DON: Deep Optimized Network model based on Coot and Convoluted Recurrent learning algorithms for healthcare monitoring in IoMT systems

• Published in: Measurement : journal of the International Measurement Confederation Vol. 242; p. 116226
• Main Authors: Lakshmanaprakash, S, Abirami, A, Madanachitran, R, Mekala, R, Vaishali, Vaibhav Hirlekar
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2025
• Subjects: Convoluted Recurrent Attention Network (CRAN); Deep Learning; Disease Diagnosis; Edge Computing; Internet of Medical Things (IoMT); Optimization; Convoluted Recurrent Attention Network (CRAN); Edge Computing; Internet of Medical Things (IoMT); Deep Learning; Optimization; Disease Diagnosis
• ISSN: 0263-2241
• DOI: 10.1016/j.measurement.2024.116226

•Coot Optimized Feature Selection enhances classifier performance by selecting relevant features.•CRAN accurately identifies and classifies genetic, chronic, and heart-related diseases.•Cray Fish Optimization optimizes hyperparameters for better efficiency in classification.•Extensive verification using medical datasets shows high accuracy and reliability. The major challenges faced in the modern era involve fulfilling urgent needs for multi-access health-tracking systems and reliable identification of diseases. Recent advancements in IoMT and technological innovations are shaping the adoption of smart healthcare systems widely across the world. A sophisticated, round-the-clock health monitoring system is required for the efficient tracking of patients, together with timely medical interventions. State-of-the-art computing and cloud infrastructures shall be demanded from smart medical facilities. This work presents the development of a Deep Optimized Network model: IoMT-enabled intelligent, automated edge computing environment for healthcare monitoring in disease diagnosis. In this regard, we have utilized the technique of feature selection, called Coot Optimized Feature Selection, for choosing only the relevant features from preprocessed medical data so that the performance of the classifier improves both at the time of training and at testing. Further, we propose a novel deep learning-based algorithm called the Convoluted Recurrent Attention Network, CRAN, which can identify and classify various diseases related to genetic disorder, chronic disease, or heart-related disorder while maintaining low time complexity with high efficiency. In this respect, the hyper-parameters of the CRAN model are fine-tuned using the Cray Fish Optimization technique, allowing optimal classification learning. Extensive performance evaluations using the widely recognized open-source medical datasets validate the effectiveness of the proposed DON model. The results identify the outcomes of the model with high accuracy in the classification of diseases, establishing it as a reliable solution for effective health monitoring. From these findings, one may infer that the integration of IoMT with advanced computational techniques would definitely enhance the healthcare delivery systems. With the DON model, high accuracy in disease identification and efficient monitoring lead to better patient outcomes by ensuring streamlined healthcare processes.