Signal Processing-Driven AI for Healthcare examines how AI techniques can be applied across four major biosignals-EEG, EMG, EOG, and ECG-to derive clinically meaningful insights. As biomedical data becomes increasingly multimodal, there is a rising need for integrated methodologies that unite these signals within robust, explainable AI pipelines suitable for healthcare environments. This book provides a unified framework that spans data acquisition, preprocessing, feature extraction, modeling, evaluation, and deployment, with an emphasis on reproducibility, practical Python-based implementations, and real-world translation to clinical workflows.
Table of Contents
Part I Foundations1. Introduction: AI, biosignals, and healthcare workflows
2. Sensors, acquisition, and data characteristics
Part II Signal Processing for Biomedical Time Series
3. Preprocessing & cleaning
4. Time-frequency and feature transforms
5. Spatial and multichannel processing
Part III Machine Learning & Deep Learning Methods
6. Classical ML for biosignals
7. Deep learning approaches
8. Explainability, uncertainty, and interpretability
Part IV Modality-Focused Chapters (EEG, EMG, EOG, ECG)
9. EEG: brain signals, pipelines, and applications
10. ECG: cardiac signal analytics and arrhythmia detection
11. EMG: muscle activation, prosthetics, and fatigue monitoring
12. EOG: eye movement, drowsiness, and human factors
Part V Multimodal Fusion, Deployment & Systems
13. Multimodal learning and sensor fusion
14. Real-time systems, edge AI, and hardware considerations
15. Data engineering, annotation, and labelling strategies
Authors
Ildar Rakhmatulin Independent Engineer and Founder, PiEEG Solutions, Edinburgh, UK.Dr. Ildar Rakhmatulin is a scientist and the creator of several popular open-source brain-computer interface (BCI) projects. He is the founder of PiEEG, a low-cost BCI solution. His experience includes working as a BCI developer at Imperial College London, a machine learning researcher at Heriot-Watt University, and a researcher in the neurotechnology group at the University of Edinburgh, UK. Additionally, he is the author of neuroscience courses on Udemy.
Ganesh R. Naik Torrens University, Adelaide, Australia. Dr. Ganesh R. Naik is a leading researcher in biomedical engineering and signal processing, ranked among the top 2% of scientists globally (Stanford University). He earned his PhD in Electronics Engineering from RMIT University, Melbourne (2009), and is currently a Senior Academic and Researcher in Computer Science and IT at Torrens University Australia. Dr. Naik has edited 16 books and published over 150 peer-reviewed papers. He serves as Associate Editor for IEEE Access, Frontiers in Neurorobotics, and two Springer journals. His career is distinguished by fellowships from Baden-W�rttemberg (Germany), ISSI (Australia), the BridgeTech Program, and the Royal Academy of Engineering (UK). Previously, he held research roles at Flinders University, Western Sydney University, and UTS, contributing to major projects in sleep technology, wearable sensors, and AI-driven biomedical signal processing.
