Cover Image

Signal processing driven machine learning techniques for cardiovascular data processing /

Features recent advances in machine learning coupled with new signal processing-based methods for cardiovascular data analysis. Topics in this book include machine learning methods such as supervised learning, unsupervised learning, semi-supervised learning, and meta-learning combined with different...

Full description

Bibliographic Details
Corporate Author: ScienceDirect (Online service)
Other Authors: Tripathy, Rajesh Kumar, Pachori, Ram Bilas
Format: eBook
Language:English
Published: London : Academic Press, 2024.
Subjects:
Machine learning.
Artificial intelligence > Medical applications.
Cardiovascular system > Data processing.
Machine Learning
Apprentissage automatique.
Intelligence artificielle > Applications en médecine.
Appareil cardiovasculaire > Informatique.
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Front Cover
  • Signal Processing Driven Machine Learning Techniques for Cardiovascular Data Processing
  • Copyright
  • Contents
  • List of contributors
  • 1 Introduction to cardiovascular signals and automated systems
  • 1.1 Heart conduction system and ECG signal
  • 1.1.1 Features of ECG signals
  • 1.1.2 Heart diseases and morphological changes in ECG signals
  • 1.1.3 Automated disease diagnosis system using ECG
  • 1.1.3.1 Recording of ECG signals
  • 1.1.3.2 Preprocessing of ECG data
  • 1.1.3.3 ECG feature extraction and selection
  • 1.1.3.4 Machine learning and deep learning
  • 1.2 Cardiac auscultation and PCG signal
  • 1.2.1 Heart valve diseases and changes in PCG
  • 1.2.2 Automated detection of HVDs using PCG
  • 1.3 PPG signal and cardiorespiratory activity
  • 1.3.1 Automated analysis of PPG signals
  • 1.4 Future scope of cardiac data processing
  • 1.5 Conclusion
  • References
  • 2 Third-order tensor-based cardiac disease detection from 12-lead ECG signals using deep convolutional neural network
  • 2.1 Introduction
  • 2.2 Dataset description
  • 2.3 Proposed method
  • 2.3.1 Preprocessing and beat segmentation
  • 2.3.2 Multivariate projection-based fixed boundary empirical wavelet transform (MPFBEWT)
  • 2.3.3 Deep convolutional neural network (CNN)
  • 2.4 Results and discussion
  • 2.5 Conclusion and summary
  • References
  • 3 Ramanujan filter bank-domain deep CNN for detection of atrial fibrillation using 12-lead ECG
  • 3.1 Introduction
  • 3.2 12-lead ECG database
  • 3.3 Proposed approach
  • 3.3.1 Time-period representation of ECG
  • 3.3.2 Development of TPR-domain deep CNN
  • 3.4 Results and discussion
  • 3.5 Conclusion
  • References
  • 4 Detection of atrial fibrillation using photoplethysmography signals: a systemic review
  • 4.1 Introduction
  • 4.2 Methods
  • 4.2.1 Search strategy, inclusion and exclusion criteria
  • 4.2.2 Data extraction
  • 4.3 Results and discussion
  • 4.3.1 Features
  • 4.3.2 Cost-effectiveness and accessibility
  • 4.3.3 Incorporation of machine and deep learning
  • 4.3.4 Clinical implications
  • 4.3.5 Limitations and research gaps
  • 4.4 Conclusion
  • References
  • 5 Machine learning-based prediction of depression and anxiety using ECG signals
  • 5.1 Introduction
  • 5.2 Mental health problems
  • 5.2.1 Anxiety disorder
  • 5.2.2 Depression disorder
  • 5.2.3 Factors affecting mental health
  • 5.3 Exploratory data analysis and preprocessing
  • 5.4 Feature extraction
  • 5.5 Machine learning-based model for prediction and classification of ECG signals
  • 5.5.1 Different machine learning models
  • 5.5.1.1 Supervised learning
  • 5.5.1.2 Unsupervised learning
  • 5.5.1.3 Semisupervised learning
  • 5.5.1.4 Transfer learning
  • 5.5.1.5 Reinforcement learning
  • 5.6 Conclusion and future scope
  • References