Ram Bilas Pachori

 In the last one or two decades, adaptive signal decomposition techniques have gained popularity for their broad applicability to almost all fields of science and technology. Empirical mode decomposition has been proposed to decompose the signal into amplitude-frequency modulated components (basis functions). Several methods have been proposed, followed by empirical mode decomposition for adaptive decomposition and to obtain improved signal representation. Empirical wavelet transform (EWT), iterative filtering, and variational mode decomposition are a few popular techniques among adaptive decomposition techniques. Recent advancements in sensor technology make it easier to acquire signals from multiple sources simultaneously, which demands multivariate/multi-channel signal decomposition methods. The univariate iterative filtering and EWT have been extended for processing multichannel signals, which will be discussed in this talk. Also, developed intelligent systems based on multivariate iterative filtering and multivariate EWT together with machine learning (ML) for epilepsy and schizophrenia diagnosis from multichannel electroencephalogram (EEG) signals will be presented. The obtained results show the effectiveness of the studied multivariate/multi- channel adaptive signal decomposition techniques.