Cognitive Analysis by Brain Signal processing With QML

Abstract

Considered as one of the most complex phenomena, Quantum Neuro-Science assumed to be appropriate real-world applications of Quantum computers and Machine Intelligence. We suggested for analysing attention in EEG data is a thorough approach that utilizes quantum concepts in various aspects. Frequency Band Analysis employs Quantum Wavelet Transform and Quantum Fourier Transform for non-stationary EEG dynamics, extracting alpha and beta power information. Connectivity Analysis assesses functional connectivity using quantum entanglement, offering insights into complex interactions between brain regions and attention networks. QML techniques, including QSVC and QNN, enhance ERP studies, accelerating P300 analysis for accurate attentional state information. Quadratic Unconstrained Binary Optimization optimizes feature selection in classification models, and hybrid quantum-classical models like QSVC and XGB enable real-time attentional state classification, advancing our understanding of cognitive states. The chapter also touches the aspects of complexity measurement.