Artificial Intelligence for Sustainable Development: Theory, Practice and Future Applications

✍ Scribed by Aboul Ella Hassanien, Roheet Bhatnagar, Ashraf Darwish

• Publisher: Springer
• Year: 2020
• Tongue: English
• Leaves: 310
• Series: Studies in Computational Intelligence, 912
• Category: Library

✦ Synopsis

This book highlights the latest advances in the field of artificial intelligence and related technologies, with a special focus on sustainable development and environmentally friendly artificial intelligence applications. Discussing theory, applications and research, it covers all aspects of artificial intelligence in the context of sustainable development. 

✦ Table of Contents

Preface
Contents
Artificial Intelligence in Sustainability Agricultures
Optimization of Drip Irrigation Systems Using Artificial Intelligence Methods for Sustainable Agriculture and Environment
1 Introduction
2 Mathematical Model
3 Algorithm
4 Simulation
5 Conclusion
References
Artificial Intelligent System for Grape Leaf Diseases Classification
1 Introduction
2 Materials and Methods
2.1 K-Means Algorithm for Fragmentation
2.2 Multiclass Support Vector Machine Classifier
3 The Proposed Artificial Intelligent Based Grape Leaf Diseases
3.1 Dataset Characteristic
3.2 Image Processing Phase
3.3 Image Segmentation Phase
3.4 Feature Extraction Phase
3.5 Classification Phase
4 Results and Discussion
5 Conclusions
References
Robust Deep Transfer Models for Fruit and Vegetable Classification: A Step Towards a Sustainable Dietary
1 Introduction
2 Related Works
3 Dataset Characteristics
4 Proposed Methodology
4.1 Data Augmentation Techniques
5 Experimental Results
6 Conclusion and Future Works
References
The Role of Artificial Neuron Networks in Intelligent Agriculture (Case Study: Greenhouse)
1 Introduction
2 Overview of AI
3 Agriculture and Greenhouse
4 Intelligent Control Systems (SISO and MIMO)
4.1 Particular Aspects of Information Technology on Greenhouse Cultivation
4.2 Greenhouse Climate Control Techniques
5 Modern Optimization Techniques
5.1 Genetic Algorithms
5.2 Main Attractions of GAs
5.3 Strong and Weak Points of FL and Neural Networks
6 Fuzzy Identification
7 Conclusion
References
Artificial Intelligence in Smart Health Care
Artificial Intelligence Based Multinational Corporate Model for EHR Interoperability on an E-Health Platform
1 Introduction
2 The Common Goal to Reduce Margin of Error in the HC Sector
3 Defining EPRs, EHRs and Clinical Systems
4 Some Hurdles in an EHR System
5 Overcoming Interoperability Issues
6 Barriers in EHR Interoperability
7 Characteristics and Improvements of the UK-NHS Model
8 Summary of MNC/MNE Characteristics
9 Proposed Solutions—the UK-NHS Model or the MNC Organizational Model
10 E-Health and AI
11 Conclusions
References
Predicting COVID19 Spread in Saudi Arabia Using Artificial Intelligence Techniques—Proposing a Shift Towards a Sustainable Healthcare Approach
1 Introduction
2 Literature Review
3 Experimental Methodology
3.1 Dataset Description and Pre-processing
3.2 Building Models
4 Model Evaluation Results and Analysis
5 Sustainable Healthcare Post COVID 19 for SA
5.1 Sustainable Healthcare
5.2 Staff and Clinical Practice Sustainability During the Pandemic
5.3 Expand Hospital-at-Home During the COVID-19 Pandemic
5.4 COVID-19 Pandemic and Sustainable Development Groups
5.5 Research Directions
6 Conclusion
References
Machine Learning and Deep Learning Applications
A Comprehensive Study of Deep Neural Networks for Unsupervised Deep Learning
1 Introduction
2 Feedforward Neural Network
2.1 Single Layer Perceptron
2.2 Multi-Layer Perceptron
3 Deep Learning
3.1 Restricted Boltzmann Machines (RBMs)
3.2 Variants of Restricted Boltzmann Machine
3.3 Deep Belief Network (DBN)
3.4 Autoencoders (AEs)
4 Applications and Implications of Deep Learning
4.1 Sustainable Applications of Deep Learning
5 Challenges and Future Scope
References
An Overview of Deep Learning Techniques for Biometric Systems
1 Introduction
1.1 Deep Learning
1.2 Deep Learning for Biometric
2 Deep Learning in Neural Networks
2.1 Autoencoders AEs
2.2 Deep Belief Networks DBN
2.3 Recurrent Neural Networks RNN
2.4 Convolutional Neural Networks CNNs
3 Deep Learning Frameworks
4 Biometrics Systems
4.1 Deep Learning for Unimodal Biometrics
4.2 Deep Learning for Multimodal Biometrics
5 Challenges
6 Conclusion and Discussion
References
Convolution of Images Using Deep Neural Networks in the Recognition of Footage Objects
1 Introduction
2 Statement of the Problem
3 Image Processing by Non-Parametric Methods
4 Using a Convolutional Neural Network in a Minimum Sampling Image Recognition Task
5 Deep Learning
6 Presence of Small Observations Samples
7 Example of Application of a Convolutional Neural Network
8 Conclusion
References
A Machine Learning-Based Framework for Efficient LTE Downlink Throughput
1 Introduction
2 4G/LTE Network KPIs
3 ML Algorithms Used in the Framework
3.1 Dimension Reduction Algorithm
3.2 K-Means Clustering Algorithm
3.3 Linear Regression Algorithm with Polynomial Features
4 A ML-Based Framework for Efficient LTE Downlink Throughput
4.1 Phase 1: Preparing Data for ML
4.2 Phase 2: Data Visualization and Evaluation
4.3 Phase 3: Analyzing Quality Metric
5 Experimental Results and Discussion
6 Conclusion
References
Artificial Intelligence and Blockchain for Transparency in Governance
1 Introduction
2 Literature Review of Research Paper
2.1 Conceptual Framework
2.2 Review Based Work
2.3 Implementation Based Work
2.4 Comparative Analysis
3 Selection and Justification of the Preferred Method
4 Preferred Method Detailed Comparison
5 Conclusions
References
Artificial Intelligence Models in Power System Analysis
1 Introduction
2 AI Techniques: Basic Review
2.1 Expert Systems (ES)
2.2 Genetic Algorithms (GA)
2.3 Artificial Neural Networks (ANNs to NNWs)
2.4 Fuzzy Logic
3 AI Applications in Power System
3.1 AI in Transmission Line
3.2 Smart Grid and Renewable Energy Systems—Power System Stability
3.3 Expert System Based Automated Design, Simulation and Controller Tuning of Wind Generation System
3.4 Real-Time Smart Grid Simulator-Based Controller
3.5 Health Monitoring of the Wind Generation System Using Adaptive Neuro-Fuzzy Interference System (ANFIS)
3.6 ANN Models—Solar Energy and Photovoltaic Applications
3.7 Fuzzy Interference System for PVPS (Photovoltaic Power Supply) System
4 Sustainability in Power System Under AI Technology
5 Conclusion and Future Work
References
Internet of Things for Water Quality Monitoring and Assessment: A Comprehensive Review
1 Introduction
2 Water Quality Assessment in Environmental Technology
3 Internet of Things in Water Quality Assessment
4 Water Quality Monitoring Systems
4.1 Hardware and Software Design
4.2 Smart Water Quality Monitoring Solutions
5 An Empirical Evaluation of IoT Applications in Water Quality Assessment
6 Conclusions
References
Contribution to the Realization of a Smart and Sustainable Home
1 Introduction
2 AI
2.1 Some Applications of AI
2.2 AI Methodological Approaches
3 IoT
3.1 The IoT History
3.2 Operation
3.3 Areas of Application
3.4 Relationship Between IoT and IA
4 Smart Home
4.1 Home Automation Principles
4.2 Definition of the Smart Home
4.3 Ambient Intelligence
4.4 Communicating Objects
5 Home Automation Technologies
5.1 Wireless Protocols
5.2 802.15.4
5.3 Carrier Currents
5.4 Wired Protocols
5.5 1-Wire
6 Home Automation Software
6.1 OpenHAB
6.2 FHEM
6.3 HEYU
6.4 Domogik
6.5 Calaos
6.6 OpenRemote
6.7 LinuxMCE
7 Home Automation and Photovoltaic Energy
8 Implementation
8.1 Cost of Home Automation
8.2 Hardware and Software Used
9 Conclusion
References
Appliance Scheduling Towards Energy Management in IoT Networks Using Bacteria Foraging Optimization (BFO) Algorithm
1 Introduction
2 Review of Related Literature
3 System Model
3.1 Category of Loads
3.2 Specific Objectives of This Work
3.3 Description of Major Home Appliances Considered
3.4 Length of Operation Time
3.5 Appliances Scheduling Optimization Problem Formulation
4 BFA Meta-Heuristic Optimization Technique
4.1 Chemotaxis
4.2 Reproduction
4.3 Elimination and Dispersal
5 Experiment Results and Discussion
5.1 User Comfort
5.2 Electricity Cost
5.3 Load or Electricity Consumption
5.4 Peak Average Ratio (PAR)
5.5 Load Balancing
6 Conclusion
References