Author : Atena Roshan Fekr
Publisher :
ISBN 13 :
Total Pages : pages
Book Rating : 4.:/5 (953 download)
Book Synopsis Exploring Human Respiratory Information Through a Design of a Wearable E-Health Monitoring System by : Atena Roshan Fekr
Download or read book Exploring Human Respiratory Information Through a Design of a Wearable E-Health Monitoring System written by Atena Roshan Fekr and published by . This book was released on 2016 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: "The measurements of human respiration signal caused by the actions of the chest wall respiratory muscles can help predict health crises. As technology matures, there exists a large potential for effective techniques that can develop the capabilities of health care systems in diagnostics and treatment of respiratory disorders. One recent area of interest is applying wearable Micro-Electro-Mechanical Systems (MEMS) to detect small movements of the body that occur during expansion and contraction of the lungs in each respiration cycle. This thesis presents a newly developed experimental system via wearable sensing technology and wireless communication. In this dissertation, we make use of accelerometer sensors to model the interior and posterior movements of the chest wall during breathing function at rest positions. These motions are analyzed in order to explore different respiratory parameters with high accuracy versus the medical references. To do so, first the problems of self-recalibration of multi-sensory systems as well as fault-tolerant multi-sensor data fusion are considered. Next, an accelerometer-based approach is developed to accurately estimate the breathing signal, respiratory timing variables and the phase shift between chest wall compartments, which is used for paradoxical breathing detection. Since it is essential to determine the critical events caused by sudden rise or fall in per breath tidal volume of the people, a technique is provided to automatically find accurate threshold values according to each individual's breath characteristics. Moreover, we integrate the use of inertial sensors with machine learning techniques to model a wide range of human respiratory patterns for the goal of cloud-based recognition of respiratory problems. Novel approaches are discussed for extracting information-rich features from the respiration signal to improve the performance of the classifiers. Furthermore, a hierarchical tree model is proposed based on multiobjective Evolutionary Algorithm (EA) to optimize two performance metrics of classification, simultaneously. Finally, an innovative biofeedback mechanism is introduced based on Dynamic Time Warping with a fast segmentation method to provide a real-time quantitative feedback during breathing therapy. So that, the proposed platform potentially lifts the people's motivation up towards treatment while precisely tracks their practice quality improvement at low cost." --
