Published 2022
Table of Contents:
“...Preface xv List of Figures xxv List of Tables xxxiii List of Contributors xxxvii List of Abbreviations xli 1 Convolutional Neural Networks in Internet of Things: A Bibliometric Study 1 1.1 Introduction 2 1.2 Related Work 3 1.3 Research Questions 4 1.4 Literature Review 5 1.5 Overview of Bibliometric Analysis 6 1.6 Methodology for Bibliometric Analysis 7 1.6.1 Database Collection 7 1.6.2 Methods for
Data Extraction 7 1.6.3 Year-Wise Publications 8 1.6.4 Network Analysis of Citations 9 1.6.4.1 Citation analysis of countries 9 1.6.4.2 Citation analysis of organizations 9 1.6.4.3 Citation analysis of authors 10 1.6.4.4 Source citation analysis 12 1.6.4.5 Citation analysis of documents 14 1.6.5 Co-occurrence Analysis for KEYWORDS/HOT RESEARCH AREAS 15 1.6.5.1 Co-occurrence for all keywords 17 1.6.5.2 Co-occurrence for author keywords 19 1.6.5.3 Co-occurrence for index keywords 19 1.7 Limitations and Future Work 20 1.8 Conclusion 24 References 24 2 Internet of Things Enabled Convolutional Neural Networks: Applications, Techniques, Challenges, and Prospects 27 2.1 Introduction 28 2.1.1 Contribution of the Chapter 31 2.1.2 Chapter Organization 31 2.2 Application of Artificial Intelligence in IoT 31 2.3 Convolutional Neural Networks and its Architecture 32 2.3.1 CNN Based on Spatial Exploration 37 2.3.2 Depth of CNNs 38 2.3.3 Multi-Path of CNNs 38 2.3.4 Width for Multi-Connection CNNs 38 2.3.5 Feature-Map Exploitation for CNN 38 2.3.6 The CNN Channels for Exploitation 39 2.3.7 Attention Exploration for CNN 39 2.4 The CNN Techniques in IoT Environment 41 2.4.1 Intelligence Healthcare System 43 2.4.2 Intelligence
Learning System 44 2.4.3 Smart City 45 2.4.4 Agriculture 46 2.4.5 Meteorology 47 2.4.6 Biometrics Applications 47 2.4.7 E-Commerce and E-Business 48 2.5 Challenges of Applicability of IoT-Enabled CNN in Various 48 2.6 Conclusion and Future Direction 52 References 53 3 Convolutional Neural Network-Based Models for Speech Denoising and Dereverberation: Algorithms and Applications 65 3.1 Introduction 66 3.2 Signal Model and Problem Formulation 69 3.2.1 Signal Model 69 3.2.2 Feature Extraction 69 3.2.3 Problem Formulation 70 3.3 One-stage CNN-based Speech Enhancement 71 3.3.1 The Architecture of GCT-Net 71 3.3.2 Gated Linear Units 73 3.3.3 S-TCMs 73 3.3.4 Framework Details 74 3.3.5 Loss Function 76 3.4 Multi-Stage CNN-based Speech Enhancement 77 3.4.1 Framework Structure 78 3.4.2 Loss Function 78 3.5 Experimental Setup 79 3.5.1 Datasets 79 3.5.2 Parameter Configuration 80 3.6 Results and Analysis 80 3.6.1 Spectrograms 81 3.6.2 PESQ Scores 84 3.6.3 ESTOI scores 85 3.6.4 SDR 86 3.6.5 Subjective Listening Test 88 3.7 Discussions and Conclusions 90 References 91 4 Edge
Computing and Controller Area Network (CAN) for IoT
Data Classification using Convolutional Neural Network 97 4.1 Introduction 98 4.1.1 Internet of Things (IoT) 99 4.1.2 Emotional Classification 100 4.1.3 Applications 102 4.2 Literature Review 104 4.3 System Design 107 4.3.1 Featured Image Formation 107 4.3.2 CNN Classification 110 4.4 Result and Discussion 115 4.5 Conclusion 119 References 120 5 Assistive Smart Cane for Visually Impaired People Based on Convolutional Neural Network (CNN) 125 5.1 Introduction 126 5.2 Literature Review 127 5.3 Proposed Methodology 132 5.3.1 Assistive Algorithm 132 5.3.2
Data Acquisition 132 5.3.3 Device Architecture 133 5.3.4 Arduino and Its Interfacing 134 5.3.5 Power 135 5.3.6 Memory 136 5.3.7 Deep Convolutional Neural Network (CNN) 136 5.3.8 Alex-Net Architecture 137 5.3.9 Xception Model 137 5.3.10 Visual Geometry Group (VGG16,19) 138 5.3.11 Residual Neural Network (ResNet) 139 5.3.12 Inception (V2, V3, InceptionResNet) 139 5.3.13 MobileNet 139 5.3.14 DenseNet 140 5.3.15 Experimental Results Analysis 140 5.4 Conclusion and Future Directions 143 References 144 6 Application of IoT-Enabled CNN for Natural Language
Processing 149 6.1 Introduction 150 6.2 Related Work 152 6.3 IoT-Enabled CNN for NLP 154 6.4 Applications of IoT-Enabled CNN for NLP 154 6.4.1 Home Automation 157 6.4.2 Boon for Disabled People 159 6.5 Applications of IoT-Enabled CNN 161 6.5.1 Smart Farming 161 6.5.2 Smart Infrastructure 166 6.6 Challenges in NLP-Based IoT Devices and Solutions 166 6.7 Conclusion 170 References 171 7 Classification of Myocardial Infarction in ECG Signals Using Enhanced Deep Neural Network Technique 179 7.1 Introduction 180 7.2 Related Work 181 7.3 The Normal ECG Signal 183 7.3.1 ECG Features 186 7.3.2 12-Lead ECG System 186 7.4 Proposed Methodology 187 7.4.1 Phase I: Pre-
Processing 188 7.4.2 Phase II: Feature Extraction 189 7.4.3 Phase III: Feature Selection 190 7.5 ECG Classification Using Deep
Learning Techniques 191 7.5.1 CNN 192 7.5.2 LSTM 195 7.5.3 Enhanced Deep Neural Network (EDN) 197 7.6 Experimental Results 202 7.6.1 Performance Evaluation 203 7.6.2 Evaluation Metrics 204 7.7 Results and Discussion 206 7.8 Conclusion 209 References 210 8 Automation Algorithm for Labeling of Oil Spill Images using Pre-trained Deep
Learning Model 213 8.1 Introduction 214 8.2 Related Work 216 8.2.1 Image Annotation Algorithm 216 8.2.2 Semantic Segmentation 218 8.3 Proposed Method 219 8.3.1 Image Pre-
Processing 219 8.3.2 Semantic Segmentation 222 8.3.3 Automation Algorithm 226 8.4 Performance Measures 229 8.4.1 Evaluation of Segmentation Models 229 8.5 Conclusion 234 References 235 9 Environmental Weather Monitoring and Predictions System Using Internet of Things (IoT) Using Convolutional Neural Network 239 9.1 Introduction 240 9.1.1 Types of Weather Forecasting 243 9.1.1.1
Computer Forecasting 243 9.1.1.2 Synoptic Forecasting 243 9.1.1.3 Persistence Forecasting 243 9.1.1.4 Statistical Forecasting 244 9.2 Literature Review 244 9.3 System Design 246 9.4 Result and Discussion 251 9.4.1 Dataset 251 9.5 Conclusion 255 References 256 10 E-
Learning Modeling Technique and Convolution Neural Networks in Online Education 261 10.1 Introduction 262 10.2 Literature Review 265 10.3 Discussion 270 10.3.1 Definition of ML and AI 271 10.3.2 Definition of ML and AI in KKU EL 272 10.3.3 ML Classifications for KKU EL 272 10.3.4 The Benefits of ML and AI in KKU EL 275 10.3.5 ML and AI are Transforming the EL Scenario in KKU 276 10.3.6 Customized EL Content 279 10.3.7 Resource Allocation 279 10.3.8 Automate Content Delivery and Scheduling
Process 279 10.3.9 Improve KKU EL Return on Investment 279 10.3.10 Improve Learner Motivation 280 10.3.11 Online Training
Programs 280 10.4 Results 282 10.4.1 ExL 285 10.4.2 EER 285 10.4.3 OnT 286 10.4.4 AC 286 10.4.5 AG and M 286 10.4.6 CC 287 10.4.7 CSL 287 10.4.8 SLS 287 10.5 Conclusion 288 References 289 11 Quantitative Texture Analysis with Convolutional Neural Networks 297 11.1 Introduction to Transfer
Learning with Convolutional Neural Networks 298 11.1.1 The ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) 299 11.1.2 Transfer
Learning Strategies 299 11.2 Texture Analysis 300 11.2.1 Textures in Nature and the Built Environment 300 11.2.2 Traditional Approaches to Texture Analysis 301 11.2.2.1 Statistical methods 301 11.2.2.2 Structural methods 303 11.2.2.3 Spectral methods 303 11.2.2.4 Modeling approaches 303 11.2.3 More Recent Approaches to Texture Analysis 303 11.2.4
Learning Approaches to Texture Analysis 303 11.2.4.1 Vocabulary-based approaches 303 11.2.4.2 Deep
learning approaches 304 11.3 Methodology of Texture Analysis with Convolutional Neural Networks 304 11.3.1 Overall Analytical Methodology 304 11.3.2 Traditional Algorithms 305 11.3.2.1 Gray level co-occurrence matrices (GLCM) 305 11.3.2.2 Local binary patterns (LBPs) 307 11.3.2.3 Textons 307 11.3.3 Deep
Learning Algorithms 309 11.4 Case Study 1: Voronoi Simulated Material Textures 309 11.4.1 Voronoi Simulation of Material Textures 309 11.4.2 Comparative Analysis of Convolutional Neural Networks and Traditional Algorithms 309 11.5 Case Study 2: Textures in Flotation Froths 312 11.5.1 Froth Image Analysis in Flotation 312 11.5.2 Recognition of Operational States with Convolutional Neural Networks 314 11.6 Case Study 3: Imaged Signal Textures 317 11.6.1 Treating Signals as Images 317 11.6.2 Monitoring of Stock Prices by the Use of Convolutional Neural Networks 318 11.7 Discussion 320 11.8 Conclusion 321 References 322 12 Internet of Things Based Enabled Convolutional Neural Networks in Healthcare 329 12.1 Introduction 330 12.2 Internet of Things Application in the Healthcare Systems 332 12.2.1 Internet of Things Operation in Healthcare Systems 333 12.2.2 Internet of...
”
Call Number:
Loading...
Located:
Loading...
Connect to the full text of this electronic book
eBook