Smart and Sustainable Intelligent Systems (Sustainable Computing and Optimization)

✍ Scribed by Namita Gupta (editor), Prasenjit Chatterjee (editor), Tanupriya Choudhury (editor)

• Publisher: Wiley-Scrivener
• Year: 2021
• Tongue: English
• Leaves: 576
• Edition: 1
• Category: Library

✦ Synopsis

The world is experiencing an unprecedented period of change and growth through all the electronic and technilogical developments and everyone on the planet has been impacted.  What was once ‘science fiction’, today it is a reality.

This book explores the world of many of once unthinkable advancements by explaining current technologies in great detail.  Each chapter focuses on a different aspect - Machine Vision, Pattern Analysis and Image Processing - Advanced Trends in Computational Intelligence and Data Analytics - Futuristic Communication Technologies - Disruptive Technologies for Future Sustainability. The chapters include the list of topics that spans all the areas of smart intelligent systems and computing such as: Data Mining with Soft Computing, Evolutionary Computing, Quantum Computing, Expert Systems, Next Generation Communication, Blockchain and Trust Management, Intelligent Biometrics, Multi-Valued Logical Systems, Cloud Computing and security etc.  An extensive list of bibliographic references at the end of each chapter guides the reader to probe further into application area of interest to him/her.

✦ Table of Contents

Cover
Half-Title Page
Series Page
Title Page
Copyright Page
Dedication
Contents
Preface
Organization of the Book
Acknowledgement
Part 1: MACHINE LEARNINGAND ITS APPLICATION
1 Single Image Super-Resolution Using GANs for High-Upscaling Factors
1.1 Introduction
1.2 Methodology
1.2.1 Architecture Details
1.2.2 Loss Function
1.3 Experiments
1.3.1 Environment Details
1.3.2 Training Dataset Details
1.3.3 Training Parameters
1.4 Experiments
1.5 Conclusions
1.6 Related Work
References
2 Landmark Recognition Using VGG16 Training
2.1 Introduction
2.2 Related Work
2.2.1 ImageNet Classification
2.2.2 Deep Local Features
2.2.3 VGG Architecture
2.3 Proposed Solution
2.3.1 Revisiting Datasets
2.4 Results and Conclusions
2.5 Discussions
References
3 A Comparison of Different Techniques Used for Classification of Bird Species From Images
3.1 Introduction
3.2 CUB_200_2011 Birds Dataset
3.3 Machine Learning Approaches
3.3.1 Softmax Regression
3.3.2 Support Vector Machine
3.3.3 K-Means Clustering
3.4 Deep Learning Approaches
3.4.1 CNN
3.4.2 RNN
3.4.3 InceptionV3
3.4.4 ImageNet
3.5 Conclusion
3.6 Conclusion and Future Scope
References
4 Road Lane Detection Using Advanced Image Processing Techniques
4.1 Introduction
4.2 Related Work
4.3 Proposed Approach
4.4 Analysis
4.4.1 Dataset
4.4.2 Camera Calibration and Distortion Correction
4.4.3 Threshold Binary Image
4.4.4 Perspective Transform
4.4.5 Finding the Lane Lines—Sliding Window
4.4.6 Radius of Curvature and Central Offset
4.5 Annotation
4.6 Illustrations
4.7 Results and Discussions
4.8 Conclusion and Future Work
References
5 Facial Expression Recognition in Real Time Using Convolutional Neural Network
5.1 Introduction
5.1.1 Need of Study
5.2 Related Work
5.3 Methodology
5.3.1 Applying Transfer Learning using VGG-16
5.3.2 Modeling and Training
5.4 Results
5.5 Conclusion and Future Scope
References
6 Feature Extraction and Image Recognition of Cursive Handwritten English Words Using Neural Network and IAM Off-Line Database
6.1 Introduction
6.1.1 Scope of Discussion
6.2 Literature Survey
6.2.1 Early Scanners and the Digital Age
6.2.2 Machine Learning
6.3 Methodology
6.3.1 Dataset
6.3.2 Evaluation Metric
6.3.3 Pre-Processing
6.3.4 Implementation and Training
6.4 Results
6.4.1 CNN Output
6.4.2 RNN Output
6.4.3 Model Analysis
6.5 Conclusion and Future Work
6.5.1 Image Pre-Processing
6.5.2 Extend the Model to Fit Text-Lines
6.5.3 Integrate Word Beam Search Decoding
References
7 License Plate Recognition System Using Machine Learning
7.1 Introduction
7.1.1 Machine Learning
7.2 Related Work
7.3 Classification Models
7.3.1 Logistic Regression
7.3.2 Decision Trees
7.3.3 Random Forest
7.3.4 K Means Clustering
7.3.5 Support Vector Machines
7.4 Proposed Work and Methodology
7.4.1 Detect License Plate
7.4.2 Segmentation
7.4.3 Training the Model
7.4.4 Prediction and Recognition
7.5 Result
7.6 Conclusion
7.7 Future Scope
References
8 Prediction of Disease Using Machine Learning Algorithms
8.1 Introduction
8.2 Datasets and Evaluation Methodology
8.2.1 Datasets
8.3 Algorithms Used
8.3.1 Decision Tree Classifier
8.3.2 Random Forest Classifier
8.3.3 Support Vector Machines
8.3.4 K Nearest Neighbors
8.4 Results
8.5 Conclusion
References
Part 2: DEEP LEARNING AND ITS APPLICATION
9 Brain Tumor Prediction by Binary Classification Using VGG-16
9.1 Introduction
9.2 Existing Methodology
9.2.1 Dataset Description
9.2.2 Data Import and Preprocessing
9.3 Augmentation
9.3.1 For CNN Model
9.3.2 For VGG 16 Model
9.4 Models Used
9.4.1 CNN Model
9.4.2 VGG 16 Model
9.5 Results
9.6 Comparison
9.7 Conclusion and Future Scope
References
10 Study of Gesture-Based Communication Translator by Deep Learning Technique
10.1 Introduction
10.2 Literature Review
10.3 The Proposed Recognition System
10.3.1 Image Acquisition
10.3.2 Pre-Processing
10.3.3 Classification and Recognition
10.3.4 Post-Processing
10.4 Result and Discussion
10.5 Conclusion
10.6 Future Work
References
11 Transfer Learning for 3-Dimensional Medical Image Analysis
11.1 Introduction
11.2 Literature Survey
11.2.1 Deep Learning
11.2.2 Transfer Learning
11.2.3 PyTorch and Keras (Our Libraries)
11.3 Related Works
11.3.1 Convolution Neural Network
11.3.2 Transfer Learning
11.4 Dataset
11.4.1 Previously Used Dataset
11.4.2 Data Acquiring
11.4.3 Cleaning the Data
11.4.4 Understanding the Data
11.5 Description of the Dataset
11.6 Architecture
11.7 Proposed Model
11.7.1 Model 1
11.7.2 Model 2
11.7.3 Model 3
11.8 Results and Discussion
11.8.1 Coding the Model
11.9 Conclusion
11.10 Future Scope
Acknowledgement
References
12 A Study on Recommender Systems
12.1 Introduction
12.2 Background
12.2.1 Popularity-Based
12.2.2 Content-Based
12.2.3 Collaborative Systems
12.3 Methodology
12.3.1 Input Parameters
12.3.2 Implementation
12.3.3 Performance Measures
12.4 Results and Discussion
12.5 Conclusions and Future Scope
References
13 Comparing Various Machine Learning Algorithms for User Recommendations Systems
13.1 Introduction
13.2 Related Works
13.3 Methods and Materials
13.3.1 Content-Based Filtering
13.3.2 Collaborative Filtering
13.3.3 User–User Collaborative Filtering
13.3.4 Item–Item Collaborative Filtering
13.3.5 Random Forest Algorithm
13.3.6 Neural Networks
13.3.7 ADA Boost Classifier
13.3.8 XGBoost Classifier
13.3.9 Trees
13.3.10 Regression
13.3.11 Dataset Description
13.4 Experiment Results and Discussion
13.5 Future Enhancements
13.6 Conclusion
References
14 Indian Literacy Analysis Using Machine Learning Algorithms
14.1 Introduction
14.2 Related Work
14.3 Solution Approaches
14.3.1 Preparation of Dataset
14.3.2 Data Reduction
14.3.3 Data Visualization
14.3.4 Prediction Models
14.4 Proposed Approach
14.5 Result Analysis
14.6 Conclusion and Future Scope
14.6.1 Conclusion
14.6.2 Future Scope
References
15 Motion Transfer in Videos using Deep Convolutional Generative Adversarial Networks
15.1 Introduction
15.2 Related Work
15.3 Methodology
15.3.1 Pre-Processing
15.3.2 Pose Detection and Estimation
15.4 Pose to Video Translation
15.5 Results and Analysis
15.6 Conclusion and Future Scope
References
16 Twin Question Pair Classification
16.1 Introduction
16.2 Literature Survey
16.2.1 Duplicate Quora Questions Detection by Lei Guo, Chong Li & Haiming Tian
16.2.2 Natural Language Understanding with the Quora Question Pairs Dataset by Lakshay Sharma, Laura Graesser, Nikita Nangia, Utku Evci
16.2.3 Duplicate Detection in Programming Question Answering Communities by Wei Emma Zhang and Quan Z. Sheng, Macquarie University
16.2.4 Exploring Deep Learning in Semantic Question Matching by Arpan Poudel and Ashwin Dhakal [1]
16.3 Methods Applied for Training
16.3.1 Count Vectorizer
16.3.2 TF-IDF Vectorizer
16.3.3 XG Boosting
16.3.4 Random Forest Classifier
16.4 Proposed Methodology
16.4.1 Data Collection
16.4.2 Data Analysis
16.4.3 Data Cleaning and Pre-Processing
16.4.4 Embedding
16.4.5 Feature Extraction
16.4.6 Data Splitting
16.4.7 Modeling
16.5 Observations
16.6 Conclusion
References
17 Exploration of Pixel-Based and Object-Based Change Detection Techniques by Analyzing ALOS PALSAR and LANDSAT Data
17.1 Introduction
17.2 Classification of Pixel-Based and Object-Based Change Detection Methods
17.2.1 Image Ratio
17.2.2 Image Differencing
17.2.3 Image Regression
17.2.4 Vegetation Index Differencing
17.2.5 Minimum Distance Classification
17.2.6 Maximum Likelihood Classification
17.2.7 Spectral Angle Mapper (SAM)
17.2.8 Support Vector Machine
17.3 Experimental Results
17.3.1 Omission Error
17.3.2 Commission Error
17.3.3 User Accuracy
17.3.4 Producer Accuracy
17.3.5 Overall Accuracy
17.4 Conclusion
Acknowledgment
References
18 Tracing Bad Code Smells Behavior Using Machine Learning with Software Metrics
18.1 Introduction
18.2 Related Work and Motivation
18.3 Methodology
18.3.1 Data Collection
18.3.2 Static Code Analysis
18.3.3 Sampling
18.3.4 Machine Learning Approach
18.4 Result Analysis and Manual Validation
18.5 Threats, Limitation and Conclusion
References
19 A Survey on Various Negation Handling Techniques in Sentiment Analysis
19.1 Introduction
19.2 Methods for Negation Identification
19.2.1 Bag of Words
19.2.2 Contextual Valence Shifters
19.2.3 Semantic Relations
19.2.4 Relations and Dependency-Based or Syntactic-Based
19.3 Word Embedding
19.4 Conclusion
References
20 Mobile-Based Bilingual Speech Corpus
20.1 Introduction
20.2 Overview of Multilingual Speech Corpus for Indian Languages
20.3 Methodology for Speech Corpus Development
20.3.1 Recording Setup
20.3.2 Capturing
20.3.3 Segregation and Editing
20.4 Description of Bilingual Speech Corpus
20.5 Conclusion and Future Scope
References
21 Intrusion Detection using Nature-Inspired Algorithms and Automated Machine Learning
21.1 Introduction
21.2 Related Work
21.3 Methodology
21.3.1 Nature Inspired Algorithms for Feature Selection
21.3.2 Automated Machine Learning
21.3.3 Architecture Search using Bayesian Search
21.3.4 Hyperparameter Optimization Through Particle Swarm Optimization (HPO-PSO)
21.4 Results
21.5 Conclusion
References
Part 3: SECURITY AND BLOCKCHAIN
22 Distributed Ownership Model for Non-Fungible Tokens
22.1 Introduction
22.2 Background
22.2.1 Blockchain Technology
22.2.2 Ownership
22.3 Proposed Architecture
22.3.1 Overview
22.3.2 Implementation
22.3.3 Rationale for Smart Contract
22.3.4 Smart Contract Tables
22.4 Use-Cases
22.4.1 Transaction Volume
22.4.2 Comparison Between NFT Tokens
22.5 Example Usage
22.5.1 Current Scenario
22.5.2 Solution by Distributed NFT
22.6 Results
22.7 Conclusion and Future Work
References
23 Comparative Analysis of Various Platforms of Blockchain
23.1 Introduction to Blockchain
23.2 Important Terms of Blockchain
23.2.1 Decentralization
23.2.2 Ledger
23.2.3 Consensus Algorithm
23.2.4 51% Attack
23.2.5 Merkle Tree
23.2.6 Cryptography
23.2.7 Smart Contract
23.3 Bitcoin or Blockchain
23.3.1 Primary Key and Public Key
23.3.2 Workflow of Bitcoin
23.4 Platforms of Blockchain
23.4.1 Ethereum
23.4.2 Hyperledger
23.4.3 R3 Corda
23.4.4 Stellar
23.4.5 Multichain
23.5 Blockchain Platforms and Comparative Analysis
23.6 Conclusion
References
24 Smart Garbage Monitoring System
24.1 Introduction
24.2 Literature Review
24.3 System Design
24.4 System Specifications
24.4.1 Components
24.4.2 Simulation Tool
24.4.3 Analytics Tool
24.5 Circuit Diagram
24.6 Proposed Approach
24.7 Implementation
24.8 Result
24.9 Conclusion
24.10 Future Scope
References
25 Study of Various Intrusion Detection Systems: A Survey
25.1 Introduction
25.2 Structure of IDS
25.3 Intrusion Detection Systems
25.3.1 Host-Based IDS (HIDS)
25.3.2 Network-Based IDS (NIDS)
25.3.3 Types of Network-Based Detection Technique
25.4 Types of Attacks
25.5 Recent Improved Solutions to Intrusion Detection
25.5.1 Based on Data Mining and Machine Learning Methods
25.5.2 Knowledge-Based
25.5.3 Evolutionary Methods and Optimization Techniques
25.6 Analysis of Exiting IDS Based on Technique Used
25.7 Analysis of Existing IDS in Different Domains
25.7.1 IDS for IoT
25.7.2 IDS in Cloud Computing Environment
25.7.3 IDS in Web Applications
25.7.4 IDS for WSN (Wireless Sensor Network)
25.8 Conclusion
References
Part 4: COMMUNICATION AND NETWORKS
26 Green Communication Technology Management for Sustainability in Organization
26.1 Introduction
26.2 Sustainability of Green ICT
26.3 Going Green and Sustainability
26.4 ICT: Green and Sustainability
26.5 Benefits: Green IT Practices
26.6 Management Perspective: Green IT
26.7 Biodegradable Device Components
26.8 Conclusion
References
27 A Means of Futuristic Communication: A Review
27.1 Introduction
27.1.1 Internet of Things
27.1.2 IoT and Cloud Computing
27.1.3 Fog Computing
27.1.4 Edge Computing
27.1.5 Comparative Analysis of Cloud, Fog and Edge Computing
27.2 Literature Review
27.3 IoT Simulators
27.4 IoT Test Beds
27.5 Conclusion and Future Scope
References
28 Experimental Evaluation of Security and Privacy in GSM Network Using RTL-SDR
28.1 Introduction
28.2 Literature Review
28.3 Privacy in Telecommunication
28.4 A Take on User Privacy: GSM Exploitation
28.4.1 IMSI Catching
28.4.2 Eavesdropping
28.5 Experimental Setup
28.5.1 Hardware and Software
28.5.2 Implementation Algorithm and Procedure
28.6 Results and Analysis
28.7 Conclusion
References
29 A Novel Consumer-Oriented Trust Model in E-Commerce
29.1 Introduction
29.2 Literature Surveys
29.3 Trust Pyramid
29.3.1 Trust Scenarios
29.3.2 Statistics of E-Commerce
29.4 Categorization of E-Commerce in Different Spheres
29.4.1 Hyperlocal
29.4.2 Travel and Hospitality
29.4.3 Business to Customer (B2C)
29.4.4 Education Technology
29.4.5 Payments and Wallets
29.4.6 Business to Business (B2B)
29.4.7 Mobility
29.4.8 Financial Technology
29.4.9 Health Technology
29.4.10 Social Commerce
29.4.11 Gaming
29.4.12 Logistics Technology
29.4.13 Online Classified and Services
29.5 Categorization of E-Commerce in Different Spheres and Investment in Last Five Years
29.6 Proposed Model
29.6.1 Different Components of Web Trust Model
29.6.2 A Novel Consumer-Oriented Trust Model
29.7 Conclusion
References
30 Data Mining Approaches for Profitable Business Decisions
30.1 Introduction to Data Mining and Business Intelligence
30.2 Outline of Data Mining and BI
30.2.1 CRISP-DM
30.3 Leading Techniques used for Data Mining in BI
30.3.1 Classification Analysis
30.3.2 Clustering
30.3.3 Regression Analysis
30.3.4 Anomaly Detection
30.3.5 Induction Rule
30.3.6 Summarization
30.3.7 Sequential Patterns
30.3.8 Decision Tree
30.3.9 Neural Networks
30.3.10 Association Rule Mining
30.4 Some Implementations of Data Mining in Business
30.4.1 Banking and Finance
30.4.2 Relationship Management
30.4.3 Targeted Marketing
30.4.4 Fraud Detection
30.4.5 Manufacturing and Production
30.4.6 Market Basket Analysis
30.4.7 Propensity to Buy
30.4.8 Customer Profitability
30.4.9 Customer Attrition and Channel Optimization
30.5 Tabulated Attributes of Popular Data Mining Technique
30.5.1 Classification Analysis
30.5.2 Clustering
30.5.3 Anomaly or Outlier Detection
30.5.4 Regression Analysis
30.5.5 Induction Rule
30.5.6 Summarization
30.5.7 Sequential Pattern
30.5.8 Decision Tree
30.5.9 Neural Networks
30.5.10 Association Rule Learning
30.6 Conclusion
References
Part 5: LATEST TRENDS IN SUSTAINABLECOMPUTING TECHNIQUES
31 Survey on Data Deduplication Techniques for Securing Data in Cloud Computing Environment
31.1 Cloud Computing
31.1.1 Introduction
31.1.2 Cloud Computing Features
31.1.3 Services Provided by Cloud Computing
31.1.4 Types of Clouds Based on Deployment Model
31.1.5 Cloud Computing Security Challenges
31.2 Data Deduplication
31.2.1 Data Deduplication Introduction
31.2.2 Key Design Criteria for Deduplication Techniques
31.3 Literature Review
31.4 Assessment Rules of Secure Deduplication Plans
31.5 Open Security Problems and Difficulties
31.5.1 Data Ownership the Board
31.5.2 Achieving Semantically Secure Deduplication
31.5.3 POW in Decentralized Deduplication Structures
31.5.4 New Security Risks on Deduplication
31.6 Conclusion
References
32 Procedural Music Generation
32.1 Introduction
32.2 Related Work
32.3 Experimental Setup
32.4 Methodology
32.5 Result
32.6 Conclusion
References
33 Detecting Photoshopped Faces Using Deep Learning
33.1 Introduction
33.2 Related Literature
33.3 Dataset Generation
33.3.1 Generating Dataset of Fake Images
33.4 Methodolody
33.4.1 Details of the Training Procedure
33.5 Results
33.6 Conclusion
33.7 Future Scope
References
34 A Review of SQL Injection Attack and Various Detection Approaches
34.1 Introduction
34.2 SQL Injection Attack and Its Types
34.3 Literature Survey
34.4 Summary
34.5 Conclusion
References
35 Futuristic Communication Technologies
35.1 Introduction
35.2 Types of Communication Medium
35.2.1 Wired Medium
35.3 Types of Wired Connections
35.3.1 Implementation of Wired (Physical Mode) Technology
35.3.2 Limitations of Wired Technology
35.4 Wireless Communication
35.4.1 Types of Wireless Technology
35.4.2 Applications of Wireless Technology
35.4.3 Limitations of Wireless Technology
35.5 Optical Fiber Communication
35.5.1 Types of Optical Fiber Communication
35.5.2 Applications of Optical Fiber Communication
35.5.3 Limitations of Optical Fiber Communication
35.6 Radar Communication
35.6.1 Types of Radar Communication
35.6.2 Applications of RADAR Communication
35.6.3 Limitations of RADAR Communication
35.7 Green Communication Technology, Its Management and Its Sustainability
35.8 Space Air Ground Integrated Communication
35.9 Ubiquitous Communication
35.10 Network Planning, Management, Security
35.11 Cognitive Radio Communication
35.12 Types of Cognitive Radio Communication
35.13 Next Generation Communications and Applications
35.14 Smart Energy Management
References
36 An Approach for Load Balancing Through Genetic Algorithm
36.1 Introduction
36.2 Motivation
36.3 Background and Related Technology
36.3.1 Load Balancing
36.3.2 Load Balancing Metrics
36.3.3 Classification of Load Balancing Algorithms
36.4 Related Work
36.5 Proposed Solution
36.5.1 Genetic Algorithm
36.5.2 Flowchart of Proposed Strategy
36.6 Experimental Setup and Results Analysis
36.6.1 Data Pre-Processing
36.6.2 Experimental Setup
36.6.3 Result Analysis
36.7 Conclusion
References
Index
EULA