Deep Learning for Data Analytics: Foundations, Biomedical Applications, and Challenges

Deep Learning for Data Analytics
Copyright
Contents
List of contributors
Preface
1 Short and noisy electrocardiogram classification based on deep learning
	1.1 Introduction
	1.2 Basic concepts
		1.2.1 Cardiac cycle
		1.2.2 Electrocardiogram
		1.2.3 The QRS wave
	1.3 Theory related to electrocardiogram analysis
		1.3.1 Discrete wavelets transform
		1.3.2 Continuous wavelet transform
		1.3.3 Convolutional neural network
			1.3.3.1 Convolutional layer
			1.3.3.2 Pooling layer
			1.3.3.3 Fully connected layer
		1.3.4 Database
	1.4 Methodology
		1.4.1 Preprocessing
		1.4.2 Classification based on deep learning
		1.4.3 Decision fusion
		1.4.4 Training the convolutional neural network model
		1.4.5 Performance parameter
	1.5 Results and discussion
	1.6 Conclusion
	References
2 Single-layer convolution neural network for cardiac disease classification using electrocardiogram signals
	2.1 Introduction
	2.2 Related works
	2.3 Methodology
		2.3.1 Convolutional neural network
		2.3.2 Network architecture
	2.4 Experimental result and analysis
		2.4.1 Data set description
			2.4.1.1 Arrhythmia
			2.4.1.2 Myocardial infarction
		2.4.2 Arrhythmia disease classification using proposed convolutional neural network
		2.4.3 Arrhythmia classification using support vector machine
		2.4.4 Myocardial infarction disease classification using the proposed convolutional neural network
			2.4.4.1 Comparison of the proposed work against the literature
	2.5 Conclusion
	References
3 Generalization performance of deep autoencoder kernels for identification of abnormalities on electrocardiograms
	3.1 Introduction
	3.2 Autoencoder
	3.3 Deep autoencoder
		3.3.1 Extreme learning machine autoencoder
		3.3.2 Deep extreme learning machine autoencoder
	3.4 Deep analysis of coronary artery disease
	3.5 Conclusion
	References
4 Deep learning for early diagnosis of Alzheimer’s disease: a contribution and a brief review
	4.1 Introduction
	4.2 Literature review
		4.2.1 Alzheimer’s disease binary classification
		4.2.2 Alzheimer’s disease binary classification using a deep learning approach
	4.3 Methods
		4.3.1 Data acquisition and preprocessing
		4.3.2 Convolutional neural network training and feature extraction
		4.3.3 Training and classification with other algorithms
	4.4 Experiments and results
		4.4.1 Experimental settings
		4.4.2 Classification results
	4.5 Conclusion
	Acknowledgment
	References
5 Musculoskeletal radiographs classification using deep learning
	5.1 Introduction
	5.2 Related works
	5.3 Data set description and challenges
		5.3.1 Description of the data set
		5.3.2 Challenges faced
	5.4 Proposed methodologies
		5.4.1 Data preprocessing
		5.4.2 Inception
		5.4.3 Xception
		5.4.4 VGG-19
		5.4.5 DenseNet
		5.4.6 MobileNet
	5.5 Statistical indicators
	5.6 Experimental results and discussions
		5.6.1 Finger radiographic image classification
		5.6.2 Wrist radiographic image classification
		5.6.3 Shoulder radiographic image classification
	5.7 Conclusion
	References
6 Deep-wavelet neural networks for breast cancer early diagnosis using mammary termographies
	6.1 Introduction
	6.2 Related works
	6.3 Breast thermography
		6.3.1 Breast thermographic images acquisition protocol
			6.3.1.1 Room preparation
			6.3.1.2 Patient preparation
			6.3.1.3 Images acquisition
	6.4 Deep-wavelet neural network
		6.4.1 Filter bank
		6.4.2 Downsampling
		6.4.3 Synthesis block
	6.5 Classification
		6.5.1 Experimental results and discussion
			6.5.1.1 Lesion detection
			6.5.1.2 Lesion classification
	6.6 Conclusion
	Acknowledgments
	References
7 Deep learning on information retrieval and its applications
	7.1 Introduction
	7.2 Traditional approaches to information retrieval
		7.2.1 Basic retrieval models
		7.2.2 Semantic-based models
		7.2.3 Term dependency-based models
		7.2.4 Learning to rank–based models
	7.3 Deep learning approaches to IR
		7.3.1 Representation learning-based methods
			7.3.1.1 Deep neural network–based methods
			7.3.1.2 Convolutional neural network–based methods
			7.3.1.3 Recurrent neural network–based methods
		7.3.2 Methods of matching function learning
			7.3.2.1 Matching with word-level similarity matrix
			7.3.2.2 Matching with attention model
			7.3.2.3 Matching with transformer model
			7.3.2.4 Combining matching function learning and representation learning
		7.3.3 Methods of relevance learning
			7.3.3.1 Based on global distribution of matching strengths
			7.3.3.2 Based on local context of matched terms
	7.4 Discussions and analyses
	7.5 Conclusions and Future Work
	References
	Further reading
8 Electrical impedance tomography image reconstruction based on autoencoders and extreme learning machines
	8.1 Introduction
	8.2 Related works
	8.3 Materials and methods
		8.3.1 Electrical impedance tomography problems and reconstruction
		8.3.2 EIT image reconstruction techniques
		8.3.3 Autoencoders
		8.3.4 Extreme learning machines
		8.3.5 Proposed reconstruction method
		8.3.6 Proposed experiments
	8.4 Results and discussions
	8.5 Conclusion
	Acknowledgments
	References
9 Crop disease classification using deep learning approach: an overview and a case study
	9.1 Introduction
		9.1.1 Literature survey
	9.2 Overview of the convolutional neural network architectures
	9.3 Architecture of SqueezeNet
	9.4 Implementation
	9.5 Results and discussion
	9.6 Conclusion
	Acknowledgment
	References
Index