Artificial Intelligence for Intelligent Systems: Fundamentals, Challenges, and Applications (Intelligent Data-Driven Systems and Artificial Intelligence)

✍ Scribed by Inam Ullah Khan (editor), Mariya Ouaissa (editor), Mariyam Ouaissa (editor), Muhammad Fayaz (editor), Rehmat Ullah (editor)

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 375
• Edition: 1
• Category: Library

✦ Synopsis

The aim of this book is to highlight the most promising lines of research, using new enabling technologies and methods based on AI/ML techniques to solve issues and challenges related to intelligent and computing systems. Intelligent computing easily collects data using smart technological applications like IoT-based wireless networks, digital healthcare, transportation, blockchain, 5.0 industry and deep learning for better decision making. AI enabled networks will be integrated in smart cities' concept for interconnectivity. Wireless networks will play an important role. The digital era of computational intelligence will change the dynamics and lifestyle of human beings. Future networks will be introduced with the help of AI technology to implement cognition in real-world applications. Cyber threats are dangerous to encode information from network. Therefore, AI-Intrusion detection systems need to be designed for identification of unwanted data traffic.

This book:

• Provides a better understanding of artificial intelligence-based applications for future smart cities
• Presents a detailed understanding of artificial intelligence tools for intelligent technologies
• Showcases intelligent computing technologies in obtaining optimal solutions using artificial intelligence
• Discusses energy-efficient routing protocols using artificial intelligence for Flying ad-hoc networks (FANETs)
• Covers machine learning-based Intrusion detection system (IDS) for smart grid

It is primarily written for senior undergraduate, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, and computer engineering.

✦ Table of Contents

Cover
Half Title
Series
Title
Copyright
Contents
Preface
About the editors
List of contributors
Part I Recent trends and challenges of artificial intelligence
1 Unleashing the power of artificial intelligence: exploring multidisciplinary frontiers for innovation and impact
1.1 Introduction
1.1.1 Brief overview of artificial intelligence and its capabilities
1.1.2 Importance of multidisciplinary approach in AI applications
1.2 Health care
1.2.1 AI in medical diagnosis and treatment
1.2.2 AI for drug discovery and personalized medicine
1.3 Finance and banking
1.3.1 AI for fraud detection and prevention
1.3.2 AI-based investment strategies and risk assessment
1.4 Transportation and logistics
1.4.1 Autonomous vehicles and intelligent transportation systems
1.4.2 Optimization algorithms for supply chain management
1.5 Education
1.5.1 Intelligent tutoring systems and personalized learning
1.5.2 AI-based student support and career guidance
1.6 Environmental sustainability
1.6.1 AI for climate change modeling and prediction
1.6.2 Smart energy management and resource optimization
1.7 Ethical and social implications
1.7.1 Considerations of bias and fairness in AI applications
1.7.2 Privacy and security concerns in multidisciplinary AI systems
1.7.3 Transparency and accountability in AI decision-making
1.8 Conclusion
1.8.1 Recap of multidisciplinary applications of AI
1.8.2 Future directions and potential impact of AI in various fields
References
2 Advancements in deep learning: unveiling future trends and applications across AI for intelligent computing
2.1 Introduction
2.1.1 Machine learning
2.1.2 Categories of machine learning
2.2 Introduction to neural networks
2.2.1 Vanishing and exploding gradient problem
2.2.2 Different types of activation functions
2.3 Training a neural network
2.3.1 Backpropagation
2.4 Architectural evolution of deep CNNs
2.4.1 Beginning of CNN
2.4.2 Revival of CNN
2.5 Existing architectures for image classification
2.5.1 LeNet
2.5.2 AlexNet
2.5.3 VGG
2.5.4 GoogLeNet
2.5.5 Applications of CNNs
2.6 Conclusion
References
3 Comprehensive comparative analysis of artificial intelligence, machine learning, and deep learning
3.1 Introduction
3.2 Fundamentals of artificial intelligence
3.2.1 Interrelationships
3.2.2 AI Instances
3.3 Machine learning: the foundation
3.4 Deep learning: the neural network revolution
3.5 Tools and frameworks
3.5.1 AI implementation tools
3.5.2 Machine learning implementation tools
3.5.3 Deep learning implementation tools
3.6 Evaluation parameters used for AI, ML, DL
3.7 Case studies and applications
3.8 Future directions and challenges
3.9 Conclusion
References
4 Applications of artificial intelligence in smart distributed processing and big data mining
4.1 Introduction
4.1.1 Applications of artificial intelligence in big data and distributed processing
4.1.2 Improving the effectiveness of data processing
4.1.3 Making possible cutting-edge analytics
4.1.4 Enabling on-demand information processing
4.1.5 Processing in a distributed manner
4.1.6 Data extraction and visualization automation
4.2 Challenges in big data mining
4.3 Frameworks of distributed processing
4.4 Distributed system and data mining
4.4.1 Scalable distributed processing techniques
4.4.2 Challenges in distributed system
4.5 Opportunities in big data mining
4.5.1 Big data mining applications
4.5.2 Trends in big data technologies
4.5.3 Tools used in big data mining
4.5.4 Technologies used in big data mining
4.6 Conclusion
References
5 Quantum AI: uniting the future of smart technologies
5.1 Introduction
5.1.1 Exploring quantum AI
5.1.2 Significance in modern technology
5.2 Quantum computing essentials
5.2.1 Understanding qubits and quantum gates
5.2.2 The quantum advantage
5.3 Quantum machine learning
5.3.1 Quantum algorithms and their applications
5.3.2 Quantum-enhanced data analysis
5.3.3 Quantum AI in industry
5.4 Quantum hardware and software
5.4.1 Quantum processors and development tools
5.4.2 Quantum programming languages
5.5 Ethics and security in quantum AI
5.5.1 Ethical considerations
5.5.2 Cybersecurity implications
5.6 The future of quantum AI and conclusion
5.6.1 Envisioning quantum AI’s role
5.6.2 Ongoing developments and challenges
5.6.3 Embracing the quantum AI fusion
5.6.4 Conclusion
References
Part II Secure artificial intelligence in computing systems
6 The significance of artificial intelligence in cybersecurity
6.1 Introduction
6.2 AI Applications in cybersecurity
6.2.1 Identifying and preventing threats through AI
6.2.2 The detection and prevention of advance threats
6.2.3 Automated and intelligent response to incidents
6.2.4 Malware detection and analysis improvements
6.2.5 Behavioral analytics and user monitoring
6.2.6 Proactive vulnerability management
6.2.7 Collaborative threat intelligence
6.3 Artificial intelligence
6.3.1 Machine learning in cybersecurity
6.3.2 Supervised learning
6.3.3 Unsupervised learning
6.3.4 Deep learning in cybersecurity
6.5 Cybersecurity and different attack types
6.5.1 Physical security attack
6.5.2 Man-in-the-middle
6.5.3 Bluetooth man-in-the-middle
6.5.4 False data injection attack
6.5.5 Botnets
6.6 Future of cybersecurity
6.7 Conclusion
References
7 Securing the internet of things with blockchain
7.1 Introduction
7.2 IoT security challenges and vulnerabilities
7.2.1 Risks associated with compromised IoT devices
7.2.2 Existing security measures
7.3 Blockchain technology for IoT security
7.3.1 Blockchain’s security features
7.3.2 Key applications of blockchain in IoT security
7.3.3 Comparative analysis of blockchain implementations for IoT security
7.3.4 Scalability, performance, and resource efficiency considerations
7.3.5 Use of smart contracts for secure and automated transactions in IoT
7.4 Limitations and challenges
7.4.1 Scalability and performance considerations
7.4.2 Energy efficiency and resource constraints
7.4.3 Regulatory and legal implications
7.5 Future research opportunities and directions
7.5.1 Privacy-preserving techniques
7.5.2 Scalability solutions
7.5.3 Interoperability and standards
7.5.4 Smart contract security
7.5.5 Edge computing and blockchain integration
7.5.6 Governance models
7.5.7 AI and machine learning
7.6 Conclusion
References
8 Data traffic management in AI-IoT network to reduce congestion
8.1 Introduction
8.2 Literature
8.3 Objectives of data traffic management in AI-IoT network
8.4 Significance of data traffic management in AI-IoT networks
8.4.1 Optimal network performance
8.4.2 Reliable data transmission
8.4.3 Enhanced quality of service
8.4.4 Efficient resource utilization
8.4.5 Scalability and scalable growth
8.4.6 Improved security and privacy
8.4.7 Economic and societal impact
8.4.8 AI-IoT network architecture
8.5 Overview of AI-IoT networks
8.5.1 Overview of AI-IoT network components
8.5.2 Importance of congestion reduction in AI-IoT networks
8.5.3 Causes of congestion in AI-IoT networks
8.5.4 Impact of congestion on AI-IoT network performance
8.5.5 Challenges in managing congestion in AI-IoT networks
8.6 Data traffic management techniques
8.6.1 Traffic shaping
8.6.2 Quality-of-service differentiation
8.6.3 Load balancing
8.6.4 Traffic engineering
8.6.5 Content delivery networks
8.6.6 Caching
8.6.7 Packet prioritization
8.6.8 Deep packet inspection
8.6.9 Adaptive and machine learning–based techniques
8.6.10 Policy-based traffic management
8.7 Congestion detection and monitoring
8.7.1 Network traffic analysis
8.7.2 Packet delay measurement
8.7.3 Queue length monitoring
8.7.4 Bandwidth utilization monitoring
8.7.5 Performance metrics analysis
8.7.6 Flow-level monitoring
8.7.7 Anomaly detection
8.7.8 Real-time monitoring and alarms
8.7.9 Probing and active measurement
8.8 Congestion control and mitigation strategies
8.8.1 Congestion control algorithms for AI-IoT networks
8.9 Dynamic resource allocation
8.9.1 Elasticity
8.9.2 Monitoring and load balancing
8.9.3 Auto-scaling
8.9.4 Virtualization
8.9.5 Resource scheduling
8.9.6 Reservation and preemption
8.9.7 Predictive analytics
8.9.8 Intelligent routing and network optimization
8.10 Case studies and best practices
8.10.1 Edge computing and local processing
8.10.2 Data filtering and aggregation
8.10.3 Traffic prioritization and QoS
8.10.4 Dynamic resource allocation and load balancing
8.10.5 Predictive analytics and machine learning
8.10.6 Protocol optimization
8.11 Successful implementations of data traffic management in AI-IoT networks
8.11.1 Smart grid systems
8.11.2 Connected vehicles
8.11.3 Smart health care systems
8.11.4 Industrial AI-IoT applications
8.11.5 Smart cities
8.12 Lessons learned from congestion reduction initiatives
8.12.1 Comprehensive approach
8.12.2 Data-driven decision-making
8.12.3 Multimodal transportation
8.12.4 Demand management strategies
8.12.5 Intelligent traffic management systems
8.12.6 Public engagement and communication
8.12.7 Continuous evaluation and adaptation
8.13 Best practices for efficient data traffic management
8.13.1 Predictive traffic routing
8.13.2 Dynamic bandwidth allocation
8.13.3 Network slicing
8.13.4 Peer-to-peer communication
8.13.5 Dynamic protocol selection
8.13.6 Traffic off-loading to edge devices
8.13.7 Application-aware traffic management
8.13.8 Adaptive multicast
8.13.9 Dynamic time slot allocation
8.13.10 User-initiated traffic control
8.14 Future trends and challenges
8.14.1 Future trends
8.14.2 5G network deployment
8.14.3 AI and machine learning–based traffic optimization
8.14.4 Security and privacy
8.14.5 Interoperability and standardization
8.14.6 Real-time decision-making
8.15 Conclusion
References
9 Artificial intelligence–enabled anomaly IDS for IoT network: trends, solutions, and challenges
9.1 Introduction
9.2 Literature study
9.3 AI-enabled anomaly intrusion detection system for IoT network
9.4 Machine learning–based anomaly IDS
9.4.1 SVM-enabled cyberattack detection for IoT network
9.4.2 Decision tree–enabled cyberattack detection for IoT network
9.4.3 Random forest–enabled cyberattack detection for IoT network
9.4.4 Logistic regression–based cyberattack detection for IoT network
9.5 AI-based anomaly IDS applications
9.5.1 AI-based anomaly IDS for smart cities
9.5.2 AI-based anomaly IDS for future transportation
9.5.3 AI-based anomaly IDS for smart grid
9.6 AI-enabled anomaly detection use cases
9.6.1 AI-anomaly detection for health care industry
9.6.2 AI-anomaly detection for banking
9.6.3 AI-anomaly detection for defense and government
9.7 Reducing false positive rate using AI
9.8 Future trends and challenges
9.9 Conclusion
References
Part III Big data analytics applying in current applications
10 Big data intelligence in health care
10.1 Introduction
10.2 Alzheimer’s disease
10.2.1 AI for AD diagnosis
10.3 Cardiovascular disease
10.3.1 AI for CVD diagnosis
10.3.2 Cardiac imaging analysis
10.4 Artificial intelligence in cancer disease
10.4.1 Magnetic resonance imaging
10.4.2 Future research in cancer disease
10.5 Diabetes diseases
10.5.1 AI in diabetes disease
10.5.2 Future AI prediction in diabetes
10.6 Tuberculosis diseases
10.6.1 Pulmonary tuberculosis detection
10.6.2 Future AI predictions in tuberculosis diseases
10.7 Stroke detection
10.7.1 Using AI in stroke disease
10.8 Hypertension disease detection
10.8.1 Hypertension disease detection using AI
10.9 Skin disease
10.9.1 AI in skin disease
10.9.2 Future detection in skin disease
10.10 Chronic liver disease detection
10.10.1 AI for liver disease
10.10.2 Radiology image analysis
10.10.3 Standardization of image analysis
10.11 Conclusion
References
11 Trends and challenges in harnessing big data intelligence for health care transformation
11.1 Introduction
11.2 Understanding big data in health care
11.2.1 Definition and characteristics of big data
11.2.2 Sources of big data in health care
11.3 The role of big data intelligence in health care
11.3.1 Improving patient care and outcome
11.3.2 Advancing medical research and drug discovery
11.3.3 Enhancing clinical decision-making
11.3.4 Transforming health care operations and management
11.4 Big data analytics in health care
11.4.1 Data mining and pattern recognition
11.4.2 Machine learning and artificial intelligence in health care
11.4.3 Natural language processing for health care data
11.5 Applications of big data in specific health care areas
11.5.1 Big data in diagnosis and imaging
11.5.2 Big data in personalized medicine and genomics
11.5.3 Big data in health care IoT and wearables
11.6 Trends and opportunities
11.6.1 The evaluation of big data in health care
11.6.2 Emerging technologies and innovations
11.7 Challenges and future directions
11.7.1 Storage
11.7.2 Security
11.7.3 Opacity of infrastructure
11.7.4 Data uncertainty
11.7.5 Ethical and legal issues
11.8 Conclusion
References
12 Improving hepatitis C diagnosis using machine learning techniques: an experimental analysis
12.1 Introduction
12.2 Literature review
12.3 Methodology
12.3.1 Data collection
12.3.2 Data preprocessing
12.4 Experimental result
12.5 Conclusion and future work
References
13 A step toward the detection of alzheimer’s disease using ensemble learning
13.1 Introduction
13.2 Literature review
13.3 Methodology
13.3.1 Dataset
13.3.2 Ensemble method
13.4 Results and discussion
13.5 Conclusion
References
14 Exploring the use of machine learning algorithms in early detection of liver disease
14.1 Introduction
14.2 Literature review
14.3 Methodology
14.3.1 Data collection and preprocessing
14.4 Data preprocessing
14.5 Result and analysis
14.6 Discussion
14.7 Conclusion and future work
References
15 Intelligent transportation channels for smart cities
15.1 Introduction
15.2 Literature
15.3 Transportation in smart city development
15.3.1 Importance of transportation in smart city development
15.3.2 Key goals and objectives of intelligent cities
15.4 Intelligent transportation channels
15.4.1 Traffic management systems
15.4.2 Intelligent traffic control systems
15.4.3 Incident management systems
15.4.4 Public transportation systems
15.4.5 Intelligent parking systems
15.4.6 Connected vehicles
15.4.7 Traveler information systems
15.4.8 How intelligent transportation channels contribute to smart city goals
15.4.9 Benefits and advantages of implementing intelligent transportation channels
15.4.10 Technologies enabling intelligent transportation channels
15.4.11 Artificial intelligence and machine learning in transportation
15.4.12 Applications of AI and ML in traffic prediction, congestion management, and autonomous vehicles
15.4.13 Challenges and ethical considerations in AI implementation for transportation
15.5 Intelligent traffic management systems
15.5.1 Components of intelligent traffic management systems
15.5.2 Traffic signal control and optimization
15.5.3 Incident detection and management
15.6 Smart mobility solutions
15.6.1 Connected and autonomous vehicles
15.6.2 Autonomous vehicles
15.7 Sustainable transportation solutions
15.7.1 Electric mobility
15.7.2 Smart parking systems
15.7.3 Bike-sharing and micro-mobility solutions
15.7.4 Flexibility and convenience
15.8 Challenges and future directions
15.8.1 Data privacy and security
15.8.2 Integration and interoperability
15.8.3 Future trends and emerging technologies
15.9 Conclusion
References
16 Digital twins for industry 4.0 and 5.0
16.1 Introduction
16.2 What makes industry 5.0 different from industry 4.0?
16.3 DT—an emerging technology for industry 4.0 and industry 5.0
16.3.1 DT technology for manufacturing industry
16.3.2 Indispensable role of DT technology in industry 4.0 and 5.0
16.3.3 Case study on DT for industry 4.0 and 5.0
16.4 Use cases of DT technology for industry 4.0 and 5.0
16.4.1 Industry 4.0
16.4.2 Industry 5.0
16.5 Key components of DT technology
16.6 Types of DTs being used in industries
16.7 Benefits of DT technology in manufacturing industries
16.8 Challenges in implementation of DT technology
16.9 Recommendations for the successful adoption of DT technology for industry 4.0 and 5.0
16.10 Conclusion
References
Index