Linked e-resources
Details
Table of Contents
Cover
Title
Copyright
End User License Agreement
Contents
Preface
List of Contributors
Machine Learning Techniques and their Applications: Survey
P. Karthik1,*, K. Chandra Sekhar1 and D. Latha2
1. INTRODUCTION
1.1. History of AI &
ML
1.2. Applications of ML
1.2.1. Speech Recognition [19]
1.2.2. Predictive Analytics [19]
1.2.3. Product Recommendation [20]
1.2.4. Image Recognition [19]
1.2.5. Video Surveillance [20]
1.2.6. Extraction [19]
1.2.7. Traffic Alerts [20]
1.2.8. Medical Diagnosis [19]
1.2.9. Sentiment Analysis [20]
1.2.10. Google Translate [20]
1.2.11. Virtual Personal Assistants [20]
1.3. Difference Between Traditional Programming Concepts and ML Concepts [23]
1.3.1. Why Must We Learn ML?
1.3.2. Difference Between AI &
ML [23]
1.4. Steps to Learn ML
1.4.1. Data Gathering [24]
1.4.2. Data Preparation [24]
1.4.3. Selecting the Model [24]
1.4.4. Training the Model [24]
1.4.5. Evaluate the Model [24]
1.4.6. Parameter Tuning [24]
1.4.7. Make Patterns [24]
1.5. Types of ML
1.6. Basic ML Methods
1.7. ML in Agriculture
1.8. ML in Sentiment Analysis
1.9. ML in Stock Prediction
1.10. ML in Disease Prediction
1.11. ML in Data Mining
1.12. ML in COVID-19
1.13. ML in Cyber Security
1.14. ML in Cloud Computing
1.15. ML in Big Data Analytics (BDA)
1.16. ML in Recommendation System
1.17. Future Experiments on Real Time Problems Using ML
CONCLUSION
REFERENCES
Applications of Machine Learning
Prediction using Machine Learning
Adluri Vijaya Lakshmi1,*, Sowmya Gudipati Sri2, Ponnuru Sowjanya2 and K. Vedavathi3
1. INTRODUCTION TO MACHINE LEARNING
2. CLASSIFICATION OF MACHINE-LEARNING
2.1. Supervised Learning
2.2. Unsupervised Learning
2.3. Reinforcement Learning.
3. BREAST CANCER PREDICTION USING ML TECHNIQUES
3.1. Introduction
3.2. Related Works
4. HEART DISEASE PREDICTION USING MACHINE LEARNING TECHNIQUES
4.1. Introduction
4.2. Existing System
5. PREDICTING IPL RESULTS USING ML TECHNIQUES
5.1. Introduction
5.2. Related Work
6. PREDICTION OF SOFTWARE BUG UTILISING ML TECHNIQUE
6.1. Introduction
6.2. Related Work
7. PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUES
7.1. Introduction
7.2. Related Work
8. WEATHER PREDICTION USING MACHINE LEARNING TECHNIQUES
8.1. Machine Learning
8.2. Use of Algorithms
CONCLUSION
REFERENCES
Machine Learning Algorithms for Health Care Data Analytics Handling Imbalanced Datasets
T. Sajana1,* and K.V.S.N. Rama Rao2
1. INTRODUCTION
2. MACHINE LEARNING- AN INTELLIGENT AUTOMATED SYSTEM
3. TYPES OF DATASETS-BY NATURE
3.1. Balanced Datasets
3.2. Imbalanced Datasets
4. ISSUES WITH IMBALANCED DATASETS
4.1. Class Imbalance Problem
4.2. Classifiers Learning On Imbalanced Datasets
4.3. Taxonomy of Various Techniques on Imbalanced Datasets
5. APPLICATION OF CONVENTIONAL DATA MINING &
MACHINE LEARNING TECHNIQUES FOR HANDLING CLASS IMBALANCE PROBLEM
6. APPLICATION OF DATA LEVEL METHODS FOR HANDLING CLASS IMBALANCE PROBLEM
6.1. Undersampling
6.2. Oversampling
7. APPLICATION OF ALGORITHMIC LEVEL METHODS FOR HANDLING CLASS IMBALANCE PROBLEM
7.1. Cost-Sensitive Classifiers
7.2. Ensemble Techniques
CONCLUSION
REFERENCES
AI for Crop Improvement
S.V. Vasantha1,*
1. INTRODUCTION
2. GENOMICS FOR AGRICULTURE
3. AI FOR AGRICULTURE
4. AI TECHNIQUES FOR CROP IMPROVEMENT
5. AI-BASED CROP IMPROVEMENT MODEL (AI-CIM)
5.1. Automation of Modern Crop Improvement Process
5.2. AI Model for Enhanced Crop Breeding
5.2.1. Automated Selective Breeding System.
5.2.2. Automated Plant Health Monitoring System
CONCLUSION
REFERENCES
Real-Time Object Detection and Localization for Autonomous Driving
Swathi Gowroju1,*, V. Swathi1, J. Narasimha Murthy1 and D. Sai Kamesh1
1. INTRODUCTION
2. LITERATURE SURVEY
3. PROPOSED METHOD
3.1. Proposed Architecture
4. IMPLEMENTATION
4.1. Bounding Boxes
4.2. Anchor Boxes
4.3. Non-max Suppression
5. RELU ACTIVATION
6. LOSS FUNCTION
7. TRAINING PARAMETERS
8. RESULTS
CONCLUSION
ACKNOWLEDGEMENT
REFERENCES
Machine Learning Techniques in Image Segmentation
Narmada Kari1,*, Sanjay Kumar Singh1 and Dumpala Shanthi2
1. INTRODUCTION
2. LITERATURE REVIEW
3. METHODOLOGY
3.1. Collection of Data
3.2. Pre-processing of Images
3.3. Training Options
3.4. Define Label IDs
3.5. Feature Extraction
3.6. Feature Reduction/Selection
3.7. Feature Classification
3.8. Machine Learning
3.8.1. Supervised Learning
3.8.2. Unsupervised Learning
3.8.3. Reinforcement Learning
3.8.4. Deep Learning
3.8.5. Deep Reinforcement Learning
CONCLUSION
REFERENCES
Optimal Page Ranking Technique for Webpage Personalization Using Semantic Classifier
P. Pranitha1,*, A. Manjula1, G. Narsimha2 and K. Vaishali3
1. INTRODUCTION
2. LITERATURE SURVEY
2.1. Challenges
2.2. Motivation of Research
2.3. Proposed Methodology
2.4. Generation of Web Pages
3. PRE-PROCESSING
3.1. Feature Extraction and Web Page Ranking
3.2. ENN-based Semantic Features
4. RE-RANKING OF WEB PAGES
4.1. Grass Hopper Optimization (GHO)
4.1.1. Social Interaction Calculation
4.1.2. Solution Updating
4.2. Artificial Bee Colony Algorithm (ABC)
4.2.1. Employed Bee Operation
4.2.2. Probability Calculation
4.2.3. Onlooker Bee Operation
4.3. Oppositional Grass Bee Optimization (OGBEE).
4.3.1. Opposition Behavior Learning (OBL)
4.3.2. Fitness Calculation
4.3.3. Updating using Grasshopper Optimization
4.3.4. Scout Bee Operation
4.3.5. Termination Criteria
5. RESULTS AND DISCUSSION
5.1. Evaluation Metrics
5.1.1. Precision
5.1.2. Recall
5.1.3. F-measure
CONCLUSION
REFERENCES
Text Analytics
Divanu Sameera1,*, Niraj Sharma2 and R.V. Ramana Chary3
1. INTRODUCTION
1.1. Text Analytics Basics
1.2. Text Analytics Examples
2. HOW TO GET STARTED WITH TEXT ANALYTICS
2.1. Analyze Your Data
2.2. Use BI Tools to Understand Your Data
2.3. Final Words
3. EXAMPLES AND METHODS FOR TEXT ANALYTICS
3.1. Text Analytics Approach 1: Word Spotting
3.1.1. The Simplicity of the Word-spotting Approach is What Makes it so Appealing [28]
3.1.2. When Word Spotting is Acceptable?
3.2. Text Analytics Approach 2. Manual Rules
3.2.1. Multiple-word Meanings Make it Hard to Create Rules
3.2.2. Mentioned Word! = Core Topic
3.2.3. Rules
3.2.4. Taxonomies Don't Exist for Software Products and Many Other Businesses
3.2.5. Not Everyone can Maintain Rules
3.3. Text Analytics Approach 3. Text Categorization
3.3.1. What is Text Categorization, and How Does it Work?
3.3.2. You Won't Notice Emerging Themes
3.3.3. Lack of Transparency
3.3.4. Preparing and Managing Training Data is Hard
3.3.5. Re-training for Each New Dataset
3.4. Approach 4: Topic-Modelling
3.4.1. What's Incredible Regarding Topic-modelling
3.5. Approach 5. Thematic Analysis
3.5.1. Thematic Analysis: How it Works
3.5.2. Advantages and Disadvantages of Thematic Analysis
3.5.3. Human in The Loop
4. CASE STUDY
CONCLUSION
REFERENCES
Human Activity Recognition System Using Smartphone
R. Usha Rani1 and M. Sunitha1,*
1. INTRODUCTION
2. LITERATURE REVIEW
3. MAIN TECHNIQUES.
4. SMARTPHONE HAR COMMANDS
4.1. HAR Section 1: Data Cleaning Through Preprocessing
4.1.1. Data Filtering
4.1.2. Data Segmentation
4.1.3. Reduction
4.1.4. Selection of Feature
4.2. HAR Section II: Procedure to Perform Classification
CONCLUSION
REFERENCES
Smart Water Bottle with Smart Technology
Dumpala Shanthi1,*
1. INTRODUCTION
2. EMBEDDED SYSTEM
3. ARDUINO NANO
4. PIN DIAGRAM
4.1. Serial Communication
4.2. Water Level Sensor
5. LDR: WORKING
6. APPLICATIONS
6.1. Light Dependent Resistor (LDR) Measurement
6.2. Message Management General Description
6.3. RA Mode
6.4. Tape Mode
6.5. Automatic Gain Control (AGC)
6.6. Sampling Use
7. MODULE
7.1. Types
7.2. Security Concerns
7.3. Other Devices' Interference
7.4. Streaming Media of Poor Quality
7.5. Specifications
CONCLUSION
REFERENCES
Real World Applications of Machine Learning in Health Care
Kari Narmada1,*, Sanjay Kumar Singh1 and Dumpala Shanthi2
1. INTRODUCTION
2. LITERATURE REVIEW
3. TYPES OF MACHINE LEARNING
3.1. Supervised Learning
3.2. Unsupervised Learning
3.3. Reinforcement Learning
3.4. Recommender Systems
4. MACHINE LEARNING APPLICATIONS IN HEALTH CARE
4.1. The Most Challenges For AI In Healthcare
4.2. Possible Risks to Generalizability in Clinical Research and Machine Learning In Health Care
CONCLUSION
REFERENCES
Investigating and Identifying Fraudulent Behaviors of Medical Claims Data Using Machine Learning Algorithms
Jyothi P. Naga1,*, K.V.S.N. Rama Rao2, L. Rajya3 and S. Suresh4
1. INTRODUCTION
2. ROLE OF MACHINE LEARNING ALGORITHMS
3. VARIOUS KINDS OF HEALTHCARE DATA
4. EXISTED WORK OF DIFFERENT MODELS ON FRAUD DETECTION
4.1. General Model
4.2. Statistical Model
4.3. Supervised Models.
5. MECHANISM FOR INVESTIGATING AND IDENTIFYING THE FRAUDULENT BEHAVIORS OF MEDICAL CLAIMS DATA.
Title
Copyright
End User License Agreement
Contents
Preface
List of Contributors
Machine Learning Techniques and their Applications: Survey
P. Karthik1,*, K. Chandra Sekhar1 and D. Latha2
1. INTRODUCTION
1.1. History of AI &
ML
1.2. Applications of ML
1.2.1. Speech Recognition [19]
1.2.2. Predictive Analytics [19]
1.2.3. Product Recommendation [20]
1.2.4. Image Recognition [19]
1.2.5. Video Surveillance [20]
1.2.6. Extraction [19]
1.2.7. Traffic Alerts [20]
1.2.8. Medical Diagnosis [19]
1.2.9. Sentiment Analysis [20]
1.2.10. Google Translate [20]
1.2.11. Virtual Personal Assistants [20]
1.3. Difference Between Traditional Programming Concepts and ML Concepts [23]
1.3.1. Why Must We Learn ML?
1.3.2. Difference Between AI &
ML [23]
1.4. Steps to Learn ML
1.4.1. Data Gathering [24]
1.4.2. Data Preparation [24]
1.4.3. Selecting the Model [24]
1.4.4. Training the Model [24]
1.4.5. Evaluate the Model [24]
1.4.6. Parameter Tuning [24]
1.4.7. Make Patterns [24]
1.5. Types of ML
1.6. Basic ML Methods
1.7. ML in Agriculture
1.8. ML in Sentiment Analysis
1.9. ML in Stock Prediction
1.10. ML in Disease Prediction
1.11. ML in Data Mining
1.12. ML in COVID-19
1.13. ML in Cyber Security
1.14. ML in Cloud Computing
1.15. ML in Big Data Analytics (BDA)
1.16. ML in Recommendation System
1.17. Future Experiments on Real Time Problems Using ML
CONCLUSION
REFERENCES
Applications of Machine Learning
Prediction using Machine Learning
Adluri Vijaya Lakshmi1,*, Sowmya Gudipati Sri2, Ponnuru Sowjanya2 and K. Vedavathi3
1. INTRODUCTION TO MACHINE LEARNING
2. CLASSIFICATION OF MACHINE-LEARNING
2.1. Supervised Learning
2.2. Unsupervised Learning
2.3. Reinforcement Learning.
3. BREAST CANCER PREDICTION USING ML TECHNIQUES
3.1. Introduction
3.2. Related Works
4. HEART DISEASE PREDICTION USING MACHINE LEARNING TECHNIQUES
4.1. Introduction
4.2. Existing System
5. PREDICTING IPL RESULTS USING ML TECHNIQUES
5.1. Introduction
5.2. Related Work
6. PREDICTION OF SOFTWARE BUG UTILISING ML TECHNIQUE
6.1. Introduction
6.2. Related Work
7. PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUES
7.1. Introduction
7.2. Related Work
8. WEATHER PREDICTION USING MACHINE LEARNING TECHNIQUES
8.1. Machine Learning
8.2. Use of Algorithms
CONCLUSION
REFERENCES
Machine Learning Algorithms for Health Care Data Analytics Handling Imbalanced Datasets
T. Sajana1,* and K.V.S.N. Rama Rao2
1. INTRODUCTION
2. MACHINE LEARNING- AN INTELLIGENT AUTOMATED SYSTEM
3. TYPES OF DATASETS-BY NATURE
3.1. Balanced Datasets
3.2. Imbalanced Datasets
4. ISSUES WITH IMBALANCED DATASETS
4.1. Class Imbalance Problem
4.2. Classifiers Learning On Imbalanced Datasets
4.3. Taxonomy of Various Techniques on Imbalanced Datasets
5. APPLICATION OF CONVENTIONAL DATA MINING &
MACHINE LEARNING TECHNIQUES FOR HANDLING CLASS IMBALANCE PROBLEM
6. APPLICATION OF DATA LEVEL METHODS FOR HANDLING CLASS IMBALANCE PROBLEM
6.1. Undersampling
6.2. Oversampling
7. APPLICATION OF ALGORITHMIC LEVEL METHODS FOR HANDLING CLASS IMBALANCE PROBLEM
7.1. Cost-Sensitive Classifiers
7.2. Ensemble Techniques
CONCLUSION
REFERENCES
AI for Crop Improvement
S.V. Vasantha1,*
1. INTRODUCTION
2. GENOMICS FOR AGRICULTURE
3. AI FOR AGRICULTURE
4. AI TECHNIQUES FOR CROP IMPROVEMENT
5. AI-BASED CROP IMPROVEMENT MODEL (AI-CIM)
5.1. Automation of Modern Crop Improvement Process
5.2. AI Model for Enhanced Crop Breeding
5.2.1. Automated Selective Breeding System.
5.2.2. Automated Plant Health Monitoring System
CONCLUSION
REFERENCES
Real-Time Object Detection and Localization for Autonomous Driving
Swathi Gowroju1,*, V. Swathi1, J. Narasimha Murthy1 and D. Sai Kamesh1
1. INTRODUCTION
2. LITERATURE SURVEY
3. PROPOSED METHOD
3.1. Proposed Architecture
4. IMPLEMENTATION
4.1. Bounding Boxes
4.2. Anchor Boxes
4.3. Non-max Suppression
5. RELU ACTIVATION
6. LOSS FUNCTION
7. TRAINING PARAMETERS
8. RESULTS
CONCLUSION
ACKNOWLEDGEMENT
REFERENCES
Machine Learning Techniques in Image Segmentation
Narmada Kari1,*, Sanjay Kumar Singh1 and Dumpala Shanthi2
1. INTRODUCTION
2. LITERATURE REVIEW
3. METHODOLOGY
3.1. Collection of Data
3.2. Pre-processing of Images
3.3. Training Options
3.4. Define Label IDs
3.5. Feature Extraction
3.6. Feature Reduction/Selection
3.7. Feature Classification
3.8. Machine Learning
3.8.1. Supervised Learning
3.8.2. Unsupervised Learning
3.8.3. Reinforcement Learning
3.8.4. Deep Learning
3.8.5. Deep Reinforcement Learning
CONCLUSION
REFERENCES
Optimal Page Ranking Technique for Webpage Personalization Using Semantic Classifier
P. Pranitha1,*, A. Manjula1, G. Narsimha2 and K. Vaishali3
1. INTRODUCTION
2. LITERATURE SURVEY
2.1. Challenges
2.2. Motivation of Research
2.3. Proposed Methodology
2.4. Generation of Web Pages
3. PRE-PROCESSING
3.1. Feature Extraction and Web Page Ranking
3.2. ENN-based Semantic Features
4. RE-RANKING OF WEB PAGES
4.1. Grass Hopper Optimization (GHO)
4.1.1. Social Interaction Calculation
4.1.2. Solution Updating
4.2. Artificial Bee Colony Algorithm (ABC)
4.2.1. Employed Bee Operation
4.2.2. Probability Calculation
4.2.3. Onlooker Bee Operation
4.3. Oppositional Grass Bee Optimization (OGBEE).
4.3.1. Opposition Behavior Learning (OBL)
4.3.2. Fitness Calculation
4.3.3. Updating using Grasshopper Optimization
4.3.4. Scout Bee Operation
4.3.5. Termination Criteria
5. RESULTS AND DISCUSSION
5.1. Evaluation Metrics
5.1.1. Precision
5.1.2. Recall
5.1.3. F-measure
CONCLUSION
REFERENCES
Text Analytics
Divanu Sameera1,*, Niraj Sharma2 and R.V. Ramana Chary3
1. INTRODUCTION
1.1. Text Analytics Basics
1.2. Text Analytics Examples
2. HOW TO GET STARTED WITH TEXT ANALYTICS
2.1. Analyze Your Data
2.2. Use BI Tools to Understand Your Data
2.3. Final Words
3. EXAMPLES AND METHODS FOR TEXT ANALYTICS
3.1. Text Analytics Approach 1: Word Spotting
3.1.1. The Simplicity of the Word-spotting Approach is What Makes it so Appealing [28]
3.1.2. When Word Spotting is Acceptable?
3.2. Text Analytics Approach 2. Manual Rules
3.2.1. Multiple-word Meanings Make it Hard to Create Rules
3.2.2. Mentioned Word! = Core Topic
3.2.3. Rules
3.2.4. Taxonomies Don't Exist for Software Products and Many Other Businesses
3.2.5. Not Everyone can Maintain Rules
3.3. Text Analytics Approach 3. Text Categorization
3.3.1. What is Text Categorization, and How Does it Work?
3.3.2. You Won't Notice Emerging Themes
3.3.3. Lack of Transparency
3.3.4. Preparing and Managing Training Data is Hard
3.3.5. Re-training for Each New Dataset
3.4. Approach 4: Topic-Modelling
3.4.1. What's Incredible Regarding Topic-modelling
3.5. Approach 5. Thematic Analysis
3.5.1. Thematic Analysis: How it Works
3.5.2. Advantages and Disadvantages of Thematic Analysis
3.5.3. Human in The Loop
4. CASE STUDY
CONCLUSION
REFERENCES
Human Activity Recognition System Using Smartphone
R. Usha Rani1 and M. Sunitha1,*
1. INTRODUCTION
2. LITERATURE REVIEW
3. MAIN TECHNIQUES.
4. SMARTPHONE HAR COMMANDS
4.1. HAR Section 1: Data Cleaning Through Preprocessing
4.1.1. Data Filtering
4.1.2. Data Segmentation
4.1.3. Reduction
4.1.4. Selection of Feature
4.2. HAR Section II: Procedure to Perform Classification
CONCLUSION
REFERENCES
Smart Water Bottle with Smart Technology
Dumpala Shanthi1,*
1. INTRODUCTION
2. EMBEDDED SYSTEM
3. ARDUINO NANO
4. PIN DIAGRAM
4.1. Serial Communication
4.2. Water Level Sensor
5. LDR: WORKING
6. APPLICATIONS
6.1. Light Dependent Resistor (LDR) Measurement
6.2. Message Management General Description
6.3. RA Mode
6.4. Tape Mode
6.5. Automatic Gain Control (AGC)
6.6. Sampling Use
7. MODULE
7.1. Types
7.2. Security Concerns
7.3. Other Devices' Interference
7.4. Streaming Media of Poor Quality
7.5. Specifications
CONCLUSION
REFERENCES
Real World Applications of Machine Learning in Health Care
Kari Narmada1,*, Sanjay Kumar Singh1 and Dumpala Shanthi2
1. INTRODUCTION
2. LITERATURE REVIEW
3. TYPES OF MACHINE LEARNING
3.1. Supervised Learning
3.2. Unsupervised Learning
3.3. Reinforcement Learning
3.4. Recommender Systems
4. MACHINE LEARNING APPLICATIONS IN HEALTH CARE
4.1. The Most Challenges For AI In Healthcare
4.2. Possible Risks to Generalizability in Clinical Research and Machine Learning In Health Care
CONCLUSION
REFERENCES
Investigating and Identifying Fraudulent Behaviors of Medical Claims Data Using Machine Learning Algorithms
Jyothi P. Naga1,*, K.V.S.N. Rama Rao2, L. Rajya3 and S. Suresh4
1. INTRODUCTION
2. ROLE OF MACHINE LEARNING ALGORITHMS
3. VARIOUS KINDS OF HEALTHCARE DATA
4. EXISTED WORK OF DIFFERENT MODELS ON FRAUD DETECTION
4.1. General Model
4.2. Statistical Model
4.3. Supervised Models.
5. MECHANISM FOR INVESTIGATING AND IDENTIFYING THE FRAUDULENT BEHAVIORS OF MEDICAL CLAIMS DATA.