In the fast-moving world, due to factors such as unhealthy lifestyle, genetic inheritance, work pressure, etc., there has been a significant increase in the number of people suffering from various disorders that adversely affect an individual’s physical and psychological health. These factors directly or indirectly affect the work-life balance, social and economic activities. Many-a-times, these disorders do not show symptoms in the early stages and become malignant in later stages.
Over the past few decades, Biomedical Signals that can be measured via Electroencephalography (EEG), Electrocardiography (ECG), Electromyography (EMG), Magnetoencephalography (MEG), Photoplethysmography (PPG), Phonocardiography (PCG), have been employed in determining the human body medical and psychological conditions. These signals have been better understood through advanced Signal Modeling techniques.
Time-Frequency (TF) Analysis-based Signal Processing techniques provide signal information simultaneously in both the time domain and frequency domain. These methods overcome the issues of unknown information in the time domain and frequency domain individually. The transformation of one-dimensional information (time domain or frequency domain) into two-dimensional information (time-frequency domain) creates a space to utilize the various advanced approaches for signal analysis. Various TF methods have been developed in recent years such as short-time Fourier transform, Spectrogram, Wavelet transform, Scalogram, Hilbert Huang Transform, Wigner-Ville Distribution, Eigenvalue Decomposition of Hankel Matrix Based method, Synchrosqueezing Transform, and others.
Recent advancements in TF-based Signal Processing techniques and ML-based algorithms can be used to design and develop accurate, fast, and remotely accessible diagnosis and prognosis systems for biomedical applications.
The aim of this Research Topic is to address the TF and ML-based studies which outline the design and development of Computer-Aided Decision Support Systems (CADSS) involving Time-Frequency Signal Processing techniques and Machine/Deep Learning-based approaches in the biomedical field.
This Research Topic will accept original research around the following research areas:
· Physiological Signal Denoising using TF and ML
· Biomedical Signal Processing using TF and ML
· TF based feature engineering for Biomedical Signals
· Physiological Disorder Analysis using TF and ML
· EEG, MEG, ECG, EMG, PPG, and other physiological signal analysis using TF and ML
In the fast-moving world, due to factors such as unhealthy lifestyle, genetic inheritance, work pressure, etc., there has been a significant increase in the number of people suffering from various disorders that adversely affect an individual’s physical and psychological health. These factors directly or indirectly affect the work-life balance, social and economic activities. Many-a-times, these disorders do not show symptoms in the early stages and become malignant in later stages.
Over the past few decades, Biomedical Signals that can be measured via Electroencephalography (EEG), Electrocardiography (ECG), Electromyography (EMG), Magnetoencephalography (MEG), Photoplethysmography (PPG), Phonocardiography (PCG), have been employed in determining the human body medical and psychological conditions. These signals have been better understood through advanced Signal Modeling techniques.
Time-Frequency (TF) Analysis-based Signal Processing techniques provide signal information simultaneously in both the time domain and frequency domain. These methods overcome the issues of unknown information in the time domain and frequency domain individually. The transformation of one-dimensional information (time domain or frequency domain) into two-dimensional information (time-frequency domain) creates a space to utilize the various advanced approaches for signal analysis. Various TF methods have been developed in recent years such as short-time Fourier transform, Spectrogram, Wavelet transform, Scalogram, Hilbert Huang Transform, Wigner-Ville Distribution, Eigenvalue Decomposition of Hankel Matrix Based method, Synchrosqueezing Transform, and others.
Recent advancements in TF-based Signal Processing techniques and ML-based algorithms can be used to design and develop accurate, fast, and remotely accessible diagnosis and prognosis systems for biomedical applications.
The aim of this Research Topic is to address the TF and ML-based studies which outline the design and development of Computer-Aided Decision Support Systems (CADSS) involving Time-Frequency Signal Processing techniques and Machine/Deep Learning-based approaches in the biomedical field.
This Research Topic will accept original research around the following research areas:
· Physiological Signal Denoising using TF and ML
· Biomedical Signal Processing using TF and ML
· TF based feature engineering for Biomedical Signals
· Physiological Disorder Analysis using TF and ML
· EEG, MEG, ECG, EMG, PPG, and other physiological signal analysis using TF and ML