Machine Learning Approaches for Convergence of IoT and Blockchain

Оглавление

Группа авторов. Machine Learning Approaches for Convergence of IoT and Blockchain

Table of Contents

Guide

List of Illustrations

List of Tables

Pages

Machine Learning Approaches for Convergence of IoT and Blockchain

Preface

1. Blockchain and Internet of Things Across Industries

1.1 Introduction

1.2 Insight About Industry

1.2.1 Agriculture Industry

1.2.2 Manufacturing Industry

1.2.3 Food Production Industry

1.2.4 Healthcare Industry

1.2.5 Military

1.2.6 IT Industry

1.3 What is Blockchain?

1.4 What is IoT?

1.5 Combining IoT and Blockchain

1.5.1 Agriculture Industry

1.5.2 Manufacturing Industry

1.5.3 Food Processing Industry

1.5.4 Healthcare Industry

1.5.5 Military

1.5.6 Information Technology Industry

1.6 Observing Economic Growth and Technology’s Impact

1.7 Applications of IoT and Blockchain Beyond Industries

1.8 Conclusion

References

2. Layered Safety Model for IoT Services Through Blockchain

2.1 Introduction

2.1.1 IoT Factors Impacting Security

2.2 IoT Applications

2.3 IoT Model With Communication Parameters

2.3.1 RFID (Radio Frequency Identification)

2.3.2 WSH (Wireless Sensor Network)

2.3.3 Middleware (Software and Hardware)

2.3.4 Computing Service (Cloud)

2.3.5 IoT Software

2.4 Security and Privacy in IoT Services

2.5 Blockchain Usages in IoT

2.6 Blockchain Model With Cryptography

2.6.1 Variations of Blockchain

2.7 Solution to IoT Through Blockchain

2.8 Conclusion

References

3. Internet of Things Security Using AI and Blockchain

3.1 Introduction

3.2 IoT and Its Application

3.3 Most Popular IoT and Their Uses

3.4 Use of IoT in Security

3.5 What is AI?

3.6 Applications of AI

3.7 AI and Security

3.8 Advantages of AI

3.9 Timeline of Blockchain

3.10 Types of Blockchain

3.11 Working of Blockchain

3.12 Advantages of Blockchain Technology

3.13 Using Blockchain Technology With IoT

3.14 IoT Security Using AI and Blockchain

3.15 AI Integrated IoT Home Monitoring System

3.16 Smart Homes With the Concept of Blockchain and AI

3.17 Smart Sensors

3.18 Authentication Using Blockchain

3.19 Banking Transactions Using Blockchain

3.20 Security Camera

3.21 Other Ways to Fight Cyber Attacks

3.22 Statistics on Cyber Attacks

3.23 Conclusion

References

4. Amalgamation of IoT, ML, and Blockchain in the Healthcare Regime

4.1 Introduction

4.2 What is Internet of Things?

4.2.1 Internet of Medical Things

4.2.2 Challenges of the IoMT

4.2.3 Use of IoT in Alzheimer Disease

4.3 Machine Learning

4.3.1 Case 1: Multilayer Perceptron Network

4.3.2 Case 2: Vector Support Machine

4.3.3 Applications of the Deep Learning in the Healthcare Sector

4.4 Role of the Blockchain in the Healthcare Field. 4.4.1 What is Blockchain Technology?

4.4.2 Paradigm Shift in the Security of Healthcare Data Through Blockchain

4.5 Conclusion

References

5. Application of Machine Learning and IoT for Smart Cities

5.1 Functionality of Image Analytics

5.2 Issues Related to Security and Privacy in IoT

5.3 Machine Learning Algorithms and Blockchain Methodologies

5.3.1 Intrusion Detection System

5.3.2 Deep Learning and Machine Learning Models

5.3.3 Artificial Neural Networks

5.3.4 Hybrid Approaches

5.3.5 Review and Taxonomy of Machine Learning

5.4 Machine Learning Open Source Tools for Big Data

5.5 Approaches and Challenges of Machine Learning Algorithms in Big Data

5.6 Conclusion

References

6. Machine Learning Applications for IoT Healthcare

6.1 Introduction

6.2 Machine Learning

6.2.1 Types of Machine Learning Techniques. 6.2.1.1 Unsupervised Learning

6.2.1.2 Supervised Learning

6.2.1.3 Semi-Supervised Learning

6.2.1.4 Reinforcement Learning

6.2.2 Applications of Machine Learning

6.2.2.1 Prognosis

6.2.2.2 Diagnosis. 6.2.2.2.1 Electronic Health Records (EHRs)

6.2.2.2.2 Medical Image Analysis

6.2.2.2.3 Treatment

6.2.2.2.4 Clinical Flow

6.3 IoT in Healthcare

6.3.1 IoT Architecture for Healthcare System

6.3.1.1 Physical and Data Link Layer

6.3.1.2 Network Layer

6.3.1.3 Transport Layer

6.3.1.4 Application Layer

6.4 Machine Learning and IoT

6.4.1 Application of ML and IoT in Healthcare

6.4.1.1 Smart Diagnostic Care

6.4.1.2 Medical Staff and Inventory Tracking

6.4.1.3 Personal Care

6.4.1.4 Healthcare Monitoring Device

6.4.1.5 Chronic Disease Management

6.5 Conclusion

References

7. Blockchain for Vehicular Ad Hoc Network and Intelligent Transportation System: A Comprehensive Study

7.1 Introduction

7.2 Related Work

7.3 Connected Vehicles and Intelligent Transportation System

7.3.1 VANET

7.3.2 Blockchain Technology and VANET

7.4 An ITS-Oriented Blockchain Model

7.5 Need of Blockchain

7.5.1 Food Track and Trace

7.5.2 Electric Vehicle Recharging

7.5.3 Smart City and Smart Vehicles

7.6 Implementation of Blockchain Supported Intelligent Vehicles

7.7 Conclusion

7.8 Future Scope

References

8. Applications of Image Processing in Teleradiology for the Medical Data Analysis and Transfer Based on IOT

8.1 Introduction

8.2 Pre-Processing

8.2.1 Principle of Diffusion Filtering

8.3 Improved FCM Based on Crow Search Optimization

8.4 Prediction-Based Lossless Compression Model

8.5 Results and Discussion

8.6 Conclusion

Acknowledgment

References

9. Innovative Ideas to Build Smart Cities with the Help of Machine and Deep Learning and IoT

9.1 Introduction

9.2 Related Work

9.3 What Makes Smart Cities Smart?

9.3.1 Intense Traffic Management

9.3.2 Smart Parking

9.3.3 Smart Waste Administration

9.3.4 Smart Policing

9.3.5 Shrewd Lighting

9.3.6 Smart Power

9.4 In Healthcare System

9.5 In Homes

9.6 In Aviation

9.7 In Solving Social Problems

9.8 Uses of AI-People. 9.8.1 Google Maps

9.8.2 Ridesharing

9.8.3 Voice-to-Text

9.8.4 Individual Assistant

9.9 Difficulties and Profit

9.10 Innovations in Smart Cities

9.11 Beyond Humans Focus

9.12 Illustrative Arrangement

9.13 Smart Cities with No Differentiation

9.14 Smart City and AI

9.15 Further Associated Technologies

9.15.1 Model Identification

9.15.2 Picture Recognition

9.15.3 IoT

9.15.4 Big Data

9.15.5 Deep Learning

9.16 Challenges and Issues

9.16.1 Profound Learning Models

9.16.2 Deep Learning Paradigms

9.16.3 Confidentiality

9.16.4 Information Synthesis

9.16.5 Distributed Intelligence

9.16.6 Restrictions of Deep Learning

9.17 Conclusion and Future Scope

References

Index

WILEY END USER LICENSE AGREEMENT

Отрывок из книги

Scrivener Publishing 100 Cummings Center, Suite 541J Beverly, MA 01915-6106

.....

This planning is critical especially in times of an emergency. Another application is creation of smart bases; this is extensively helping in reducing man power and enhancing security. Here, sensors can be accommodated with everyday operation for better analysis and efficiency. Storing the sensor signals is a challenging task, since most of the military operations are highly confidential and the information, if leaked, may lead to extensive misuse and might become a threat to a nation. If we try to resolve the security issue with the use of blockchain technology, a public blockchain would not be recommended as it is decentralized and can be accessed by multiple nodes, so a private blockchain is the alternative that we turn to, but the security offered by it is not fool proof and thus cannot be 100% relied on [15]. Another application is that of data warfare, this comprises of any data that will be useful to the military ranging from tracking food supplies to keeping track of weather forecast at all times to make sure no operation or mission is planned during an unfavorable weather condition, for example, air defence practice or performance would be scheduled keeping the expected weather under consideration. The military is also required to maintain proper records of data pertaining to equipment availability, training of employed personnel, track of the enemy’s activity allowing them to observe any suspicious activity that may be performed, knowledge about the strength and equipment possessed by the enemy forces, thus on the whole boosting the intelligence and field forces of the military to be prepared and equipped for any possible threat well in advance.

A suggested application is to attach a sensor onto the solider similar to a RFID (radio frequency identification) which will be extremely beneficial especially during times such as that of war. Even if any solider is martyred or abducted, there will be a better chance to tracking and retrieving the person. It will also allow to monitor the actions undertaking by any solider and to be able to cover all scopes of improvement. However, this is a sphere where deploying IoT will be very money intensive, the scope is very large and so is the required investment. While implementing any such model, budgetary constraints play a major role as a determinant factor. Looking at the changes that have been brought about, we may say that the military sector has undergone considerable advancement and specialization due to the incorporation of these technologies in this sphere. They can now be better equipped and prepared to face various adverse circumstances.

.....