Modelling and Analysis of Active Biopotential Signals in Healthcare. Volume 2 / edited by Varun Bajaj and G. R. Sinha.

Format:

Book

Contributor:

Bajaj, Varun, editor.

Sinha, G. R., 1975- editor.

Series:

IPEM-IOP Series in Physics and Engineering in Medicine and Biology Series

Language:

English

Subjects (All):

Biomedical engineering.

Signal processing.

Physical Description:

1 online resource (444 pages)

Edition:

First edition.

Place of Publication:

Bristol, England : IOP Publishing, [2020]

Summary:

This book describes the sources and characteristics of different biopotential signals and provides an understanding of how a range of signals can be modelled and analysed for a number of applications. It is a valuable guide for all researchers and practitioners who are engaged in studies and research in this area.

Contents:

Intro

Preface

Acknowledgements

Editor biographies

Varun Bajaj

G R Sinha

Contributors

Chapter 1 Classification of motor-imagery tasks from EEG signals using the rational dilation wavelet transform

1.1 Introduction

1.2 Methodology

1.2.1 The dataset

1.2.2 Rational dilation wavelet transforms

1.2.3 Feature extraction

1.2.4 Classification and performance measures

1.3 Results and discussion

1.4 Conclusion

References

Chapter 2 A deep learning framework for emotion recognition using improved time-frequency image analysis of electroencephalography signals

2.1 Introduction

2.2 Description of the EEG dataset

2.3 Methodology

2.3.1 The Stockwell transform

2.3.2 The proposed modified version of the Stockwell transform

2.3.3 Differential evolution optimization algorithm

2.3.4 Convolutional neural network (CNN)

2.4 Results and discussion

2.4.1 Time-frequency analysis of EEG signals using a modified ST

2.4.2 Performance analysis of DenseNet CNN

2.4.3 Comparison to the conventional ST

2.4.4 Performance analysis using other time-frequency images

2.4.5 Performance analysis using different train-test ratios

2.4.6 Performance analysis using other CNN architectures

2.4.7 Comparative study with the existing techniques

2.5 Conclusion

Chapter 3 Multivariate phase synchrony based on fuzzy statistics: application to PTSD EEG signals

3.1 Introduction

3.2 Method

3.2.1 Generalized phase synchrony (GePS)

3.2.2 Fuzzy hypothesis testing

3.2.3 Fuzzy generalized phase synchrony

3.3 Data

3.3.1 Synthetic data

3.3.2 Resting state EEG signals

3.4 Results

3.4.1 Simulated data

3.4.2 PTSD EEG data

3.5 Conclusion

Acknowledgments

References.

Chapter 4 A study of the influence of meditation and music therapy on the vital parameters of the human body through EEG signal analysis: a review

4.1 Introduction

4.2 Meditation

4.2.1 The origin of meditation

4.2.2 Types of meditation

4.2.3 Mindfulness meditation

4.3 Music therapy and its application in medical science

4.3.1 Meditation and music therapy

4.4 Measurement of neurological response

4.4.1 Invasive methods

4.4.2 Non-invasive methods

4.5 EEG signal processing

4.5.1 Data acquisition

4.5.2 Preprocessing

4.5.3 Feature extraction

4.5.4 Classification

4.6 Studies conducted globally in the field of meditation and music therapy using EEG signal processing

4.7 Limitations and future scope

4.8 Conclusion

Chapter 5 Cross-wavelet transform aided focal and non-focal electroencephalography signal classification employing deep feature extraction

5.1 Introduction

5.2 Dataset description

5.3 Methodology

5.3.1 Cross-wavelet transform

5.3.2 Deep feature extraction

5.3.3 Transfer learning

5.3.4 Machine-learning classifiers

5.4 Results and discussion

5.4.1 EEG signal analysis using the XWT

5.4.2 Performance analysis of the proposed method

5.4.3 Comparison to the existing literature

5.5 Conclusion

Chapter 6 Local binary pattern based feature extraction and machine learning for epileptic seizure prediction and detection

6.1 Introduction

6.2 Literature review

6.3 Theoretical background

6.3.1 Feature extraction

6.3.2 Classification techniques

6.4 The proposed approach

6.4.1 Implementation of the BP on EEG signals

6.4.2 BP feature generation based EEG recognition

6.4.3 TP feature generation based EEG recognition

6.4.4 Multilevel models

6.4.5 DWT based feature generation

6.4.6 TQWT based feature generation.

6.4.7 Feature generation

6.4.8 Feature selection

6.5 Results and discussion

6.5.1 The used datasets

6.5.2 DWT and BP based EEG classification

6.5.3 DWT and TP based EEG classification

6.5.4 TQWT and BP based EEG classification

6.5.5 TQWT and BP based EEG classification

6.6 Conclusions

Chapter 7 Increasing the usability of the Devanagari script input based P300 speller

7.1 Introduction

7.2 Methodology

7.2.1 Design of the DS display paradigm

7.2.2 Data acquisition and preprocessing

7.2.3 Classification of P300

7.3 Experiments and results

7.3.1 Experimental set-up

7.3.2 Results of classification of P300

7.4 Discussion

7.4.1 Comparative analysis

7.4.2 Workload evaluation

7.5 Conclusion

Bibliography

Chapter 8 A comprehensive review of the fabrication and performance evaluation of dry electrodes for long-term ECG monitoring

8.1 Introduction

8.2 Why this review?

8.3 Working principles of the ECG lead and necessary instrumentation

8.3.1 Origin of the cardiac potential and ECG signal

8.3.2 Placement of leads

8.3.3 Integrated circuit associated with waveform generation

8.4 Categories of biopotential ECG electrodes

8.4.1 Introduction and advantages of the dry electrode

8.4.2 Fabrication and performance evaluation of contact surface electrodes

8.4.3 Fabrication and performance evaluation of contact penetrating electrodes

8.4.4 Fabrication and performance evaluation of noncontact capacitive electrodes

8.5 Issues with dry electrodes and future scope

8.6 Conclusion

Chapter 9 Effective cardiac health diagnosis using event-driven ECG processing with subband feature extraction and machine learning techniques

9.1 Introduction

9.2 Background and literature review

9.3 The electrocardiograph (ECG) in healthcare.

9.4 The proposed approach

9.4.1 Dataset

9.4.2 The ECG signal reconstruction

9.4.3 The event-driven acquisition

9.4.4 The event-driven segmentation

9.4.5 The adaptive-rate resampling and denoising

9.4.6 Extraction of features and dimension reduction

9.4.7 Machine learning algorithms

9.5 The performance evaluation measures

9.5.1 Compression ratio

9.5.2 Computational complexity

9.5.3 Classification accuracy

9.6 Experimental results and discussion

9.6.1 Experimental results

9.6.2 Discussion

9.7 Conclusion

Chapter 10 Analysis of heart patients using a tree based ensemble model

10.1 Introduction

10.2 Related works

10.3 Methodology

10.3.1 Data description

10.3.2 Algorithms

10.4 Formula representation

10.5 Proposed ensemble method

10.6 Results

10.7 Discussion

10.8 Conclusion

Conflict of Interest

Funding

Chapter 11 Heartbeat classification using parametric and time-frequency methods

11.1 Introduction

11.2 Background and literature review

11.3 Materials and methods

11.3.1 Dataset

11.3.2 Wavelet transform

11.3.3 Denoising with multiscale principal component analysis

11.3.4 Feature extraction

11.3.5 Machine learning methods

11.3.6 The performance evaluation measures

11.4 Experimental results

11.5 Discussion

11.6 Conclusion

Chapter 12 Segmentation of ECG waves using LSTM networks

12.1 Introduction

12.1.1 ECG waves, intervals and segments

12.1.2 ECG wave segmentation

12.2 Methodology

12.2.1 Architectural details of the LSTM model

12.2.2 Bidirectional LSTM (BiLSTM) network

12.2.3 Stacked BiLSTM network

12.2.4 Semantic segmentation

12.3 Experimental set-up

12.3.1 Dataset details

12.3.2 System implementation details.

12.4 Results

12.4.1 Results using a single LSTM based model

12.4.2 Results using a BiLSTM based model

12.4.3 Results using a stacked BiLSTM based model

12.5 Discussion

12.5.1 Comparative analysis: proposed LSTM networks

12.5.2 Comparative analysis: existing state-of-the-art versus the proposed method

12.6 Conclusion

Chapter 13 Deep convolutional neural network based diagnosis of COVID-19 using x-ray images

13.1 Introduction

13.2 Methodology

13.2.1 Convolutional neural network

13.2.2 Convolution layers

13.2.3 Pooling layers

13.2.4 Fully connected layer

13.2.5 Fine-tuning

13.2.6 Deep CNN models

13.3 Results and discussion

13.3.1 Dataset description

13.4 Conclusion

Chapter 14 Otitis media diagnosis model for tympanic membrane images processed in two-stage processing blocks

14.1 Introduction

14.2 Materials and methods

14.2.1 Database

14.2.2 Convolutional neural network

14.2.3 Feature selection

14.2.4 Artificial neural networks

14.2.5 Support vector machines

14.2.6 k-nearest neighbors

14.2.7 Decision tree

14.2.8 Naïve Bayes

14.3 Experimental results

14.4 Discussion

14.5 Conclusion

Chapter 15 Modelling and analysis for active infrared thermography for breast cancer screening

15.1 Introduction

15.2 Numerical modelling and simulation

15.2.1 Modelling of the dense breast

15.2.2 Fatty breast

15.2.3 Simulation

15.3 Post-processing analysis schemes

15.3.1 Frequency domain phase approach

15.3.2 Time domain approach

15.4 Results and discussion

15.4.1 Results obtained for the dense breast

15.4.2 Results obtained for the fatty breast

15.4.3 Signal-to-noise ratio (SNR)

15.5 Conclusion

Chapter 16 Photoacoustic microscopy: fundamentals, instrumentation and applications.

Notes:

Description based on publisher supplied metadata and other sources.

Description based on print version record.

Includes bibliographical references.

ISBN:

9780750340991

0750340991

OCLC:

1429724773