Time-frequency analysis is critical in biomedical signal analysis, which helps diagnose and monitor physiological conditions such as heart rate variability, seizure detection, and brain-computer interfacing. This edited book includes original theoretical, practical, and review chapters aimed at proposing advancements in time-frequency signal processing methods for biomedical healthcare applications. Exemplary themes of interest include biomedical signal processing challenges in complex physiological data, signals from remote sensors, wearables, and nearables such as ballistography-based sensors.
Features:
• Discusses detailed time-frequency signal processing applications for simple to complex biomedical research.
• Reports novel time-frequency techniques used for biomedical signals.
• Presents theoretical basis of time–frequency analysis and state-of-the-art applications tailored for various biomedical problems.
• Provides a forum for presenting new and improved techniques and theories related to time-frequency analysis.
• Combines the primary knowledge of time-frequency signal analysis and processing, from theory and applications.
This book is aimed at graduate students and researchers in bioengineering, and signal processing.
This edited book includes original theoretical, practical, and review chapters aimed at proposing advancements in time-frequency signal processing methods for biomedical healthcare applications. This book is aimed at graduate students and researchers in bioengineering, and signal processing.
I. Introduction to Time-Frequency Analysis for Biomedical Engineering.
Chapter 1: Wavelet-Based Biomedical Signal Analysis: A Tutorial Approach for
Pathological Assessment. II. Time-Frequency Analysis of Specific Biomedical
Signals.
Chapter 2: Time-Frequency Analysis of ECG Signal.
Chapter 3:
Application of decomposition techniques to physiological time series with
variable spectral content. III. Applications in Neurological Signal
Processing.
Chapter 4: Denoising of Single-Channel EEG Signals Using Wavelet
Transform with Krawtchouk Functions.
Chapter 5: Optimized Feature Selection
and Neural Network-Based Classification of Motor Imagery Using EEG Signals: A
Time-Frequency Approach.
Chapter 6: Electroencephalogram Based Driver
Drowsiness Detection Using Entropy Features with Light Weight Deep Learning
Model. IV. Seizure Detection and Classification using Time-Frequency
Features.
Chapter 7: From Signals to Automated System: Seizure Detection
Using Time-Frequency EEG Features An Experimental Investigation.
Chapter 8:
Deep Learning based Epileptic Seizure Classification in Neonates using
STFT-Transformed EEG Signals.
Chapter 9: E-PRESTO: Epileptic PREictal State
detection using Time-series mOdelling.
Chapter 10: Sliding Window-Based
Epileptic Seizure Detection using Classifier Fusion and TQWT with Statistical
Features. V. Advanced Techniques and Machine Learning Applications.
Chapter
11: Arrhythmia detection using WPD with Bagging and Boosting Ensemble Machine
Learning Methods.
Chapter 12: EEG based biometric authentication using
Wavelet Packet Decomposition and Ensemble Classifiers
Ganesh R. Naik is a globally recognized biomedical engineer and signal processing expert, ranked in the top 2% of researchers by Stanford University. He holds a PhD from RMIT University and is currently a senior academic at Torrens University Australia. A prolific researcher, he has edited 16 books and authored over 150 papers. Dr. Naik is an associate editor for several prestigious journals, including IEEE ACCESS. His career includes significant research roles at Flinders University, Western Sydney University, and the University of Technology Sydney, where he contributed to advancements in sleep health and wearable technologies. He has received numerous fellowships, including from the Royal Academy of Engineering UK, the Government of Australia, and Germany's BadenWürttemberg Scholarship.
