• Cover
• Half-Title Page
• Series Page
• Title Page
• Copyright Page
• Dedication
• Contents
• Preface
• Acknowledgments
• 1 Post Pandemic: The New Advanced Society
• 1.1 Introduction
• 1.1.1 Themes
• 1.1.1.1 Theme: Areas of Management
• 1.1.1.2 Theme: Financial Institutions Cyber Crime
• 1.1.1.3 Theme: Economic Notion
• 1.1.1.4 Theme: Human Depression
• 1.1.1.5 Theme: Migrant Labor
• 1.1.1.6 Theme: Digital Transformation (DT) of Educational Institutions
• 1.1.1.7 School and College Closures
• 1.2 Conclusions
• References
• 2 Distributed Ledger Technology in the Construction Industry Using Corda
• 2.1 Introduction
• 2.2 Prerequisites
• 2.2.1 DLT vs Blockchain
• 2.3 Key Points of Corda
• 2.3.1 Some Salient Features of Corda
• 2.3.2 States
• 2.3.3 Contract
• 2.3.3.1 Create and Assign Task (CAT) Contract
• 2.3.3.2 Request for Cash (RT) Contract
• 2.3.3.3 Transfer of Cash (TT) Contract
• 2.3.3.4 Updation of the Task (UOT) Contract
• 2.3.4 Flows
• 2.3.4.1 Flow Associated With CAT Contract
• 2.3.4.2 Flow Associated With RT Contract
• 2.3.4.3 Flow Associated With TT Contract
• 2.3.4.4 Flow Associated With UOT Contract
• 2.4 Implementation
• 2.4.1 System Overview
• 2.4.2 Working Flowchart
• 2.4.3 Experimental Demonstration
• 2.5 Future Work
• 2.6 Conclusion
• References
• 3 Identity and Access Management for Internet of Things Cloud
• 3.1 Introduction
• 3.2 Internet of Things (IoT) Security
• 3.2.1 IoT Security Overview
• 3.2.2 IoT Security Requirements
• 3.2.3 Securing the IoT Infrastructure
• 3.3 IoT Cloud
• 3.3.1 Cloudification of IoT
• 3.3.2 Commercial IoT Clouds
• 3.3.3 IAM of IoT Clouds
• 3.4 IoT Cloud Related Developments
• 3.5 Proposed Method for IoT Cloud IAM
• 3.5.1 Distributed Ledger Approach for IoT Security
• 3.5.2 Blockchain for IoT Security Solution
• 3.5.3 Proposed Distributed Ledger-Based IoT Cloud IAM
• 3.6 Conclusion
• References
• 4 Automated TSR Using DNN Approach for Intelligent Vehicles
• 4.1 Introduction
• 4.2 Literature Survey
• 4.3 Neural Network (NN)
• 4.4 Methodology
• 4.4.1 System Architecture
• 4.4.2 Database
• 4.5 Experiments and Results
• 4.5.1 FFNN
• 4.5.2 RNN
• 4.5.3 CNN
• 4.5.4 CNN
• 4.6 Discussion
• 4.7 Conclusion
• References
• 5 Honeypot: A Trap for Attackers
• 5.1 Introduction
• 5.1.1 Research Honeypots
• 5.1.2 Production Honeypots
• 5.2 Method
• 5.2.1 Low-Interaction Honeypots
• 5.2.2 Medium-Interaction Honeypots
• 5.2.3 High-Interaction Honeypots
• 5.3 Cryptanalysis
• 5.3.1 System Architecture
• 5.3.2 Possible Attacks on Honeypot
• 5.3.3 Advantages of Honeypots
• 5.3.4 Disadvantages of Honeypots
• 5.4 Conclusions
• References
• 6 Examining Security Aspects in Industrial-Based Internet of Things
• 6.1 Introduction
• 6.2 Process Frame of IoT Before Security
• 6.2.1 Cyber Attack
• 6.2.2 Security Assessment in IoT
• 6.2.2.1 Security in Perception and Network Frame
• 6.3 Attacks and Security Assessments in IIoT
• 6.3.1 IoT Security Techniques Analysis Based on its Merits
• 6.4 Conclusion
• References
• 7 A Cooperative Navigation for Multi-Robots in Unknown Environments Using Hybrid Jaya-DE Algorithm
• 7.1 Introduction
• 7.2 Related Works
• 7.3 Problem Formulation
• 7.4 Multi-Robot Navigation Employing Hybrid Jaya-DE Algorithm
• 7.4.1 Basic Jaya Algorithm
• 7.5 Hybrid Jaya-DE
• 7.5.1 Mutation
• 7.5.2 Crossover
• 7.5.3 Selection
• 7.6 Simulation Analysis and Performance Evaluation of Jaya-DE Algorithm
• 7.7 Total Navigation Path Deviation (TNPD)
• 7.8 Average Unexplored Goal Distance (AUGD)
• 7.9 Conclusion
• References
• 8 Categorization Model for Parkinson's Disease Occurrence and Severity Prediction
• 8.1 Introduction
• 8.2 Applications
• 8.2.1 Machine Learning in PD Diagnosis
• 8.2.2 Challenges of PD Detection
• 8.2.3 Structuring of UPDRS Score
• 8.3 Methodology
• 8.3.1 Overview of Data Driven Intelligence
• 8.3.2 Comparison Between Deep Learning and Traditional Machine
• 8.3.3 Deep Learning for PD Diagnosis
• 8.3.4 Convolution Neural Network for PD Diagnosis
• 8.4 Proposed Models
• 8.4.1 Classification of Patient and Healthy Controls
• 8.4.2 Severity Score Classification
• 8.5 Results and Discussion
• 8.5.1 Performance Measures
• 8.5.2 Graphical Results
• 8.6 Conclusion
• References
• 9 AI-Based Smart Agriculture Monitoring Using Ground-Based and Remotely Sensed Images
• 9.1 Introduction
• 9.2 Automatic Land-Cover Classification Techniques Using Remotely Sensed Images
• 9.3 Deep Learning-Based Agriculture Monitoring
• 9.4 Adaptive Approaches for Multi-Modal Classification
• 9.4.1 Unsupervised DA
• 9.4.2 Semi-Supervised DA
• 9.4.3 Active Learning-Based DA
• 9.5 System Model
• 9.6 IEEE 802.15.4
• 9.6.1 802.15.4 MAC
• 9.6.2 DSME MAC
• 9.6.3 TSCH MAC
• 9.7 Analysis of IEEE 802.15.4 for Smart Agriculture
• 9.7.1 Effect of Device Specification
• 9.7.1.1 Low-Power
• 9.7.2 Effect of MAC Protocols
• 9.8 Experimental Results
• 9.9 Conclusion & Future Directions
• References
• 10 Car Buying Criteria Evaluation Using Machine Learning Approach
• 10.1 Introduction
• 10.2 Literature Survey
• 10.3 Proposed Method
• 10.4 Dataset
• 10.5 Exploratory Data Analysis
• 10.6 Splitting of Data Into Training Data and Test Data
• 10.7 Pre-Processing
• 10.8 Training of Our Models
• 10.8.1 Gaussian Naïve Bayes
• 10.8.2 Decision Tree Classifier
• 10.8.3 Tuning the Model
• 10.8.4 Karnough Nearest Neighbor Classifier
• 10.8.5 Tuning the Model
• 10.8.6 Neural Network
• 10.8.7 Tuning the Model
• 10.9 Result Analysis
• 10.9.1 Confusion Matrix
• 10.9.2 Gaussian Naïve Bayes
• 10.9.3 Decision Tree Classifier
• 10.9.4 Karnough Nearest Neighbor Classifier
• 10.9.5 Neural Network
• 10.9.6 Accuracy Scores
• 10.10 Conclusion and Future Work
• References
• 11 Big Data, Artificial Intelligence and Machine Learning: A Paradigm Shift in Election Campaigns
• 11.1 Introduction
• 11.2 Big Data Reveals the Voters' Preference
• 11.2.1 Use of Software Applications in Election Campaigns
• 11.2.1.1 Team Joe App
• 11.2.1.2 Trump 2020
• 11.2.1.3 Modi App
• 11.3 Deep Fakes and Election Campaigns
• 11.3.1 Deep Fake in Delhi Elections
• 11.4 Social Media Bots
• 11.5 Future of Artificial Intelligence and Machine Learning in Election Campaigns
• References
• 12 Impact of Optimized Segment Routing in Software Defined Networks
• 12.1 Introduction
• 12.2 Software-Defined Network
• 12.3 SDN Architecture
• 12.4 Segment Routing
• 12.5 Segment Routing in SDN
• 12.6 Traffic Engineering in SDN
• 12.7 Segment Routing Protocol
• 12.8 Simulation and Result
• 12.9 Conclusion and Future Work
• References
• 13 An Investigation into COVID-19 Pandemic in India
• 13.1 Introduction
• 13.1.1 Symptoms of COVID-19
• 13.1.2 Precautionary Measures
• 13.1.3 Ways of Spreading the Coronavirus
• 13.2 Literature Survey
• 13.3 Technologies Used to Fight COVID-19
• 13.3.1 Robots
• 13.3.2 Drone Technology
• 13.3.3 Crowd Surveillance
• 13.3.4 Spraying the Disinfectant
• 13.3.5 Sanitizing the Contaminated Areas
• 13.3.6 Monitoring Temperature Using Thermal Camera
• 13.3.7 Delivering Essential Things
• 13.3.8 Public Announcement in the Infected Areas
• 13.4 Impact of COVID-19 on Business
• 13.4.1 Impact on Financial Markets
• 13.4.2 Impact on Supply Side
• 13.4.3 Impact on Demand Side
• 13.4.4 Impact on International Trade
• 13.5 Impact of COVID-19 on Indian Economy
• 13.6 Data and Result Analysis
• 13.7 Conclusion and Future Scope
• References
• 14 Skin Cancer Classification: Analysis of Different CNN Models via Classification Accuracy
• 14.1 Introduction
• 14.2 Literature Survey
• 14.3 Methodology
• 14.3.1 Dataset Preparation
• 14.3.2 Dataset Loading and Data Pre-Processing
• 14.3.3 Creating Models
• 14.4 Models Used
• 14.5 Simulation Results
• 14.5.1 Changing Size of MaxPool2D(n,n)
• 14.5.2 Changing Size of AveragePool2D(n,n)
• 14.5.3 Changing Number of con2d(32n-64n) Layers
• 14.5.4 Changing Number of con2d-32*n Layers
• 14.5.5 ROC Curves and MSE Curves
• 14.6 Conclusion
• References
• 15 Route Mapping of Multiple Humanoid Robots Using Firefly-Based Artificial Potential Field Algorithm in a Cluttered Terrain
• 15.1 Introduction
• 15.2 Design of Proposed Algorithm
• 15.2.1 Mechanism of Artificial Potential Field
• 15.2.1.1 Potential Field Generated by Attractive Force of Goal
• 15.2.1.2 Potential Field Generated by Repulsive Force of Obstacle
• 15.2.2 Mechanism of Firefly Algorithm
• 15.2.2.1 Architecture of Optimization Problem Based on Firefly Algorithm
• 15.2.3 Dining Philosopher Controller
• 15.3 Hybridization Process of Proposed Algorithm
• 15.4 Execution of Proposed Algorithm in Multiple Humanoid Robots
• 15.5 Comparison
• 15.6 Conclusion
• References
• 16 Innovative Practices in Education Systems Using Artificial Intelligence for Advanced Society
• 16.1 Introduction
• 16.2 Literature Survey
• 16.2.1 AI in Auto-Grading
• 16.2.2 AI in Smart Content
• 16.2.3 AI in Auto Analysis on Student's Grade
• 16.2.4 AI Extends Free Intelligent Tutoring
• 16.2.5 AI in Predicting Student Admission and Drop-Out Rate
• 16.3 Proposed System
• 16.3.1 Data Collection Module
• 16.3.2 Data Pre-Processing Module
• 16.3.3 Clustering Module
• 16.3.4 Partner Selection Module
• 16.4 Results
• 16.5 Future Enhancements
• 16.6 Conclusion
• References
• 17 PSO-Based Hybrid Weighted k-Nearest Neighbor Algorithm for Workload Prediction in Cloud Infrastructures
• 17.1 Introduction
• 17.2 Literature Survey
• 17.2.1 Machine Learning
• 17.3 Proposed System
• 17.3.1 Load Aware Cloud Computing Model
• 17.3.2 Wavelet Neural Network
• 17.3.3 Evaluation Using LOOCV Model
• 17.3.4 k-Nearest Neighbor (k-NN) Algorithm
• 17.3.5 Particle Swarm Optimization (PSO) Algorithm
• 17.3.6 HWkNN Optimization Algorithm Based on PSO
• 17.3.7 PSO-Based HWkNN (PHWkNN) Load Prediction Algorithm
• 17.4 Experimental Results
• 17.5 Conclusion
• References
• 18 An Extensive Survey on the Prediction of Bankruptcy
• 18.1 Introduction
• 18.2 Literature Survey
• 18.2.1 Data Pre-Processing
• 18.2.1.1 Balancing of Imbalanced Dataset
• 18.2.1.2 Outlier Data Handling
• 18.2.2 Classifiers
• 18.2.3 Ensemble Models
• 18.3 System Architecture and Simulation Results
• 18.4 Conclusion
• References
• 19 Future of Indian Agriculture Using AI and Machine Learning Tools and Techniques
• 19.1 Introduction
• 19.2 Overview of AI and Machine Learning
• 19.3 Review of Literature
• 19.4 Application of AI & Machine Learning in Agriculture
• 19.5 Current Scenario and Emerging Trends of AI and ML in Indian Agriculture Sector
• 19.6 Opportunities for Agricultural Operations in India
• 19.7 Conclusion
• References
• Index
• Also of Interest
• Check out these published and forthcoming titles in the "Artificial Intelligence and SoftComputing for Industrial Transformation
• EULA

Preface

The primary goal of an advanced society, also known as Society 5.0, is to create a human-centric society in which economic progress and social problems are balanced by implementing a system that integrates cyberspace and physical space. That is, a society which aims to create a better social and economic model by adapting the technological innovations of Industry 4.0. Society 5.0 is a huge societal transformation plan that visualizes a "super-smart society." It is a follow-up to Industry 4.0, where "information" was the predominant factor but cross-sectional knowledge sharing was not adequate, making cooperation among different sectors difficult. Also, finding the information needed from among information overflow is a tedious task, thereby limiting the scope of actions due to various factors like lack of skills, different abilities of those doing the work, etc. In Industry 4.0, data is accessed from the cloud and operations like searching, retrieving and analyzing data happen over the internet, with the burden of analysis being carried by humans. Whereas, in Society 5.0, people, systems and things will all be connected and the vast amounts of data from sensors will be collected in real time, accumulated and analyzed using artificial intelligence (AI), and the resultant analyses fed back to humans in different forms. Society 5.0 balances economic advancements with the resolution of social problems by incorporating the latest technological advancements like big data, AI, the internet of things (IoT) and robotics in all industrial and societal activities. Of course, Industry 4.0 will be a major component of Society 5.0, but is not the only component-it is also about citizens, organizations, stakeholders, academia and so on. In short, using the technological advancements to provide solutions to better the lives of humans is what an advanced society all about. Some salient features of an advanced society are problem-solving and value-adding, bringing out divergent abilities, decentralization, resilience, sustainability and environmental harmony.

A 360-degree view of the different dimensions of this revolution is presented in this book, including the various industries transforming industrial manufacturing, the security and challenges ahead and the far-reaching implications for society and the economy. The main objective of this edited book is to cover the impact that the new advanced society has on several platforms such as smart manufacturing systems, where artificial intelligence can be integrated with existing systems to make them smart, new business models and strategies, where anything and everything is possible through the internet and cloud, smart food chain systems, where food products can be delivered to any corner of the world at any time and in any situation, smart transport systems in which robots and self-driven cars are taking the lead, advances in security systems to assure people of their privacy and safety, and smart healthcare systems, where biochips can be incorporated into the human body to predict deadly diseases at early stages. Finally, it can be understood that the social reformation of Society 5.0 will lead to a society where every person leads an active and healthy life.

Included in this book are the fundamentals of Society 5.0, artificial intelligence, and the industrial internet of things, featuring their working principles and application in different sectors. In order to meet these objectives, accomplished writers in the field have contributed the 19 chapters summarized below.

• - Chapter 1 discusses areas of management, cybercrime in the financial sector, human depression, and school/college closures. Moreover, the constraints posed by returning migrant workers and the remedial measures devised to overcome them, and how to build a new advanced society in a post-COVID-19 era are also discussed.
• - Chapter 2 elaborates on the clients, architects, contractors, material suppliers, etc., in the construction industry. The complex supply chain of globally manufactured construction products has to be managed for the sake of meeting quality requirements and customer satisfaction. But, the lack of accountability in the construction industry sometimes leads to various types of errors, delays, and even accidents at some stages. This chapter introduces the key to ending these disputes with the help of Corda, a distributed ledger platform for permissioned networks inspired by blockchain technology. This helps in maintaining transparency among the actors involved in this industry, thus avoiding any miscommunication.
• - Chapter 3 analyzes the identity and access management challenges in the IoT, followed by a proposal of a cloud identity management model for the IoT using distributed ledger technology.
• - Chapter 4 elucidates the development of an efficient deep neural network (DNN) with a reduced number of parameters to make it real-time implementable. The architecture was implemented on German traffic sign recognition benchmark (GTSRB) dataset. Four variations of neural network architectures-feedforward neural network (FFNN), radial basis function neural network (RBNN), convolutional neural network (CNN), and recurrent neural network (RNN)-are designed. The various hyperparameters of the architectures-batch size, number of epochs, momentum, initial learning rate-are tuned to achieve the best results.
• - Chapter 5 deals with the basic aspects of honeypots, their importance in modern networks, types of honeypots, their level of interaction, and their advantages and disadvantages. Furthermore, this chapter also discusses how honeypots enhance the security architecture of a network.
• - Chapter 6 provides an in depth review of the necessity for security in IoT platforms and applications of the industrial internet of things (IIoT). Over the past decade, cyberattacks have mostly occurred on IoT devices; therefore, cybersecurity is introduced to deal with these cyberattacks. Furthermore, one of the chief attack modes in the IIoT are botnets and denial-of-service attacks. These attacks happen in several ways, and once they have occurred it is hard to predict and stop them. This chapter highlights many suggestions from diverse authors, which are detailed in tabular form.
• - Chapter 7 proposes an efficient navigation controller embedding hybrid Jaya-DE algorithm to obtain the optimum path of an individual robot. The efficiency of the proposed navigation controller was evaluated through simulation. The outcomes of the simulation revealed the efficacy of the suggested controller in monitoring the robots towards achieving a safe and optimal path. The strength of the suggested controller was further verified with a similar problem framework. The potency of the proposed controller can be seen from the outcome in resolving the navigation of mobile robots as compared to its competitor.
• - Chapter 8 discusses a study conducted for diagnosing Parkinson's disease using different machine learning (ML) algorithms for categorization and severity prediction through the measure of 16 voice and eight kinematic features accomplished with various archives. The dataset included 40 people with Parkinson's disease and healthy patients generated with the help of spiral drawings and voice readings. Of the various ML algorithms used for estimating, the highest accuracy (94.87%) was demonstrated by ANN, while Naïve Bayes was the least precise (71.79%). The work also predicted a severity score by suggesting some scientific measures with a prototype dataset.
• - Chapter 9 discusses the challenges faced in the development of a multi-sensor classification system and their possible solutions. Smart agriculture in rural areas can largely benefit from the low-power, low-cost sensors and aerial devices to sense (soil, temperature, salinity, water, light, insects, pests) and exchange data/images for monitoring and controlling crops.
• - Chapter 10 builds a classification model that classifies whether a customer is going to buy a car with specific features. This research work consisted of four ML models and an analysis of their results. These classifying models were Gaussian Naïve Bayes, decision tree, Karnough Nearest Neighbors and neural networks. The author also attempted to find the best hyperparameter value to obtain the best result from these models. These results are used to compare the accuracies of every model and decide the best model for use in real-time prediction. Here, the author was predicting whether a customer was going to buy a car or not buy a car with particular features available in it. Hence, for this prediction the best accuracy we got was 97.4%, which was given by the decision tree classifier. Also, the neural network had about the same prediction accuracy. Therefore, this ML model can be used by a firm to determine whether or not a new car with specific features will sell well or by a customer wanting to know whether a particular car will be bought by other customers as well.
• - Chapter 11 examines the use of AI and ML in political campaigns. It is divided into three sections-the first section explores internet penetration and the influence of social media on the Indian Lok Sabha election; the second section explores the forms of deepfake and automated social media bots and their use during the election campaign; and the final section explores the future of AI and ML in the election campaign in India.
• - Chapter 12 attempts to explain the impact of segment routing (SR) in...