Machine Learning and IoT for Intelligent Systems and Smart Applications (Computational Intelligence in Engineering Problem Solving)

✍ Scribed by Madhumathy P (editor), M Vinoth Kumar (editor), R. Umamaheswari (editor)

• Publisher: CRC Press
• Year: 2021
• Tongue: English
• Leaves: 243
• Edition: 1
• Category: Library

✦ Synopsis

The fusion of AI and IoT enables the systems to be predictive, prescriptive, and autonomous, and this convergence has evolved the nature of emerging applications from being assisted to augmented, and ultimately to autonomous intelligence. This book discusses algorithmic applications in the field of machine learning and IoT with pertinent applications. It further discusses challenges and future directions in the machine learning area and develops understanding of its role in technology, in terms of IoT security issues. Pertinent applications described include speech recognition, medical diagnosis, optimizations, predictions, and security aspects.

Features:

• Focuses on algorithmic and practical parts of the artificial intelligence approaches in IoT applications.
• Discusses supervised and unsupervised machine learning for IoT data and devices.
• Presents an overview of the different algorithms related to Machine learning and IoT.
• Covers practical case studies on industrial and smart home automation.
• Includes implementation of AI from case studies in personal and industrial IoT.

This book aims at Researchers and Graduate students in Computer Engineering, Networking Communications, Information Science Engineering, and Electrical Engineering.

✦ Table of Contents

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Editors' Biographies
Contributors
1. A Study on Feature Extraction and Classification Techniques for Melanoma Detection
1.1 Introduction
1.2 Feature Extraction
1.2.1 Fourier Transform (FT)
Drawbacks
1.2.2 Short Time Fourier Transform (STFT)
Drawbacks
1.2.3 Wavelet Transform
1.2.3.1 Discrete Wavelet Transform
Drawbacks
1.2.3.2 Discrete Curvelet Transform
Drawbacks
1.2.3.3 Discrete Contourlet Transform
Drawbacks
1.2.3.4 Discrete Shearlet Transform
Drawbacks
1.2.3.5 Bendlet Transform
1.3 Classification
1.3.1 Logistic Regression
1.3.2 K-Nearest Neighbor
1.3.3 Decision Trees
1.3.4 Support Vector Machine
1.4 Skin Cancer Diagnostic System for Melanoma Detection
1.5 Conclusion
References
2. Machine Learning Based Microstrip Antenna Design in Wireless Communications
2.1 Introduction
2.2 Machine Learning in MSA Design
2.3 Application of MSA in IOT
2.4 Design & Analysis of MSA Using ANN
2.4.1 Artificial Neural Network
2.5 Results and Discussion
2.6 Design of Microstrip Antenna and Characterization Using SVM Method
2.7 Design of MSA for IoT Applications
2.8 Conclusion
References
3. LCL-T Filter Based Analysis of Two Stage Single Phase Grid Connected Module with Intelligent FANN Controllers
3.1 Introduction
3.2 Literature Survey
3.3 Proposed System
3.3.1 Mode of Operation-1: (t0-t1)
3.3.2 Mode of Operation-2: (t1-t2)
3.3.3 Mode of Operation-3: (t2-t3)
3.3.4 Mode of Operation-4: (t3-t4)
3.3.5 Mode of Operation-5: (t4-t5)
3.4 State Space Modeling and LCL-T Filter Design
3.4.1 Stability Analysis
3.4.2 Design of FANN Controller
3.5 Simulation Results
3.5.1 Hardware Implementation of Two Stage Single Phase LCL-T Inverter
3.6 Conclusion
References
4. Motion Vector Analysis Using Machine Learning Models to Identify Lung Damages for COVID-19 Patients
4.1 Introduction
4.1.1 Background of the Study
4.1.2 Motivation and Problem Statement
4.1.3 Structure of the Chapter
4.2 Proposed Methodology
4.2.1 Data Collection and Pre-Processing
4.2.2 Feature Extraction
4.2.2.1 Block Matching Algorithm
4.2.2.2 Region-Wise Edge Factor-Based Motion Vector Extraction
4.2.3 Feature Processing
4.2.4 Classification
4.3 Results and Discussion
4.3.1 Feature Analysis
4.3.2 Classification Analysis
4.4 Conclusion
References
5. Enhanced Effective Generative Adversarial Networks Based LRSD and SP Learned Dictionaries with Amplifying CS
5.1 Introduction
5.2 Related Work
5.2.1 SpR and DL
5.2.2 The Producer and the Discriminator
5.2.2.1 Discriminative LR and Sparse DL
5.3 Proposed Work
5.3.1 Decomposing LR and SP
5.3.2 Enhanced Effective Generative Adversarial Networks
5.3.3 The Producer and the Discriminator
5.3.4 Fusion Scheme
5.4 Experimental Setup
5.4.1 Applying Enhanced Effective Generative Adversarial Networks
5.5 Discussion
5.6 Conclusion
References
6. Deep Learning Based Parkinson's Disease Prediction System
6.1 Introduction
6.2 Literature Survey
6.3 Proposed Methodology
6.4 Implementation
6.4.1 Data Collection
6.4.2 Data Preprocessing
6.4.3 Deep Learning Algorithm with RBM
6.4.4 Training Phase
6.4.5 Testing Phase
6.5 Result Analysis
6.6 Conclusion
References
7. Non-uniform Data Reduction Technique with Edge Preservation to Improve Diagnostic Visualization of Medical Images
7.1 Introduction
7.2 Methodology
7.2.1 Algorithm of the Data Reduction Algorithm
7.2.2 Algorithm of the Proposed Data Reduction Method with Enhanced Edge Information
7.3 Results and Discussion
7.3.1 Regression Analysis
7.4 Conclusion
References
8. A Critical Study on Genetically Engineered Bioweapons and Computer-Based Techniques as Counter Measure
8.1 Introduction and History
8.2 Genetically Engineered Pathogen
8.2.1 Designer Genes
8.2.2 Binary Bioweapon
8.2.3 Gene Therapy as Bioweapon
8.2.4 Stealth Virus
8.2.5 Hot Swapping Disease
8.2.6 Designer Disease
8.3 Computer-Based Detection and Counter Measure Techniques
8.3.1 Computer and Artificial Intelligence-Based Counter Measure Techniques
8.3.2 Computer-Assisted Surgery as Counter Measure
8.3.3 Big Data as Healthcare
8.3.4 Computer-Assisted Decision Making
8.3.5 Computer Vision-Based Techniques as Counter Measure
8.3.6 IoT-Based System as Counter Measure for Bioweapon Against Crop War
8.4 Conclusion
References
9. An Automated Hybrid Transfer Learning System for Detection and Segmentation of Tumor in MRI Brain Images with UNet and VGG-19 Network
9.1 Introduction
9.2 Related Works
9.3 Proposed System
9.4 Experimental Setup and Results
9.5 Discussion
9.6 Conclusion and Future Work
References
10. Deep Learning-Computer Aided Melanoma Detection Using Transfer Learning
10.1 Introduction
10.2 Related Research Work
10.2.1 Benign Sample Image 1
10.2.2 Benign Sample Image 2
10.2.3 Melanoma Sample Image 1
10.2.4 Melanoma Sample Image 2
10.3 Transfer Learning CAD SCC Model
10.3.1 Model Summary
10.3.2 Sample Images
10.4 Accuracy Results Achieved Through the Proposed Processing
10.4.1 Loss Results Achieved Through the Proposed Processing
10.4.2 Confusion Matrix
10.4.3 Classification Report
10.5 Conclusion
References
11. Development of an Agent-Based Interactive Tutoring System for Online Teaching in School Using Classter
11.1 Introduction
11.2 Literature Review
11.3 Methods and Materials
11.3.1 Standard Intelligent Learning System
11.4 Implementation
11.4.1 Student Enrollment
11.4.2 Standard Intelligent Learning System
11.4.3 Evaluation System
11.5 Result and Discussion
11.5.1 Classter Student Performance Assessment
11.5.2 RNN Network
11.6 Conclusion
References
12. Fusion of Datamining and Artificial Intelligence in Prediction of Hazardous Road Accidents
12.1 Introduction
12.2 Related Works on Prediction of Road Accidents
12.3 Motivation and Problem Statement
12.4 Proposed Methodology
12.5 Kaggle and Government Statistical Data
12.6 Dark Sky
12.6.1 The Datasets Help to Assume the Constant Weather Conditions on the Whole Day
12.6.2 The Environmental Factors Depend on Previous Environmental Datasets
12.6.3 Apriori Algorithm for Road Accident Prediction
12.6.4 Road Accident Analysis and Classification Using Apriori Algorithm
12.6.5 Strong Association Rule Mining for Road Accidents
12.6.6 Naïve Bayes Algorithm for Prevention of Road Accidents
12.6.7 Sample Example
12.6.8 Training Dataset
12.7 Software Used for Prediction
12.7.1 Jupyter
12.7.2 Python
12.7.3 HTML and CSS
12.8 Results and Discussion
12.9 Graphical Representation
12.10 Road Category and Road Features
12.11 Accidents by Road Environment
12.12 Accidents by Weather Condition
12.13 Types of Vehicles Involved in Road Accidents
12.14 Prevention
12.14.1 Using AI Techniques to Predict and Prevent Road Accidents
12.14.2 Machine Learning Process Reduces the Life Risk
12.14.3 Avoid the Rush and Drunk Driving
12.15 Limitation
12.16 Recommendation
12.17 Significance of the Study
12.18 Conclusion
References
Index