DEVELOPING A HYBRID INTELLIGENT TECHNIQUE FOR MOBILE HEALTH APPLICATIONS

Abstract

Mobile Health in remote medical systems has opened up new opportunities in healthcare systems. It is a steadily growing field in telemedicine and it combines recent developments in artificial intelligence and cloud computing with telemedicine applications. However, today’s Mobile Health research still missing an intelligent remote engine for neuromuscular disorders diagnosis. Moreover, Remote patient monitoring and emergency cases need an intelligent algorithms to alert with better diagnostic decisions and fast response to patient care. Many neuromuscular disorders that affect the nerves and muscles are hereditary and may cause death. Electromyography (EMG) is the most widely adopted clinical tool used to record and analyze myoelectric signals. EMG detects muscle response during different actions and gives useful identification of the neuromuscular disorders. Early diagnosis of these disorders through EMG signal processing and classification is necessary to help in finding out the best method of treatment of these disorders. This thesis involves the design of a new hybrid neuromuscular disorders diagnosis system for mobile health applications based on support vector machine and artificial neural networks. Given a collection of EMG data for normal subjects and Myopathy and Amyotrophic lateral sclerosis (ALS) patients, in this thesis a subset of these objects was used to build the classifiers and compare them to decide which classifier provides the best performance in terms of classification accuracy.