Development of Sensory Graph-Modeled Data Analysis Through Process Mining Techniques with Markovian Geometric Diffusion for Healthcare Application

Abstract

In the healthcare application, data analysis and mining techniques plays an effective role in handling huge data. Still
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.