Applied Learning Algorithms for Intelligent IoT

Cover
Half Title
Title Page
Copyright Page
Contents
Contributors
1. Convolutional Neural Network in Computer Vision
	Introduction
		Convolutional Neural Network (CNN)
		Distinctive Properties of CNN
		Activation Functions for CNN
		Loss Function
		Datasets and Errors
		Bias and Variance
		Overfitting and Underfitting
	Understanding Padding and Stride
		Padding
		Stride
	Parameters and Hyper Parameters
	CONV Layer
		Filter
		Feature Map
		Convolution Operation
		Key Points about Convolution Layers and Filters
	Pooling Layer
		Key Points about Pooling Layer
		Types of Pooling
	Forward Propagation
		Calculating the Parameters
		Activation Shape and Size
	Backward Propagation
		Optimizers
		Other Ways to Improve the Performance of CNN
			Image Data Augmentation
			Deeper Hidden Layers
			Early Stopping
	Application of CNN
		Image Classification
	RCNN and Object Detection
		Region-Based Convolutional Neural Network (R-CNN)
		Fast R-CNN
		Faster R-CNN
		You Only Look Once (YOLO)
	Transfer Learning
		Transfer Learning for CNN
		Fine-Tuning or Freezing?
	Neural Style Transfer (NST)
2. Trends and Transition in the Machine Learning (ML) Space
	Introduction to Machine Learning
	Motivations for Machine Learning Algorithms
	Data Analytics and Machine Learning
	Supervised Learning
	Classification
	Naive Bayes (NB)
	Support Vector Machine (SVM) Classifier
	Types of Learners
		Eager Learners
		Document Classification
		Illustration
		Logistic Regression
	Practical Use Cases
		Weather Prediction
		Patient's Health Monitoring
		Unsupervised Learning
		Gaussian Mixture Models
		Hidden Markov Models
	Types of Unsupervised Learning
	Applications of Unsupervised Learning
	Process of Machine Learning
		Gathering Input Data
		Data Preparation
		Choosing a Model
		Training
		Evaluation
		Parameter Tuning
		Prediction
	Machine Learning - Practical Use Cases
		ML in Banking
		ML in Agriculture
		ML in Health Care
		ML in Automobile Industry
	Implementation
		Pandas
		Matplotlib
		Jupyter Notebook
		Google Colab
		scikit-learn
	Conclusion
	References
3. Next-Generation IoT Use Cases across Industry Verticals Using Machine Learning Algorithms
	Introduction
		Sensors
		Connectivity
		Data Processing
		User Interface
	IoT in Industry
		Machine Diagnosis and Prognosis System
		Remote Monitoring and Production Control
		Indoor Air Quality Monitoring System
		Noise Monitoring System
		Inventory Management System
	IoT in Health Care
		Pharmacy Management
		Drug Monitoring
		Smart Pills
		Wearables
		Fitness Trackers
		Smart Hearing Aids
		Wearables to Monitor Diseases
		Use of IoT for Physicians
		Medical Alert System
	Data Analytics for IoT
		IoT Data Analytics Using Machine Learning Algorithms
	Conclusion
	References
4. A Panoramic View of Cyber Attack Detection and Prevention Using Machine Learning and Deep Learning Approaches
	Introduction
	State of the Art Techniques
		Android-Based Malware Detection
		Ransomware Malware Detection
		Windows-Based Malware Detection
		Linux-Based Malware Detection
	Malware Detection Tools Used
	Conclusion
	References
5. Regression Algorithms in Machine Learning
	Introduction
	Background Study
	Different Types of Regression Algorithms in Machine Learning
		Simple Linear Regression
		Significance of Linear Regression
			Simple Linear Regression Model in Health-Related Data Analysis
		Polynomial Regression
			Polynomial Regression Model in COVID-19 Growth Pattern Analysis
		Support Vector Machine Regression
		Decision Tree Regression
		Random Forest Regression
	Case Study on Air Quality Prediction Using Machine Learning Regression Techniques
	Conclusions and Future Work
	References
6. Machine Learning-Based Industrial Internet of Things (IIoT) and Its Applications
	History of Internet of Things
	Scope of IoT
	Features of IOT
	Leading Types of IoT
	Advantages of IoT
		Machine Learning and Deep Learning
		Applications of ML
	IIoT - Industrial Internet of Things
	History of IIoT
	Advantages of IIoT
	IIoT in Industry 4.0
	IoT and IIoT
		The Future of IIoT
	IIoT Use Cases
		What Is Smart Manufacturing?
		Assets Tracking
		Industrial Example
		Digital Twins
		Industrial Example
		Advantages of Digital Twins
	Smart Metering
		Advantages of Smart Metering System
		Disadvantages of Smart Metering System
		Smart Farming
		How Smart Farming Can Be Done?
		Data Collection
		Informed Action and Planning
		Things to Be Considered before Implementing Smart Farming
	Advantages of Smart Farming:
		Livestock Management Using IoT
		Monitoring the Health of Cattle
		Monitoring Reproductive Cycle and Calving
		Fine-Tuning Feeding
		Maximizing Milking
		Connected Vehicles
	Conclusion
	References
7. Employee Turnover Prediction Using Single Voting Model
	Introduction
		Role of Supervisors
		Role of HR Department
	Related Work
	System Implementation
		Data Preprocessing
		Materials and Methods Used
			Logistic Regression
			Different Categories of Logistic Regression
			Deriving Logit Function
			Performance of Logistic Regression Model
			Naive Bayes Classification
			Categories of Naive Bayes Classification
				Outline placeholder
					Multinomial Naive Bayes
					Bernoulli Naive Bayes
					Gaussian Naive Bayes
			Benefits of Using Naive Bayes
			Areas of Applications
			Voting Classifier
			Hard Voting
			Soft Voting
	Results and Discussions
	Conclusion
	References
8. A Novel Implementation of Sentiment Analysis Toward Data Science
	Introduction
	Related Work
	Background of Sentiment Analysis
	Proposed Methodology
		Speech to Text Model
		Implementation of Sentiment Analysis
		Architecture of Sentiment Analysis
	Results
		Future Proposals of Speech-to-Text Sentiment Analysis
	Conclusion and Future Directions
	References
9. Conspectus of k-Means Clustering Algorithm
	Introduction
	Background Study
	Overview of K-Means Clustering
	An Insight about the Operational Working of K-Means Clustering
	Steps Involved in K-Means Clustering Algorithm
	Real-Time Project Implementation on Synchronic Health Fitness Detector of Combatants in Armed Conflicts Using K-Means Clustering Algorithm
		Proposed Work
		Design Methodology and Implementation
			Combatant's Segment
			Chief of Armed Force's Segment
			Army Control Room's Segment
		Results
	Real-World Use Cases of K-Means Clustering
	K-Means Clustering Algorithm Used as a Solution for Following Business Problems
		Purchaser Division
		Conveyance Enhancement
		Archive Arranging and Gathering
		Client Maintenance
		Rebate Examination
	Comparisons of K-Means Clustering with Other Unsupervised Algorithms
	Pros and Cons
	Conclusions and Future Work
	References
10. Systematic Approach to Deal with Internal Fragmentation and Enhancing Memory Space during COVID-19
	Introduction
		Internal Fragmentation
		Best-Fit Approach and Memory Bank
		Linear and Lasso Regression
	Literature Survey
		Dynamic Memory Allocation and Internal Fragmentation
		Internal Fragmentation Standards and Compatibility of Systems
		Processor Allocation and Internal Fragmentation
		ML and Cloud Storage
		Best-Fit Approach and Internal Fragmentation
		Storage and Dependability Study
		Lasso Regression Analysis and Cloud Computing
		Data Placement and Machine Learning
		Memory Resource Management
	Existing Technique
		Overview of the Existing Technique with Illustration
	Proposed Technique - Optimized Approach to Deal with Residual Space in Internal Fragmentation
		Flow Chart of the Proposed Technique
		Schematic of Memory Bank Approach
		Memory Bank Algorithm
	Linear Regression
	Lasso Regression
	Implementation Using Open Source Software - Scilab and Jupyter (Python)
		Pseudo Code of the Proposed Technique
			Using Scilab
			Using Jupyter (Python)
		Graphical Representation
			Inference
			Inference
			Inference
		Software Packages Used
		Results and discussions
	Conclusion and Future Work
	References
11. IoT Automated Spy Drone to Detect and Alert Illegal Drug Plants for Law Enforcement
	Introduction
		Objectives
	Literature Survey
		Existing System
		Proposed System
	Architectural Diagrams
	Methodology
		Technical Approach
		VGG16 Architecture
		Modules Involved
		Description of Working Modules
			The Steps Involved in the Image Classification VGG16 Model
		Remote Interface Encryption Is Done by Using Vigenere Cipher and MD5 Hashing Techniques
			Vigenere Cipher
			Encryption
			Decryption
			MD5 Hashing Techniques
			Drone Frame
	Implementation
		Implementation of Methodologies of the Neural Network Models
		Implementing VGG16
			Import Packages
			Import DataSet
			Image Preprocessing
			Import Target Image Input
			Visualize the Plant in RGB
			Visualize the Plant in HSV
		Segmentation
			Color-Based Segmentation
			Segmentation Function
		Computer Vision Model
	Experimental Results
		Remote Interface Screenshots
	Conclusion
	References
12. Expounding k-means-inspired network partitioning algorithm for SDN Controller Placement
	Introduction
	Leveraging on Unsupervised Learning
	k-Means Algorithm
		Data-Set for k-Means Algorithm
		Distance Formula of Centroid in k-Means Algorithm
		Mechanism to Compute the Value of K
	Properties of k-Means
	Compare the k-Means with Fuzzy C Mean, K Mediods, and k-Means++
	k-Means Clustering in Software Defined Network (SDN)
		Exploring the k-Means Clustering in Resolving SDN Challenges
		SDN Network Partitioning of Saren Topology-Based using k-Means
	Conclusion
	References
13. An Intelligent Deep Learning-Based Wireless Underground Sensor System for IoT-Based Agricultural Application
	Introduction
		System Overview
		Scope of the Project
		Literature Survey
		Underground Communications Networks
		WUSN in Crop Production
		Test Bed Development for WUSN
	Soil Moisture Measurement
		Underground Mining
			Underground Mine Communications
			Occupational Health Hazard in Mining
		Wireless Underground Sensor
			Agriculture Field Monitoring
			Spatio-Temporal Soil Moisture Measurement
			Channel Model and Analysis for Wireless Underground Sensor Networks in Soil Medium
	System Analysis
		Existing System
		Proposed System
		System Requirements
			Software Requirements
			Hardware Requirements
			Module Description
			Interfacing Sensor - Humidity Sensor
			General Description
			Product Description
			Features
			Applications
			Soil Moisture Sensor
			General Description
			Product Description
			Features
			Applications
			Programming Microcontroller
			Perisoil Moistural Feature
			Analog Features
			Special Microcontroller Features
			CMOS Technology
			Pin Diagram
			Device Overview
			Memory Organization
			Data Memory Organization
			I/O ports:
			PORTA and the TRISA Registers
			PORTB and the TRISB Registers
			PORTC and the TRISC Register:
			PORTD and TRISD Registers
			PORTE and TRISE Registers
			Features of Microcontroller
			Inside a Microcontroller
			Read Only Memory (ROM)
			Random Access Memory (RAM)
			Electrically Erasable Programmable ROM (EEPROM)
			Memory Organization of Microcontroller
			Special Function Register (SFR)
			Central Processing Unit (CPU)
			Data Transmission through Soil
			Visual Basic
			Internet of Things (IoT)
	System Architecture
		Architecture Description
		Wireless Underground Sensor Design Architecture
		Components of WUSN
			Cloud
			Arduino
			pH Sensor
			Soil Moisture Sensor
			Transmitter and Receiver
			Classification Based on Soil
			Result
	Conclusion
	References
14. Predicting Effectiveness of Solar Pond Heat Exchanger with LTES Containing CuO Nanoparticle Using Machine Learning
	Introduction
		Solar Pond
		Low-Temperature Energy Storage System (LTES) for Solar Pond
	Background Study
	Experimental Setup
	Experimentation
	Performance Parameters of Solar Pond
	Modeling Using Machine Learning
	Data Collection and Preprocessing
		Data Cleaning
		Normalization
		Outlier Analysis
		Correlation Analysis
	Multi-Linear Regression
	Splitting Dataset into Training and Testing Data
	Fitting and Prediction
	Results and Discussion
		Accuracy
		Goodness of Fit
	Future Works
	References
Index