Computational Intelligence in Sustainable Computing and Optimization

Trends and Applications

1st Edition - October 8, 2024
Imprint: Morgan Kaufmann
Editors: Balamurugan Balusamy, Vinayakumar Ravi, Rajesh Kumar Dhanaraj, Sudha Senthilkumar, Brindha K
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 3 7 2 4 - 9
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 3 7 2 5 - 6

Computational Intelligence in Sustainable Computing and Optimization: Trends and Applications focuses on developing and evolving advanced computational intelligence algori… Read more

Purchase options

BLOOM INTO SPRING SAVINGS

Save up to 25% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Computational Intelligence in Sustainable Computing and Optimization: Trends and Applications focuses on developing and evolving advanced computational intelligence algorithms for the analysis of data involved in applications, such as agriculture, biomedical systems, bioinformatics, business intelligence, economics, disaster management, e-learning, education management, financial management, and environmental policies. The book presents research in sustainable computing and optimization, combining methods from engineering, mathematics, artificial intelligence, and computer science to optimize environmental resources

Computational intelligence in the field of sustainable computing combines computer science and engineering in applications ranging from Internet of Things (IoT), information security systems, smart storage, cloud computing, intelligent transport management, cognitive and bio-inspired computing, and management science. In addition, data intelligence techniques play a critical role in sustainable computing. Recent advances in data management, data modeling, data analysis, and artificial intelligence are finding applications in energy networks and thus making our environment more sustainable.

Title of Book
Cover image
Title page
Table of Contents
Copyright
Contributors
Chapter 1. Journey of computational intelligence in sustainable computing and optimization techniques: An introduction
1 Introduction to computational intelligence
2 Goals of computational intelligence
2.1 Fuzzy logic sets
2.1.1 Evolution of fuzzy logic
2.1.2 Understanding the concept of fuzzy logic
2.2 Fuzzy logic set and decision trees
2.2.1 Fuzzy control
2.2.2 Merits of fuzzy logic system
2.2.3 Demerits of fuzzy logic systems
2.2.4 Application of fuzzy logic control system
2.3 Fuzzy semantics in artificial intelligence
2.3.1 Examples of fuzzy logic
2.4 Applications of fuzzy logic and fuzzy semantics
2.5 Advantages of fuzzy semantic and fuzzy logic systems
2.6 Disadvantages of fuzzy semantic and fuzzy logic systems
2.7 AI in immunology—machine learning algorithms for immunological data analysis
3 Artificial neural networks
3.1 Structure of artificial neural network
3.1.1 Merits of artificial intelligence neural network
3.1.2 Demerits of artificial intelligence neural network
3.2 Working principle of artificial intelligence neural networks
3.2.1 Types of artificial intelligence neural networks
3.2.2 Uses of artificial intelligence neural networks
3.3 Advantages and disadvantages of artificial neural network
3.4 Neural network architecture types
3.4.1 Perceptron model
3.4.2 Radial basis function
3.4.3 Multilayer perceptron
3.4.4 Recurrent
3.4.5 Long short-term memory neural network
3.4.6 Hopfield network
3.4.7 Boltzmann machine neural network
3.4.8 Convolutional neural network
3.4.9 Modular neural network
3.4.10 Physical neural network
3.5 Applications of neural networks
3.5.1 Facial recognition
3.5.2 Stock market prediction
3.5.3 Social media
3.5.4 Aerospace
3.5.5 Defense
3.5.6 Healthcare
3.5.7 Signature verification and handwriting analysis
3.5.8 Weather forecasting
4 Evolutionary intelligence computing
4.1 Evolutionary computational intelligence algorithms
4.1.1 Evolutionary computational intelligence algorithms and biological-based neural network
4.2 Working principle of evolutionary computation
4.2.1 Evolutionary algorithms function
4.3 Types of evolutionary algorithms
4.3.1 Genetic algorithms
4.3.2 Genetic programming
4.3.3 Evolutionary programming
4.3.4 Evolutionary strategies
4.4 Real-time applications of evolutionary algorithms
5 Swarm intelligence and unit swarm mathematical optimization
5.1 Principles of swarm intelligence
5.1.1 Applications of swarm intelligence
5.1.2 Particle or element swarm optimization
5.2 Uses of swarm intelligence
5.3 Clustering behavior of ants
5.4 Nest building behavior of wasps and termites
5.5 Flocking and schooling in birds and fish
5.6 Ant colony optimization
5.7 Particle swarm optimization
5.8 Swarm-based network management
5.9 Cooperative behavior in swarms of robots
6 Artificial intelligence immune system
6.1 History of artificial intelligence immune systems
6.1.1 Applications of artificial intelligence immune system
6.2 Significance of artificial immune systems
6.3 Advantages and disadvantages of the artificial immune system
6.4 Survey on artificial intelligence immune system
6.5 Techniques involved in artificial immune system
6.5.1 Clonal selection algorithm
6.5.2 Negative selection algorithm
6.5.3 Immune network algorithms
6.5.4 Dendritic cell algorithms
7 Foundations of sustainable computing
7.1 Green computing
7.1.1 Important of green computing
7.2 History of green computing
7.3 Applications of green computing
7.4 Advantages and challenges of green computing
7.4.1 Advantages
7.5 Challenges
7.6 Origins and motivations of computational sustainable
7.7 Biodiversity and conservation of computational sustainable
7.8 Sustainable artificial intelligence
7.9 Current and future use cases of sustainable AI
7.10 Optimization techniques
7.10.1 Optimization techniques application
7.11 Optimizing software
7.12 Intelligent transportation systems
7.13 Electrical grid
7.14 Power management
7.15 Material recycling
7.16 Cloud, edge, and parallel computing
7.17 Telecommuting
7.18 Real-life applications of optimization
7.18.1 Benefits of optimization
8 Computational learning theory
8.1 Importance of computational learning theory
8.2 Computational learning theory in machine learning
9 Probabilistic models
9.1 Categories of probabilistic models
9.1.1 Generative models
9.1.2 Discriminative models
9.1.3 Graphical models
9.2 Importance of probabilistic models
9.3 Advantages of probabilistic models
9.4 Disadvantages of probabilistic models
Chapter 2. Designing computational intelligence techniques based smart framework for sustainable computing
1 Introduction
2 The prospects of high-tech smart cities
3 IoT and information amassment
4 AI and data analysis
5 Blockchain solutions
6 Concrete applications of smart cities
6.1 Challenges of establishing smart cities
6.2 The potential of blockchain-enabled smart cities
7 The road ahead for smart cities
7.1 Free and available urban technology
7.2 Blockchain technology to facilitate ongoing evolution
7.3 Blockchain to organize urban chaos
7.4 Blockchain's potential to improve urban life
7.5 Personal belongings in the information age
8 Smart city peer-to-peer system
8.1 Blockchain city planning: A tactic for the future
8.2 Blockchain, IoT, and AI together to make cities smarter and greener
9 AI, IOT, blockchain-based cities uses cases
9.1 AI, IoT with blockchain-controlled smart lock
10 Conclusion
Chapter 3. Multiple parameter optimization methods based on computational intelligence techniques in context of sustainable computing
1 Introduction
1.1 Machine learning formulated as optimization
2 Multiple parameter optimization methods
2.1 Genetic algorithm
2.1.1 Main components of genetic algorithm
3 Particle swarm optimization
4 Conclusion
Chapter 4. IoT-based vulnerability assessment for sustainable computing: Threats, current solutions, and open challenges
1 Introduction
2 Proposed techniques
2.1 Stage-1: Chest X-ray analysis
2.2 Stage-2: Diagnosis engine
2.3 Training the neural network
2.4 Working of IoT spirometer
2.4.1 Analyzing the sample
3 Experimental analysis of proposed method and traditional method
3.1 Performance evaluation of the proposed system
3.2 Different detection mechanisms
4 Conclusion and future work
Chapter 5. Amalgamation of optimization techniques in big data analytics through granular computing: A roadmap to smart industry framework
1 Introduction
2 Importance of sustainable computing in big data analytics
2.1 Environmental and ethical considerations
2.2 Integration of optimization techniques and granular computing
3 Applications and case studies
4 Green data centers
4.1 Real-world scenario showing the effectiveness of the integration
5 Potential future developments in computational intelligence
6 Ethical and social implications of these technologies
6.1 Directions for future research in sustainable computing and smart industries
7 Conclusion
Chapter 6. Computational intelligence for data analysis in pattern recognition and biomedical fields
1 Introduction
1.1 Machine learning algorithms
1.2 Deep learning
1.3 Image processing techniques
1.4 Signal processing
1.5 Natural language processing (NLP)
1.6 Genomic and sequencing data analysis
1.7 Pattern matching and classification
1.8 Time series analysis
1.9 Data mining and feature selection
1.10 Ensemble learning
1.11 Anomaly detection
2 GAIT-based pattern recognition in biomedical field
2.1 Gait recognition and its applications in the medical field
2.2 Pattern recognition is exceptionally helpful in abnormal gait recognition in the biomedical field for several key reasons
2.3 Hidden Markov model and deep neural network based model
2.4 LSTM-CNN based model
2.5 RNN-LSTM based model
2.6 RNN-based autoencoder model
2.7 Gait-structural graph convolutional network (AGS-GCN) based model
2.8 Sparse representation classifier based model
2.9 DNN based model
2.10 RNN based model
2.11 Combination of CNN, LSTM, SVM and KNN based model
2.12 CNN based model
3 Gait-based recognition for Parkinson's disease
3.1 PCA and LDA based model
3.2 CNN based model
3.3 RNN-LSTM based model
3.4 LSTM-DNN based model
3.5 SVM-ANN based model
3.6 Different machine learning based techniques
3.7 Different machine learning and ANN based techniques
4 Gait-based recognition for cerebral palsy
4.1 CNN based model
4.2 Different machine learning based techniques
4.3 Few deep learning (FCN, LSTM, CNN and transformer) based model
5 Conclusion
Chapter 7. A block chain and artificial intelligence–enabled smart IoT framework for the development of sustainable city
1 Introduction
1.1 Peer-to-peer energy trading system
1.2 DITrust chain based on IoHT
1.3 Cognitive edge architecture for shared economic service
1.4 Vulnerabilities sustainability of secure edge computing
1.5 RON-enhanced blockchain propagation system
1.6 Learning via actions in a smart city context
Observation-based security system
1.7 New smart city development for minimal carbon emissions and environmental sustainability
The development of a smart city building model
1.8 Ideal IoT resource management
1.9 Applications of artificial intelligence and machine learning in smart cities
Applications of DRL-based UAVs in B5G and 5G connectivity
Smart city health care and machine learning
2 Conclusion
Chapter 8. Computational intelligence–based heuristic approach for maximizing energy efficiency in sustainable transportation and mobility
1 Introduction
2 Literature review
2.1 Recent trends in sustainable transportation and mobility
2.2 Computational intelligence in sustainable transportation
2.3 Electrification and sustainable transportation
2.4 Future directions in sustainable transportation
2.5 Eco-friendly mobility services
2.6 Intelligent traffic management
2.7 Electric vehicle routing and energy optimization
2.8 Urban freight transportation and computational intelligence
3 Proposed framework: Computational intelligence for energy efficiency in transportation
3.1 Computational intelligence: A multifaceted paradigm
3.2 Relevance to energy efficiency in transportation
3.3 Synergy between computational intelligence and sustainable transportation
3.4 Maximizing energy efficiency in sustainable transportation using computational intelligence
4 Result analysis
4.1 Energy consumption
4.2 Emissions (CO2)
4.3 Travel time
Chapter 9. Computational intelligence for sustainable computing in health care informatics
1 Introduction
2 Privacy-preserving federated learning
3 Predictive healthcare models
3.1 Enhancing data quality in EHRs
3.2 Energy-efficient healthcare infrastructure
3.3 Sustainable mental health monitoring
4 Sustainable laboratory practices
5 Working on disease risk prediction using machine learning algorithms
5.1 Algorithm 1: Mathematical model for disease risk prediction
6 Results
7 Conclusion
Chapter 10. Computational intelligence for sustainable computing in traditional medical system Ayurveda
1 Introduction
2 Background
2.1 Computational intelligence (CI)
2.2 Sustainable development
2.3 Sustainable computing
2.4 Ayurveda
3 Computational intelligence applications in the healthcare domain
4 Ayurveda-based sustainable development initiatives in India
5 Computational intelligence in Ayurveda
5.1 Prakriti Identification
5.2 Diet recommendation system
5.3 Pulse diagnosis
5.4 Medicinal plant identification
6 Challenges
7 Conclusion
Chapter 11. Computational intelligence approach for anomaly detection and prediction in health care information
1 Introduction
2 Motivation
3 Machine learning
3.1 Supervised machine learning
3.2 Unsupervised learning
3.3 Semi-supervised learning
3.4 Reinforcement learning
4 Deep learning
4.1 Artificial neural network (ANN)
4.2 Convolutional neural network (CNN)
4.3 Recurrent neural networks (RNN)
5 Anomaly detection
5.1 Types of anomaly
6 Anomaly detection methods
6.1 Statistical methods
6.2 Machine learning-based methods
6.3 Time-series analysis
6.4 Clustering-based methods
6.5 Deep learning-based methods
6.6 Ensemble methods
7 Output of anomaly detection
8 Machine learning for anomaly detection
9 Machine learning algorithms for anomaly detection
9.1 Isolation forest
9.2 Random forests
9.3 One-class support vector machines (SVM)
9.4 Support vector data description (SVDD)
9.5 Autoencoders
9.6 Local outlier factor (LOF)
9.7 Gaussian mixture models
10 Anomaly detection in health care information
11 Detection of anomalies in different diseases
11.1 Cancer
11.2 Diabetes
11.3 Lung disease
12 Comparison of popular anomaly detection algorithms
13 Conclusion
Chapter 12. Artificial intelligence–based computational intelligence solutions for robotic automation
1 Introduction
2 Role of AI in robotic automation
3 The integration of CI techniques
4 AI-based CI solutions
4.1 Finance
4.2 Energy
4.3 Education
4.4 Customer service
4.5 Cyber security
5 Challenges and future directions
6 Conclusion
Chapter 13. Developing green computing awareness based on optimization techniques for environmental sustainability
1 Introduction
1.1 Cloud computing
1.2 Green cloud computing
1.2.1 Green cloud computing features
1.2.2 Green cloud computing advantages
1.2.3 Green cloud computing limits
1.3 Cloud computing and virtualization
1.4 Green algorithms
1.5 Optimization techniques
2 Virtual machine placement
2.1 Need for VMP
2.2 Literature review
2.2.1 ACO based VMP
2.2.2 Other optimization
2.2.3 PSO
2.2.4 Hybrid ACO algorithm (HACOS)
3 Virtual machine migration
3.1 Important issues with VM migration
3.2 ACO based VMM
3.2.1 AIVMM algorithm
3.2.2 AIVMM results
4 Green cloud for sustainable development
4.1 Green cloud attributes
4.2 RUAEE algorithm
5 Green scheduling algorithm in cloud computing data centers
5.1 DVFS
5.2 CACO
5.3 Honeynet
5.3.1 Calculation of energy consumption
5.4 EEDPFSP
6 Green data center optimization
6.1 ABC based energy saving
6.2 Server virtualization
7 Conclusion
Chapter 14. Bio-inspired meta-heuristic algorithm for solving engineering optimization problems based on computational intelligence
1 Introduction to computational intelligence and engineering optimization
1.1 Computational intelligence
1.2 Bio-inspired algorithms in engineering optimization
2 Bio-inspired approaches for solving optimization problems
3 Application of metaheuristic algorithms in engineering optimization
3.1 Structural design and engineering
3.2 Scheduling and time management
3.3 Energy systems and resource allocation
3.4 Mechanical design and product development
3.5 Network design and routing
3.6 Manufacturing and process optimization
3.7 Aircraft and aerospace design
3.8 Environmental engineering
3.9 Data mining and decision support
3.10 Robotics and automation
4 Evolutionary algorithms: Mimicking natural selection for optimization
5 Swarm intelligence: Harnessing collective behavior for problem solving
5.1 Ant colony optimization (ACO)
5.1.1 Working of ACO algorithm
5.2 Particle swarm optimization
5.2.1 Algorithm
5.3 Bee colony optimization (BCO)
5.4 Firefly algorithm
5.5 Cuckoo search algorithm
6 Genetic algorithms: Evolutionary principles for problem solving
6.1 Initialization
6.2 Fitness evaluation
6.3 Selection
6.4 Crossover
6.5 Mutation
6.6 Replacement and termination
7 Differential evolution: Efficient optimization through mutation and recombination
7.1 Mutation in differential evolution
7.2 Crossover
7.3 Selection
7.4 Population update
8 Harmony search: Finding optimal solutions through musical harmony
9 Hybrid metaheuristic algorithms: Combining multiple approaches for improved performance
9.1 Combining strategies
9.2 Advantage of hybridization
10 Case studies of bio-inspired metaheuristic algorithms
10.1 Optimizing structural design with bio-inspired algorithms
10.2 Enhancing energy systems efficiency
10.3 Revolutionizing data mining with ant colony optimization
10.4 Solving complex scheduling tasks with swarm intelligence
11 Challenges and future directions in engineering optimization with computational intelligence
12 Conclusion: Harnessing the power of bio-inspired metaheuristic algorithms for engineering optimization
Chapter 15. Secure sharing of health records stored in cloud using cryptographic secret sharing schemes through computational intelligence: A review
1 Introduction
1.1 Cryptographic secret sharing schemes
1.1.1 Shamir secret sharing (SSS)
1.1.2 Blakely's secret sharing (BSS)
1.1.3 Verifiable secret sharing (VSS)
1.1.4 Quantum secret sharing (QSS)
1.1.5 Visual cryptography
1.1.6 Homomorphic secret sharing (HSS)
1.1.7 Attribute based secret sharing (ABSS)
1.1.8 Ramp secret sharing (RSS)
1.1.9 Dynamic secret sharing (DSS)
1.2 Computational intelligence
1.3 Cryptographic secret sharing schemes with computational intelligence
2 Literature review
3 Comparative analysis
4 Computational intelligence and secure sharing
4.1 Computational intelligence techniques
4.1.1 Fuzzy logic
4.1.2 Neural networks
4.1.3 Evolutionary computing algorithms
4.1.4 Swarm intelligence
4.1.5 Artificial immune system
4.2 Enhancing EHRs security with computational intelligence
5 Conclusion
Chapter 16. Private blockchain-based encryption framework using Computational Intelligence approach
1 Introduction
2 Technologies of blockchain
2.1 Block structure
2.2 Algorithm of consensus
2.3 Types of blockchain networks
2.3.1 Coin: Ethereum
3 Privacy regulations
3.1 Blockchain and privacy
3.1.1 Decentralized identity
4 Cryptography related technologies
4.1 Hash function
4.2 Encryption on asymmetric
5 Benefits of cryptography in blockchain
6 Limitations of cryptography in blockchain
7 Artificial Intelligence
8 Computational Intelligence
8.1 Artificial Intelligence vs. Computational Intelligence
9 Interlinking of the blockchain technology and CI
9.1 Advantages of combining CI with blockchain
9.2 Challenges to the adoption of CI based blockchain solutions
9.3 Trends for blockchain and CI combo
10 A futuristic approach
11 Conclusion
Index

Balamurugan Balusamy

Dr. Balamurugan Balusamy is currently working as an Associate Dean Student in Shiv Nadar Institution of Eminence, Delhi-NCR. He is part of the Top 2% Scientists Worldwide 2023 by Stanford University in the area of Data Science/AI/ML. He is also an Adjunct Professor, Department of Computer Science and Information Engineering, Taylor University, Malaysia. His contributions focus on engineering education, block chain, and data sciences.

Affiliations and expertise

Shiv Nadar University, Delhi-NCR, India

Vinayakumar Ravi

Dr. Vinayakumar Ravi is an Assistant Research Professor at the Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, Saudi Arabia. Dr. Ravi has been a Postdoctoral Research Fellow developing and implementing novel computational and machine learning algorithms and applications for big data integration and data mining with Cincinnati Children's Hospital Medical Center, Cincinnati, USA. He received his Ph.D. in Computer Science from Amrita School of Engineering, Coimbatore, India. His current research interests include applications of data mining, Artificial Intelligence, machine learning and, deep learning for biomedical informatics, cyber security, image processing, and natural language processing. Dr. Ravi is editor of Efficient Data Handling for Massive Internet of Medical Things: Healthcare Data Analytics, Springer. Dr. Ravi is an editorial board member for Journal of the Institute of Electronics and Computer (JIEC), International Journal of Digital Crime and Forensics (IJDCF), and he has organized a shared task force on detecting malicious domain names (DMD 2018) as part of SSCC'18 and ICACCI'18.

Affiliations and expertise

Assistant Research Professor, Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, Saudi Arabia

Rajesh Kumar Dhanaraj

Dr. Rajesh Kumar Dhanaraj is a professor at the Symbiosis International (Deemed University) in Pune, India. His research and publication interests include cyber-physical systems, wireless sensor networks, and cloud computing. He is a senior member of the Institute of Electrical and Electronics Engineers (IEEE), a member of the Computer Science Teacher Association (CSTA) and member of the International Association of Engineers (IAENG). He is an expert advisory panel member of Texas Instruments Inc. (USA), and an associate editor of International Journal of Pervasive Computing and Communications (Emerald Publishing).

Affiliations and expertise

Professor, Symbiosis International (Deemed University), Pune, India

Sudha Senthilkumar

Dr. Sudha Senthilkumar is an Associate Professor in the School of Computer Science and Engineering at Vellore Institute of Technology. She received her PhD degree in the School of Information Technology and Engineering from VIT University, Vellore. Her current research interests include cryptography, network security, Big Data, Blockchain technologies, machine learning, deep learning, and remote user authentication using smart cards.

Affiliations and expertise

Associate Professor, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamilnadu, India

Brindha K

Dr. Brindha K is an Associate Professor in the School of Information Technology and Engineering at Vellore Institute of Technology. She received her Ph.D. from VIT, ME in Computer Science and Engineering from Sathyabama University. She has received the active researcher award from VIT for the past twelve years, and is one of the reviewers in the JVLC Elsevier Journal. She is a life member of the Computer Society of India. Her research interests include deep learning, machine learning, cryptography, network security, Cloud computing, and blockchain.

Affiliations and expertise

Associate Professor, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamilnadu, India

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Computational Intelligence in Sustainable Computing and Optimization

Trends and Applications

Purchase options

BLOOM INTO SPRING SAVINGS

Institutional subscription on ScienceDirect

Balamurugan Balusamy

Vinayakumar Ravi

Rajesh Kumar Dhanaraj

Sudha Senthilkumar

Brindha K

Related books