Sustainable Resource Management in Next-Generation Computational Constrained Networks

Subhasis Dash, PhD is an assistant professor in the School of Computer Engineering at the Kalinga Institute of Industrial Technology with over 22 years of teaching experience. His research interests include wireless sensor networks, distributed computing, and operating systems. Manas Ranjan Lenka, PhD is an assistant professor in the School of Computer Engineering, at the Kalinga Institute of Industrial Technology with over 18 years of experience. His current research focuses on wireless sensor networks, mobile wireless networks, Internet of Things, and blockchain. S. Balamurugan, PhD is the Director of Intelligent Research Consultancy Services and serves as a consultant for many other companies and start-ups. He has published over 70 books, 300 articles in national and international journals and conferences, and 300 patents. His research interests include artificial intelligence, machine learning, soft computing algorithms, and robotics and automation. Ambika Prasad Tripathy is a senior technical leader with Cisco’s Network Security Business Unit with over 17 years of experience. He has worked in the network industry to standardize Yang-based subscription mechanisms and their applications. He specializes in Sigtran, 3G, 4G core networks, switching and routing, telemetry, and datacenter, network, and cloud security. Amarendra Mohanty is a senior engineer at the Intel Corporation in India with over 17 years of research experience. He has worked for a number of leading companies in the computer science field, including Intel, VMWare, TCS, and Aricent. His specializations include network security, network virtualization, data center networking, routing and switching, and 3G wireless networks in the development and QA fields.

• Preface xv1 Enhancing Digital Learning Pedagogy for Lecture Video Recommendation Using Brain Wave Signal 1Rabi Shaw, Simanjeet Kalia and Sourabh Mohanty1.1 Introduction 21.2 Related Work 41.2.1 E-Learning, M-Learning, and T-Learning 41.2.2 Involvement of Networking Reforms in Education 61.2.3 Literature Review for Use of NeuroSky Headset in Education Domain 61.3 Background 101.4 Dataset 101.5 Proposed Method and Result 111.5.1 Collaborative Filtering Using Brain Signal–Induced Preferences 111.5.1.1 Neurophysiological Experiment 111.5.1.2 Deducing Preferences from Brain Signals 141.5.2 Proposed Methodology for FlipRec Model 161.5.2.1 Module for Data Preparation 161.5.2.2 FlipRec: Preferred Recommendation Model 191.5.3 Using Brain Signal Technology, a Cognitively Aware Lecture Video Recommendation System in Flipped Learning 201.5.3.1 Finding Successful Cognitive States with a Clustering Method 201.5.3.2 Feature Derivation for Estimating Attention 221.6 Result Analysis 231.7 Conclusion and Future Research 25References 252 Blockchain-Based Sustainable Supply Chain Management 31Anuja Ajay, Saji M. S. and Subhasis Dash2.1 Introduction 322.1.1 Significance of Blockchain for SCM 342.1.2 Introduction to Blockchain Interoperability 352.2 Blockchain for Supply Chain Management 352.2.1 Characteristics and Requirements of Blockchain-Based Supply Chain 372.2.1.1 Characteristics of Supply Chain 372.2.1.2 Requirements of Supply Chain 402.2.2 Blockchain-Based Data Sharing for Supply Chain 412.2.3 Access Control and Trust Management in Blockchain- Based SCM 432.2.3.1 Access Control Mechanisms in SCM 432.2.3.2 Trust Management in Supply Chain 442.3 Interoperability in Blockchain 452.3.1 Overview of Blockchain Interoperability Approaches 452.3.1.1 Public Connectors 452.3.1.2 Blockchain of Blockchains (BoB) 462.3.1.3 Hybrid Connectors 462.3.2 Gateways for Interoperability and Manageability 482.3.3 Interoperability Approaches 492.4 Design Considerations and Open Challenges 502.5 Summary 512.5.1 Advantages of Blockchain for SSCM 512.6 Scope of Future Work Emphasis 52References 533 Revolutionizing Aquaculture With the Internet of Things (IoT): An Insightful Learning 59Arpita Nayak, Atmika Patnaik, Ipseeta Satpathy, Veena Goswami and B.C.M. Patnaik3.1 Introduction 603.2 Environmental Monitoring via IoT for Sustainable Aquaculture 633.3 The Primacy of IoT in Enhancing Fish Health Monitoring 673.4 Delving Into IoT: Improving Agricultural Water Quality Management 703.5 Connecting the Dots: Using IoT Fish Behavior Monitoring to Improve Aquaculture Practices 743.6 The Worldwide Deployment of IoT in Aquaculture: Advantages and Success Factors 793.7 Conclusion 81Acknowledgment 81References 814 Energy Consumption Optimization in Wireless Sensor Networks 87Avik Das, Shatyaki Ghosh and Arindam Basak4.1 Introduction 874.1.1 WSN Application and Hardware Characteristics 904.2 MAC Layer Approaches 934.2.1 IEEE 802.15.4 Standard along with the ZigBee Technology 944.2.2 Different Other MAC Approaches 954.3 Routing Approaches 984.4 Transmission Power Control Approaches 994.5 Autonomic Approaches 1024.6 Application of ZigBee in a WSN 1054.7 WSN with Cloud Computing 1064.8 Final Considerations and Future Directions 109References 1105 Airline Prediction Using Customer Feedback and Rating Using Machine Learning and Deep Learning 115Ch Sambasiva Rao, Pabbathi Manobhi Ram, Viswanadhapalli Siva and Motakatla Satya Sai Krishna Reddy5.1 Introduction 1165.1.1 Customer Ratings and Recommendation 1165.2 Literature Survey 1175.3 System Design 1195.4 Methodology 1205.4.1 Modules 1205.4.1.1 Data Collection 1205.4.1.2 Review-Based Airline Prediction 1205.4.1.3 Rating-Based Airline Prediction 1215.5 Algorithm Used: Random Forest, Convolutional Neural Network, and AdaBoost 1215.5.1 Random Forest System 1215.5.2 Convolutional 1D Neural Network–Based Training 1225.5.2.1 Sequential Model 1225.5.2.2 Add 1D Convolutional Layer 1235.5.2.3 Adding 1D Max Pooling Layer 1235.5.2.4 Adding Dense Layer 1235.5.2.5 Neural Network Training 1235.5.3 AdaBoost Algorithm 1245.6 Experimental Results and Evaluations 1255.7 Screenshots 1265.8 Conclusion 130References 1306 The Breakthrough of Future Delivery: Delivery Robots 133Ayushi Gupta6.1 Introduction 1336.2 Related Work 1366.3 Evolution of Delivery Robot 1386.4 Working Principal/Model of Delivery Robots 1416.5 Benefits of Delivery Robots 1436.6 Applications of Delivery Robots 1496.7 Development Projects 1536.8 Challenging Issues with Delivery Robots 1586.9 Conclusion and Future Work 165References 1667 Emergence of Cloud Computing in IoT Applications 169Priyanshu Sonthalia and Doddi Puneet7.1 Introduction 1707.1.1 Characteristics of Cloud Computing 1707.1.2 Types of Cloud Deployment Models 1717.1.3 Categories of Cloud Computing Architectures 1727.1.4 Types of Cloud Service Models 1737.2 Benefits of IoT and Cloud Integration 1747.2.1 Scalability and Elasticity of Cloud Resources for Managing IoT Data 1747.2.2 Reduced Infrastructure Costs with Cloud-Based Solutions 1747.2.3 Improved Accessibility and Availability of IoT Services with Cloud Deployment 1757.2.4 Enhanced Processing Power and Analytics Capabilities with Cloud Computing 1757.2.5 Reduced Time to Market and Increased Innovation with Cloud-Based IoT Development 1757.3 Cloud-Based IoT Architecture 1757.3.1 Four Layers of Cloud-Based IoT Architecture 1757.3.2 Role of Gateways in Linking IoT Devices to the Cloud 1767.3.3 Overview of Cloud-Based IoT Platforms and Services 1777.3.4 Cloud-Based IoT Standards and Protocols, such as MQTT, CoAP, AMQP, and HTTP 1777.4 Cloud-Based IoT Applications 1807.5 Challenges in IoT Cloud Integration 1817.5.1 Security Risks and Challenges Associated with Cloud-Based IoT Solutions 1817.5.2 Latency and Bandwidth Constraints of IoT Systems Hosted in the Cloud 1817.5.3 Interoperability Issues Between Different IoT Devices and Cloud Platforms 1827.5.4 Legal and Regulatory Challenges Associated with IoT Using Cloud Solutions 1827.6 Open Issues and Research Directions 1827.6.1 Future Trends and Developments in Cloud-Based IoT Solutions 1827.6.2 Opportunities for Research in Cloud-Based IoT Solutions 1827.6.3 Overview of Emerging Cloud-Based IoT Standards and Protocols 1837.7 Case Study 1: Smart Home Automation Using Cloud-Based IoT 1837.8 Case Study 2: Industrial IoT Optimization Using Cloud-Based IoT 1847.9 Conclusion 185References 1868 Conceptual Assessment of Sensory Networks and Its Functional Aspects 189Barat Nikhita, Siddhant Prateek Mahanayak and Kunal Anand8.1 Introduction 1898.2 Evolution of IoT 1918.2.1 Phase 1: Early Adopters (Pre-2010) 1928.2.2 Phase 2: Connectivity and Smart Devices (2010–2015) 1938.2.3 Phase 3: Big Data and Cloud Computing (2015 to Present) 1948.2.4 Phase 4: Artificial Intelligence and Edge Computing (Present and Future) 1958.3 Features of IoT 1968.4 Architectural Framework of IoT 1998.4.1 Device Layer 2008.4.2 Network Layer 2018.4.3 Platform Layer 2028.4.4 Application Layer 2038.5 Components of IoT 2048.6 Applications of IoT 2068.7 Case Study 2118.7.1 Overview of Barcelona Smart City Project 2118.7.2 Methodology 2128.8 Conclusion 213References 2149 System Security Using Artificial Intelligence and Reduction of Data Breach 221M. Avrit, G. P. Siranjeevi, Shruti Mishra, Sandeep Kumar Satapathy, Priyanka Mishra, Pradeep Kumar Mallick and Gyoo Soo Chae9.1 Introduction 2229.2 Related Work 2249.3 Methodology 2249.3.1 Implementation of Socket Programming Concept 2249.3.2 Machine Learning 2259.3.3 Deep Learning 2259.3.4 Human Assistance 2259.4 Proposed Model 2259.5 Experimental Result/Result Analysis 2279.6 Conclusion and Future Work 231References 23110 Mitigating DDoS Attacks: Empowering Network Infrastructure Resilience with AI and ML 233Teja Pasonri, Saurav Singh, Vedant Shirapure, Sandeep Kumar Satapathy, Sung-Bae Cho, Shruti Mishra and Pradeep Kumar Mallick10.1 Introduction 23410.1.1 Categories of DDoS Attack 23510.1.1.1 SYN Flood Attacks 23510.1.1.2 UDP Flood Attacks 23510.1.1.3 MSSQL Attacks 23510.1.1.4 LDAP Attacks 23510.1.1.5 Portmap Attacks 23610.1.1.6 NetBIOS Attacks 23610.1.2 Harnessing Machine Learning for DDoS Threat Detection 23610.1.3 AI Models for DDoS Threat Detection 23610.1.4 Beyond Classification: AI for Real-Time Detection and Mitigation 23710.1.5 Collaboration and Knowledge Sharing 23710.2 Related Work 23710.3 Methodology 23910.3.1 Pseudocode-1: Jupyter Project Code 24010.3.2 Pseudocode-2: Project KNN Model 24110.3.3 Hyperparameter Tuning and Evaluation 24210.3.4 Enhancing Model Accuracy 24210.3.5 Ping Request and DDoS Attack 24210.4 Proposed Model 24310.5 Experimental Result/Result Analysis 24510.5.1 Demo of DDoS Attack 24510.5.2 Packet Sniffing and Detecting Traffic 24610.5.3 Accuracy Graph 24610.5.4 Precision Graph 24710.6 Conclusion/Future Work 248References 24811 CyberEDU: An Interactive Educational Tool for DDoS Attack Simulation and Prevention 251Pulkit Srivastava, Vedant Shah, Priyanshu Singh, Sandeep Kumar Satapathy, Sung-Bae Cho, Shruti Mishra and Pradeep Kumar Mallick11.1 Introduction 25211.2 Related Work 25511.3 Methodology 25711.4 Proposed Model 26011.5 Experimental Result/Result Analysis 26311.6 Conclusion and Future Work 267References 26712 Resource Management and Performance Optimization in Constraint Network Systems 269Amarendra Kumar Mohanty12.1 Introduction 27012.2 Resource Allocation Principles 27112.3 Network Capacity and Utilization 27412.4 Performance Optimization Strategies 28012.4.1 Resource Management in Physical Networks 28112.4.2 Resource Management in Virtual Networks 29712.4.3 Resource Management in Software-Defined Networking (SDN) 30012.5 Real-World Applications 30212.5.1 Data Plane Development Kit Libraries 30612.5.2 Virtual Machine Device Queues (VMDQ) 30912.6 Conclusion and Future Directions 311References 31213 Resource-Constrained Network Management Using Software-Defined Networks 315Sayan Bhattacharyya, Manas Ranjan Lenka and Subhasis Dash13.1 Introduction 31513.2 Software-Defined Network Architecture and Its Key Components 31713.2.1 Application Plane 31913.2.1.1 Network Application 32013.2.1.2 Language-Level Virtualization 32013.2.2 Control Plane 32013.2.2.1 Network Operating System (NOS) 32013.2.2.2 Network Hypervisor 32013.2.3 Data Plane 32113.2.3.1 Network Infrastructure 32113.2.4 SDN Protocols 32113.2.4.1 Northbound Protocol 32113.2.4.2 Southbound Protocol 32213.2.4.3 Eastbound Protocol 32213.2.4.4 Westbound Protocol 32313.2.5 SDN Workflows 32413.3 Challenges and Opportunities of SDN in Resource- Constrained Scenarios 32613.4 State-of-the-Art Techniques and Tools for Efficient Network Resource Management in SDN Environments 32713.5 Performance of the Existing Techniques and Tools with Use Case 32913.6 Conclusion and Future Scope 330References 33114 Vehicles Smoke Monitoring Using Internet of Things and Machine Learning 337Dhavakumar P. and Selvakumar Samuel14.1 Introduction 33714.2 Vehicle CO 2 Emissions 33814.2.1 Impacts of CO 2 Emissions 33914.3 Recommended Solutions with Internet of Things 34014.3.1 IoT System and CO 2 Sensors 34014.3.2 Benefits of the IoT System 34214.3.3 Air Quality Monitoring System (AQMS) 34314.4 ml Algorithms 34614.4.1 K-Means Algorithm (KM) 34614.4.2 Decision Tree Algorithm (DT) 34714.4.3 Naive Bayes Algorithm (NB) 34714.4.4 Controlling Carbon Unlimited Flow Operation with Machine Learning Approach (CULTML) 34714.5 Proposed System Architectures and Designs 34814.5.1 Vehicular Unit 34914.5.2 Software Unit 35014.5.3 Road Transport Office (RTO) Unit 35114.6 Logical Design of the Proposed System 35214.6.1 Summation Detector Using Artificial Intelligence 35214.6.2 Digit Recognition 35214.7 Experimental Results 35414.8 Physical Design of the Proposed System 35614.9 Conclusion 357References 35715 Enhancing Home Security through IoT Innovation: Recommendations for Biometric Door Lock System to Deter Break-Ins 359Muhammad Ehsan Rana, Kamalanathan Shanmugam, Lim Enya and Hrudaya Kumar Tripathy15.1 Introduction 36015.2 Literature Review 36115.2.1 Home Security Concerns in Malaysia 36215.2.2 Introduction to Biometric Solutions 36315.2.3 Enhancing Biometrics with Machine Learning 36415.2.4 Biometrics in the Realm of Smart Home Security 36515.2.5 Review of Existing Commercial Systems 36715.2.5.1 Samsung Smart Door Lock 36715.2.5.2 Philips EasyKey 36915.2.5.3 Comparison of Systems 37115.3 Recommendations for the Implementation of the Proposed Biometric Door Lock System 37215.3.1 Software Requirements 37315.3.2 Key Hardware Requirements 37415.3.2.1 Arduino Nano 37415.3.2.2 DFRobot HuskyLens 37515.3.2.3 DFRobot UART Fingerprint Scanner 37515.3.2.4 Five-Volt Single-Channel Relay Module 37615.3.2.5 12VDC Solenoid Lock 37615.3.3 Workflow of the Proposed System 37615.3.4 Key Features of the Proposed System 37815.3.5 Testing the Biometric Door Lock System 38015.3.5.1 Fingerprint Authentication Test 38015.3.5.2 Facial Recognition Test 38115.3.5.3 Dual Authentication Test 38215.3.5.4 Access Log Test 38415.3.5.5 Mobile Application Integration Test 38515.3.5.6 Scalability Test 38615.3.5.7 Accuracy Result Analysis 38715.4 Conclusion and Future Recommendations 389References 390Index 393