Machine Learning Approaches for Urban Computing (Studies in Computational Intelligence, 968)

✍ Scribed by Mainak Bandyopadhyay (editor), Minakhi Rout (editor), Suresh Chandra Satapathy (editor)

• Publisher: Springer
• Tongue: English
• Leaves: 214
• Category: Library

✦ Synopsis

This book discusses various machine learning applications and models, developed using heterogeneous data, which helps in a comprehensive prediction, optimization, association analysis, cluster analysis and classification-related applications for various activities in urban area. It details multiple types of data generating from urban activities and suitability of various machine learning algorithms for handling urban data. The book is helpful for researchers, academicians, faculties, scientists and geospatial industry professionals for their research work and sets new ideas in the field of urban computing.

✦ Table of Contents

Preface
Contents
Editors and Contributors
Urbanization: Pattern, Effects and Modelling
1 Introduction
1.1 Necessity of Understanding Land Surface Temperature as a Part of Analysing Urban Pattern
1.2 Necessity on Extraction of Building Footprint
2 Study Area and Data Used
3 Method
3.1 Land Use Analysis
3.2 Spatial Metrics and Urban Expansion Analysis
3.3 Urban Growth Indices
3.4 Land Use Modelling Using SLEUTH
3.5 Building Footprint Extraction
3.6 Land Surface Temperature Analysis
4 Results
4.1 Land Use Analysis
4.2 Results of Modelling Urban Land Use Change Using SLEUTH
4.3 Land Surface Temperature
4.4 Building Footprint Extraction
5 Conclusion
References
A Spatiotemporal Accessibility Analysis of Bus Transportation Facility in the National Capital Territory (NCT) of Delhi, India
1 Introduction
2 Literature Review
2.1 Study Area
3 Methodology
4 Data
5 Travel Time Calculation
6 Accessibility Analysis
7 Results
8 Conclusions
References
Extraction of Information from Hyperspectral Imaging Using Deep Learning
1 Introduction
2 Hyperspectral Imaging
2.1 Spatial–Spectral Classifications
3 Dimensionality Reduction
4 HSI Classification
4.1 Deep Learning Overview
4.2 Significance of 3D CNN in HSI
4.3 Parameters in CNN
5 Dataset Description
6 Result Analysis
6.1 Ground Truth Image Significance
6.2 Class Wise Accuracy
6.3 Confusion Matrix
7 Conclusion
References
Detection of Coronavirus (COVID-19) Using Deep Convolutional Neural Networks with Transfer Learning Using Chest X-Ray Images
1 Introduction
2 Materials and Methods
2.1 Data Set Collection and Findings
2.2 VGG16 Architecture
2.3 Proposed Architecture of VGG16 with Transfer Learning
3 Experimental Set-up and Results
4 Discussion
5 Conclusion
References
Vehicle Detection and Count in the Captured Stream Video Using Machine Learning
1 Introduction
2 Overview of the Approach for Vehicle Detection in the Captured Video Stream
2.1 Chapter Perspective
2.2 Video Tracking
3 Methodology for Vehicle Detection
3.1 Information Gathering
3.2 Information Analysis
3.3 Noise Minimization
3.4 Designing of Algorithms
3.5 Target Detection
3.6 Module to Identify and Count the Moving Vehicles
4 Important Terminologies
4.1 OpenCV
4.2 Background Subtractor
4.3 Morphological Transformations
4.4 Thresholding
4.5 Classification of Vehicles
4.6 Background Subtraction and Vehicle Detection
4.7 Feature Extraction
4.8 Dimensionality Reduction
5 Classification of Vehicles
5.1 ANN Algorithm
5.2 AdaBoost Algorithm
6 Experiment Results and Discussion
6.1 Contours Formation
6.2 Identification and Vehicle Count
6.3 Non-thermal Surveillance
6.4 Thermal Surveillance
7 Scope for Future Work
8 Conclusion
References
Dimensionality Reduction and Classification in Hyperspectral Images Using Deep Learning
1 Introduction
2 Hyperspectral Imaging Analysis
2.1 HSI Sensors
2.2 Reference Datasets
2.3 HSI Issues and Challenges
2.4 Applications of HSI
3 Dimensionality Reduction in HSI
3.1 Components of Dimensionality Reduction
3.2 Techniques for Dimensionality Reduction
3.3 Performance Metrics and Quality Criteria
3.4 Experimental Analysis
4 Deep Learning for Hyperspectral Data
4.1 Types of Features
4.2 Deep Learning Layers
4.3 CNN Classification Model
4.4 Performance Evaluation Metrics
4.5 Comparative Analysis
4.6 Deep Learning Limitations
5 Conclusion
Reference
Machine Learning and Deep Learning Algorithms in the Diagnosis of Chronic Diseases
1 Introduction
2 Machine Learning Framework and Performance Metrics
3 ML Algorithms in Clinical Practice
3.1 Cancers
3.2 Alzheimer’s
3.3 Diabetes
3.4 Hepatic Fibrosis
3.5 Heart Attacks
3.6 Asthma or Chronic Obstructive Pulmonary Diseases (COPD)
3.7 Kidney Injuries
3.8 Others
4 Deep Learning in Medical Diagnosis
5 Conclusions
References
Security Enhancement of Contactless Tachometer-Based Cyber Physical System
1 Introduction
1.1 Need of System
1.2 Problem Statement
1.3 Objective of Research
1.4 Application of Research
2 Materials and Methods
2.1 Material
2.2 Methods
2.3 Mathematical Modeling of BLDC Motor
3 Proposed Framework
4 Software Modification for CPS Security
4.1 Security of Cyber Physical System
4.2 Steps to Create HEC Token
4.3 Steps to Establish Connection Between Splunk Master and CPS
5 Result Analysis
6 Conclusion
Appendix
Code of the system
References
Optimization of Loss Function on Human Faces Using Generative Adversarial Networks
1 Introduction
2 Literature Survey
3 Dataset
4 Proposed Method
4.1 Inputting the Dataset
4.2 Preprocessing
5 Building the Model
5.1 Discriminator
5.2 Generator
5.3 Training of the Sub-models
5.4 The Loss Function
6 Result Analysis
7 Conclusion and Future Work
References