Innovative Trends in Computational Intelligence

Preface
Acknowledgements
Contents
About the Editors
Data Mining in Healthcare and Prediction Model Using Data Mining Technique on COVID-19
1 Introduction
2 Data Mining for Healthcare
2.1 Healthcare Management
2.2 Customer Relationship Management
2.3 Measuring Treatment Effectiveness
2.4 Detecting Fraud and Abuse
3 Analysing Patient Results and Protection
4 Architecture and Techniques for Healthcare Organization
4.1 Data Selection
4.2 Data Preprocessing
4.3 Data Transformation
4.4 Data Mining
4.5 Data Interpretation or Evaluation
5 Impending of Data Mining
6 Prediction Model Using Data Mining
7 Simulation Environment
8 Results
9 Challenges in Data Mining for Healthcare Applications
10 Limitation of a Prediction Model in Data Mining
10.1 Obtaining Massive Training Datasets
10.2 Data Labelling
10.3 Generalizability of Learning
10.4 Bias in Data
11 Future Scopes in Data Mining for Healthcare
11.1 Ubiquitous Data Mining
11.2 Multimedia Data Mining
11.3 Distributed Data Mining
11.4 Spatial and Geographic Data Mining
11.5 Time Series and Sequence Data Mining
12 Conclusion
References
Computational Intelligence in Intelligent Transportation Systems: An Overview
1 Introduction
2 Computational Intelligence
2.1 The Notion of Computational Intelligence
2.2 Artificial Intelligence Versus Computational Intelligence
2.3 Paradigms of Computational Intelligence
3 Intelligent Transportation System
4 Computational Intelligence Techniques Applied to ITS
5 Opportunities and Challenges
6 Conclusion
References
Insights to Computational Intelligence Techniquesfor Computer Vision
1 Introduction to Computer Vision
2 Brief History
3 Limitations of Traditional Methods
4 Modern Approach
5 Introduction to Deep Learning
6 Convolutional Neural Network
6.1 Convolution Layer
6.2 Properties Related to Convolution Layers
6.3 Nonlinear Layer
6.4 Pooling Layer
6.5 Fully Connected Layer
6.6 Understanding the Working In-Depth
7 Fully Convolutional Network (FCN)
8 Object Detection Algorithms and Techniques
8.1 R-CNN
8.2 Fast R-CNN
8.3 Faster R-CNN
8.4 YOLO
8.5 SSD
8.6 Feature Pyramid Layer
8.7 RetinaNet
9 Case Study
10 Latest Innovation in Computer Vision
11 Conclusion
References
A Two-Stage Multifeature Selection Method to Predict Healthcare Data Using Neural Network
1 Introduction
2 Related Work
3 Materials and Theoretical Background
3.1 Dataset
3.2 Two-Stage Feature Selection and Preprocessing
3.3 Particle Swarm Optimization (PSO)
3.3.1 Genetic Algorithm (GA)
4 Proposed Work
5 Experimental Results
6 Performance Evaluation Methods
6.1 Confusion Matrix
6.2 ROC Curve (Receiver Operating Characteristics)
7 Conclusion
References
Computational Approaches for Detection and Classification of Crop Diseases
1 Agriculture and Crop Disease
2 Pathogens
3 Phytoplasma
4 Symptoms of Phytoplasma
5 Case Study: Rice Crop
5.1 Disease Detection Methodology
5.2 Different Techniques Used in Molecular Diagnosis
5.2.1 Polymerase Chain Reaction (PCR)
5.2.2 Fluorescence RT-PCR Using TaqMan Probe Technology
5.2.3 Loop-Mediated Isothermal Amplification (LAMP)
5.2.4 Random Amplified Polymorphic DNA (RAPD)
5.2.5 Microarray
5.2.6 Enzyme-Linked Immunosorbent Assay (ELISA)
5.2.7 Fluorescence ELISA
6 Computational Approaches
6.1 Image Processing
6.1.1 Image Acquisition
6.1.2 Preprocessing
6.1.3 Segmentation
6.1.4 Feature Extraction
6.1.5 Classification
6.2 Cousins of AI
6.2.1 Deep Learning
6.2.2 Neural Network (NN)
6.2.3 Neural Network Models
6.2.4 Types of Neural Networks
7 Architecture and Tools
8 Predictive Mechanisms
9 Summary
References
Three-Layer Multimodal Biometric Fusion Using SIFT and SURF Descriptors for Improved Accuracy of Authentication of Human Identity
1 Biometric Introduction
1.1 Overview
1.2 Block Diagram of a Biometric System
1.3 Modes of Operation
1.4 Evaluation of Biometric Systems
2 Multi-Biometric Systems
2.1 Multi-Biometric Sources
3 Fusion in Biometric Systems
4 Biometrics Evaluation Metrics
4.1 Outcomes with ORL Database
4.2 Outcomes with PUT Database
5 Finger Feature Generation
6 Palm Print Feature Generation
6.1 SIFT Feature Extraction
6.2 SURF Feature Extraction
7 Multimodal Fusion
8 Conclusion and Future Perspectives
9 Future Perspective
References
Applying Computation Intelligence for Improved Computer Vision Capabilities
1 Introduction
1.1 What Is an Image?
1.2 Image Formation
1.3 Restrictions with Computer Vision
1.4 Evolution of the Camera
2 The Three-Level Paradigm
2.1 Levels of Vision
2.2 Difficulties Faced Using Computer Vision Algorithms
2.3 Methods to Solve the Problems Faced Using Computer Vision Algorithms
3 Image Processing
3.1 Point Operators
3.2 Pixel Transformations
3.3 Types of Images
4 Image Filtering
4.1 Image Derivatives and Averages
5 Image Segmentation
5.1 Types of Segmentation
5.2 Methods of Image Segmentation
5.3 Active Contours (Snake's Method)
6 Edge Detection
7 Object Recognition
7.1 Object Recognition Models
8 YOLO Family Model
9 Pattern Recognition
10 Facial Recognition
11 Computer Vision Tools
12 Current Research Accomplishments
13 Use Cases
13.1 Areas Where Computer Vision Is Being Used
14 Conclusion
References
ECG Feature Extraction
1 Introduction
2 Preprocessing of ECG Signal
2.1 Baseline Wander Correction
2.2 Bandpass Filter
3 Segmentation
3.1 QRS Wave Detection
3.2 Detection of R Point Using DOM Method
3.3 Detection of Q and S Using DOM Method
3.4 Delineation of P and T Waves
3.4.1 Poffset Detection
3.4.2 Ponset Detection
3.4.3 Tonset Detection
3.4.4 Toffset Detection
3.5 Comparison of Tan's Approach and Ecgpuwave Software
4 Feature Extraction
4.1 Segmentation Features
5 Conclusion
Competing Interests
References
Computational Intelligence in Web Mining
1 Introduction
1.1 General Overview of Web Mining
1.2 Web Mining Perspective
2 Web Data Classification
2.1 Web Content Data
2.2 Web Structure Data
2.3 Web Usage Data
3 Web Mining Technique
3.1 Web Content Mining
3.2 Web Structure Mining
3.3 Web Usage Mining
4 Web Mining Applications
5 Future Directions
6 Conclusion
References
A Review on Cognitive Computational Neuroscience: Overview, Models, and Applications
1 Introduction
2 Cognitive Science
3 Computational Neuroscience
4 Artificial Intelligence
5 Interdependence of Cognitive Science, Computational Neuroscience, and Artificial Intelligence
6 Biological Background
7 Models for Cognitive Computational Neuroscience
8 Applications of Computational Neuroscience
9 Future Directions
10 Conclusion
References
Artificial Neural Network: Models, Applications, and Challenges
1 Introduction
2 Architecture of Neural Network
3 Comparison Between Biological Neural Network and Artificial Neural Network (Table 1)
4 Taxonomy of Network Architecture
4.1 Feedforward Neural Networks
4.1.1 Single-Layer Perceptron (SLP)
4.1.2 Multilayer Perceptron (MLP)
4.1.3 Radial Basis Neural Networks (RBNF)
4.2 Recurrent/Feedback Networks
4.2.1 Kohonen Self-organizing Map Network (SOM)
4.2.2 Hopfield Networks
4.2.3 Adaptive Resonance Theory (ART) Models
4.2.4 Long Short-Term Memory (LSTM) Networks
4.2.5 Convolutional Neural Networks (CNN)
5 Applications of Artificial Neural Networks
6 Challenges in Artificial Neural Networks
7 Future Scope
8 Conclusion
References
Proportional and Multi-Stimulations Haptic Device for Active Upper Limbs Prosthetics Control
1 Introduction
2 System Description
3 Tests and Evaluations
3.1 Grasp Recognition
3.2 Strength Variation Detection
3.3 Slid Detection
3.4 System Sensitivity Adjustment
4 Machine Learning Use
5 Discussion
6 Conclusion
References
Index