Artificial Intelligence Techniques in IoT Sensor Networks

Artificial Intelligence Techniques in IoT Sensor Networks is a technical book which can be read by researchers, academicians, students and professionals interested in artificial intelligence (AI), sensor networks and Internet of Things (IoT). This book is intended to develop a shared understanding of applications of AI techniques in the present and near term. The book maps the technical impacts of AI technologies, applications and their implications on the design of solutions for sensor networks. This text introduces researchers and aspiring academicians to the latest developments and trends in AI applications for sensor networks in a clear and well-organized manner. It is mainly useful for research scholars in sensor networks and AI techniques. In addition, professionals and practitioners working on the design of real-time applications for sensor networks may benefit directly from this book. Moreover, graduate and master’s students of any departments related to AI, IoT and sensor networks can find this book fascinating for developing expert systems or real-time applications. This book is written in a simple and easy language, discussing the fundamentals, which relieves the requirement of having early backgrounds in the field. From this expectation and experience, many libraries will be interested in owning copies of this work.

Table of Contents:
Preface Chapter 1 Adaptive Regularized Gaussian Kernel FCM for the Segmentation of Medical Images – An Artificial Intelligence Based IoT Implementation for Teleradiology Network 1.1 Introduction 1.2 Proposed Methodology 1.2.1 Fuzzy C Means Clustering 1.3 Results and Discussion 1.4 Conclusion References Chapter 2 Artificial Intelligence Based Fuzzy Logic with Modified Particle Swarm Optimization Algorithm for Internet of Things Enabled Logistic Transportation Planning 2.1. Introduction 2.2. Related works 2.3. Proposed Method 2.3.1. Package Partitioning 2.3.2. Planning of delivery path using HFMPSO algorithm 2.3.3. Inserting Pickup Packages 2.4. Experimental Validation 2.4.1. Performance analysis under varying package count 2.4.2. Performance analysis under varying vehicle capacities 2.4.3. Computation Time (CT) analysis 2.5. Conclusion References Chapter 3 Butterfly Optimization based Feature Selection with Gradient Boosting Tree for Big Data Analytics in Social Internet of Things 3.1. Introduction 3.2. Related works 3.3. The Proposed Method 3.3.1. Hadoop Ecosystem 3.3.2. BOA based FS process 3.3.3. GBT based Classification 3.4. Experimental Analysis 3.4.1. FS Results analysis 3.4.2. Classification Results Analysis 3.4.3. Energy Consumption Analysis 3.4.4. Throughput Analysis 3.5. Conclusion References Chapter 4 An Energy Efficient Fuzzy Logic based Clustering with Data Aggregation Protocol for WSN assisted IoT system 4. 1. Introduction 4. 2. Background Information 4. 2.1. Clustering objective 4. 2. 2. Clustering characteristics 4. 3. Proposed Fuzzy based Clustering and Data Aggregation (FC-DR) protocol 4. 3. 1. Fuzzy based Clustering process 4. 3. 2. Data aggregation process 4. 4. Performance Validation 4. 5. Conclusion References Chapter 5 Analysis of Smart Home Recommendation system from Natural Language Processing Services with Clustering Technique 5. 1. Introduction 5. 2. Review of Literatures 5. 3. Smart Home- Cloud Backend Services 5. 3.1 Internet of Things (IoT) 5. 4. Our Proposed Approach 5. 4.1 Natural Language Processing Services (NLPS) 5. 4. 2 Pipeline Structure for NLPS 5. 4. 3 Clustering Model 5. 5. Results and analysis 5. 6. Conclusion References Chapter 6 Metaheuristic based Kernel Extreme Learning Machine Model for Disease Diagnosis in Industrial Internet of Things Sensor Networks 6. 1. Introduction 6. 2. Proposed Methodology 6. 2. 1. Deflate based Compression Model 6. 2. 2. SMO-KELM based Diagnosis Model 6. 3. Experimental results and validation 6. 4. Conclusion References Chapter 7 Fuzzy Support Vector Machine with SMOTE for Handling Class Imbalanced Data in IoT Based Cloud Environment 7. 1. Introduction 7. 2. The Proposed Model 7. 2.1. SMOTE Model 7. 2.2. FSVM based Classification Model 7. 3. Simulation Results and Discussion 7. 4. Conclusion References Chapter 8 Energy Efficient Unequal Clustering Algorithm using Hybridization of Social Spider with Krill Herd in IoT Assisted Wireless Sensor Networks 8. 1. Introduction 8. 2. Research Background 8. 3. Literature survey 8. 4. The proposed SS-KH algorithm 8. 4. 1. SS based TCH selection 8. 4. 2. KH based FCH algorithm 8. 5. Experimental validation 8. 5. 1 Implementation setup 8. 5. 2. Performance analysis 8. 6. Conclusion References Chapter 9 IoT Sensor Networks with 5G Enabled Faster RCNN Based Generative Adversarial Network Model for Face Sketch Synthesis 9. 1. Introduction 9. 2. The Proposed FRCNN-GAN Model 9. 2.1. Data Collection 9. 2.2. Faster R-CNN based Face Recognition 9. 2.3. GAN based Synthesis Process 9. 3. Performance Validation 9. 4. Conclusion References Chapter 10 Artificial Intelligence based Textual Cyberbullying Detection for Twitter Data Analysis in Cloud-based Internet of Things 10. 1. Introduction 10. 2. Literature review 10. 3. Proposed Methodology 10. 3.1. Preprocessing 10. 3.2. Feature extraction 10. 3.3. Feature selection using ranking method 10. 3.4. Cyberbully detection 10. 3.5. Dataset Description 10. 4. Result and discussion 10. 4.1. Evaluation Metrics 10. 4.2. Comparative analysis 10. 5. Conclusion References Chapter 11 An Energy Efficient Quasi Oppositional Krill Herd Algorithm based Clustering Protocol for Internet of Things Sensor Networks 11. 1. Introduction 11. 2. The Proposed Clustering algorithm 11. 3. Performance Validation 11. 4. Conclusion References Chapter 12 An effective Social Internet of Things (SIoT) Model for Malicious node detection in wireless sensor networks 12. 1. Introduction 12. 2. Review of Recent Kinds of literature 12. 3. Network Model: SIoT 12. 3.1 Malicious Attacker Model in SIoT 12. 4. Proposed MN in SIoT System 12. 4.1 Trust based Grouping in SIoT network 12. 4.2 Exponential Kernel Model for MN detection 12. 4.3.1 Example of Proposed Detection System 12. 4.4 Detection Model 12. 5. Results and analysis 12. 6. Conclusion References Chapter 13 IoT Based Automated Skin Lesion Detection and Classification using Grey Wolf Optimization with Deep Neural Network 13. 1. Introduction 13. 2. The Proposed GWO-DNN Model 13. 2.1. Feature Extraction 13. 2.2. DNN based classification 13. 3. Experimental Validation 13. 4. Conclusion References Index