This edited book is a collection of quality research articles reporting research advances in the area of deep learning, IoT and urban computing. It describes new insights based on deep learning and IoT for urban computing and is useful for architects, engineers, policymakers, facility managers, academicians, and researchers who are interested in expanding their knowledge of the applications of deep learning trends involving urban computing.
Author(s): M.A. Jabbar, Sanju Tiwari, Fernando Ortiz-Rodriguez
Series: River Publishers Series in Computing and Information Science and Technology
Publisher: River Publishers
Year: 2023
Language: English
Pages: 257
City: Gistrup
Cover
Half-Title
RIVER PUBLISHERS SERIES IN COMPUTING AND INFORMATION SCIENCE AND TECHNOLOGY
Title
Copyrights
Contents
Preface
List of Contributors
List of Figures
List of Tables
List of Abbreviations
1 Requirement Analysis of Data Analytics Software Within the Scope of a Smart University
1.1 Introduction
1.2 Literature Review
1.2.1 Smart campus studies
1.2.2 Requirements analysis studies
1.3 Proposed Methodology
1.3.1 Software development process
1.3.2 Software development models and its steps
1.4 V-Model
1.4.1 Previous steps of the project
1.4.2 V-model of software requirements specifications
1.4.3 Planning with the core team
1.5 Adaptation of the Proposed Methodology
1.6 Conclusion
1.7 Acknowledgment
References
2 Performance Analysis of Deep Learning Models for Re-identification of a Person in a Public Surveillance System
2.1 Introduction
2.2 Literature Survey
2.2.1 Existing video surveillance commercial products
2.2.2 A general automated visual surveillancesystem framework
2.2.3 Multi-camera tracking and person re-identification
2.2.4 ReID system framework
2.2.5 Overview of previous Work in ReID
2.2.6 Multi-camera tracking andperson-re-identification datasets
2.2.7 Challenges faced by ReID system
2.3 Proposed System
2.4 Experimental Results and Discussion
2.5 Conclusion
References
3 Exploiting Trajectory Data to Improve Smart City Services
3.1 Introduction
3.2 General Framework of Urban Computing
3.3 Trajectory Data and Trajectory Data Mining
3.3.1 Trajectory data
3.3.2 Trajectory data mining
3.3.2.1 Primary mining methods
3.3.2.2 Secondary mining methods
3.4 Applications of Trajectories
3.5 Issues for Trajectory Data Mining
3.6 Publicly Available Trajectory Datasets
3.7 Conclusion and Future Work
References
4 An End–End Framework for Autonomous Driving Cars in a CARLA Simulator
4.1 Introduction
4.2 Related Work
4.2.1 Autonomous driving simulators
4.2.2 Object detection
4.2.3 Literature review
4.3 Proposed Work
4.3.1 Methodology
4.3.2 Work flow
4.3.3 Traffic signal detection
4.3.3.1 Dataset selection
4.3.3.2 Dataset pre-processing and loading
4.3.3.3 Model selection
4.3.4 End–End framework
4.3.4.1 Dataset selection
4.3.4.2 Dataset pre-processing and loading
4.3.4.3 Model
4.4 Evaluation Metrics
4.5 Result of Prediction
4.5.1 Traffic signal detection
4.5.2 End–End framework
4.6 Conclusion
References
5 IoT and Artificial Intelligence Techniques for Public Safety and Security
5.1 Introduction
5.2 Proposed Method
5.3 Smart City Technology Framework
5.4 Other Technologies that are Connected
5.5 Conclusion and Future Work
References
6 Deep Learning Approaches for the Classification of IoT-based Hyperspectral Images
6.1 Introduction
6.2 IoT in Remote Sensing and HSI Analysis
6.2.1 Applications of IoT-based remote sensing and HSI
6.2.2 Challenges in IoT-based remote sensing and HSI
6.3 Preliminaries
6.3.1 Dimensionality reduction
6.3.1.1 Principal component analysis (PCA)
6.3.1.2 Kernel PCA
6.3.2 Deep learning models
6.3.2.1 Gated recurrent unit
6.3.2.2 Long short-term memory
6.3.2.3 3D CNN
6.3.2.4 Auto-encoders
6.3.2.5 Generative adversarial network
6.3.3 Activation function
6.4 Methodology
6.4.1 Gated recurrent unit
6.4.2 Long short-term memory
6.4.3 3D CNN
6.4.4 Auto-encoder
6.4.5 Generative adversarial network
6.5 Experimental Setup
6.5.1 Hyperspectral datasets
6.5.2 Experimental setup and parameters
6.6 Results and Discussion
6.7 Conclusion
References
7 Artificial Intelligence and IoT for Smart Cities
7.1 Introduction
7.2 Artificial Intelligence
7.3 Artificial Intelligence History
7.4 Benefits of AI
7.5 Limitations or Challenges of AI
7.6 Applications of Artificial Intelligence [14, 21]
7.7 IoT
7.8 History of IoT
7.9 Advantages of the Internet of Things (IoT)
7.9 Disadvantages of Internet of Things (IoT)
7.10 Application of IoT
7.11 Smart Cities
7.12 How Do Smart Cities Work?
7.13 Advantages of Smart Cities [3]
7.14 Disadvantages of Smart Cities
7.15 Need for Smart City
7.16 Smart City Security
7.17 Smart Cities in the Various Parts of the World
7.18 Conclusion
References
8 Intelligent Facility Management System forSelf-sustainable Homes in Smart Cities:An Integrated Approach
8.1 Introduction
8.2 BIM and Energy Efficient Buildings
8.3 BIM in MEP Application
8.4 Integration of BIM and Wireless Sensor Networks (WSNs)
8.5 AI in Smart Homes
8.5.1 Data exchange levels of powered smart homes (AI and IoT)
8.6 Genetic Algorithm Based Strategy for Efficient Energy Management
8.7 Intelligent Model Algorithms for IoT Application
8.8 Intelligence Awareness Target (IAT)
8.9 Intelligence Energy Efficiency (IE2S) Algorithm
8.9.1 Intelligence service (IST) algorithm
8.10 BIM and Big Data Analytics
8.10.1 Data acquisition
8.10.2 Communication technologies
8.10.3 Hadoop ecosystem
8.10.4 Decision making
8.11 Conclusion
References
9 Artificial Intelligence and IoT for Smart Cities
9.1 Introduction
9.1.1 Impact of AI in smart city
9.1.2 Advantages of smart city
9.2 Implementation of Smart City
9.2.1 Aspects of smart city
9.2.2 Smart city components
9.3 Artificial Intelligence (AI) in Smart City
9.3.1 AI-enabled smart city applications
9.3.1.1 Machine learning
9.3.1.2 Deep learning
9.3.2 Applications of AI in smart city applications
9.4 Challenges in IoT-based Smart City Implementation
9.5 Conclusion
References
Index
About the Editors
BackCover
