Machine Learning for Smart Environments/Cities: An IoT Approach

Preface
About This Book
Contents
About the Editors
1 An Introduction and Systematic Review on Machine Learning for Smart Environments/Cities: An IoT Approach
1.1 Introduction
1.2 Smart Environments, Internet of Things, and Machine Learning Concepts
1.2.1 Smart Environments
1.2.2 Internet of Things
1.2.3 Machine Learning
1.3 Results
1.3.1 Smart Cities
1.3.2 Smart Homes
1.3.3 Smart Buildings
1.3.4 Smart Health
1.3.5 Smart Grids
1.3.6 Smart Transportation
1.3.7 Smart Industries
1.4 Discussion
1.5 Conclusions
References
Part I Smart Environments
2 Model-Based Digital Threads for Socio-Technical Systems
2.1 Introduction
2.2 Digital Thread
2.2.1 Definition
2.2.2 Digital Representations
2.2.3 Digital Twins
2.2.4 Digital Twin Dimensions
2.3 Development Methodology
2.3.1 Model-Driven System Engineering (MBSE)
2.3.2 Models and Data
2.3.3 Life Cycle Support
2.4 Traffic Monitoring System (TMS)
2.5 The TMS Digital Twin Modeling Case
2.5.1 Concept Exploration
2.5.2 Preliminary Design
2.5.3 Remaining Development Phases
2.6 SysML v2 Improvements
2.7 Conclusion
References
3 IoT Regulated Water Quality Prediction Through Machine Learning for Smart Environments
3.1 Introduction
3.2 Literature Review
3.3 Dataset Description
3.4 Methodology
3.5 Results and Discussion
3.6 Conclusion
References
4 The Power of Augmented Reality for Smart Environments: An Explorative Analysis of the Business Process Management
4.1 Introduction
4.1.1 Research Design
4.2 The Historical Evolution of Augmented Reality for Smart Environments
4.3 Augmented Reality and Business Process Management
4.3.1 Smart Environment
4.4 Case Studies from Different Sectors
4.4.1 Methodology
4.4.2 Cases Study Description
4.5 Discussion
4.6 Conclusion
References
5 Internet of Things Applications for Smart Environments
5.1 Introduction
5.1.1 IoT in E-Education
5.2 IoT Technology Benefits on E-Learning
5.2.1 Online Self Learning
5.2.2 Smart Collaboration
5.3 Internet of Things and Smart Homes and E-learning
5.3.1 Smart Homes
5.3.2 Smart Home Service Adoption
5.3.3 Critical Factors for Smart Home Service
5.4 Conclusion
References
6 Exploring Interpretable Machine Learning Methods and Biomarkers to Classifying Occupational Stress of the Health Workers
6.1 Introduction
6.2 Biomarkers and Machine Learning Models
6.3 Healthcare Internet of Things
6.3.1 Heart Activity, Skin Response, and Temperature
6.4 Biomarker Occupational Stress Classifier Model
6.5 Explainable Artificial Intelligence
6.5.1 Explainability and Interpretability
6.5.2 Explainable Recommendation
6.6 Data Security and Privacy
6.7 Conclusion
References
Part II Smart Cities
7 Smart Cities, The Internet of Things, and Corporate Social Responsibility
7.1 Introduction
7.2 Smart Cities, Business and CSR
7.3 IoT’s—The Benefits
7.3.1 IoT’s: Waste, Water Supply and Air Pollution
7.3.2 IoT’s: Urban Transportation and Electricity Supply
7.3.3 IoT’s: Societal Health and Well-Being
7.4 IoT’s: Challenges, Problems, Issues, and Impacts
7.4.1 IoT’s: Communication and Data Transmission
7.4.2 IoT’s: Data Security and Privacy
7.4.3 IoT’s: Quality of Service (QoS)
7.4.4 IoT’s: Social Challenges
7.5 Addressing ICT and IoT Problems, Issues and Challenges—A CSR Approach
7.6 Discussion
7.7 Conclusion
References
8 Intelligent Techniques for Optimization, Modelling and Control of Power Management Systems Efficiency
8.1 Introduction
8.2 History of the Electric Systems
8.3 Generation and Transport of Electricity
8.4 Smart Grid
8.5 Power Electronics in Smart Grid
8.6 Hard-Switching and Soft-Switching
8.7 Artificial Intelligence in Power Electronics
8.7.1 Model Approach
8.7.2 Dataset
8.7.3 Methods
8.7.4 Experiments Description
8.8 Results
8.9 Conclusion
References
9 Intelligent Simulation and Emulation Platform for Energy Management in Buildings and Microgrids
9.1 Introduction
9.2 The Role of Machine Learning in IoT
9.3 MARTINE—Multi-agent Based Real-Time Infrastructure for Energy
9.3.1 Cyber-Physical Infrastructure
9.3.2 Knowledge Layer
9.4 Illustrative Case
9.4.1 Load Forecasting
9.4.2 Load Consumption Emulation
9.5 Conclusions
References
10 Machine Learning Applications and Security Analysis in Smart Cities
10.1 Introduction
10.2 Smart Cities
10.2.1 Smart City Technologies
10.2.2 Features of Smart Cities
10.2.3 Why Do We Need Smart Cities?
10.2.4 Smart City Examples
10.3 Machine Learning Applications in Smart Cities
10.3.1 Smart Waste
10.3.2 Continuous Learning
10.3.3 Asphalt Condition Monitoring
10.3.4 Air Pollution Forecast
10.3.5 Vehicle Routing in Smart Cities
10.3.6 Effective Transportation Planning
10.3.7 Forecasting of Air Quality
10.3.8 License Plate Recognition System in Smart Transportation
10.3.9 Tourism Developing
10.3.10 Intelligent Parking System
10.3.11 Density Monitoring Systems
10.3.12 Smart Stall Systems
10.3.13 Barrier-Free Smart Transportation
10.3.14 Smart Real Estate Management in Smart Cities
10.3.15 Smart Hotel
10.4 Discussion
10.5 Conclusion
References
11 Recent Developments of Deep Learning in Future Smart Cities: A Review
11.1 Introduction
11.2 Development of Deep Learning Research in Smart Cities
11.3 Future Direction of Deep Learning Research in Smart Cities
11.4 Conclusion
References
12 Smart and Sustainable Cities in Collaboration with IoT: The Singapore Success Case
12.1 Introduction
12.2 Background Related to Smart Cities in Perspective of IoT Collaboration
12.2.1 A Look at Devices
12.3 Methodology for Classifying a City as an SSC
12.4 Results and Discussion of the Evaluation of Singapore as a Success Case
12.4.1 Governance (Electronic Headquarters, Transparency, Interactive Street Map, Communication with Citizens)
12.4.2 Mobility (Sustainable Urban Mobility Plans, Multimodal Integration of Public Transport, Deployment of Alternative Means, ICT in Traffic Control)
12.4.3 Sustainability
12.4.4 Economic Development
12.4.5 Intellectual Capital
12.4.6 Quality of Life (Health and Sanitation, Universal Access, Deployment of Several ICT Measures for the Enjoyment of the City)
12.5 Discussion
12.6 Conclusion
References