Machine Intelligence, Big Data Analytics, and IoT in Image Processing

Ashok Kumar, PhD, is an assistant professor at Lovely Professional University, Phagwara, Punjab, India. He has 15+ years of teaching and research experience, filed 3 patents, and published many articles in international journals and conferences. His current areas of research interest include cloud computing, the Internet of Things, and mist computing. Megha Bhushan, PhD, is an assistant professor at the School of Computing, DIT University, Dehradun, Uttarakhand, India. She has filed 4 patents and published many research articles in international journals and conferences. Her research interest includes software quality, software reuse, ontologies, artificial intelligence, and expert systems. Jose Galindo, PhD, is currently in the Department of Computer Languages and Systems, University of Seville, Spain. He has developed many tools such as FaMa, FaMaDEB, FaMaOVM, TESALIA, and VIVID, and his research interests include recommender systems, software visualization, variability-intensive systems, and software product lines. Lalit Garg, PhD, is a Senior Lecturer in the Department of Computer Information Systems, University of Malta, and an honorary lecturer at the University of Liverpool, UK. He has edited four books and published over 110 papers in refereed journals, conferences, and books. He has 12 patents and delivered more than twenty keynote speeches in different countries, and organized/chaired/co-chaired many international conferences. Yu-Chen Hu, PhD, is a distinguished professor in the Department of Computer Science and Information Management, Providence University, Taichung City, Taiwan. His research interests include image and signal processing, data compression, information hiding, information security, computer network, and artificial network.

• Preface xvPart I: Demystifying Smart Healthcare 11 Deep Learning Techniques Using Transfer Learning for Classification of Alzheimer’s Disease 3Monika Sethi, Sachin Ahuja and Puneet Bawa1.1 Introduction 41.2 Transfer Learning Techniques 61.3 AD Classification Using Conventional Training Methods 91.4 AD Classification Using Transfer Learning 121.5 Conclusion 16References 162 Medical Image Analysis of Lung Cancer CT Scans Using Deep Learning with Swarm Optimization Techniques 23Debnath Bhattacharyya, E. Stephen Neal Joshua and N. Thirupathi Rao2.1 Introduction 242.2 The Major Contributions of the Proposed Model 262.3 Related Works 282.4 Problem Statement 322.5 Proposed Model 332.5.1 Swarm Optimization in Lung Cancer Medical Image Analysis 332.5.2 Deep Learning with PSO 342.5.3 Proposed CNN Architectures 352.6 Dataset Description 372.7 Results and Discussions 392.7.1 Parameters for Performance Evaluation 392.8 Conclusion 47References 483 Liver Cancer Classification With Using Gray-Level Co-Occurrence Matrix Using Deep Learning Techniques 51Debnath Bhattacharyya, E. Stephen Neal Joshua and N. Thirupathi Rao3.1 Introduction 523.1.1 Liver Roles in Human Body 533.1.2 Liver Diseases 533.1.3 Types of Liver Tumors 553.1.3.1 Benign Tumors 553.1.3.2 Malignant Tumors 573.1.4 Characteristics of a Medical Imaging Procedure 583.1.5 Problems Related to Liver Cancer Classification 603.1.6 Purpose of the Systematic Study 613.2 Related Works 623.3 Proposed Methodology 663.3.1 Gaussian Mixture Model 683.3.2 Dataset Description 693.3.3 Performance Metrics 703.3.3.1 Accuracy Measures 703.3.3.2 Key Findings 743.3.3.3 Key Issues Addressed 753.4 Conclusion 77References 774 Transforming the Technologies for Resilient and Digital Future During COVID-19 Pandemic 81Garima Kohli and Kumar Gourav4.1 Introduction 824.2 Digital Technologies Used 844.2.1 Artificial Intelligence 854.2.2 Internet of Things 854.2.3 Telehealth/Telemedicine 874.2.4 Cloud Computing 874.2.5 Blockchain 884.2.6 5g 894.3 Challenges in Transforming Digital Technology 904.3.1 Increasing Digitalization 914.3.2 Work From Home Culture 914.3.3 Workplace Monitoring and Techno Stress 914.3.4 Online Fraud 924.3.5 Accessing Internet 924.3.6 Internet Shutdowns 924.3.7 Digital Payments 924.3.8 Privacy and Surveillance 934.4 Implications for Research 934.5 Conclusion 94References 95Part II: Plant Pathology 1015 Plant Pathology Detection Using Deep Learning 103Sangeeta V., Appala S. Muttipati and Brahmaji Godi5.1 Introduction 1045.2 Plant Leaf Disease 1055.3 Background Knowledge 1095.4 Architecture of ResNet 512 V 2 1115.4.1 Working of Residual Network 1125.5 Methodology 1135.5.1 Image Resizing 1135.5.2 Data Augmentation 1135.5.2.1 Types of Data Augmentation 1145.5.3 Data Normalization 1145.5.4 Data Splitting 1165.6 Result Analysis 1165.6.1 Data Collection 1175.6.2 Feature Extractions 1175.6.3 Plant Leaf Disease Detection 1175.7 Conclusion 119References 1206 Smart Irrigation and Cultivation Recommendation System for Precision Agriculture Driven by IoT 123N. Marline Joys Kumari, N. Thirupathi Rao and Debnath Bhattacharyya6.1 Introduction 1246.1.1 Background of the Problem 1276.1.1.1 Need of Water Management 1276.1.1.2 Importance of Precision Agriculture 1276.1.1.3 Internet of Things 1286.1.1.4 Application of IoT in Machine Learning and Deep Learning 1296.2 Related Works 1316.3 Challenges of IoT in Smart Irrigation 1336.4 Farmers’ Challenges in the Current Situation 1356.5 Data Collection in Precision Agriculture 1366.5.1 Algorithm 1366.5.1.1 Environmental Consideration on Stage Production of Crop 1406.5.2 Implementation Measures 1416.5.2.1 Analysis of Relevant Vectors 1416.5.2.2 Mean Square Error 1416.5.2.3 Potential of IoT in Precision Agriculture 1416.5.3 Architecture of the Proposed Model 1436.6 Conclusion 147References 1477 Machine Learning-Based Hybrid Model for Wheat Yield Prediction 151Haneet Kour, Vaishali Pandith, Jatinder Manhas and Vinod Sharma7.1 Introduction 1527.2 Related Work 1537.3 Materials and Methods 1557.3.1 Methodology for the Current Work 1557.3.1.1 Data Collection for Wheat Crop 1557.3.1.2 Data Pre-Processing 1567.3.1.3 Implementation of the Proposed Hybrid Model 1577.3.2 Techniques Used for Feature Selection 1597.3.2.1 ReliefF Algorithm 1597.3.2.2 Genetic Algorithm 1617.3.3 Implementation of Machine Learning Techniques for Wheat Yield Prediction 1627.3.3.1 K-Nearest Neighbor 1627.3.3.2 Artificial Neural Network 1637.3.3.3 Logistic Regression 1647.3.3.4 Naïve Bayes 1647.3.3.5 Support Vector Machine 1657.3.3.6 Linear Discriminant Analysis 1667.4 Experimental Result and Analysis 1677.5 Conclusion 173Acknowledgment 173References 1748 A Status Quo of Machine Learning Algorithms in Smart Agricultural Systems Employing IoT-Based WSN: Trends, Challenges and Futuristic Competences 177Abhishek Bhola, Suraj Srivastava, Ajit Noonia, Bhisham Sharma and Sushil Kumar Narang8.1 Introduction 1788.2 Types of Wireless Sensor for Smart Agriculture 1798.3 Application of Machine Learning Algorithms for Smart Decision Making in Smart Agriculture 1798.4 ml and WSN-Based Techniques for Smart Agriculture 1858.5 Future Scope in Smart Agriculture 1888.6 Conclusion 190References 190Part III: Smart City and Villages 1979 Impact of Data Pre-Processing in Information Retrieval for Data Analytics 199Huma Naz, Sachin Ahuja, Rahul Nijhawan and Neelu Jyothi Ahuja9.1 Introduction 2009.1.1 Tasks Involved in Data Pre-Processing 2009.2 Related Work 2029.3 Experimental Setup and Methodology 2059.3.1 Methodology 2059.3.2 Application of Various Data Pre-Processing Tasks on Datasets 2069.3.3 Applied Techniques 2079.3.3.1 Decision Tree 2079.3.3.2 Naive Bayes 2079.3.3.3 Artificial Neural Network 2089.3.4 Proposed Work 2089.3.4.1 PIMA Diabetes Dataset (PID) 2089.3.5 Cleveland Heart Disease Dataset 2119.3.6 Framingham Heart Study 2159.3.7 Diabetic Dataset 2179.4 Experimental Result and Discussion 2209.5 Conclusion and Future Work 222References 22210 Cloud Computing Security, Risk, and Challenges: A Detailed Analysis of Preventive Measures and Applications 225Anurag Sinha, N. K. Singh, Ayushman Srivastava, Sagorika Sen and Samarth Sinha10.1 Introduction 22610.2 Background 22810.2.1 History of Cloud Computing 22810.2.1.1 Software-as-a-Service Model 23010.2.1.2 Infrastructure-as-a-Service Model 23010.2.1.3 Platform-as-a-Service Model 23210.2.2 Types of Cloud Computing 23210.2.3 Cloud Service Model 23210.2.4 Characteristics of Cloud Computing 23410.2.5 Advantages of Cloud Computing 23410.2.6 Challenges in Cloud Computing 23510.2.7 Cloud Security 23610.2.7.1 Foundation Security 23610.2.7.2 SaaS and PaaS Host Security 23710.2.7.3 Virtual Server Security 23710.2.7.4 Foundation Security: The Application Level 23810.2.7.5 Supplier Data and Its Security 23810.2.7.6 Need of Security in Cloud 23910.2.8 Cloud Computing Applications 23910.3 Literature Review 24110.4 Cloud Computing Challenges and Its Solution 24210.4.1 Solution and Practices for Cloud Challenges 24610.5 Cloud Computing Security Issues and Its Preventive Measures 24810.5.1 General Security Threats in Cloud 24910.5.2 Preventive Measures 25410.6 Cloud Data Protection and Security Using Steganography 25810.6.1 Types of Steganography 25910.6.2 Data Steganography in Cloud Environment 26010.6.3 Pixel Value Differencing Method 26110.7 Related Study 26310.8 Conclusion 263References 26411 Internet of Drone Things: A New Age Invention 269Prachi Dahiya11.1 Introduction 26911.2 Unmanned Aerial Vehicles 27111.2.1 UAV Features and Working 27411.2.2 IoDT Architecture 27511.3 Application Areas 28011.3.1 Other Application Areas 28411.4 IoDT Attacks 28511.4.1 Counter Measures 29111.5 Fusion of IoDT With Other Technologies 29611.6 Recent Advancements in IoDT 29911.7 Conclusion 302References 30312 Computer Vision-Oriented Gesture Recognition System for Real-Time ISL Prediction 305Mukul Joshi, Gayatri Valluri, Jyoti Rawat and Kriti12.1 Introduction 30512.2 Literature Review 30712.3 System Architecture 30912.3.1 Model Development Phase 30912.3.2 Development Environment Phase 31112.4 Methodology 31212.4.1 Image Pre-Processing Phase 31212.4.2 Model Building Phase 31312.5 Implementation and Results 31412.5.1 Performance 31412.5.2 Confusion Matrix 31812.6 Conclusion and Future Scope 318References 31913 Recent Advances in Intelligent Transportation Systems in India: Analysis, Applications, Challenges, and Future Work 323Elamurugan Balasundaram, Cailassame Nedunchezhian, Mathiazhagan Arumugam and Vinoth Asaikannu13.1 Introduction 32413.2 A Primer on ITS 32513.3 The ITS Stages 32613.4 Functions of ITS 32713.5 ITS Advantages 32813.6 ITS Applications 32913.7 ITS Across the World 33113.8 India’s Status of ITS 33313.9 Suggestions for Improving India’s ITS Position 33413.10 Conclusion 335References 33514 Evolutionary Approaches in Navigation Systems for Road Transportation System 341Noopur Tyagi, Jaiteg Singh and Saravjeet Singh14.1 Introduction 34214.1.1 Navigation System 34314.1.2 Genetic Algorithm 34714.1.3 Differential Evolution 34814.2 Related Studies 34914.2.1 Related Studies of Evolutionary Algorithms 35114.3 Navigation Based on Evolutionary Algorithm 35214.3.1 Operators and Terms Used in Evolutionary Algorithms 35314.3.2 Operator and Terms Used in Evolutionary Algorithm 35714.4 Meta-Heuristic Algorithms for Navigation 35914.4.1 Drawbacks of DE 36214.5 Conclusion 362References 36315 IoT-Based Smart Parking System for Indian Smart Cities 369E. Fantin Irudaya Raj, M. Appadurai, M. Chithamabara Thanu and E. Francy Irudaya Rani15.1 Introduction 37015.2 Indian Smart Cities Mission 37115.3 Vehicle Parking and Its Requirements in a Smart City Configuration 37315.4 Technologies Incorporated in a Vehicle Parking System in Smart Cities 37515.5 Sensors for Vehicle Parking System 38315.5.1 Active Sensors 38415.5.2 Passive Sensors 38615.6 IoT-Based Vehicle Parking System for Indian Smart Cities 38715.6.1 Guidance to the Customers Through Smart Devices 38915.6.2 Smart Parking Reservation System 39115.7 Advantages of IoT-Based Vehicle Parking System 39215.8 Conclusion 392References 39316 Security of Smart Home Solution Based on Secure Piggybacked Key Exchange Mechanism 399Jatin Arora and Saravjeet Singh16.1 Introduction 40016.2 IoT Challenges 40416.3 IoT Vulnerabilities 40516.4 Layer-Wise Threats in IoT Architecture 40616.4.1 Sensing Layer Security Issues 40716.4.2 Network Layer Security Issues 40816.4.3 Middleware Layer Security Issues 40916.4.4 Gateways Security Issues 41016.4.5 Application Layer Security Issues 41116.5 Attack Prevention Techniques 41116.5.1 IoT Authentication 41216.5.2 Session Establishment 41316.6 Conclusion 414References 41417 Machine Learning Models in Prediction of Strength Parameters of FRP-Wrapped RC Beams 419Aman Kumar, Harish Chandra Arora, Nishant Raj Kapoor and Ashok Kumar17.1 Introduction 42017.1.1 Defining Fiber-Reinforced Polymer 42117.1.2 Types of FRP Composites 42217.1.2.1 Carbon Fiber–Reinforced Polymer 42217.1.2.2 Glass Fiber 42317.1.2.3 Aramid Fiber 42417.1.2.4 Basalt Fiber 42417.2 Strengthening of RC Beams With FRP Systems 42517.2.1 FRP-to-Concrete Bond 42617.2.2 Flexural Strengthening of Beams With FRP Composite 42717.2.3 Shear Strengthening of Beams With FRP Composite 42717.3 Machine Learning Models 42817.3.1 Prediction of Bond Strength 43017.3.2 Estimation of Flexural Strength 43417.3.3 Estimation of Shear Strength 43417.4 Conclusion 441References 44118 Prediction of Indoor Air Quality Using Artificial Intelligence 447Nishant Raj Kapoor, Ashok Kumar, Anuj Kumar, Aman Kumar and Harish Chandra Arora18.1 Introduction 44818.2 Indoor Air Quality Parameters 45018.2.1 Physical Parameters 45318.2.1.1 Humidity 45318.2.1.2 Air Changes (Ventilation) 45418.2.1.3 Air Velocity 45418.2.1.4 Temperature 45418.2.2 Particulate Matter 45518.2.3 Chemical Parameters 45618.2.3.1 Carbon Dioxide 45618.2.3.2 Carbon Monoxide 45618.2.3.3 Nitrogen Dioxide 45618.2.3.4 Sulphur Dioxide 45718.2.3.5 Ozone 45718.2.3.6 Gaseous Ammonia 45818.2.3.7 Volatile Organic Compounds 45818.2.4 Biological Parameters 45918.3 AI in Indoor Air Quality Prediction 45918.4 Conclusion 464References 465Index 471