Intelligent Wireless Sensor Networks and the Internet of Things: Algorithms, Methodologies, and Applications

✍ Scribed by Bhanu Chander, Anoop Benet Nirmala, Koppala Guravaiah, G. Kumaravelan

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 368
• Category: Library

✦ Synopsis

The edited book Intelligent Wireless Sensor Networks and Internet of Things: Algorithms, Methodologies and Applications is intended to discuss the progression of recent as well as future generation technologies for WSNs and IoTs applications through Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL). In general, computing time is obviously increased when the massive data is required from sensor nodes in WSN’s. the novel technologies such as 5G and 6G provides enough bandwidth for large data transmissions, however, unbalanced links faces the novel constraints on the geographical topology of the sensor networks. Above and beyond, data transmission congestion and data queue still happen in the WSNs.

This book

·Addresses the complete functional framework workflow in WSN and IoT domains using AI, ML, and DL models.

·Explores basic and high-level concepts of WSN security, and routing protocols, thus serving as a manual for those in the research field as the beginners to understand both basic and advanced aspects sensors, IoT with ML & DL applications in real-world related technology.

·Based on the latest technologies such as 5G, 6G and covering the major challenges, issues, and advances of protocols, and applications in wireless system.

·Explores intelligent route discovering, identification of research problems and its implications to the real world.

·Explains concepts of IoT communication protocols, intelligent sensors, statistics and exploratory data analytics, computational intelligence, machine learning, and Deep learning algorithms for betterment of the smarter humanity.

·Explores intelligent data processing, deep learning frameworks, and multi-agent systems in IoT-enabled WSN system.

·This book demonstrates and discovers the objectives, goals, challenges, and related solutions in advanced AI, ML, and DL approaches.

This book is for graduate students and academic researchers in the fields of electrical engineering, electronics and communication engineering, computer engineering, and information technology.

✦ Table of Contents

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
About the editors
List of contributors
Key features
About the book
Chapter 1: Energy-efficient WSN with deep learning using dispersed data mining strategy-based LSTM
1.1 Introduction on improving the lifetime of a WSN
1.2 Training LSTM-RNNs—The hybrid learning approach
1.2.1 Using network optimization techniques to create an efficient sustainable network
1.2.2 Energy- efficient secured routing protocol
1.3 Recurrent neural networks
1.3.1 Basic architecture
1.3.2 Training recurrent neural networks
1.3.3 LSTM networks are superior to RNN
1.3.4 Cells and their variants
1.3.5 LSTM–dominated neural networks
1.3.6 Working of LSTMs in RNN
1.4 Optimization of adaptive method for data reduction
1.5 Experimental analysis
1.5.1 Analysis of energy usage
1.5.2 Transmission ratio analysis
1.5.3 Network lifetime ratio analysis
1.5.4 Efficiency analysis
1.6 Application of LSTM over RNN
1.6.1 Early education activities
1.6.2 Cognitive education exercises
1.6.3 Comprehension of handwriting
1.6.4 Automatic interpreting
1.6.5 Photo editing
1.7 Conclusion
References
Chapter 2: Learning-based intelligent energy efficient routing protocols in WSN
2.1 Introduction
2.2 Wireless sensor networks
2.3 Protocols in wireless sensor networks
2.4 Protocols in underwater wireless sensor networks
2.5 Protocols in wireless underground sensor networks
2.6 Protocols in wireless body area networks (WBANs)
2.7 Protocols in unmanned aerial vehicles
2.8 Protocols in wireless multimedia sensor networks
2.9 Research challenges
References
Chapter 3: Optimizing secure routing for mobile ad-hoc and WSN in IoT through dynamic adaption and energy efficiency
3.1 Introduction
3.1.1 Wireless sensor network
3.1.1.1 Motivation
3.1.2 Ad hoc networks (AN)
3.1.3 Mobile ad hoc networks (MANET)
3.1.4 Overview of IoT
3.2 Design of WSN in IoT
3.2.1 Integration of WSN into IoT
3.3 Applications of WSN and IoT
3.4 Secure routing in IoT–based MANET
3.4.1 Energy efficiency in secure routing
3.5 Cresent zone–based location aided routing protocol
3.6 Literature review
3.7 Methodology
3.8 Results and discussion
3.9 Conclusion
References
Chapter 4: Energy efficient in-network data aggregation in Internet-of-Things
4.1 Introduction
4.1.1 Data reduction techniques
4.1.1.1 Data aggregation
4.2 Data aggregation routing in IoT
4.2.1 Tree-based approaches
4.2.2 Cluster-based approaches
4.2.2.1 Grid-based approach
4.2.3 Centralized approaches
4.3 IoT data aggregation scheduling
4.3.1 Effect of heterogeneity charging rate of devices
4.3.2 Effect of duty cycling on aggregation delay
4.3.3 Impact of waiting time on data accuracy
4.3.4 Effect of content type
4.3.5 Link-delay aware data aggregation
4.4 Secure data aggregation in IoT
4.4.1 Encrypted data aggregation
4.4.2 Data aggregation under node/device compromise attack
4.4.3 Blockchain-based data aggregation
4.5 Conclusion
References
Chapter 5: Future 6G approaches: Integrating intelligent security, sensing, and communication into a green network’s architecture
5.1 Introduction
5.2 Evolution of multiple communications generations
5.3 Key components of 6G
5.3.1 Multiband ultrafast speed transmission (THz waves)
5.3.2 Efficiency broadcasting
5.3.3 Artificial intelligence
5.3.4 Operational intelligence (OI)
5.3.5 Environmental intelligence (EI)
5.3.6 Service intelligence (SI)
5.3.7 High security, secrecy, and privacy
5.4 Envision of 6G application
5.4.1 One hundred gigabits per second (Gbps)
5.4.2 Ten million linked devices per km2
5.4.3 A maximum energy consumption of one nanojoule per bit
5.5 Fundamental enabling technologies of 6G networks
5.5.1 Blockchain
5.5.2 Quantum communication
5.5.3 Unmanned aerial vehicles (UAV)
5.5.4 Free Cell Networking
5.5.5 Wireless Data and Energy Transfer (WIET)
5.5.6 Big Data Analytic (BDA)
5.6 Application of 6G
5.6.1 Holographic communication
5.6.2 Extended reality
5.6.3 Connected autonomous vehicles
5.6.4 Industry 5.0
5.6.5 Digital health-care
5.6.6 Digital twins
5.6.7 Brain computer interaction (BCI)
5.6.8 Distributed ledger application
5.7 Security and privacy
5.8 Advantages, disadvantages of 6G technologies
5.8.1 Advantages
5.8.2 Disadvantages
5.9 Conclusion
References
Chapter 6: Energy efficient wireless sensors architecture with LSTM based on Machine Learning Technique
6.1 Introduction
6.2 Methodology
6.2.1 Protocols
6.2.2 LEACH protocol
6.2.2.1 Set-Up Phase
6.2.2.2 Steady Phase
6.2.3 EESR protocol
6.3 Machine learning–based approaches
6.3.1 Supervised machine learning approach
6.3.1.1 K-nearest neighbour (KNN)
6.3.1.2 Decision tree (D-tree or DT)
6.3.1.3 Physical networks
6.3.1.4 Support vector machines (SVM)
6.3.1.5 Bayesian statistics
6.3.2 Unsupervised machine learning approach
6.3.2.1 K-means clustering
6.3.2.2 Principal component analysis (PCA)
6.3.3 Reinforcement learning
6.4 Operational challenges
6.4.1 Routing issues in WSN
6.4.2 Issues with data collection and clustering
6.4.3 Issues with event recognition and query processing
6.4.4 Localisation and object targeting issues
6.4.4.1 Issues in medium access control
6.5 Research-based machine learning–based WSN
6.6 Practical applications of wireless sensor networks
6.7 Research and future developments
6.8 Conclusion
References
Chapter 7: Healthcare 4.0: Blockchain technology application in healthcare ecosystem
7.1 Introduction
7.2 Healthcare 4.0
7.3 Blockchain technology
7.3.1 Blockchain technology in healthcare
7.3.2 Implications of blockchain in healthcare
7.4 Industry representatives to implement healthcare facilities through blockchain
7.5 Blockchain in COVID-19
7.6 Blockchain technology: Indian healthcare system
7.7 Issues and challenges
7.8 Future directions
7.9 Conclusion
Notes
References
Chapter 8: Inventory tracking via IoT in the pharmaceutical industry
8.1 Introduction
8.1.1 Classical inventory models in brief
8.1.2 Industy 4.0
8.1.3 IoT
8.1.4 IoT enabled by RFID technology
8.1.5 IoT application development
8.2 Inventory models include data from Industry 4.0
8.3 IoT for pharmaceutical
8.4 Review of literature
8.4.1 Pharmaceutical sector
8.4.2 PSC organization
8.4.3 PSC wholesalers
8.4.4 Pharma supply chain reverse logistics
8.5 Healthcare pharmaceutical inventories
8.5.1 Hospital pharmacy inventories
8.5.2 Retail pharmacy inventories
8.6 Internet of Things
8.6.1 Narrow-band IoT technology
8.6.2 RFID
8.6.3 Bluetooth network design
8.6.4 Technology comparison
8.7 Inventory
8.7.1 Inventory-associated costs
8.7.2 Methods of inventory management
8.7.3 Assessment of inventory control
8.7.4 Inventory management determinants
8.7.5 Inventory management and information technology
8.8 Inventory management
8.9 Forms of inventory administration
8.9.1 JIT
8.9.2 MRP
8.9.3 EOQ
8.9.4 DSI
8.10 Principles of inventory management
8.10.1 Demand forecasting
8.10.2 Warehouse flow
8.10.3 Inventory turns/stock rotation
8.10.4 Cycle counting
8.10.5 Process auditing
8.11 Methods of inventory control
8.11.1 Periodic system
8.11.2 Perpetual system
8.12 Components of inventory management
8.12.1 Inventory forecast analytics
8.12.2 Optimized purchase orders
8.12.3 Inventory control
8.13 Techniques used for various inventory management problems
8.13.1 Challenge #1
8.13.2 Challenge #2
8.13.3 Challenge #3
8.13.4 Challenge #4
8.13.5 Challenge #5
8.13.6 Challenge #6
8.13.7 Challenge #7
8.13.8 Challenge #8
8.13.9 Challenge #9
8.13.10 Challenge #10
8.13.11 Challenge #11
8.13.12 Challenge #12
8.13.13 Challenge #13
8.13.14 Challenge #14
8.13.15 Challenge #15
8.13.16 Challenge #16
8.13.17 Challenge #17
8.13.18 Challenge #18
8.13.19 Challenge #19
8.13.20 Challenge #20
8.14 Pharmaceutical inventory management system
8.14.1 Overview
8.14.2 Importance of inventory management in the pharmaceutical industry
8.14.3 Pharmacy inventory management methods
8.14.4 The visual method
8.14.5 The periodic method
8.14.6 The perpetual inventory management method
8.14.7 The hybrid method
8.14.8 Factors affecting pharmacy inventory management
8.14.9 Shaping pharmacy inventory management
8.14.10 IoT in pharmaceutical manufacturing
8.14.11 IoT–Pharma architecture
8.15 Use Cases
8.15.1 Industrial mechanics
8.15.2 Material tracking
8.15.3 Logistics
8.15.4 Optimize the clinical trials
8.15.5 Regulatory compliance
8.15.6 Smart equipment
8.15.7 Smart pills and implanted devices
8.15.8 Rich insights
8.15.9 Better physician engagement
8.16 Conclusion
Notes
References
Chapter 9: Decentralized file sharing system based on IPFS and blockchain
9.1 Introduction
9.1.1 Blockchain
9.1.2 IPFS
9.1.3 ECC
9.2 Literature review
9.3 Proposed work
9.3.1 Architecture
9.3.1.1 Uploading process
9.3.1.2 Downloading process
9.4 Results and discussion
9.5 Challenges
9.6 Conclusion
Bibliography
Chapter 10: FAWT–based advanced multiboost learning algorithm for driver fatigue detection using brain EEG signals
10.1 Introduction
10.2 State-of-art-methods
10.3 Method
10.3.1 EEG dataset
10.3.2 Feature extraction using FAWT
10.4 Results and analysis
10.5 Comparative study
10.6 Conclusion
Acknowledgement
Bibliography
Chapter 11: Feature fusion-based learning algorithm using multi-domain signal features for wearable healthcare devices
11.1 Introduction
11.2 Method
11.2.1 Mathematical formulation
11.2.2 CCA and DCA
11.2.3 Nonlinear medical dataset
11.3 Results and discussion
11.4 Comparative analysis
11.5 Conclusion
Acknowledgements
Bibliography
Chapter 12: The intelligence of WSNs
12.1 Introduction and background
12.2 Literature background
12.2.1 Network types
12.2.1.1 Wired networking
12.2.1.2 Wireless networking
12.3 Wireless sensor networks (WSNs)
12.4 Wireless body area network (WBAN)
12.4.1 WBAN architectures
12.4.2 WBAN communication stack layers
12.4.3 WBAN technologies
12.4.4 Types of WBAN devices
12.4.4.1 Wireless sensor node
12.4.5 Applications of WBAN
12.4.5.1 Healthcare
12.4.5.2 Military and defense
12.4.6 IOT with WBAN
12.4.7 WBAN systems for healthcare
12.4.8 WBAN scenarios for the healthcare system
12.5 Conclusion
References
Chapter 13: Applications of wireless sensor networks in IoT
13.1 Introduction to wireless sensor networks
13.2 WSN history
13.2.1 Node operation on the basis of conditions
13.2.2 WSN protocols
13.2.3 Accomplishment of WSN mechanism
13.2.4 Categorization of wireless sensor networks
13.2.5 Kinds of movability in wireless sensing elements networks
13.2.6 Protected communication of nodes of WSN
13.2.7 Operating systems for WSN
13.2.8 Categories of WSN services
13.3 WSN communication protocols
13.4 Commonly used sensors
13.5 Survey of technical papers
13.5.1 Understanding of accurate agronomy supervising system on the basis of network of wireless sensing elements
13.5.2 Preciseness agronomy supervising framework on the basis of WSN
13.5.3 Preciseness agronomy utilizing networks of wireless sensing elements: Chances and ultimatums
13.5.4 Wireless sensing element networks in precise agronomy
13.5.5 Energy-effective wireless sensing element networks for agronomy accuracy: An analysis
13.5.6 Utilization of wireless sensing element networks for greenhouse requirements control in agronomic accuracy
13.5.7 Wireless sensing element network in precise agronomy application
13.5.8 Agronomics field supervision utilizing wireless sensing elements networks for enhancing crop yield
13.5.9 Case study 1: Monitoring snow and ice on UK highways during winters
13.5.10 Weather station to assist in decision-making
13.5.10.1 Saving money and improving the environment
13.5.11 Case study 2: Forecasting volcanic eruptions in Masaya with smart wireless sensing elements
13.5.12 Real-time monitoring at Masaya volcano with 80 sensors
13.5.12.1 Saving lines by opening data
13.5.13 Case study 3: Protection of beluga whales in Alaska utilizing flexible sensor platform
13.6 Features of wireless sensing elements network
13.7 How can wireless sensing elements networks create a secured and productive mining industry?
13.7.1 Design of a wireless sensing element network
13.7.2 Design of a wireless sensing element node
13.7.3 Advantages of using a wireless sensing elements network
13.8 Conclusion
Bibliography
Chapter 14: Security considerations in IoT using machine learning and deep learning
14.1 Introduction
14.2 Definition
14.3 Smart appliances in various fields
14.4 Features
14.4.1 Significant features of ML and DL
14.4.2 Machine learning
14.4.3 Deep learning
14.4.4 Machine learning in security considerations smart appliances
14.4.5 Taxonomy of the survey: Deep learning in security considerations smart appliances
14.5 Machine learning and deep learning methods in new information technologies
14.5.1 IoT
14.5.2 Cloud computing
14.5.3 Edge computing
14.5.4 Hybrid models
14.5.5 Fog computing
14.5.6 Internet of Drones
14.5.7 Internet of Vehicles
14.6 IoT with machine learning/deep learning
14.6.1 IoT architecture
14.6.2 Deep learning methods for IoT
14.6.3 Behaviour modelling and analysis of IoT using deep learning
14.6.4 ML/DL in IoT security
14.6.4.1 Safety and security threats in IoT
14.6.5 Attack surface for IoT (s)
14.6.5.1 Physical devices are the attack surface
14.6.5.2 Network service at attack surface
14.6.5.3 Cloud service at attack surface
14.6.5.4 Emerging ML techniques in IoT security
14.7 Architecture (smart home)
14.7.1 The MufHAS architecture (smart home)
14.7.1.1 System architecture
14.8 Intrusion detection in IoT
14.8.1 Anomaly/intrusion detection
14.8.2 Intrusion detection systems for IoT
14.9 Applications and security challenges
14.10 Research and future direction of smart appliances
14.11 Conclusion
References
Chapter 15: Blockchain-energized smart healthcare monitoring system
15.1 Introduction
15.2 Healthcare system
15.2.1 Insurance industry
15.2.2 Pharmaceutical industry
15.2.3 Doctors
15.2.4 Patients
15.2.5 Government
15.3 Major issues facing healthcare and challenges in the healthcare system
15.4 Concept and application areas of block chain technology
15.5 Challenges to block chain applications in healthcare
15.6 Integrated blockchain-energised smart healthcare system framework
15.7 Conclusion and inference
15.8 Future research directions
References
Index