Self-coach: an intelligent WBAN system for heart disease prediction using non-dominated sorting genetic algorithm
Year: 2016
Type: dissertation
Abstract: Wireless Body Area Network (WBAN) is a new technology based on an \nadvanced healthcare system and Wireless Sensor Network (WSN). This domain has \nbeen designed for monitoring patients using their physical signals by providing lowcost, \nwearable, unobtrusive solutions for the continuous monitoring of cardiovascular \nhealth and physical activity status. Recent studies have addressed the use of WBAN, \nby means of real-time comprehensive health monitoring systems such as the Personal \nHealth Monitoring system (PHM). The aim of utilizing these systems is to provide a \nfast and early diagnosis; however, WBAN has not fulfilled its potential while using \nthe existing methods of machine learning and data mining techniques. The proposed \nmethod is a new framework for early heart failure prediction systems based on an \nintelligent WBAN named Self-Coach. Self-Coach is an intelligent monitoring system \ndue to the detection/prediction method it uses, which provides real-time health status \nmonitoring using the Non-Dominated Sorting Genetic Algorithm. \nIn this study, Self-Coach is proposed as a new medical diagnosis method based on \nthe hybrid approach. This approach applies the Support Vector Machine (SVM) to \nclassification, where its parameter values are optimized and visualized by the Non- \nDominated Sorting Genetic Algorithm-II (NSGA-II). To predict a potential health \ntolerance threshold for a particular patient, the optimal boundary curve between both \nthe healthy and unhealthy class and the patient's possible health positions based on \nnew conditions (blood pressure and heart rate) have been explored with NSGA-II. The optimal boundary is a set of non-dominated offspring from the unhealthy class \nthat has been generated with NSGA-II and verified with the SVM. These members \nare plotted as a Pareto Front curve known as the optimal boundary curve. Based on \nthe SVM classification results, this is the most fitted curve which can separate the \nhealthy class from the unhealthy. \nTo explore the potential health position of a particular patient, new possible positions \nwill be generated with NSGA-II. To generate these points, the patient's dynamic \ndata (blood pressure and heart rate) will be increased and simulated utilizing NSGAII. \nThe potential tolerance threshold for each patient is the new health position for \nthat particular patient based on the new health conditions which will cross the optimal \nboundary or be dominated by at least one of these members. \nTo evaluate the Self-Coach's performance, its experimental results (optimal boundary \nmembers and explored tolerance thresholds for each individual) have been verified \nusing SVM and compared with the raw dataset classification results. Based on the \nsimulated results, this method can provide 24-hour health monitoring care for elderly \npeople and those who might have coronary heart disease. It is a new technology for \nthis domain. Real-time data analysis is a significant part of Self-Coach, which makes \nit a good candidate for supporting a broad array of high-impact applications in the \ndomain of the healthcare system, for training, rehabilitation, surgical recovery and as \na home-based monitoring healthcare system.
Author: Babak Emami-Abarghouei
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W2808568362