Applied Intelligence in Human-Computer Interaction

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Editors
Contributors
Chapter 1: Prediction of extreme rainfall events in Rajasthan
1.1 Introduction
1.1.1 The area of work
1.1.2 Problem addressed
1.1.3 Literature survey
1.1.4 Dataset creation
1.1.5 Feature importance
1.1.6 Random Forest Regressor
1.1.7 Multi-layer perceptron
1.1.8 Basic RNN
1.1.9 LSTM
1.1.10 Conclusion and future work
Bibliography
Chapter 2: Diagnostic model for wheat leaf rust disease using image segmentation
2.1 Introduction
2.1.1 Image segmentation
2.1.2 Properties of segmentation
2.1.3 Image segmentation process
2.1.4 Object detection, classification, and segmentation
2.1.4.1 Semantic and instance segmentation
2.2 Related work
2.3 Materials and methods
2.3.1 Dataset
2.3.2 Segmentation techniques
2.3.2.1 Pixel-based segmentation
2.3.2.2 Area-based segmentation
2.3.2.3 Edge-based segmentation
2.3.2.4 Physics-based segmentation
2.4 Proposed approach
2.5 Performance parameters
2.6 Experimental setup
2.7 Experimental results
2.8 Performance analysis
2.9 Conclusion
References
Chapter 3: A comparative study of traditional machine learning and deep learning approaches for plant leaf disease classification
3.1 Introduction
3.2 Materials and methods
3.2.1 Dataset used
3.2.2 Log-Gabor transform
3.2.3 Convolutional neural networks
3.2.4 Performance measures
3.2.4.1 Accuracy
3.2.4.2 Precision
3.2.4.3 Recall
3.2.4.4 F1 score
3.3 Experimental results and discussion
3.4 Conclusion and future work
References
Chapter 4: Application of artificial intelligence and automation techniques to health service improvements
4.1 Introduction
4.2 The advance of artificial intelligence and machine learning
4.2.1 Machine learning
4.2.2 Deep learning
4.2.3 Supervised learning
4.2.4 Unsupervised learning
4.2.5 Reinforcement learning
4.3 The use of AI in the healthcare decision-making process
4.4 The potential impact of AI on the healthcare workforce and clinical care
4.5 Creating a supportive environment for the use of AI in health systems
4.6 Organization of data
4.7 Trust and data management
4.8 Working with the technology industry
4.9 Accountability
4.10 Managing strategic transformation capability
4.11 AI-based biometric authentication
4.12 Results
4.12.1 Application of AI in diabetic detection using machine learning
4.12.2 Detection of glaucoma using machine learning
4.12.3 Deep learning for glaucoma detection
4.12.4 Deep learning techniques for glaucoma detection using OCT images
4.12.5 Conclusions
References
Chapter 5: Artificial intelligence in disaster prediction and risk reduction
5.1 Introduction
5.2 Discovering the un-predicting
5.2.1 Predicting shaking
5.2.2 AI in flood prediction
5.3 Disaster information processing using AI
5.3.1 Artificial intelligence in early warning system monitoring and disaster prediction
5.3.1.1 Example
5.3.2 Social media, artificial intelligence information extraction, and situational awareness
5.4 Public issues
5.5 Artificial intelligence in disaster management: A quick overview
5.6 Conclusion
References
Chapter 6: IoT-based improved mechanical design for elevator cart
6.1 Introduction
6.2 A closer look at the elevator
6.3 IoT and devices
6.4 The tech behind an elevator
6.5 Design of the new model
6.5.1 Temperature modulation and user interface
6.6 Cellphone reception
6.6.1 Current in-cart cellphone coverage models in elevators
6.6.2 Proposed solution to the problem of network coverage
6.7 Results and findings
6.8 Conclusion
Acknowledgment
References
Chapter 7: Wearable IoT using MBANs
7.1 Introduction: background and driving forces
7.2 The IEEE 802.15.6 standard
7.3 Overview of the 802.15.6 standard
7.4 Channel communication modes for MBAN
7.5 Resource allocation
7.5.1 Slotted Aloha access
7.5.2 CSMA/CA access
7.6 Research and development for MBAN
7.7 Conclusions
References
Chapter 8: Simultaneous encryption and compression for securing large data transmission over a heterogeneous network
8.1 Introduction
8.1.1 Research scope
8.1.2 Research objectives
8.1.3 Organization of the paper
8.2 Literature review
8.2.1 Research gap analysis
8.3 Proposed technique
8.4 Assessment platform
8.4.1 Experiment setup
8.4.1.1 System requirement
8.4.1.2 Data preparation
8.4.2 Assessment parameters
8.4.2.1 Randomness analysis using the NIST
8.4.2.2 Throughput
8.4.2.3 Percentage of space saving
8.5 Result analysis
8.6 Conclusion and future work
References
Chapter 9: 2D network on chip
9.1 Introduction
9.2 Literature survey
9.3 Methodology
9.3.1 Router
9.3.2 Routing
9.3.3 Pseudo code
9.4 Result
9.5 Conclusion
References
Chapter 10: Artificial intelligence-based techniques for operations research and optimization
10.1 Introduction
10.2 Problem formulation
10.3 AI-based metaheuristics/optimization methods
10.3.1 Evolutionary algorithms
10.3.1.1 Genetic algorithms (GA)
10.3.1.2 Evolution strategies (ES)
10.3.1.3 Evolutionary programming (EP)
10.3.1.4 Differential evolution (DE)
10.3.2 Other nature-inspired algorithms
10.3.2.1 Particle swarm optimization
10.3.2.2 Ant colony optimization (ACO)
10.3.2.3 Cuckoo search
10.3.3 Artificial neural networks
10.3.3.1 Feed-forward network for objective function simplification
10.3.3.2 Hopfield networks for combinatorial optimization problems
10.4 Conclusion
References
Chapter 11: Heuristic strategies for warehouse location with store incompatibilities in supply chains
11.1 Introduction
11.2 Capacitated facility location with store incompatibilities
11.3 Heuristics based on Vogel’s Approximation Method (VAM)
11.3.1 Modified VAM heuristic (MVH1) for incompatible store pairs
11.3.2 Modified VAM heuristic (MVH2) using minimum product for incompatible pairs
11.3.3 Modified VAM heuristic (MVH3) using minimum supply costs
11.4 Greedy heuristics
11.4.1 Greedy Heuristic based on Supply Costs and Demand Product (GDH1)
11.4.2 Greedy heuristic based on supply costs-to-demand ratio (GDH2)
11.4.3 Randomized greedy heuristics
11.5 Experimental work
11.6 Conclusions
References
Chapter 12: Novel scheduling heuristics for a truck-and-drone parcel delivery problem
12.1 Introduction: Background and driving forces
12.2 Traveling salesman problem (TSP)-based truck-drone parcel delivery problems
12.3 Constrained single truck-and-drone parcel delivery problem (CSTDP)
12.4 Modified TSP heuristics for the CSTDP
12.4.1 Modified nearest neighbor (mNN) heuristic
12.4.2 Modified nearest insertion (mNI) heuristic
12.4.3 Modified minimum spanning tree (mMST) heuristic
12.5 Experimental work
12.6 Conclusions
References
Chapter 13: A reliable click-fraud detection system for the investigation of fraudulent publishers in online advertising
13.1 Introduction
13.2 Related work
13.3 Methods and materials
13.3.1 Dataset details
13.3.2 Data pre-processing
13.3.3 Feature engineering
13.3.4 Data re-sampling using data-level sampling strategies
13.3.4.1 SMOTE: synthetic minority oversampling technique
13.3.4.2 RUSBoost
13.3.5 Proposed feature selection approach: hybrid-manifold feature subset selection
13.4 Classification approaches
13.4.1 Gradient boosting machine
13.5 Validation using 10-fold cross-validation
13.6 Classification matrix and assessment methods for multi-class classification
13.7 Results and discussion
13.7.1 Impact of sampling
13.7.2 Impact of feature selection
13.7.3 Performance comparison
13.8 Conclusion
Abbreviations
References
Chapter 14: Crypto-currency analytics and price prediction: A survey
14.1 Introduction
14.2 Bitcoin
14.3 Blockchain
14.4 Twitter
14.5 Major algorithms and ways to predict crypto-prices
14.5.1 Sentiment analysis
14.5.2 Naїve Bayes
14.5.3 Support vector machine
14.5.4 Decision tree
14.5.5 Bayesian regression
14.5.6 ARIMA
14.6 Advantages of different algorithms
14.7 Disadvantages of different algorithms
14.8 Technology or experience?
14.9 Accuracy
14.10 Ethics
14.11 Why data analysis
14.12 Conclusion
References
Chapter 15: Interactive remote control interface design for a cyber-physical system
15.1 Introduction
15.2 Related works
15.3 Research methodology
15.4 Results and discussion
15.5 Deep learning applications in CPS
15.6 Conclusion and future work
Acknowledgment
References
Chapter 16: Collateral-based system for lending and renting of NFTs
16.1 Background
16.1.1 Blockchain [ 1 ]
16.1.2 How do we solve the problem of centralization?
16.1.3 Blockchain applications
16.1.4 Non-fungible tokens (NFTs)
16.1.5 Trends in the NFT market
16.2 Collateral-based system in traditional banks [ 6 ]
16.3 Overview
16.3.1 Problem statement
16.3.2 Proposed solution
16.4 NFT lifecycle
16.5 Contract overview
16.5.1 Getters
16.5.1.1 Get NFT details
16.5.1.2 Get NFT list available for rent
16.5.1.3 Get lend NFT details
16.5.1.4 Get rent NFT details
16.5.1.5 Get user lend NFT details
16.5.1.6 Get user rent NFT details
16.5.2 Algorithms
16.5.2.1 Add user
16.5.2.2 Lend NFT
16.5.2.3 Rent NFT
16.5.2.4 Stop lending
16.5.2.5 Claim collateral
16.5.2.6 Return NFT
16.6 Gas graphs
16.7 Revenue model
16.7.1 Lending charge
16.7.2 Late fee
16.8 Future scope
16.8.1 Credit score
16.8.2 Capped collateral
16.8.3 Buy recommendation
16.8.4 Rent bidding
16.9 Conclusion
References
Index