APPLICATION OF ML IN ELECTROENCEPHALOGRAPHY
Dr. R.D. CHINTAMANI
Dr. RAJESH BOGHEY
Dr. PANKAJ MISHRA
Dr. N.S. PATANKAR
Genre/Subject – MACHINE LEARNING
Book code – CCTTTB022237
ISBN – 978-93-94435-07-0
DOI – 10.55083/bk.schlup/isbn.978-93-94435-07-0.cctttb032237
Dr. Rameshwar Dadarao Chintamani has a Bachelor’s Degree in Information Technology from S.G.G.S COE&T, Nanded and a Master’s Degree from M.I.T. COE, Aurangabad, Dr.B.A.M.U, Aurangabad. Here he studied the diversified aspects and importance of research and that was the turning point in his educational life, he enrolled for the Ph.D. Program from the Patel Group of Institution’s, Madhyanchal Professional Univeristy, Bhopal, M.P. Since 2008 he joined Department of Information Technology, Sanjivani College of Engineering, Kopargaon as Assistant Professor, and currently looking after all the Machine Learning research related activities as Coordinator in Department. He has published more than 10 National and International research papers in various prestigious Research Journals and Conferences. From his childhood, he was very active in extracurricular activities like playing Cricket, Social Activities and many more . He has the interest to develop new models in the field of Machine Learning.
ABOUT BOOK / ABSTRACT
The brain-computer interface holds tremendous promise for biomedical engineering. Biomedical engineering is concerned with computer-assisted diagnosis of life- threatening diseases and illnesses. Computer and medical science’s emerging generation creates a diverse space for patients’ and doctors’ findings and solutions. Visual imagery associated with motor vehicles EEG classification is a method for detecting critical disease based on a prediction sample. The complexity of the EEG signal associated with motor imagery creates a bottleneck in terms of accuracy and prediction. The value placed on accuracy and prediction has eroded the credibility of the EEG signal recorded with the aid of an electrode and a computer storage device for detecting critical illness. The EEG signal is analogous and non-stationary in nature. The analogue signal is converted to a digital signal and stored in the computer’s memory; the stored signal then undergoes classification processing. The processing of the raw signal for classification was harmed by the classification ratio and feature component selection. The extraction and selection of features are critical steps in classifying frequency-based transforms with varying degrees of decomposition and signal range analysis. The most frequently used transform functions include FFT, STFT, CSP, and wavelet transforms. Wavelet transform is the most frequently used transform function for extracting features from EEG signal data. The characteristic component of EEG signals varies according to signal band, including alpha, game, beta, and delta. Each of these bands has a distinct frequency range.