Artificial Intelligence and Machine Learning in Smart City Planning shows the reader practical applications of AIML techniques and describes recent advancements in this area in various sectors. Owing to the multidisciplinary nature, this book primarily focuses on the concepts of AIML and its methodologies such as evolutionary techniques, neural networks, machine learning, deep learning, block chain technology, big data analytics, and image processing in the context of smart cities. The text also discusses possible solutions to different challenges posed by smart cities by presenting cutting edge AIML techniques using different methodologies, as well as future directions for those same techniques.
Human beings are the smart and advanced species on this planet because they can think, evaluate, and solve complicated issues. On the other hand, Artificial Intelligence is in the initial stage when compared to human intelligence in many aspects. Then the purpose of Machine Learning is to take decisions based on the data available with efficiency. Research has been going on in technologies like Machine Learning (ML), Artificial Intelligence (AI), and Deep Learning to solve real-world complex issues. The decisions are taken by machines based on the data to automate the process. Some real-world problems use these data-driven decisions, where programing logic cannot be used directly. That is why there is a need for Machine Learning to solve real-world issues with efficacy at a large scale.
Machine Learning is a part of Artificial Intelligence which helps the computer systems to sense the data and take proper decision for forecasting. Machine Learning extracts patterns from raw data by using algorithms. Machine Learning allows computer systems to learn through experience rather than explicitly programmed. Machine learning models consist of learning algorithms which executes some task and enhance their performance over time with experience.
Machine Learning is the fastly expanding technology in the present world. Some researchers named that we are in the golden era of Artificial Intelligence and Machine Learning. Real-world complex problems are solved by the Machine Learning algorithms, which are not resolved with the help of conventional methods in Obulesu et al.. The real-world applications of Machine Learning algorithms are prediction of weather, emotion analysis, detection and prevention of error, sentiment analysis, recognition of object, stock market forecasting, speech synthesis and recognition, customer segmentation, smart city planning, fraud detection and prevention.
Key Features:
- Reviews the smart city concept and teaches how it can contribute to achieving urban development priorities
- Explains soft computing techniques for smart city applications
- Describes how to model problems for effective analysis, intelligent decision making, and optimal operation and control in the smart city paradigm
- Teaches how to carry out independent projects using soft computing techniques in a vast range of areas in diverse fields like engineering, management, and sciences
Author(s): Vedik Basetti, Chandan Kumar Shiva
Publisher: Elsevier
Year: 2023
Language: English
Pages: 326
Artificial Intelligence and Machine Learning in Smart City Planning
Copyright
Contributors
A study of postgraduate students perceptions of key components in ICCC to be used in artificial intelligen ...
Introduction
Integration of Command and Control Center
The purposes of utilization of ICCC
Need for ICCC assessment
MoHUA livability index at smart cities
Current process of implementation of ICCC
Architecture of ICCC
The ICCCs command and control layer is in charge of managing
ICCC maturity assessment framework
Maturity assessment process
Evaluation criteria: ICCC functional capability assessment
ICCC functional capability assessment
Technology assessment
Governance assessment
ICCC maturity ranking
On-site maturity assessment
Importance of ICCC security
Reasons of increasing the securing of ICCC
Conclusion
Reference
Implementing an ANN model and relative importance for predicting the under drained shear strength of fi ...
Introduction
Background
ANN ``artificial neural networks´´
Data collection
Performance indicators and developed ANNs model
Equivalent equation of ANN model
Results and discussions
Relative importance
Conclusions
References
Machine learning algorithms-based solar power forecasting in smart cities
Introduction
Overview of machine learning
Methodology
Data collection and data preprocessing for accurate energy prediction
Data preprocessing
Data preprocessing techniques
Building the model
Training and testing the model
Machine learning models
Mean-absolute error (MAE)
Mean-absolute percentage error (MAPE)
Root mean-square error (RMSE)
Results and analysis
Conclusion
References
Experience in using sensitivity analysis and ANN for predicting the reinforced stone columns bearing cap ...
Introduction
Background
ANNs ``artificial neural networks´´
ANN structure selection
Data collection
Performance measures
Results and discussions
Model equation and sensitivity analysis
Conclusions
References
An investigation into the effectiveness of smart city projects by identifying the framework for measuring p ...
Introduction
Measuring the effectiveness of smart cities
About measurement concept
The reasons for designing frameworks using indicators are such as:
Performance measurement and its dimensions
Performance effectiveness and its dimensions: Product measures
Process measures
People measures
Policy measures
Place measures
Measurement models used in industries
Designing a framework for smart city performance measurement
Conclusion
References
Powering data-driven decision-making for the development of urban economies in India
Overview
Literature review
Best practices and the complexity discourse
Factors in the local economy
Economic clusters and agglomeration
AI/ML in local economy: Problem statement
LEIP: Introduction and methodology
Rapid economic assessment
Economic competency
Cluster analysis
Decision support system
Envisioning AI/ML in LEIP and future of local economic planning
Tool architecture
Annexure: Indicators used for index building under rapid economic assessment, scoring and data sources
References
References
References
References
Effective prediction of solar energy using a machine learning technique
Introduction
Significance of this estimate
Research technique
Object and roof segmentation
Calculating the azimuth and pitch of a roof
Increase the quantity of solar panels
Calculating solar potential
Results
Conclusion
References
Renewable energy based hybrid power quality compensator based on deep learning network for smart cities
Introduction
CIGRE LV multifeeder microgrid: Analysis of power quality issues
Case 1: Without compensation
Custom power devices
Custom power park
Deep learning network
Renewable energy-based hybrid power quality compensator with CIGRE LV multifeeder microgrid
Working of deep neural network used in ReHPQC in CIGRE multifeeder microgrid
Scaled conjugate gradient backpropagation
Case 2-With compensation using ReHPQC
Conclusion
References
Smart transportation based on AI and ML technology
Introduction
Review of related literature
The built environments role in creating an efficient and competitive city
Current challenges in mobility and transportation systems
ML is being used in battery research and development
Artificial intelligence (AI) role in electric vehicle (EV) and smart grid integration
An overview of the integration process and the primary issues it faces
The production and distribution of electricity should be optimized
Smart warehouse logistics and supply chain management
Utilization of intelligent logistics
A storage facility equipped with cutting-edge technology
Conclusions and future directions are summarized in this section
Blockchain-based digitalization of supply chain logistics
Reducing the cost of personal transportation by pooling resources
Internal logistical integration that is both intelligent and seamless
Machine learning for robustness in advanced logistical planning
Last-mile delivery systems that use cutting-edge technology
Outer space logistical considerations
References
Further reading
A study on the perceptions of officials on their duties and responsibilities at various levels of the organi ...
Introduction
Smart Cities Mission (SCM)
Smart city assessment
Challenges in SCM
Stakeholders involved in SCM
Involvement of stakeholders in smart cities
Duties and responsibilities of the officials in executing the AI
Importance of roles of stakeholders in implementing SCM
Local governments and municipal governments
Institutions of finance and investors
Nationals/citizens
Conclusion
References
Reigniting the power of artificial intelligence in education sector for the educators and students competence
Introduction
Significance of the study
Need of the study
Objectives of the study
Scope of the study
Review of literature
Research methodology
Types of data
Research method
Limitations of the study
Theoretical framework
Analysis of artificial intelligence in education sector
Conclusion
References
Forecasting off-grid solar power generation using case-based reasoning algorithm for a small-scale system
Overview
Literature review
AI/ML in forecasting and imputation of missing values
CBR algorithm
Euclidean distance equation
Interpolation technique
Results and discussion
Data collection
Error metrics
Comparison of forecasted values using CBR with and without interpolation
Applications of CBR in forecasting and imputation of missing values
Summary
References
Sensitivity analysis and estimation of improved unsaturated soil plasticity index using SVM, M5P, and ra ...
Introduction
Background
Soft computing techniques
``Support vector machines´´ (SVM)
Details of kernel
M5P model tree
``Random forest regression´´ (RF) regression
Data collection
Performance measures
Analysis results and detailed discussions
Sensitivity analysis
Conclusions
References
Waste water-based pico-hydro power for automatic street light control through IOT-based sensors in smart cit ...
Introduction
System description
Waste water collection analysis
Sewage water treatment
Pico-hydropower generation
BES system design and analysis
IOT devices for automatic light control
Circuit connections
Working
Conclusion and result analysis
References
Predicting subgrade and subbase California bearing ratio (CBR) failure at Calabar-Itu highway using AI (GP, ...
Overview
AI/ML in highway pavement subgrade and subbase construction and maintenance
Application of AI/ML in subgrade and subbase CBR
Recent developments
Statistical analysis of the database
Research program
Preliminary studies
GP prediction of California bearing ratio (CBR)
ANN prediction of California bearing ratio (CBR)
EPR prediction of California bearing ratio (CBR)
Summary
References
Further reading
Machine learning and predictive control-based energy management system for smart buildings
Introduction: Smart cities and smart buildings
Energy management system for a smart building
Building-integrated microgrids
Predictive control-based EMS design for BIMGs
Fundamentals on model predictive control (MPC)
Developing models of BIMGs
Smart homes
Basics of FPGA
Role of FPGA is developing IoT for smart homes
IoTs for home energy management (HEM) using FPGA
Application of machine learning
Brief description on artificial intelligence (AI) and machine learning (ML)
Application of ML on the EMS of a smart building
Objective function
Important system constraints
Renewable energy and load data prediction
Methodology used for optimization
Simulation results
Future trends and research challenges in smart building
References
Deep learning model for flood estimate and relief management system using hybrid algorithm
Introduction
Literature survey
Flood detection system design
Important steps involved in flood management
Identify flood periods
Cluster flood sequences
Rainfall feature extraction
Flood alert
Conclusion and future work
References
Further reading
Smart grid: Solid-state transformer and load forecasting techniques using artificial intelligence
Introduction
Power distribution system
Future power distribution system in smart city
Solid-state transformer
Various enhanced features of SST
Different Configurations of SST
Load forecasting
Statistical approach
Artificial intelligence-based technique
Summary
References
Generative adversarial network-based deep learning technique for smart grid data security
Introduction
Problem formulation and design considerations
Chaotic encryption
GAN
Proposed methodology
Data encryption
Data-hiding through GAN
Result and discussion
Experimental setup
Conclusion
References
An overview of smart city planning-The future technology
Introduction
Approach to artificial intelligence, machine learning, and deep learning for smart city planning
Overview of smart city
Smart energy
Smart health care
Smart transportation
Smart government
Smart building
Cybersecurity in smart city planning
Cybersecurity
Cybersecurity in smart cities using DL, ML, and AI
Conclusion
References
Integration of IoT with big data analytics for the development of smart society
Introduction
Key terminology of IoT and big data
Need of IoT
Use of big data for faster computations
Standards and protocols of IoT
Data analytics for IoT
Characteristics of IoT-generated data
Big data analytics life cycle
Types of data analytics technologies for IoT
IoT-based big data analytics platform
Requirements
Proposed IoT-based big data analytics pipeline
Comparison with existing platforms
Challenges and issues of IoT and data analytics
Conclusions and future directions
References
Index
