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

✍ Scribed by Himansu Das (editor), Chittaranjan Pradhan (editor), Nilanjan Dey (editor)

• Publisher: Academic Press
• Year: 2020
• Tongue: English
• Leaves: 212
• Edition: 1
• Category: Library

✦ Synopsis

Deep learning, a branch of Artificial Intelligence and machine learning, has led to new approaches to solving problems in a variety of domains including data science, data analytics and biomedical engineering. Deep Learning for Data Analytics: Foundations, Biomedical Applications and Challenges provides readers with a focused approach for the design and implementation of deep learning concepts using data analytics techniques in large scale environments. Deep learning algorithms are based on artificial neural network models to cascade multiple layers of nonlinear processing, which aids in feature extraction and learning in supervised and unsupervised ways, including classification and pattern analysis. Deep learning transforms data through a cascade of layers, helping systems analyze and process complex data sets. Deep learning algorithms extract high level complex data and process these complex sets to relatively simpler ideas formulated in the preceding level of the hierarchy. The authors of this book focus on suitable data analytics methods to solve complex real world problems such as medical image recognition, biomedical engineering, and object tracking using deep learning methodologies. The book provides a pragmatic direction for researchers who wish to analyze large volumes of data for business, engineering, and biomedical applications. Deep learning architectures including deep neural networks, recurrent neural networks, and deep belief networks can be used to help resolve problems in applications such as natural language processing, speech recognition, computer vision, bioinoformatics, audio recognition, drug design, and medical image analysis.

✦ Table of Contents

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