Nonlinear signal analysis and pattern Recognition using machine learning Techniques

Abstract

In this thesis three different real world and non-linear signals are considered to identify patterns using advanced signal processing and machine learning techniques. These signals belong to various dynamic systems, power quality disturbances in power distribution network and biomedical EEG signal. A model is a mathematical description of the dynamic behaviour of a system. Most of the physical systems are nonlinear in nature and therefore non-linear signal analysis is useful in many fields of engineering such as communication engineering, speech processing, and many control theory applications. Other real world signals which have attracted the attention is the time varying Power quality (PQ) distortion and Electroencephalogram (EEG) signal. PQ distortion is attributed due to the various disturbances like voltage sag, swell, impulsive, and oscillatory transients, multiple notch, momentary interruption, harmonics, and voltage flickers etc in electrical power network. In order to improve the quality of electrical power it is required to record continuously the disturbance waveforms using power monitoring equipment s. Various algorithms and time series analysis methods have been applied to address these issues. EEG is a highly complex signal containing a lot of information about the human brain function and neurological disorders. Epileptic seizure is a group of disorders characterized by recurrent discharge from the cerebral cortex that result in irregular disturbance of brain function. Detection of epilepsy by visual scanning of EEG signal is very time consuming and may be inaccurate, particularly for long recordings. The detection of epileptic seizures in the EEG signals is an important part in the diagnosis of epilepsy. newlineThe methods proposed here exhibits improved performance accuracy which is superior to the considered models. The proposed model is also compared with some iterative existing methods and found suitable by taking into consideration the merits of non-iterative approach. newlineFrom the overall analysis of the