapidly transforming our environments and services, but its security<br />vulnerabilities are increasingly apparent. Device identification is crucial for protection, and implementing appropriate security measures is essential as IoT devices grow in smart cities. These vulnerabilities pose risks to urban system integrity. To address this challenge, a novel model known as the Digital Twin in IDS Using Split Learning Predictive Maintenance in IoT in Smart Manufacturing (DISLIS) model detects cyberattacks in IIoT environments using the WUSTL-IIoT-2021 dataset, which includes over a million recordings from a SCADA testbed. An Effective Feature Selection Process (EFSP) for dimensionality reduction and combines baseline and advanced models, including a Dummy Classifier, Logistic Regression, and a deep learning architecture with dropout regularization, to ensure consistent classification performance. The Improved Cyberattack Detection Process (ICDP) employs a multi-layer probabilistic model based on Restricted Boltzmann Machines to enhance detection probability and learn complex data distributions. An enhanced Dung Beetle Optimization technique fine-tunes hyperparameters for optimal accuracy. A digital Twin model is developed to provide effective predictive maintenance for the IoT environment. The anomaly detection module utilizes XGBoost, Support Vector Machines (SVM), and Deep Convolutional Neural Networks (D-CNN) for effective classification. The Random-Access Channel (RAC) study evaluates network access in 5G-enabled IIoT systems, analyzing success and collision probabilities for reliable communication. The experimental analysis is dummy classifier, XGBoost, SVM, DCNN of confusion matrix’s, DISLIS accuracy, DISLIS loss calculations.</p> Dr. P. Shanmuga Sundari, Dr. Rekha Gangula, Hemalatha P, Dr. P. K. Venkateswar Lal, A. Sreenivasa Rao, Dr. Putta Brundavani Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2064 Fri, 13 Nov 2026 00:00:00 +0000 A Hybrid SHAP and Hotelling’s T²-Based Feature Selection Framework for Deep Learning-Based DDoS Intrusion Detection https://www.intmaritimeengineering.org/index.php/ijme/article/view/2065 <p>As cyberattacks are increasing in today’s digital world, especially Distributed Denial of Service attacks, securing network resources has become crucial for both individuals and network administrators. Here comes the need for a reliable and trusted Intrusion Detection System, which plays a significant role in determining and detecting threats by monitoring network traffic and alerting the network administrator. Therefore, we have designed and evaluated a deep learning-based IDS that focuses on DDoS network attacks using a popular dataset. This CICDDoS2019 dataset contains a wide range of network traffic patterns. To strengthen the model’s performance, we have used the Shapley method for feature selection along with the Hotelling T<sup>2</sup> test to choose the top contributing set of features, which contribute the most in deciding whether there is an attack or not. The feature selection method reduced the original 87 features to the 21 most predictive attributes. After selecting the features, we used a dense multilayer perceptron (MLP) — a deep learning model well-known for recognising complex data patterns. The model was trained and tested on the optimal dataset to differentiate benign and DDoS network attacks. The model performance is evaluated using metrics like accuracy, recall, precision, balanced accuracy, and F1-score. The results show that combining Shapley with the Dense MLP model achieved 99.75±0.020% accuracy with consistently high precision (99.72±0.037%), recall (99.78±0.012%), and ROC-AUC (&gt;0.995) across datasets on three independent runs. The proposed framework also demonstrated highly accurate detection of DDoS attacks, maintaining a low false-positive rate while effectively distinguishing malicious traffic from legitimate network activities. This study shows the impact of meaningful feature selection in enhancing the predictive capability of deep learning models for intrusion detection. The results demonstrate that integrating meaningful feature selection with deep learning strengthens IDS performance offers a practical, interpretable, and computationally efficient solution for real-time DDoS detection.</p> V. Radhakrishna, A. Sreenivasa Rao, R Eswar Sai Singh, V. Sravan Kiran Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2065 Fri, 13 Nov 2026 00:00:00 +0000 Adaptive Hidden Probability Edge Reliable Normalization for Deception Detection in the EEG Signal https://www.intmaritimeengineering.org/index.php/ijme/article/view/2066 <p>Lie detection applications are used in security, forensic and psychological assessments. Electroencephalography. An<br />EEG can measure other brain activities. Using misleading actions. This researches contribution is the adaptive hidden. Probability Reliable Normalisation Deep Learning. EEG-based Deception Detection with Hidden. Probability according channel weighting, probability reliable normalisation and heterogeneous. The AHPR-NDL can capture both. There are spatio-temporal and between-downscape-drinking interactions keyed into misleading. Thinking Processes. Also, the interchannel weights which are jointly learnt, reliable. Interactions are tuned by normalisation and diverse propagations. The approach is capable of online learning. We Required. To demonstrate the generalisation ability and stability of AHPR-NDL method, we use two widely accepted datasets: the EEG records of Concealed information test (CIT) and competitive EEG record. And reflect decentralised as well as more naturalistic learning and deceptions components accordingly. Numerous experiments show the proposal’s The model outperforms conventional processes regular. There’s a statistical significance between learning and deep learning. By improving interaction between various components of the model and, therefore maximizing the informative structure and topological integral information existing in EEG data AHPR-NDL achieves 96.2% and 94.1% accuracy on CIT EEG and EEG that maximises precision, recall and f1-s. A temporal decay analysis for a few epochs of training confirmed that AHPR-NDL gradually converges to the best accuracy, striking a balance between learning and generalisation. The study further compared the performance of AHPR-NDL with the performance of baselines models, including RF + KNN, SVM, Bi-GRU, CIT-LieDetect CNN, and CNN-GA, which outperformed each of the baselines in terms of accuracy, specificity and AUC scores in controlled.</p> Revoori Swetha, Damodar Reddy Edla Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2066 Fri, 13 Nov 2026 00:00:00 +0000 Beyond CNNS: A Multi- Scale Spectral-Structural Feature Extraction Approach for Interpretable Chest X-Ray Classification https://www.intmaritimeengineering.org/index.php/ijme/article/view/2067 <p>Medical image classification, especially the analysis of chest X-ray images, is a complex issue due to high intra-class<br />variability, low contrast areas, and subtle pathological features. Although convolutional neural networks (CNNs) achieve state-of-the-art performance, they require large amounts of labeled data, have limitations such as high computational cost and low interpretability. To overcome these limitations, we have proposed a multi-scale matrix-based feature extraction framework in this paper. The proposed approach generates a hierarchical multi-resolution matrix representation by 2 × 2 average pooling, which can have various scales from 512 × 512 to 8 × 8. At each scale, you get features like matrix rank, log determinant, trace, and log-scale eigenvalues. These features comprehensively reflect the structural and spectral properties of the image. The features obtained at all scales are combined into a feature vector of size 1101 for grayscale or 3303 for RGB images. This feature vector is given as input to a dense multi-layer perceptron (MLP) classifier which learns the nonlinear decision boundaries and provides an accurate classification. The proposed method significantly reduces the computational complexity while eliminating the need for convolution-based feature learning. The experiment results demonstrate that this approach shows good generalization ability even in low data conditions. This research contributes to the development of hierarchical matrix-based feature extraction method, utilization of spectral eigen features and design of a low-resource, and efficient classification framework.</p> V. Sravan Kiran, Annaluri Sreenivasa Rao, V. Radhakrishna, Attili Venkata Ramana Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2067 Fri, 13 Nov 2026 00:00:00 +0000 Spatial Temporal Cross Modality Deep Learning for Multi-Electrode EEG-Based Epilepsy Detection https://www.intmaritimeengineering.org/index.php/ijme/article/view/2068 <p>The broad spectrum of neurobiological disorders caused by abnormal electrical activity in brain results in recurrent seizures called as epilepsy. Early prediction of seizure onset is crucial, as it provides a vital time window for timely intervention and treatment. In our previous work, we introduced a multimodality framework for epileptic seizure detection using EEG features. Though it improved the accuracy, it could not reduce the seizure detection onset time. This is due to ineffectiveness in learning correlation between the EEG signals collected from multiple electrodes. The earlier work considered cross modality only from feature representation view. It did not use the multi electrode signal correlation for seizure detection. To solve this problem, this work proposes spatial temporal cross modality learning to capture local and long range interactions between EEG signals across multiple electrodes. Graph neural network is used to learn cross modality features from multiple electrodes. The features are then classified by optimized Long Short-Term Memory (LSTM) network. Optimization of hyperparameter is achieved with a variant of elephant heard optimization (V-EHO) algorithm.</p> Kumbam Venkat Reddy, A.Viji Amutha Mary Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2068 Fri, 13 Nov 2026 00:00:00 +0000 Graph Neural Network–Enhanced Smart Education Management for Dynamic Student Trajectory Prediction https://www.intmaritimeengineering.org/index.php/ijme/article/view/2069 <p>Interest in Behaviour (IoB) and AI in students’ education is growing in both industries and academia. Tools for e-learning can aid student learning, with the need for stronger assessment procedures for fairness. Chatbots could enhance education, but lack of user acceptance studies poses a challenge. To takles this, a new model has introduced DHGSIT model combines Deep Learning (DL), Graph Neural Networks (GNN), the Internet of Behaviors (IoB), and the TOPSIS decision-making methodology to support smart education management through adaptive learning analytics and intelligent decision-making which is mainly developed to predict the student’s performance. Label and one-hot encoding as well as the Interquartile Range (IQR) normalization approach to reduce noise and improve model reliability were used in the model. The IoB framework converts educational behavioural data into information at five levels of the hierarchy so that the student’s talent and behaviour on various fields can get analysed. Besides, the model makes use of explainable Artificial Intelligence (XAI) to study the patterns of learners’ behavior and performance that, in turn, can be used to make the most appropriate educational recommendations. The YOLOv7 system uses EMA technique to improve behavioural recognition to reduce localization errors in object detection. DT and LSTMs combine machine learning and DL for sequence analysis. TOPSIS ranks alternatives using weighted performance and distance metrics. The GNN module represents educational entities and relationships, updating node embeddings with attention-based message passing for spatial and temporal dependencies. The experimental analysis is conducted in python and the parameters used for the analysis are accuracy, loss, predicted<br />and observed of GNN, precision, recall, and F1-Score.</p> RuoMeng LI Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2069 Fri, 13 Nov 2026 00:00:00 +0000 Big Data Analytics and Its Impact on Risk Management in Financial Investments https://www.intmaritimeengineering.org/index.php/ijme/article/view/2070 <p>Today, the growth of technology and staying ahead of competitors heavily rely on Financial Information Systems (FIS) and Big Data Analytics (BDA). Increasingly, big data is being used to extract valuable insights from large datasets. In sectors such as e-commerce, data analytics tools improve product recommendations and operational efficiency. Internet businesses often turn to Flink to efficiently manage their vast data centers. This study examines the technological revolution through the IBMQSD framework, distributed computing, and deep learning methods for detailed financial analyses such as stock market forecasting and risk management. It starts with data cleaning and standardization, then uses domain-specific analysis to extract key features related to transportation, HR analytics, and energy trends. Regression Modeling uses tools like the Phillips-Perron test for financial behavior analysis. The Deep Learning Model uses Long Short-Term Memory (LSTM) and Conventional Neural Network (CNN) for financial risk prediction, while Econometric Modeling analyzes investment-risk relationships for proactive risk mitigation and portfolio optimization. The High-Resolution Imaging Process applies complex algorithms for imaging, and Big Data Processing Platforms, such as Hadoop and Swift, enable fast, secure data management. Data integrity is maintained through reliable storage solutions with the latest encryption features. The result indicates accuracy, loss, data speed and write, resource utilization, precision, recall, and F1-score.</p> Baogang Fei, Enying Zhang Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2070 Fri, 13 Nov 2026 00:00:00 +0000 Power Optimized and Reliable Modified Edge Preserving Architecture for Noise Aware Preprocessing Applications https://www.intmaritimeengineering.org/index.php/ijme/article/view/2071 <p>The rising use of System-on-Chip (SoC) technology in the fields of embedded vision, surveillance, biomedical imaging<br />and portable electronic devices has produced a growing demand for high performance and low power image preprocessing systems. Random-valued impulse noise is one of the many variables that degrades images and severely degrades the quality of the collected binary image data, which badly affects future image analysis and processing operations. This work proposes an efficient SoC based architecture to remove the random valued impulse noise from the collected binary data in order to overcome this problem. The decision-tree-based detector to detect the noisy values and employs an effective design to locate the edge is proposed in this design. Decision tree based hybrid integrated de-noising method (DTHIDM) is used as proposed methodology for this project to implement efficient de-noising process. If there are noisy values, edges, or blocks in this region, the distribution of the values is different. Therefore, we determine whether current pixel is an Seclusion point by observing the smoothness of its surrounding pixels. The noise may seriously affect the performance of image processing techniques. Hence, an efficient denoising technique becomes a very important issue in data processing.</p> Y B Shabber Hussain, Dr Poornima G Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2071 Fri, 13 Nov 2026 00:00:00 +0000 Quantum-Resistant Intrusion Detection Using Multi-Agent Reinforcement Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2072 <p>The rising cyber threat complexity heightens the need for advanced Intrusion Detection Systems (IDSs) capable of swiftly identifying familiar and new attack methods, highlighting an urgent concern. Feature selection, by diminishing input features, boosting detection accuracy, and cutting computational time, significantly enhances machine learning-based IDS performance. To tackle these issues a model has developed QIDSMR caters to 6G-enabled Internet of Things (IoT), tackling quantum-attackers and network variations. A multi-slice 6G architecture with NEUROSAFE-6G, encompassing layers for security adaptability. The Threat Model addresses cryptographic vulnerabilities, integrity breaches, and diverse attacks from classical and quantum adversaries. IoT-Quantum Key Distribution (QKD) customizes key generation based on device capabilities and security needs. Quantum entropy and anomaly scores enhance detection in Q-IDS. Quantum Evolutionary Algorithms (QEA) utilizes probabilistic qubit encoding and gate adaptation for diversity. Integration of quantum entropy variations and anomaly scores improve detection efficiency. Energy-efficient interferometry aids intrusion detection. Hyperparameter optimization involves Convolutional Neural Network (CNN) classifiers and Quantum Particle Swarm Optimization (QPSO). A QCNN hybrid with variational quantum circuits detects complex attacks. Multi-Agent Reinforcement Learning strengthens detection methods. DSAC focuses on scalable deployment with energy-aware optimization and collaborative learning. The simulation parameters are detection accuracy, response time, attack detection delay, overhead, false positive rate, and communication overhead.</p> Dr. Dileep Kumar Padidem, Dr. B. Abdul Raheem, Dr. G. Nithya, Dr. Putta Brundavani, G. Sujatha, Mogiligundla Kondaiah Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2072 Fri, 13 Nov 2026 00:00:00 +0000 Artificial Intelligence-Driven Energy Management in Grid Energy Storage Systems: Design and Performance Evaluation https://www.intmaritimeengineering.org/index.php/ijme/article/view/2073 <p>Grid energy storage systems are a trending technology, attracting researchers due to their significant market and need. An update is essential for this technology, as it has several drawbacks, such as improper charging, high cost, resource limitations, and weak grid stability. To overcome these drawbacks, this study presents a Solar PV system with grid stability (SPGSEV) model. This model integrates core modules, such as mobility and charging systems, charging stations, and a solar-powered photovoltaic system with battery storage and PV modules. The grid stability management system is developed to achieve effective resource utilization and, with the Multi-Objective Remora Optimization Algorithm (MOROA), to support proper decision-making and charge scheduling. The overall framework is implemented in MATLAB, and the parameters measured for result analysis include Electricity Price, Voltage, PVs Capacity, PVs Output Power, Power Loss, Voltage Magnitude, and Stay Time. The results are also compared with earlier models such as EMEVC, OEPSM, and EVESS. The outcome proves the stability of the proposed model by attaining lower loss and high PV output power, which leads to maximum energy utilization and grid stability for the energy storage systems.</p> Shunfeng Jiao, Tianyong Zhong, Jie Pan, Weijie Gao, Yanyu Liang, Xin Xu Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2073 Fri, 13 Nov 2026 00:00:00 +0000 Enhanced Multibiometric Authentication Using Deep Feature Extraction and Optimized Feature-Score Level Fusion of Gait and Fingerprint https://www.intmaritimeengineering.org/index.php/ijme/article/view/2074 <p>Biometric authentication systems have been a cornerstone of secure identity authentication in civilian and defense<br />applications. Among all the modalities, fingerprint and gait recognition are widely used because they are unique, nonintrusive, and anti-spoofing. However, unimodal systems are plagued by limitations like susceptibility to noise, intra-class variation, and spoofing attacks. This paper introduces a robust multibiometric authentication system that incorporates both feature-level fusion and score-level fusion of gait and fingerprint features. Feature level fusion is based on deep learning models—specifically, 3D CNNs and ResNet50—to acquire discriminative, rich representations from input data. The experimental evaluation on benchmark databases—CASIA-B and OUISIR for gait, and FVC2004 and LivDet2017 for fingerprints achieved 97.3% recognition rate, lowering Equal Error Rate (EER) to 2.1%, outperforming traditional fusion techniques. An optimized hybrid fusion of biometric characteristics, powered by deep learning and adaptive optimization, can significantly enhance authentication security and performance.</p> Mayank Shekhar, Ripon Patgiri, Amit Kumar Trivedi Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2074 Fri, 13 Nov 2026 00:00:00 +0000 Prediction Modeling and Optimization of Power Grid Energy Storage System Based on Machine Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2075 <p>The rise of renewable energy, like solar panels and wind turbines, stems from price hikes and emissions rules. Weather affects energy production from solar farms. The power operations like pneumatic transports. Challenges with grid capacity arise from renewables’ growth. The power market shifts from government control to deregulation. Regulations affect energy expenses, efficiency, and environmental impact benefits. To address this issue, the authors propose a technical solution that allows the EPGCCS system combines Deep Reinforcement Learning (DRL) with solar photovoltaic (PV), battery storage, and grid management to enhance pneumatic transport plant efficiency. It involves designing the plant, simulating processes, optimizing mathematically, developing control systems, initializing renewable energy sources, and optimizing scheduling through DRL. The plant integrates PV modules, inverters, a battery system, grid connection, and an air transport system for energy-efficient material handling. Simulation involves random arrivals and airflow calculations using the Hudson formula. The PV system uses performance mappings and cloud forecasting, while battery management employs a flexible state-of-charge estimation method. A model combining Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Model Predictive Control (MPC) was created to optimize costs under set constraints. Enhancements like Priority Experience Replay (PER), adaptive noise exploration, and improved Adadelta optimization methods were added to enhance convergence rate, scheduling, and computational efficiency for automated day-ahead scheduling and real-time operational efficacy.</p> Shunfeng Jiao, Chuyun She, Guoxing Wu, Jie Zhang, Na Qiao Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2075 Fri, 13 Nov 2026 00:00:00 +0000 A Novel Multiple Music Recognition Technique Based on Deep Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2076 <p>Multiple Music Recognition is an attractive technology were most of the researches are concentrating on recent times. The introduction and Deep Learning (DL) and Artificial Intelligence (AI) technology created lots of new opportunities in this area. The primary drawbacks which are currently present in this technology are reaching maximum accuracy is the creation of multiple music. To overcome that drawback in this article a new model is developed namely, CNN and SelfSupervised Learning with BoYaTCN (CNSSBO) model which is the combination of the model like Convolutional Neural Networks (CNN) and self-supervised learning with the BoYaTCN model. Primarily, it begins with dataset preparation and preprocessing, which includes Mel-spectrogram generation, data processing and augmentation, noise injection, pre-training, and fine-tuning stages to enhance data quality. The CNSSBO model integrates CNN architectures, YAMNet for sound detection, an MLP-CNN model, and the BoYaTCN model to effectively capture the audio signals. Additionally, loss function analysis is incorporated to optimize model performance. The simulation is implemented in Python, and the effectiveness of the CNSSBO model is evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The results demonstrate the capability of the hybrid framework in improving music recognition performance.</p> Juanjuan Shi, Dongxia Li Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2076 Fri, 13 Nov 2026 00:00:00 +0000 A Design for Talent Cultivation of Students Through Integrated Deep Learning with Hybrid Optimal Attention Model in Edge-Cloud-IoT Environment https://www.intmaritimeengineering.org/index.php/ijme/article/view/2077 <p>Student talent enhancement is highly concentrated in today’s educational system. Students are getting distracted by several activities, and their concentration is out of education. Therefore an effective model is needed to enhance to students’ talent by performance several activities on daily basis to them. To address this issue, a new model created the integrated DL model with Hybrid Optimal Attention in Edge-Cloud network (IDHOEC) framework units several cutting-edge technologies to detect the student talent. To achieve these, Edge-Cloud-IoT systems equipped with Raspberry Pi and Arduino sensors are used for managing data in real-time. The cloud setup is in charge of image storage, handling databases, and displaying information through LXD containerized services. Student monitoring is done through YOLO-based object detection. A bio-inspired approach not only increases the effectiveness of the model but also makes its decisions more understandable. The use of a Bayesian-optimized LSTM (BO-LSTM) model leads to better student performance prediction. Capsule Network (CapsNet) and dynamic routing help preserve spatial relationships when features are being represented. Deep Neural Network (DNN) are capable of learning nonlinear mappings and after that, they are optimized using gradient descent. A Modified Aquila Optimization (MAO)-optimized attention-based CapsNet enhances feature extraction and accuracy.</p> Xiaoli Zhang, Zhouyi Lai Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2077 Fri, 13 Nov 2026 00:00:00 +0000 A Design of Intelligent Autonomous Mining with Dynamic Time Warping Through Deep Learning for End-to-End Industrial Internet of Things Application https://www.intmaritimeengineering.org/index.php/ijme/article/view/2078 <p>Industrial Internet of Things (IIoT) environment is tremendously developed in recent times which needs improvement in terms of Autonomous Mining. For that purpose, in this article Intelligent Autonomous Mining with Dynamic Time Warping through Deep Learning (IADTDL) is developed. The architecture of the model consists of core modules, including system model construction, dataset details, IIoT architecture, hybrid feature extraction, semantic segmentation process, modeling approach and selection, deep learning classification, equipment description, and input data source integration. The proposed model is implemented and simulated using Python. Performance evaluation is carried out using key metrics such as accuracy, loss, precision, recall, F1-score, and ROC curve. The results are compared with existing baseline models, including STRCA, DIMLF, and UDMCP. Experimental findings demonstrate that the proposed IADTDL model achieves superior performance across all evaluation metrics, which greatly helps to enhance the suitability for intelligent autonomous mining in IIoT applications.</p> Dr. N. Satyavathi, Dr. K. Prakash, Dr. N. Prasad, Dr. Shekhar Katukoori, Dr. Chikati Aravind Kumar, A. Anitha, P. Vemulamma Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2078 Fri, 13 Nov 2026 00:00:00 +0000 Development of Sensory Graph-Modeled Data Analysis Through Process Mining Techniques with Markovian Geometric Diffusion for Healthcare Application https://www.intmaritimeengineering.org/index.php/ijme/article/view/2079 <p>In the healthcare application, data analysis and mining techniques plays an effective role in handling huge data. Still<br />attaining maximum accuracy is a challenging task in the area which is still under a open research. This paper presents the development of a Sensory Graph-Modeled Data Analysis framework using Process Mining Techniques with Markovian Geometric Diffusion (SGPMMG) for healthcare applications. The proposed model aims to enhance the performance of healthcare systems by effectively utilizing sensor-generated data for accurate prediction. The architecture of SGPMMG consists of key modules, including dataset acquisition and preprocessing, effective mining with evaluation, sensory graphbased data analysis, crash report extraction, and Markovian geometric diffusion. The model is implemented and evaluated through simulation in Python. For comparative analysis, existing models such as ADMGD, MRMIS, and IPMSW are considered. The performance of the proposed approach is assessed using multiple evaluation metrics, including execution time, compression ratio, accuracy, precision, recall, and F1-score. The results demonstrate that the SGPMMG model achieves superior performance which results in computational efficiency and higher prediction accuracy.</p> Dr. E. Balakrishna, Dr. N. Satyavathi, Dr. K. Rajeshkanna, Dr. Swathi Bolugoddu, Dr. K. Rekhadevi, Dr. M. Sukesh, Gopu. Vijayalaxmi Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2079 Fri, 13 Nov 2026 00:00:00 +0000 A Design of Multimodal Sarcasm Detection Integrating Multi-View Interactive Model and Dual-Branch mBERT with LSTM Model https://www.intmaritimeengineering.org/index.php/ijme/article/view/2080 <p>Multimodal Sarcasm Detection integration enhances cross-modal alignment by assigning importance weights and<br />promoting interactions among textual, visual, and knowledge-based features.Combining GEN from HuffPost, The Onion, and Sarcasm Corpus V2 helped us accurately represent both formal and sarcastic ways of speaking. To tackle this problem a new novel has developed the MSDMDL model, using DenseNet-121 to extract image features and BERT for text and knowledge representation, thus enabling a deeper semantic encoding across different types of data. The Multi-View Interaction Module aligns text, image, and knowledge features through attention mechanisms for better cross-modal interactions. The Fusion Module enhances features and applies multi-scale convolution to not only detect fine details but also overall patterns, therefore improving multimodal understanding. The Feature Integration Module refines fused features through the use of fully connected layers, normalization, and dropout, ultimately resulting in a better ability to generalize and robustness. Besides, the LSTM Module is responsible for learning the order and dependencies within text data. In the meantime, an attention mechanism is used to assign weights to different words based on their importance for identifying sarcasm. The Dual-Branch mBERT Module derives additional semantic information through supervised attention and cross-lingual learning, thus increasing its capability to work across different languages and domains. The performance analysis is accuracy, loss, precision, f1-score, recall, and ROC curve.</p> Dr. Thanveer Jahan, Dr. E. Balakrishna, Dr. Latha Panjala, Dr. Swetha Arra, Dr. Nagunuri Rajender, Dr. K. Rajashekar, Dr. Salim Amirali Jiwani, Dr. Salim Amirali Jiwani Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2080 Fri, 13 Nov 2026 00:00:00 +0000 A Multilayer Hierarchical Adaptive Volt-Var Control for Voltage Regulation and Reactive Power Coordination in Distributed PV Inverters https://www.intmaritimeengineering.org/index.php/ijme/article/view/2081 <p>The rapid proliferation of Distributed Energy Resources (DERs), particularly grid-connected photovoltaic (PV) systems, has significantly altered the operational characteristics of modern distribution networks. While DERs contribute to reducing greenhouse gas emissions and enhancing energy resilience, they simultaneously introduce challenges such as voltage rise, reactive power imbalance, and bidirectional power flow and Conventional voltage regulation relies on passive or slowacting devices such as On-Load Tap Changers (OLTCs), shunt capacitors, and voltage regulators. This paper proposes aAdaptive Volt–VAR Control with Hierarchical Coordination (AVVC–HCS) framework that combines local autonomy with supervisory optimization and it employs voltage–VAR sensitivities, dynamic trust-region updates, and learning-based adaptation to ensure fast response, fairness, and global voltage regulation. The proposed approach is simulated on IEEE 33-bus and IEEE 69-bus radial distribution systems using a MATLAB–OpenDSS co-simulation platform in achieving voltage regulation, reactive power coordination, loss reduction, fast dynamic recovery, and fair inverter participation under varying PV penetration levels.</p> Kakumani Ratna Jyothy, Ch. Padmanabha Raju, R. Srinivasa Rao Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2081 Fri, 13 Nov 2026 00:00:00 +0000 Next-Gen Immunotherapy Optimization Using Deep Molecular Interaction Networks https://www.intmaritimeengineering.org/index.php/ijme/article/view/2082 <p>Improving lung cancer immunotherapy necessitates better biomarker identification, predictive modeling, and treatment analysis, with challenges in T cell expansion from reagents and contamination. Prognostic evaluations depend on cancer cell arrangement, tumor-infiltrating lymphocytes, and gene alterations. To address this, issue a new technique is developed the Lung Cancer Immunotherapy Optimization Through Integrated Molecular Interaction (LCIOIM) model by utilizing multimodal data, including clinical, genomic, radiographic, and immunological data, from 1, 435 NSCLC patients treated during 2010 to 2025. The Patient Feature Encoder (PFE) employs multi-layer perceptron networks to correlate transcriptome and pathway data with unique signatures. The Immune Evasion vs. Neoantigen Silencing Module uses a tumor dynamics model to assess immunotherapy resistance. The Immunotherapy Sensitivity Calculation (ISC) estimates treatment effectiveness based on Tumor Mutational Burden (TMB), immune checkpoint activity, HLA expression, markers of immunogenic cell death, and mRNA vaccine responsiveness. Mamdani and Sugeno systems enable transparent clinical decision-making. The Image and Data Analysis module assesses tumor cell proliferation and morphology through geometric modeling. The Classification Process employs ensemble methods and SVM classifiers, optimized with MobileNetV3-Small feature vectors. A Hierarchical Multi-Scale Transformer (HMT) learns semantic representations across scales. Additionally, a Semi-Supervised Adversarial Learning Mechanism improves biomarker prediction using labeled and unlabeled data. The Multi-Objective Loss Function Framework integrates focal classification loss, modality-specific learning loss, and cosine alignment loss for effective feature fusion and reliable predictions.</p> Dr. B. Ranga Swamy, Dr. Nidamanuri Srinu, Sreelalitha Talluri, Dr. Sanaboina Leela Krishna, Dr. T. V. Sai Krishna, Dr. Sriharsha Vikruthi, Dr. Ayyappa Chakravarthi M., Dr. Masthan Rao Kale Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2082 Fri, 13 Nov 2026 00:00:00 +0000 Detection of Rice Blast Disease Using DCNN and Vision Transformer Model with PSO-Lemon-OVT-NetX Architecture Based Effective Attention Fusion https://www.intmaritimeengineering.org/index.php/ijme/article/view/2083 <p>Rice blast disease is one among the major threats which directly affects the production of rice in global manner. In<br />order to maximize the yield several methods are developed in recent times but still it needs improvement in terms of<br />detection accuracy. For that purpose, in this article a hybrid model is developed with the combination of the models like Deep Convolutional Neural Networks (DCNN), Vision Transformer (ViT), and an optimized feature selection strategy using a PSO-Lemon-OVT-NetX architecture. Initially, image data are acquired from the tilleringstage samples using single push-broom hyperspectral camera. Followed by that data leakage is prevented using effective preprocessing which performed certain activities such as normalization, resizing and Principal Component Analysis (PCA). Then the DCNN model is employed to perform initial feature extraction and classification process to avoid the vanishing gradient problem. To enhance feature representation, an effective attention fusion is introduced which is the combination of multiscale detection heads and attention modules. The extracted features are further refined using the proposed PSO-Lemon-OVT-NetX architecture, which combines Particle Swarm Optimization (PSO) with an improved optimization strategy. Subsequently, a Vision Transformer (ViT) model is utilized for final classification and as well the Modified Grey Wolf Optimization algorithm is integrated to fine-tune the model parameters. Experimentation is performed in Python and the parameters which are calculated for the performance analysis are loss, accuracy, F1-Score, precision and recall. Overall, this proposed model provides an effective solution to increase the crop yield by attaining maximum accuracy in the early detection of rice disease.</p> Dr. Thanveer Jahan, Dr. K. Prakash, Dr. E. Balakrishna, Dr. Latha Panjala, Dr. Swetha Arra, Dr. Nagunurirajender, Dr. K. Rajashekar, Dr. Salim Amirali Jiwani Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2083 Fri, 13 Nov 2026 00:00:00 +0000 Explainable Vision Transformers for Early Crop Disease Localization in Smart Farming https://www.intmaritimeengineering.org/index.php/ijme/article/view/2084 <p>Early detection and localization of crop diseases are critical for improving agricultural productivity and ensuring food<br />security. This study introduces a novel Centroid Entropy Localization Explainable Vision Transformer (CEL-EViT)<br />framework designed for accurate and interpretable identification of plant diseases in smart farming applications. The proposed approach integrates the classification capabilities of Vision Transformers (ViTs) with a Centroid Entropy Localization (CEL) module, which highlights disease-affected regions, providing explainable visual insights alongside predictions. The model divides input leaf images into patches, extracts deep feature representations, and employs attention-based mechanisms to capture subtle disease patterns. The CEL module computes entropy-weighted centroids to precisely localize diseased areas, enabling both high accuracy and interpretability. Experiments conducted on multiple crops—including tomato, mango, papaya, and maize—demonstrate that CEL-EViT significantly outperforms baseline models such as CNN, ResNet50, and hybrid ViT-CNN. The proposed model achieves an average classification accuracy of 96.6%, Intersection over Union (IoU) of 87.9%, and explainability score of 87.1%, along with high localization consistency and minimal centroid distance errors. These results confirm that CEL-EViT effectively identifies early disease symptoms while providing reliable visual explanations for the affected regions. The framework offers a scalable and practical solution for deployment in real-time precision agriculture systems, including drones and edge devices, facilitating timely interventions, reducing crop losses, and supporting sustainable farming practices. Overall, the proposed method demonstrates the potential of combining deep learning and explainable attention mechanisms for robust, interpretable, and early crop disease management.</p> Swapna Saturi, B. Vijaya Sri, Dr. K. Durga Prasad, Naga Bhavani Chakka, Dr. Kotte Vinay Kumar, Kasetti Silpa Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2084 Fri, 13 Nov 2026 00:00:00 +0000 Hyperspectral Imaging Model for High-Speed Chemometric Analysis in Industrial Applications https://www.intmaritimeengineering.org/index.php/ijme/article/view/2085 <p>Hyperspectral imaging (HSI) has become an effective instrument of the rapid, non-destructive chemometric analysis<br />in manufacturing. In this paper proposed FejérKorovkin Probabilistic Component Analysis Classification (PCF-PC) is<br />combined with deep learning to classify materials quickly and correctly. The PCF-PC method incorporates FejerKorokin filtering for the processing of the hyperspectral images. Based on the estimated features, Probabilistic Component analysis is performed for the estimation of the features. With the estimated features, deep learning-based classification is performed for the classification of the industrial materials with the hyperspectral images. The approach is a hybrid between FK smoothing to remove noise, probabilistic extraction of latent features to learn spectral variations and 1D Convolutional Neural networks (CNN) to learn features through a hierarchical approach, and therefore effectively classification of complex hyperspectral data. The framework was tested using the SWIR plastic waste dataset whereby it had overall accuracy of 97.7% and average F1-score of 97.4% and outperformed the traditional PCA, probabilistic PCA, SVM, and standalone deep learner methods. The hybrid model also showed effective processing, and it took less than 5 seconds per hyperspectral cube, which is appropriate to real-time industrial use. The findings indicate the usefulness of probabilistic component analysis with deep learning in high-dimensional hyperspectral data and offers a scalable and accurate solution that is computationally efficient, which can be used in industrial chemometric analyses: plastic sorting, quality control, and environmental monitoring.</p> Dr. Shiramshetty Gouthami, Dr. Jose Mary Golamari, A. Sreenivasa Rao, Dr. P. Rajeshwari, Dr. Md. Mazharunnisa, Dannuri Mounika Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2085 Fri, 13 Nov 2026 00:00:00 +0000 Detecting and Preventing Sinkhole and Wormhole Attacks in RPL Network Layer of IoT Networks Using Hybrid Machine Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2086 <p>This study proposes a hybrid machine learning and trust-based framework to identify and prevent sinkhole and wormhole attacks in the Routing Protocol for Low-Power and Lossy Networks (RPL) at the network layer of Internet of Things (IoT) deployments. With the increasing number of IoT devices in Low Power and Lossy Networks (LLNs), RPL will be subjected to attacks that compromise network reliability, integrity, and its performance. The research challenge is to develop a lightweight, scalable security mechanism capable of identifying multiple attack types while minimizing energy consumption and computational overload. To address this challenge, this paper proposed an anomaly detection that combines network traffic patterns and node behavior to identify sinkhole and wormhole attacks in the network. While existing works performed single attack detection either by using Machine Learning (ML) or Trust model (TM), this work integrates both ML to analyze traffic patterns and TM to analyze node behavioral patterns for multiple attack detection. This hybrid approach outperforms existing detection techniques by achieving (&gt;98%) accuracy in five hundred node RPL networks with minimal energy consumption of (≤0.59 mJ per node). The combined approach minimizes the false positive rate and thereby enhances the packet delivery ratio; it also paved the way for future extension of multiple attack detection schemes in RPL networks.</p> Brindhadevi J, Dr. Devarajan K. Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2086 Fri, 13 Nov 2026 00:00:00 +0000 A Data-Driven Framework for Analysing the Digital Transformation of Global Music Culture Using Deep Learning and Cultural Analytics https://www.intmaritimeengineering.org/index.php/ijme/article/view/2087 <p>Recent developments in the realm of digital music platforms along with advancements in data-driven analyses have had a drastic effect on the way music has been produced, distributed and consumed. Consequently, some new paradigms for global music culture have emerged. Despite the growing popularity of data-driven analytics in studying various transformations in the area, previous researches are limited to isolated prediction models and analyses of specific music platforms. As a result, there is currently no generalised framework that would incorporate both temporal evolution and feature-level interactions within the context of digital transformation of music culture. Hence, the purpose of this study is to develop a general framework that would enable data-driven analysis of digital transformation in global music culture. For the purpose of this experiment, a dataset Spotify Global Music Dataset was used. This experiment uses a hybrid approach that involves Bidirectional Long Short-Term Memory and Deep Neural Network for temporal and feature-level learning respectively. At the same time, cultural affinity analysis based on similarity measurements was employed. The results of the experiment show that the developed model demonstrates 0.962 accuracy, 0.974 precision, 0.964 recall, 0.969 F1-Score, and 0.962 ROC-AUC respectively, thus proving its effectiveness and stability.</p> Juanjuan Shi, Dongxia Li Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2087 Fri, 13 Nov 2026 00:00:00 +0000 Design Methodology for Thermal Protection Intelligent Power-Aware LDO Using ETP and PTAT https://www.intmaritimeengineering.org/index.php/ijme/article/view/2088 <p>With modern electronic devices should be able to yield stable voltage and current over a variety of environments. Designed LDO regulator castoff in the electronic device is a system that requires numerous voltages and load currents. This paper presents a comprehensive study on the optimization of Low Dropout Voltage Regulators (LDOs) with Excess Thermal Protection (ETP) using an intelligent method. The aim was to improve output voltage stability, efficiency, and thermal management under various operating conditions. The initial output voltage was 5V, and after optimization, it increased to 5.02V, with voltage stability improving from ±0.01V to ±0.02V. The proposed model significantly decreases the power dissipation from 7W to 6.5W, with significant LDO efficiency from 71.4% to 98.5%. The optimization process involved 100 iterations with a convergence time of 2 seconds, achieving an output voltage of 3.501V, and the proposed model reduced the dissipation of power by 6.8W. LDO efficiency improved to 98.5% after optimization, and thermal protection was triggered at 70°C. Peak temperature rise reduced from 30°C to 25°C in traditional optimization and from 30°C to 26°C in optimization. The proposed optimization model achieved 98.5% simulation accuracy, with a temperature recovery time of 2.5 seconds, compared to 4 seconds before optimization. These results demonstrate the successful application of optimization techniques in enhancing the performance of LDOs, providing improved voltage regulation, thermal stability, and efficiency, which can be crucial for modern electronics requiring robust power management.</p> Y. Avanija, K. Suresh Reddy Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2088 Fri, 13 Nov 2026 00:00:00 +0000 PCA-Based Feature Optimization for Motor Imagery EEG Classification Using Machine Learning Models https://www.intmaritimeengineering.org/index.php/ijme/article/view/2089 <p>A fundamental component of Brain–Computer Interface (BCI) systems is Motor imagery (MI)-based electroencephalogram (EEG) signal categorization. However, inter-subject variability and high dimensionality frequently restrict its performance. This paper proposes a thorough machine learning (ML) framework for categorization using a recently collected dataset that hasn’t been thoroughly examined in previous research. In order to improve MI-EEG signal recognition, this paper introduces a hybrid ML approach that combines feature standardization, dimensionality reduction using Principal Component Analysis (PCA), and multi-model classification. To improve discriminative power and cut down on redundancy, the collected features are first normalized and condensed to a compact representation using PCA. A stratified train–test split is then used to train and assess several supervised learning algorithms, including Naïve Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), K-Nearest Neighbors (KNN), Gradient Boosting (GB), Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (XGBoost). According to experimental data, NB performs the lowest (52.70%), whereas Logistic Regression has the best average classification accuracy of 85.91%, followed by SVM (79.16%) and RF (77.68%). Ensemble and boosting techniques like LightGBM (75.37%), and XGBoost (75.06%) yield competitive results, demonstrating their subject-matter resilience. The results show that PCA greatly improves classification efficiency without sacrificing high accuracy. All things considered, the suggested architecture provides a dependable and scalable MI-EEG classification solution and has potential for BCI applications in real time.</p> Gouthami Velakanti, Shameedha Begum B Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2089 Fri, 13 Nov 2026 00:00:00 +0000 A Design of an Effective Banking Application with Customer Churn Prediction and Enhanced Market Equilibrium Based Security Testing Through Machine Learning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2090 <p>Banking application and compliance with the EU PSD2 directive and the impact of protection motivation theory on<br />information security. It identifies a gap in PMT literature and examines factors influencing consumer adoption of Fintech banking amidst ongoing digitalization. To overcome this issue, a new model has developed Customer Churn Prediction and Enhanced Market Equilibrium based Security Testing (CCMEST). This investigation proposes that integrating analytical modeling, market analysis, security validation, hypothesis testing, and machine learning will enhance banking applications through a model that factors in labor, capital, management, and effort using a Cobb-Douglas production function to assess firm value-added and managerial incentives and Cumulative distribution function (CDF). Companies will be evaluated on capital, management talent, and their effectiveness in achieving market equilibrium while assessing compensation and value-added. Security Testing involved 19 tests on banking API operations, focusing on secure communication, authentication, transaction fetching, and unauthorized request rejection. Hypothesis Testing evaluated statistical correlations using t-statistics, p-values, and PLS-SEM, with significant results determined by pre-set thresholds. Machine Learning Models applied UMAP for dimensionality reduction, followed by DBSCAN and K-means clustering, favoring K-means for its superior silhouette coefficient of 0.5225 compared to DBSCAN’s 0.5099. The performance analysis is CCMEST ML Model accuracy, precision, recall, F1-Score, CCMEST Overall Performance, CCMEST Overall Performance.</p> Narasimha Rao Thota Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2090 Fri, 13 Nov 2026 00:00:00 +0000 A Development of Advanced Credit Card Fraud Detection Through Deep Learning Approaches with Data Analytics for Secured Banking Application https://www.intmaritimeengineering.org/index.php/ijme/article/view/2091 <p>Credit Card Fauld Detection in Banking application technological advancements complicate cybercrime and hinder credit card fraud detection. Traditional methods are ineffective. A company developed an event-based temporal graph (ETG) to detail transactions among users, cards, devices, and accounts. This review examines machine learning algorithms for detecting financial fraud amid rising digital transactions. We examine many forms of fraud, such as money laundering, insurance fraud, credit card fraud, and financial statement fraud, as well as the unique detection difficulties associated with each new model Credit Card Fauld Detection Through Deep Learning Approaches with Data Analytics (CCFDDA). A method for credit card fraud detection that integrates deep learning and traditional machine learning with data preprocessing. Using a Kaggle dataset of 284, 807 transactions (492 fraudulent), we perform Principal Component Analysis (PCA) for feature anonymization and address class imbalance. Our analysis identifies key fraud indicators through statistical methods, and we enhance data completeness by removing incomplete rows, improving model learnability. In the Feature Normalization phase, Min-Max scaling normalizes numerical attributes to the range of 0 to 1 to mitigate scale bias. The cleaned transaction data is represented using overlapping sliding windows to maintain temporal dependencies. The machine-learning fraud detection component evaluates several models, including Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), XGBoost, CatBoost, and Logistic Regression (LR), to identify fraudulent transactions and addresses class imbalance through various classification and ensemble techniques. Softmax assigns class probabilities, while a class-weighted loss function addresses class imbalance. The architecture employs machine learning, statistical analysis, structured preprocessing, and temporal graph-based deep learning for fraud detection. Its Deep Learning module utilizes a Dynamic Graph Neural Network (DGNN) for time-dependent classification and message passing, enabling it to model changing transaction interactions over time for effective fraud detection.</p> Narasimha Rao Thota Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2091 Fri, 13 Nov 2026 00:00:00 +0000 Smart Navigation Solutions for Efficient Electric Vehicle Charging and Route Planning https://www.intmaritimeengineering.org/index.php/ijme/article/view/2092 <p>The fast increase in the adoption of electric vehicles (EVs) has made more intelligent navigation systems required that are not only can guide users efficiently, but also covers charging availability, electricity life, and car-related demands. A key challenge lack of incorporated platforms that support EV users is faced route planning with charging in realtime with a flock of vehicles and real-time operational information. This paper smart navigation and charging system of Electric vehicles have been built on a Python Flask back end and a web-based frontend which responds to the back-end developed with HTML, CSS and JavaScript. The proposed system will use geocoding and reverse geocoding procedures to transform user based locations to geographic coordinates so that it can be spatially processed accurately. The Haversine formula is used in doing distance computing to workout the best way and find the closer charging stations according to approachingness and accessibility. Interactive map visualization is done by using Leaflet Maps where the users can view station positioning and route systems in a transparent and user-friendly manner. The system besides routing includes other functionalities such as routing has a multi-vehicle profile management module that has the ability to create and control various electric cars with single account, and different battery capacity, range, and charging characteristics. A battery health monitoring agent pre-charges charges and estimations battery degradation, tracks charge cycles providing numerical, as well as graphical, trends in support informed decisions on maintenance. To enhance user convenience and clear the managing stations, a safe payment interface is incorporated incharging slots reservation. Experimental testing in various settings of navigation and charging has better route clarity, less user effort and increased decision-making over traditional navigation systems. Scalability of the modular client server architecture efficiency, effective management ofdata and integration of other services. In general, the suggested system would bring about a coherent and integrated system. Smart electric vehicle navigation is an extensible solution to navigate accusing management and acting as a pragmatic basisof applications of EV mobility in the future.</p> Dr. C. M. Chidambaranathan, K. Yashwanth, Dr. P. Ramesh, B. Meghana Copyright (c) 2026 International Journal of Maritime Engineering https://www.intmaritimeengineering.org/index.php/ijme/article/view/2092 Fri, 13 Nov 2026 00:00:00 +0000