Cognitive Machine Intelligence: Applications, Challenges, and Related Technologies (Intelligent Data-Driven Systems and Artificial Intelligence)

✍ Scribed by Inam Ullah Khan (editor), Salma El Hajjami (editor), Mariya Ouaissa (editor), Salwa Belaqziz (editor), Tarandeep Kaur Bhatia (editor)

• Publisher: CRC Press
• Year: 2024
• Tongue: English
• Leaves: 373
• Edition: 1
• Category: Library

✦ Synopsis

Cognitive Machine Intelligence: Applications, Challenges, and Related Technologies offers a compelling exploration of the transformative landscape shaped by the convergence of machine intelligence, artificial intelligence, and cognitive computing. In this book, the authors navigate through the intricate realms of technology, unveiling the profound impact of cognitive machine intelligence on diverse fields such as communication, healthcare, cybersecurity, and smart city development. The chapters present study on robots and drones to the integration of machine learning with wireless communication networks, IoT, quantum computing, and beyond. The book explores the essential role of machine learning in healthcare, security, and manufacturing. With a keen focus on privacy, trust, and the improvement of human lifestyles, this book stands as a comprehensive guide to the novel techniques and applications driving the evolution of cognitive machine intelligence. The vision presented here extends to smart cities, where AI-enabled techniques contribute to optimal decision-making, and future computing systems address end-to-end delay issues with a central focus on Quality-of-Service metrics. Cognitive Machine Intelligence is an indispensable resource for researchers, practitioners, and enthusiasts seeking a deep understanding of the dynamic landscape at the intersection of artificial intelligence and cognitive computing.

This book:

• Covers a comprehensive exploration of cognitive machine intelligence and its intersection with emerging technologies such as federated learning, blockchain, and 6G and beyond.
• Discusses the integration of machine learning with various technologies such as wireless communication networks, ad-hoc networks, software-defined networks, quantum computing, and big data.
• Examines the impact of machine learning on various fields such as healthcare, unmanned aerial vehicles, cybersecurity, and neural networks.
• Provides a detailed discussion on the challenges and solutions to future computer networks like end-to-end delay issues, Quality of Service (QoS) metrics, and security.
• Emphasizes the need to ensure privacy and trust while implementing the novel techniques of machine intelligence.

It is primarily written for senior undergraduate and 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 Page
Title Page
Copyright Page
Table of Contents
Editors
List of contributors
Preface
Part I: AI trends and challenges
Chapter 1: AI-based computing applications in future communication
1.1 Introduction
1.2 Artificial Intelligence
1.2.1 Why is artificial intelligence important?
1.3 Artificial and social networks
1.3.1 Network theory
1.3.2 Network analysis
1.4 Scholarly investigation into social network intelligence
1.5 AI as it is portrayed in the media
1.5.1 2013: AlexNet and variational autoencoders
1.5.2 In 2018
1.5.3 Last three year’s review
1.6 Latest developments in AI
1.6.1 Computer vision
1.6.2 Features of computer vision
1.6.3 AI in education
1.6.4 AI-optimized hardware
1.7 Definition of artificial superintelligence (ASI)
1.7.1 The state of artificial intelligence at the moment
1.8 The future of digital communications using AI
1.9 The benefits of AI-powered automation for digital communication
1.9.1 Increased efficiency
1.9.2 Improved accuracy
1.9.3 Enhanced personalization
1.9.4 Increased security
1.10 How does AI impact digital communications?
1.10.1 Artificial Intelligence’s effect on communication
1.11 What’s next for AI in digital communications?
1.11.1 Source
1.11.2 Input transducer
1.11.3 Encoder of source
1.11.4 Encoder of channels
1.12 Prediction for the future of digital communications
1.12.1 In-app messaging becomes dominant
1.12.2 VR adoption: Make or break
1.12.3 The need for human contact and validation
1.13 What will the future of AI look like?
1.14 Few predictions for AI
1.14.1 In 2030
1.14.2 In 2050
1.15 Predictions on future technologies
1.15.1 Robotics
1.15.2 Augmented reality and virtual reality
1.15.3 Nanotech
1.15.4 Space exploration
1.15.5 Superconductors
1.15.6 3D printing
1.15.7 Autonomous vehicle
1.16 Conclusion
References
Chapter 2: Advances of deep learning and related applications
2.1 Introduction
2.2 Deep learning techniques
2.3 Multilayer perceptron
2.4 Convolutional neural network
2.5 Recurrent neural network
2.6 Long-term short-term memory
2.7 GRU
2.8 Autoencoders
2.9 Attention mechanism
2.10 Deep generative models
2.11 Restricted Boltzmann machine
2.12 Deep belief network
2.13 Modern deep learning platforms
2.13.1 PyTorch
2.13.2 TensorFlow
2.13.3 Keras
2.13.4 Caffe (Convolutional architecture for fast feature embedding) and Caffe2
2.13.5 Deeplearning4j
2.13.6 Theano
2.13.7 Microsoft cognitive toolkit (CNTK)
2.14 Challenges of deep learning
2.15 Applications of deep learning
2.16 Conclusion
References
Chapter 3: Machine learning for big data and neural networks
3.1 Introduction
3.2 Machine learning and fundamentals
3.2.1 Supervised learning
3.2.2 Decision trees
3.2.3 Linear regression
3.2.4 Naive Bayes
3.2.5 Logistic regression
3.3 Unsupervised learning
3.3.1 K-Means algorithm
3.3.2 Principal component analysis
3.4 Reinforcement learning
3.5 Machine learning in large-scale data
3.6 Data analysis in big data
3.7 Predictive modelling
3.7.1 Understanding customer behavior and preferences
3.7.2 The role of supply chain and performance management in organizational success
3.7.3 Management of quality and enhancement
3.7.4 Risk mitigation and detection of fraud
3.8 Neural networks
3.8.1 Artificial neural network
3.8.2 RNN
3.8.3 CNN
3.8.4 Deep learning using convolutional neural networks to find building defects
3.9 Data generation and manipulation
3.9.1 Generative Adversarial Networks
3.9.2 Domains of real-world applications
3.9.3 Financial applications
3.9.4 Medical and data science
3.9.5 Internet of Things
3.10 Conclusion
References
Part II: Machine intelligence in network technologies
Chapter 4: Deformation prediction and monitoring using real-time WSN and machine learning algorithms: A review
4.1 Introduction
4.2 Causes of landslides
4.2.1 Climate changes
4.2.2 Earthquake
4.2.3 Deforestation
4.3 Early warning system
4.3.1 Risk Knowledge
4.3.2 Monitoring and warning services
4.3.3 Dissemination and communication
4.3.4 Response capability
4.3.5 Classification of early warning system
4.4 Landslide monitoring techniques
4.4.1 Multi-antenna GPS deformation monitoring systems
4.4.2 Monitoring landslide deformation using InSAR Technique
4.4.3 Electro-Mechanical System (MEMS) tilt sensor
4.4.4 Low-cost vibration sensor network
4.4.5 Extensometer
4.4.6 Rain gauge
4.5 Landside prediction modeling and forecasting using machine learning and statistical analysis
4.6 Conclusion
Acknowledgments
References
Chapter 5: Unmanned aerial vehicle: Integration in healthcare sector for transforming interplay among smart cities
5.1 Introduction
5.1.1 Objectives of the chapter
5.1.2 Significance of study
5.2 UAVs in healthcare: Applications and benefits
5.2.1 Specific applications of UAVs in healthcare sector
5.2.1.1 Transportation
5.2.1.2 Livestock monitoring
5.2.1.3 Disaster relief
5.2.1.4 Public health surveillance and medical research
5.2.2 Benefits of UAVs in healthcare sector
5.3 Communication protocols for UAVs in healthcare
5.3.1 Diverse communication protocols suitable for UAVs in healthcare settings
5.3.2 Addressing challenges and requirements of real-time data transmission
5.4 Deployment strategies and logistics
5.4.1 Different deployment strategies for UAVs in healthcare
5.4.2 Logistical considerations
5.5 Security challenges and solutions
5.5.1 Security challenges associated with UAVs in healthcare
5.5.2 Potential solutions and mitigation strategies
5.5.3 Importance of regulatory compliance and adherence to safety standards
5.6 Regulatory and legal framework
5.6.1 Need for standardized regulations and guidelines to ensure safe and ethical use of UAVs
5.7 Conclusion and future scope
References
Chapter 6: Blockchain technologies using machine learning
6.1 Introduction
6.2 Understanding blockchain technologies
6.2.1 Introduction to blockchain
6.2.2 Key components of a blockchain network
6.2.3 Consensus mechanisms and their impact
6.2.4 Benefits and limitations of BCT
6.2.4.1 Benefits of BCT
6.2.4.2 Limitations of BCT
6.3 ML fundamentals
6.3.1 Overview of ML
6.3.2 Types of ML algorithms
6.3.2.1 Supervised learning algorithms
6.3.2.2 Unsupervised learning algorithms
6.3.2.3 Semi-supervised learning algorithms
6.3.2.4 Reinforcement learning algorithms
6.3.2.5 Deep learning algorithms
6.3.3 Data pre-processing and feature engineering
6.3.3.1 Data pre-processing
6.3.3.2 Feature engineering
6.4 Evaluating ML models
6.4.1 Common evaluation metrics
6.5 Synergies between blockchain and ML
6.5.1 Combining ML models on the blockchain
6.6 Applications of blockchain and ML integration
6.7 Challenges and limitations in BCT and ML integration
6.7.1 Scalability issues
6.7.2 Data availability and quality
6.7.3 Regulatory and legal challenges
6.7.4 Trusted oracles and data feeds
6.7.5 Energy efficiency concerns
6.8 Future prospects and research directions
6.8.1 Federated learning on blockchain networks
6.8.2 Integration of privacy-preserving techniques
6.8.3 AI-driven smart contracts
6.9 Conclusion
References
Chapter 7: Q-learning and deep Q networks for securing IoT networks, challenges, and solution
7.1 Introduction
7.2 Methodology
7.2.1 Proposed algorithm for training DQNs as agents in IoT networks for security
7.2.1.1 The algorithm
7.2.1.2 Program
7.2.1.3 Various security actions
7.2.2 Algorithm for applying security actions using a DQN in IoT network security
7.2.2.1 Program
7.3 Result and conclusion
References
Chapter 8: The application of artificial intelligence and machine learning in network security using a bibliometric study
8.1 Introduction
8.2 Analysis of state-of-art network security AI/ML models
8.2.1 Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection
8.2.2 A novel online incremental and decremental learning algorithm based on variable support vector machine
8.2.3 An effective intrusion detection framework based on SVM with feature augmentation, knowledge-based systems
8.2.4 A novel hybrid KPCA and SVM with GA model for intrusion detection
8.2.5 A novel SVM-KNN-PSO ensemble method for intrusion detection system
8.2.6 SVM-DT-based adaptive and collaborative intrusion detection
8.2.7 Random forest modeling for network intrusion detection system
8.3 Analysis of the state-of-art malware detection AL/ML models
8.3.1 Malware detection classification using machine learning
8.3.2 A review of Android malware detection approaches based on machine learning
8.3.3 A two-layer deep learning method for Android malware detection using network traffic
8.3.4 A lightweight network-based Android malware detection system
8.3.5 Phishing website classification and detection using machine learning
8.3.6 Static and dynamic malware analysis using machine learning
8.4 Research findings in AI/ML-based network security models
8.5 Research findings in AL/ML-based malware detection systems
8.6 Conclusion
References
Chapter 9: Machine learning approaches for intrusion detection: Enhancing cybersecurity and threat mitigation
9.1 Introduction
9.2 Traditional intrusion detection methods
9.3 Machine learning algorithms for intrusion detection
9.4 Related works
9.5 Addressing the research gap: Adaptive intrusion detection
9.6 Challenges of integrating machine learning in IDS
9.7 Feature engineering for intrusion detection
9.8 Enhancing robustness with ensemble learning
9.9 Future research directions
9.10 Conclusion
References
Part III: Cognitive machine intelligence applications
Chapter 10: The rise of AI in the field of healthcare
10.1 Introduction
10.2 2 Types of AI
10.2.1 AI type 1: skill base
10.2.1.1 Weak AI or narrow AI
10.2.1.2 General-purpose AI
10.2.1.3 Super AI
10.2.2 AI Type: function-based
10.2.2.1 Reactive apparatus
10.2.2.2 Memory machines with limited memory
10.2.2.3 Mind theory
10.2.2.4 Confidence
10.3 Features of artificial intelligence
10.3.1 Eliminate monotonous and tedious tasks
10.3.2 Data acquisition
10.3.3 A copy of human cognition
10.3.4 Avoid natural disaster
10.3.5 Chatbots and facial recognition
10.4 Artificial intelligence: unraveling the shade of innovation
10.4.1 Machine learning: the art of adaptation
10.4.2 Neural networks: mirroring the human brain
10.4.3 Deep learning: navigating complexity
10.4.4 Natural language processing
10.4.5 Computer vision: seeing the unseen
10.4.6 Reinforcement learning: learning from experience
10.4.7 Generative adversarial networks: fostering creativity
10.4.8 Explainable AI: illuminating the black box
10.4.9 Ethics and bias in AI: navigating a moral compass
10.4.10 Artificial general intelligence: the quest for human-level AI
10.4.11 Quantum AI: bridging new realities
10.4.12 AI in creativity: collaborating with machines
10.4.13 AI in finance: predicting the economic future
10.4.14 AI and climate change: a greener tomorrow
10.5 Revolutionizing healthcare through technology: a comprehensive overview
10.5.1 Introduction: healthcare in the digital age
10.5.2 AI in diagnostics: enhancing precision and early detection
10.5.3 Personalized medicine: tailoring treatment to individuals
10.5.4 Drug discovery and development: accelerating breakthroughs
10.5.5 Electronic health records and AI: enabling informed decision-making
10.5.6 Telemedicine and virtual health assistants: expanding access to care
10.5.7 Robotics in surgery: advancing precision and minimally invasive procedures
10.5.8 Mental health and AI: revolutionizing approaches
10.5.9 Ethical considerations: balancing progress and privacy
10.5.10 The human touch: AI as a collaborator
10.6 Conclusion
References
Chapter 11: A comprehensive survey of machine learning applications in healthcare
11.1 Introduction
11.2 Machine learning in healthcare
11.2.1 Machine learning algorithms in healthcare
11.2.2 Supervised, unsupervised, and reinforcement learning techniques
11.2.2.1 Supervised learning
11.2.2.1.1 Support vector machines
11.2.2.1.2 Random Forest
11.2.2.1.3 Neural Networks
11.2.2.1.4 K-Nearest neighbours
11.2.2.1.5 Gaussian Naive Bayes
11.2.2.2 Unsupervised learning
11.2.2.3 Reinforcement learning
11.3 Medical imaging and diagnostic applications
11.3.1 Image classification and segmentation
11.3.2 Computer-aided detection and diagnosis
11.3.3 Radiomics and radiogenomics in cancer diagnosis
11.3.4 Neuroimaging for brain disorder diagnosis
11.4 Clinical decision support systems
11.4.1 ML-driven risk prediction models
11.4.2 Decision support for treatment planning
11.4.3 Early warning systems for patient deterioration
11.5 Electronic Health Records analysis
11.5.1 Predictive modelling using EHR data
11.5.2 Natural Language Processing for extracting medical information
11.5.3 Clinical data integration and interoperability
11.6 Disease prediction and prevention
11.6.1 ML-based models for disease risk assessment
11.6.2 Predictive analytics for patient outcomes
11.6.3 Population health management using ML
11.7 Personalised medicine and treatment
11.7.1 Pharmacogenomics and drug response prediction
11.7.2 Precision oncology and targeted therapies
11.7.3 Individualised treatment recommendations
11.8 Drug discovery and development
11.8.1 AI-driven drug screening and design
11.8.2 ML in clinical trials and drug efficacy evaluation
11.8.3 Repurposing existing drugs with ML
11.9 Ethical, legal, and privacy considerations
11.9.1 Ethical challenges in using ML in healthcare
11.9.1.1 Fairness and bias
11.9.1.2 Transparency and explainability
11.9.1.3 Informed consent
11.9.1.4 Data security and privacy
11.9.1.5 Clinical validation
11.9.1.6 AI can assist in making medical decisions
11.9.2 Legal implications and regulatory frameworks
11.9.3 Privacy-preserving ML techniques for healthcare data
11.10 Challenges and future directions
11.10.1 Data quality, quantity, and interoperability
11.10.2 Interpretability and explainability of ML models
11.10.3 Integration of ML algorithms into clinical workflows
11.10.4 Addressing bias and fairness in healthcare AI
11.11 Conclusion
References
Chapter 12: A deep learning approach for the early diagnosis of melanoma cancer: Study and analysis
12.1 Introduction
12.2 Relevant work
12.3 Theoretical framework
12.4 Proposed methodology
12.5 Results
12.5.1 Results of identification of melanoma cancer using dermatoscopy by physicians
12.5.2 Results of identification of melanoma cancer by CNN
12.6 Conclusion
References
Chapter 13: A study and analysis on nowcasting: Forms of precipitation using improvised random forest classifier
13.1 Introduction
13.2 Relevant work
13.3 IRFC model for weather forecasting
13.3.1 Dataset used
13.3.2 Data preprocessing
13.3.3 Training set
13.3.4 Testing set
13.3.5 Proposed model: Random forest
13.3.6 Model evaluation
13.4 Results and discussion
13.5 Conclusion
References
Chapter 14: A study and comparative analysis on prediction of tsunami using convolutional neural network
14.1 Introduction
14.2 Relevant work
14.3 Proposed methodology
14.3.1 Architecture
14.3.2 Dataset description
14.3.3 Data preprocessing
14.3.4 Training dataset
14.3.5 Testing dataset
14.3.6 CNN model
14.3.7 Model evaluation
14.4 Results and discussions
14.4.1 Accuracy
14.4.2 Sensitivity
14.4.3 Specificity
14.4.4 Precision
14.5 Conclusion
References
Chapter 15: Towards smarter Chatbots: Unravelling the capabilities of ChatGPT
15.1 Introduction
15.2 ChatGPT summary compilation
15.2.1 Background of ChatGPT
15.3 Architecture of ChatGPT
15.4 Training ChatGPT
15.4.1 Data sources used in training ChatGPT
15.5 Applications of ChatGPT
15.5.1 Advantages
15.5.2 Disadvantages
15.6 Conclusion
References
Index