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

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