Computational Intelligence Techniques for Green Smart Cities (Green Energy and Technology)

✍ Scribed by Mohamed Lahby (editor), Ala Al-Fuqaha (editor), Yassine Maleh (editor)

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 418
• Category: Library

✦ Synopsis

This book contains high-quality and original research on computational intelligence for green smart cities research. In recent years, the use of smart city technology has rapidly increased through the successful development and deployment of Internet of Things (IoT) architectures. The citizens' quality of life has been improved in several sensitive areas of the city, such as transportation, buildings, health care, education, environment, and security, thanks to these technological advances

Computational intelligence techniques and algorithms enable a computational analysis of enormous data sets to reveal patterns that recur. This information is used to inform and improve decision-making at the municipal level to build smart computational intelligence techniques and sustainable cities for their citizens. Machine intelligence allows us to identify trends (patterns). The smart city could better integrate its transportation network, for example. By offering a better public transportation network adapted to the demand, we could reduce personal vehicles and energy consumption. A smart city could use models to predict the consequences of a change, such as pedestrianizing a street or adding a bike lane. A city can even create a 3D digital twin to test hypothetical projects.

This book comprises many state-of-the-art contributions from scientists and practitioners working in machine intelligence and green smart cities. It aspires to provide a relevant reference for students, researchers, engineers, and professionals working in this area or those interested in grasping its diverse facets and exploring the latest advances in machine intelligence for green and sustainable smart city applications.

✦ Table of Contents

Preface
Contents
About the Editors
State of the Art
Machine Learning Techniques for Renewable Energy Forecasting: A Comprehensive Review
1 Introduction
2 Background of Forecasting Methods
2.1 Persistence Models
2.2 Physical Models
2.3 Statistical Models
2.4 Artificial Intelligence (AI) Models
3 Research Methodology
3.1 Mapping Questions
3.2 Search Strings
3.3 Selection of Papers
3.4 Data Extraction
3.5 Analysis and Classification
4 Results and Discussion
4.1 Overview of the Selected Studies
4.2 RQ1: In Which Years, Sources, and Publication Channels Papers Were Published?
4.3 RQ2: Which Research Types Are Adopted in Selected Papers?
4.4 RQ3: Which Contexts Are Targeted in Selected Papers?
4.5 RQ4: What Kinds of Renewable Energy Are Targeted in Selected Papers?
4.6 RQ5: Which Domain Fields Are Targeted in Selected Papers?
4.7 RQ6: Which Forecasting Task Research Was Used in the Selected Papers?
4.8 RQ7: Which Forecasting Period Was Considered in the Selected Papers?
4.9 RQ8: Which Machine Learning Models, Data Mining Tasks and Techniques are Used to Deal with Renewable Energy Forecasting?
5 Implications for Researchers
5.1 RQ1
5.2 RQ2
5.3 RQ3
5.4 RQ4
5.5 RQ5
5.6 RQ6
5.7 RQ7
5.8 RQ8
6 Conclusion
References
Machine Learning for Green Smart Homes
1 Introduction
1.1 A Little History
1.2 Where Are We Today?
2 Smart Green Homes
3 Home Energy Management
4 Big Data
5 Machine Learning Application to Residential Data
5.1 Machine Learning Algorithms
6 Energy Modelling
7 Use Cases
7.1 CENTS
7.2 BIM4EEB/BIMcpd
7.3 H2020: InterConnect
7.4 Retrokit
8 Conclusion
References
Artificial Intelligence Based Smart Waste Management—A Systematic Review
1 Introduction
2 Background
3 Methodology
3.1 Identification of Literature
3.2 Screening
3.3 Quality Assessment
4 Result and Discussion
4.1 Research Trend
4.2 Addressing RQ1
4.3 Addressing RQ2
4.4 Addressing RQ3
5 Contribution
6 Conclusion
References
Machine Learning and Green Transportation
Traffic Sign Detection for Green Smart Public Transportation Vehicles Based on Light Neural Network Model
1 Introduction
2 Related Works
3 Proposed Approach
4 Experiments and Results
5 Conclusions
References
Green Transportation Balanced Scorecard Model: A Fuzzy-Delphi Approach During COVID-19
1 Introduction
2 Conceptual and Theoretical Framework
2.1 Supply Chains and Green Supply Chain Management
2.2 Green Transport and Green Transport Indicators
3 Research Methodology
3.1 The Balanced Scorecard Model BSC
3.2 Fuzzy-Delphi Method
4 Results and Discussion
4.1 Proposed Green Transportation Indicators
4.2 Selected Green Transportation Model With a Balanced Scorecard Approach
4.3 Discussion of the Criteria Adopted
5 Conclusion
1. References
Green Smart City Intelligent and Cyber-Security-Based IoT Transportation Solutions for Combating the Pandemic COVID-19
1 Introduction
2 Supervising IoT Transportation Platform for Combating Pandemic COVID-19
3 Methodology
3.1 Encryption Algorithms
3.2 CoAP Protocol
3.3 IoT Network Topologies
4 Related Works
5 The Proposed Approach
6 Discussion and Results
7 Conclusion
References
Machine Learning and Green Health
Deep Learning-Based Convolutional Neural Network with Cuckoo Search Optimization for MRI Brain Tumour Segmentation
1 Introduction
1.1 Magnetic Resonance Imaging (MRI)
2 Literature Review
3 System Design
4 Result and Discussion
5 Conclusion
References
Role of Deep Learning for Smart Health Care
1 Introduction
2 Working Principle of Deep Learning for Health Care
3 Deep Learning for Health Care in Practice
3.1 Deep Learning in Medical Imaging
3.2 Machine Learning for Textual Data in Health Care
3.3 Smart Internet of Medical Thing (IoMT) Devices
3.4 Privacy Preserving Health Care Data Analytics Techniques
3.5 Open Issues
3.6 The Need and Requirements for Deep Learning in Health Care Systems
3.7 Summary
References
The Solution of Computer Vision for Combating Covid-19
1 Object Detection and Object Counting
1.1 Introduction
1.2 Method
1.3 Proposal to Improvement
2 Mask Face Recognition
2.1 Introduction
2.2 Related Work
2.3 System Overview
2.4 Proposal to Improvement
3 Control Wearing Masks and Social Distance
3.1 Detect and Track People Movement
3.2 Estimate Distance
4 Conclusion
References
Machine Learning for Green Smart Health Toward Improving Cancer Data Feature Awareness
1 Introduction
2 The Findings from the Medical Literature
3 Approach
4 Experimental Results
4.1 Experimental Results
4.2 Modeling the Classification Techniques
4.3 Missing Values
4.4 Experimental Feature Selection
4.5 Relevancy of STD Features with Cervical Cancer
4.6 Relevancy of HIV and AIDS Features with Cervical Cancer
4.7 Relevancy of HPV Features with Cervical Cancer
4.8 Relevancy of Smoking Features with Cervical Cancer
4.9 Justification of the Feature Relevancy by the Average Error of Root Mean Squared Error and Mean Absolute Error)
4.10 Justification of the Feature Selection Accuracy by True Positive (TP) and False Positive (FP) Error
4.11 Classification Algorithm Performance for Cervical Cancer Data
5 Conclusion
References
Machine Learning and Green Environment
Solar Radiation Forecasting for Smart Building Applications
1 Introduction
2 Solar Radiation Forecasting Overview
2.1 Solar Energy Forecasting Methods Categories
2.2 Time Series-based Methods
3 Application of Forecasting Methods to a Mediterranean Site and Comparison
3.1 Presentation of the Meteorological Station
3.2 Performances of Forecasting Models
4 Energy Management Strategies Applied to a Smart Microgrid with Photovoltaic Production and Battery Storage
5 Conclusion
References
Prediction of Air Quality Index Using Machine Learning Techniques and the Study of Its Influence on the Health Hazards at Urban Environment
1 Introduction
1.1 Impact of Air Pollution on Health-Indian Scenario
1.2 Distribution Levels of Toxic Contents
2 Related Works
3 Proposed Work and Methodology
3.1 Data Collection and Exploratory Data Analysis
3.2 Data Pre-processing
3.3 Exploratory Data Analysis
3.4 Model Building
4 Experimental Results
4.1 Experimental Environment
4.2 Performance Analysis
4.3 Experimental Results and Discussion
5 Conclusions
References
Deep Learning for Green Smart Environment
1 Problem
2 Related Works
3 Convolutional Neural Network (CNN)
3.1 Overview
3.2 Compare Convolutional Neural Network (CNN) to Artificial Neural Network (ANN)
3.3 The Basic Architecture of Convolutional Neural Network
3.4 Properties of Convolutional Neural Network
4 NEU-Bin Design
4.1 Transfer Learning
4.2 Residual Network 50 (ResNet50)
4.3 Data Augmentation
4.4 Model
5 Methodology
5.1 Dataset
5.2 Experimental Settings
6 Result
6.1 Experimental Result
6.2 Confusion Matrix
7 Conclusion
References
Machine Learning and Fuzzy Technique for Environmental Time Series Analysis
1 Introduction
2 Related Work
3 Proposed Methodology
3.1 Fuzzy Technique and Membership Function
3.2 Data Processing Model
3.3 Regression Models
3.4 Metrics and Residuals
3.5 Study Sites
3.6 Filling Up Missing Data
3.7 Regression Model
3.8 Classify Model
4 Conclusion
References
Calculation of the Energy of a Two-Circuit Solar System with Thermosiphon Circulation Based on the Internet of Things
1 Introduction
2 Method of Research
3 The Counterpart of the Modular Controller for the Solar Thermal System
4 Conclusion
References
Case Studies and Smart Applications
Smart Human–Computer Interaction Interactive Virtual Control with Color-Marked Fingers for Smart City
1 Introduction
2 Research Review
3 Methodology
3.1 Research Design
3.2 Prototype Design
3.3 Operational Procedures of the Prototype
3.4 How the Algorithm Works
4 Methodology
5 Conclusion
References
Machine Learning for Green Smart Video Surveillance
1 Introduction
2 Computational Complexity of Video Encoders
2.1 The VVC—Data Structures and Coding Tools
3 Methods for Reduction of Computational Complexity in Standard Video Encoders: A Review
3.1 Machine Learning Methods
3.2 Heuristic Methods
3.3 Comparison of Different Approaches for Reduction of the Computational Complexity of VVC
4 Complexity-Aware Omnidirectional Video Coding: Case Study
4.1 Performance Evaluation Study: HEVC Versus VVC
4.2 A Machine Learning Approach for Low-Complexity Coding of Omnidirectional Video
5 Conclusions
References
ArkiCity: Analysing the Object Detection Performance of Cloud-Based Image Processing Services Using Crowdsourced Data
1 Introduction
2 ArkiCity
2.1 A Democratic Approach to Urban Planning
2.2 Technical Architecture
3 Related Work
3.1 Similar Digital Platforms
3.2 Computer Vision as a Service
4 Computational Analysis
4.1 Data Preparation and Labelling
4.2 Experiments Setting
4.3 Results
5 Concluding Remarks
References
Relevance of Green Manufacturing and IoT in Industrial Transformation and Marketing Management
1 Introduction
2 Literature Review
2.1 Introduction [26]
2.2 Growth [26]
2.3 Maturity [26]
2.4 Decline [26]
2.5 Improve Customer Retention [35, 36]
2.6 Complaint Free Customer Service [36]
2.7 Real-time Analytics [36]
2.8 Customized Marketing Promotions [36]
2.9 Adjust Prices according to Demand [36]
3 Research Methodology/Discussion
4 Results
5 Conclusion
References