product iamge

IoT-enabled Convolutional Neural Networks: Techniques and Applications

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Convolutional neural networks (CNNs), a type of deep neural network that has become dominant in a variety of computer vision tasks, in recent few years has attracted interest across a variety of domains due to their high efficiency at extracting meaningful information from visual imagery. Convolutional neural networks (CNNs) excel at a wide range of machine learning and deep learning tasks. As sensor-enabled internet of things (IoT) devices pervade every aspect of modern life, it is becoming increasingly critical to run CNN inference, a computationally intensive application, on resource-constrained devices.

Through this edited volume we aim to provide a structured presentation of CNN enabled IoT applications in vision, speech, and natural language processing. This book discusses a variety of CNN techniques and applications, including but not limited to, IoT enabled CNN for speech de-noising, a smart app for visually impaired people, disease detection, ECG signal analysis, weather monitoring, texture analysis, etc.

Unlike other books on the market, this book covers the tools, techniques, and challenges associated with the implementation of CNN algorithms, computation time, and the complexity associated with reasoning and modelling various types of data. We have included CNN's current research trends and future directions.

Author(s): Mohd Naved, V. Ajantha Devi, Loveleen Gaur, Ahmed A. Elngar
Series: River Publishers Series in Automation, Control and Robotics
Publisher: River Publishers
Year: 2023

Language: English
Pages: 407
City: Gistrup

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
List of Figures
List of Tables
List of Contributors
List of Abbreviations
Chapter 1: Convolutional Neural Networks in Internet of Things: A Bibliometric Study
1.1: Introduction
1.2: Related Work
1.3: Research Questions
1.4: Literature Review
1.5: Overview of Bibliometric Analysis
1.6: Methodology for Bibliometric Analysis
1.6.1: Database Collection
1.6.2: Methods for Data Extraction
1.6.3: Year-Wise Publications
1.6.4: Network Analysis of Citations
1.6.4.1: Citation analysis of countries
1.6.4.2: Citation analysis of organizations
1.6.4.3: Citation analysis of authors
1.6.4.4: Source citation analysis
1.6.4.5: Citation analysis of documents
1.6.5: Co-occurrence Analysis for KEYWORDS/HOT RESEARCH AREAS
1.6.5.1: Co-occurrence for all keywords
1.6.5.2: Co-occurrence for author keywords
1.6.5.3: Co-occurrence for index keywords
1.7: Limitations and Future Work
1.8: Conclusion
References
Chapter 2: Internet of Things Enabled Convolutional Neural Networks: Applications, Techniques, Challenges, and Prospects
2.1: Introduction
2.1.1: Contribution of the Chapter
2.1.2: Chapter Organization
2.2: Application of Artificial Intelligence in IoT
2.3: Convolutional Neural Networks and its Architecture
2.3.1: CNN Based on Spatial Exploration
2.3.2: Depth of CNNs
2.3.3: Multi-Path of CNNs
2.3.4: Width for Multi-Connection CNNs
2.3.5: Feature-Map Exploitation for CNN
2.3.6: The CNN Channels for Exploitation
2.3.7: Attention Exploration for CNN
2.4: The CNN Techniques in IoT Environment
2.4.1: Intelligence Healthcare System
2.4.2: Intelligence Learning System
2.4.3: Smart City
2.4.4: Agriculture
2.4.5: Meteorology
2.4.6: Biometrics Applications
2.4.7: E-Commerce and E-Business
2.5: Challenges of Applicability of IoT-Enabled CNN in Various Fields
2.6: Conclusion and Future Direction
References
Chapter 3: Convolutional Neural Network-Based Models for Speech Denoising and Dereverberation: Algorithms and Applications
3.1: Introduction
3.2: Signal Model and Problem Formulation
3.2.1: Signal Model
3.2.2: Feature Extraction
3.2.3: Problem Formulation
3.3: One-stage CNN-based Speech Enhancement
3.3.1: The Architecture of GCT-Net
3.3.2: Gated Linear Units
3.3.3: S-TCMs
3.3.4: Framework Details
3.3.5: Loss Function
3.4: Multi-Stage CNN-based Speech Enhancement
3.4.1: Framework Structure
3.4.2: Loss Function
3.5: Experimental Setup
3.5.1: Datasets
3.5.2: Parameter Configuration
3.6: Results and Analysis
3.6.1: Spectrograms
3.6.2: PESQ Scores
3.6.3: ESTOI scores
3.6.4: SDR
3.6.5: Subjective Listening Test
3.7: Discussions and Conclusions
References
Chapter 4: Edge Computing and Controller Area Network (CAN) for IoT Data Classification using Convolutional Neural Network
4.1: Introduction
4.1.1: Internet of Things (IoT)
4.1.2: Emotional Classification
4.1.3: Applications
4.2: Literature Review
4.3: System Design
4.3.1: Featured Image Formation
4.3.2: CNN Classification
4.4: Result and Discussion
4.5: Conclusion
References
Chapter 5: Assistive Smart Cane for Visually Impaired People Based on Convolutional Neural Network (CNN)
5.1: Introduction
5.2: Literature Review
5.3: Proposed Methodology
5.3.1: Assistive Algorithm
5.3.2: Data Acquisition
5.3.3: Device Architecture
5.3.4: Arduino and Its Interfacing
5.3.5: Power
5.3.6: Memory
5.3.7: Deep Convolutional Neural Network (CNN)
5.3.8: Alex-Net Architecture
5.3.9: Xception Model
5.3.10: Visual Geometry Group (VGG16,19)
5.3.11: Residual Neural Network (ResNet)
5.3.12: Inception (V2, V3, InceptionResNet)
5.3.13: MobileNet
5.3.14: DenseNet
5.3.15: Experimental Results Analysis
5.4: Conclusion and Future Directions
References
Chapter 6: Application of IoT-Enabled CNN for Natural Language Processing
6.1: Introduction
6.2: Related Work
6.3: IoT-Enabled CNN for NLP
6.4: Applications of IoT-Enabled CNN for NLP
6.4.1: Home Automation
6.4.2: Boon for Disabled People
6.5: Applications of IoT-Enabled CNN
6.5.1: Smart Farming
6.5.2: Smart Infrastructure
6.6: Challenges in NLP-Based IoT Devices and Solutions
6.7: Conclusion
References
Chapter 7: Classification of Myocardial Infarction in ECG Signals Using Enhanced Deep Neural Network Technique
7.1: Introduction
7.2: Related Work
7.3: The Normal ECG Signal
7.3.1: ECG Features
7.3.2: 12-Lead ECG System
7.4: Proposed Methodology
7.4.1: Phase I: Pre-Processing
7.4.2: Phase II: Feature Extraction
7.4.3: Phase III: Feature Selection
7.5: ECG Classification Using Deep Learning Techniques
7.5.1: CNN
7.5.2: LSTM
7.5.3: Enhanced Deep Neural Network (EDN)
7.6: Experimental Results
7.6.1: Performance Evaluation
7.6.2: Evaluation Metrics
7.7: Results and Discussion
7.8: Conclusion
References
Chapter 8: Automation Algorithm for Labeling of Oil Spill Images using Pre-trained Deep Learning Model
8.1: Introduction
8.2: Related Work
8.2.1: Image Annotation Algorithm
8.2.2: Semantic Segmentation
8.3: Proposed Method
8.3.1: Image Pre-Processing
8.3.2: Semantic Segmentation
8.3.3: Automation Algorithm
8.4: Performance Measures
8.4.1: Evaluation of Segmentation Models
8.5: Conclusion
References
Chapter 9: Environmental Weather Monitoring and Predictions System Using Internet of Things (IoT) Using Convolutional Neural Network
9.1: Introduction
9.1.1: Types of Weather Forecasting
9.1.1.1: Computer Forecasting
9.1.1.2: Synoptic Forecasting
9.1.1.3: Persistence Forecasting
9.1.1.4: Statistical Forecasting
9.2: Literature Review
9.3: System Design
9.4: Result and Discussion
9.4.1: Dataset
9.5: Conclusion
References
Chapter 10: E-Learning Modeling Technique and Convolution Neural Networks in Online Education
10.1: Introduction
10.2: Literature Review
10.3: Discussion
10.3.1: Definition of ML and AI
10.3.2: Definition of ML and AI in KKU EL
10.3.3: ML Classifications for KKU EL
10.3.4: The Benefits of ML and AI in KKU EL
10.3.5: ML and AI are Transforming the EL Scenario in KKU
10.3.6: Customized EL Content
10.3.7: Resource Allocation
10.3.8: Automate Content Delivery and Scheduling Process
10.3.9: Improve KKU EL Return on Investment
10.3.10: Improve Learner Motivation
10.3.11: Online Training Programs
10.4: Results
10.4.1: ExL
10.4.2: EER
10.4.3: OnT
10.4.4: AC
10.4.5: AG and M
10.4.6: CC
10.4.7: CSL
10.4.8: SLS
10.5: Conclusion
References
Chapter 11: Quantitative Texture Analysis with Convolutional Neural Networks
11.1: Introduction to Transfer Learning with Convolutional Neural Networks
11.1.1: The ImageNet Large-Scale Visual Recognition Challenge (ILSVRC)
11.1.2: Transfer Learning Strategies
11.2: Texture Analysis
11.2.1: Textures in Nature and the Built Environment
11.2.2: Traditional Approaches to Texture Analysis
11.2.2.1: Statistical methods
11.2.2.2: Structural methods
11.2.2.3: Spectral methods
11.2.2.4: Modeling approaches
11.2.3: More Recent Approaches to Texture Analysis
11.2.4: Learning Approaches to Texture Analysis
11.2.4.1: Vocabulary-based approaches
11.2.4.2: Deep learning approaches
11.3: Methodology of Texture Analysis with Convolutional Neural Networks
11.3.1: Overall Analytical Methodology
11.3.2: Traditional Algorithms
11.3.2.1: Gray level co-occurrence matrices (GLCM)
11.3.2.2: Local binary patterns (LBPs)
11.3.2.3: Textons
11.3.3: Deep Learning Algorithms
11.4: Case Study 1: Voronoi Simulated Material Textures
11.4.1: Voronoi Simulation of Material Textures
11.4.2: Comparative Analysis of Convolutional Neural Networks and Traditional Algorithms
11.5: Case Study 2: Textures in Flotation Froths
11.5.1: Froth Image Analysis in Flotation
11.5.2: Recognition of Operational States with Convolutional Neural Networks
11.6: Case Study 3: Imaged Signal Textures
11.6.1: Treating Signals as Images
11.6.2: Monitoring of Stock Prices by the Use of Convolutional Neural Networks
11.7: Discussion
11.8: Conclusion
References
Chapter 12: Internet of Things Based Enabled Convolutional Neural Networks in Healthcare
12.1: Introduction
12.2: Internet of Things Application in the Healthcare Systems
12.2.1: Internet of Things Operation in Healthcare Systems
12.2.2: Internet of Things and Patient Monitoring Systems
12.2.3: Internet of Things and Healthcare Data Classification
12.3: Application of Internet of Things Enabled Convolutional Neural
12.3.1: IoT-Enabled CNN for Improving Healthcare Diagnosis
12.3.2: IoT-Enabled CNN for Improving Healthcare Monitoring System
12.4: The Challenges of Internet of Things Enabled Convolutional Neural
12.5: Framework for Internet of Things Enabled CNN in Healthcare Systems
12.5.1: The Practical Application of the Proposed Framework
12.5.1.1: Dataset
12.5.1.2: Dataset pre-processing
12.5.2: Convolutional Neural Network Classification
12.5.3: Performance Evaluation Metrics
12.6: Results and Discussion
12.6.1: Performance Evaluation of the Proposed Model
12.6.2: Performance Comparison of the Proposed Model
12.7: Conclusion and Future Directions
References
Index
About the Editors