Artificial Intelligence-based Signal Processing for Brain Activity Analysis is an indispensable resource for addressing the pressing challenges in medicine, detection of brain-related disorders, brain-computer interfacing, and neuromarketing. It delves into contemporary AI, ML, and signal processing approaches for analysis of brain activity.
The salient features of this book include:
(1) Acquisition, preprocessing, noise removal, and processing methods for brain signals, including EEG, ECoG, MEG, fMRI, and fNIRS.
(2) Latest AI and ML algorithms relevant for classification of brain signals, including traditional machine learners, deep transfer learners, LSTM and auto-encoders, and transformers.
(3) Applications in medicine, including mental healthcare, mental stress reduction, psychological disorder detection, OCD detection, sleep disorder detection, seizure detection, brain tumor detection, Alzheimer’s disease detection, and bipolar disorder prediction.
(4) Applications in brain-computer interfacing (BCI), gaming and entertainment, and neuromarketing.
(5) Recent case studies and experimental and research works.
The text is primarily written for senior undergraduate students, graduate students, industry professionals, researchers, and academicians working in the field of AI, ML, signal processing techniques, biomedical signal processing, brain signal analysis, and brain activity analysis.
Table of Contents:
1. Introduction and Acquisition Methods of Brain Signals 2. AI-EEG: Advanced Integration and Machine Learning Standards for EEG Data Acquisition and Processing 3. Feature Extraction from Brain Signals in Brain-Computer Interface (BCI) Technology 4. PTSD Diagnosis Based on False Memory Tasks and Fuzzy Synchronization Likelihood Index 5. XAI-Enhanced EEG Analysis for Limb Task Identification 6. EEG-based Estimation of Obsessive Compulsive Disorder Severity using Nonlinear Regression via Deep Negative Correlation Learning and Fuzzy Weighting 7. Determination of OCD severity using rule-based representation learner: an EEG study 8. A Deep Transfer Convolutional Neural Network Framework Leveraging VGG16 for Motor Imagery Classification from EEG Signals 9. Classification of Inner Speech EEG signals for BCI Applications 10. Using AttnSleep for Single-channel BCI Processing 11. Comprehensive Analysis of Seizure activity in Critical Care Patients with Harmful Brain Patterns 12. Integration of Multimodal Data for Enhanced Artifacts Detection and Removal in EEG-based BCI Systems 13. Emotion Recognition from EEG Signals Using Machine Learning Algorithms 14. Enhanced U-Net Based on Multi-Scale Fashion for MRI Segmentation 15. Analysis of Alzheimer MRI Image and their Associated Cancer Disease 16. A Review on Feature Extraction Techniques for Diagnosis of Neurological Disorders using Brain Signals
