Computational Intelligence for Information Retrieval

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1: Hybrid Computational Intelligence for Pattern Recognition
	1.1 Introduction
		1.1.1 Computational Intelligence and Hybrid Intelligence
	1.2 Evolution of Computational Intelligence in Health Care
		1.2.1 Artificial Neural Network
		1.2.2 Machine Learning
		1.2.3 Deep Learning
	1.3 Hybrid Computational Intelligence for Disease Prediction
		1.3.1 Prediction of COVID-19 with Hybrid Computational Intelligence
		1.3.2 Analysis of Parkinson’s Disease Using EEG Images
	1.4 Areas of Hybrid Computational Intelligence for Future Research
		1.4.1 Expert Systems
		1.4.2 Neural Nets
		1.4.3 Searching Process
		1.4.4 E-Learning
		1.4.5 Solving the Constraint
	1.5 Conclusion
	References
Chapter 2: Secure Image Transmission Using Nested Images
	2.1 Introduction
	2.2 Literature Survey
	2.3 Proposed Work
		2.3.1 Phase 1: Creation of Intermediate Transformed Image
		2.3.2 Phase 2: Creation of Final Transformed Image
		2.3.3 Phase 3: Recovery of Intermediate Transformed Image
		2.3.4 Phase 4: Recovery of Confidential Image
	2.4 Idea for Enhancing the Transformed Image Security
		2.4.1 Intermediate Transformed Image Creation
		2.4.2 Final Transformed Image Creation
	2.5 Recovery Process
	2.6 Experimental Results and Discussion
		2.6.1 Technique
		2.6.2 Technique
		2.6.3 Comparison between Both Techniques
		2.6.4 Comparison of Transformed Image Creation Results with Other Techniques
		2.6.5 Conclusion
	Conflict of Interest
	References
Chapter 3: Accist: Automatic Traffic Accident Detection and Notification with Smartphones
	3.1 Introduction
	3.2 Related Work and Our Contribution
		3.2.1 Related Work
		3.2.2 Our Contribution
	3.3 Research Methodology
		3.3.1 Data Pre-Processing
		3.3.2 Feature Extraction
		3.3.3 Proposed Model Architecture for Critical Accident Detection
		3.3.4 Mobile Alert and Cloud Computing
	3.4 Conclusion
	3.5 Future Work
	References
Chapter 4: Emotion Prediction through EEG Recordings Using Computational Intelligence
	4.1 Introduction
		4.1.1 Electroencephalography
	4.2 Literature Survey
	4.3 Emotion Prediction of EEG Recordings through Computational Intelligence Methods
		4.3.1 Data Collection
		4.3.2 Data Preprocessing
		4.3.3 Computational Intelligence with Feature Selection and Feature Extraction
		4.3.4 Classification
		4.3.5 Evaluation Parameters
	4.4 Conclusion
	References
Chapter 5: Finger Vein Feature Extraction Using Contrast Enhancement Dynamic Histogram Equalization for Image Enhancement
	5.1 Introduction
	5.2 Related Works
	5.3 Proposed Method
		5.3.1 Image Enhancement
		5.3.2 Normalization
	5.4 Dynamic Histogram Equalization (DHE)
		5.4.1 Dynamic Histogram Equalization Algorithm
	5.5 Contrast Enhancement Dynamic Histogram Equalization (CEDHE)
		5.5.1 Algorithm Steps for CEDHE
	5.6 Results and Discussion
	5.7 Performance Evaluation
		5.7.1 Quality Measures
		5.7.2 Mean Square Error (MSE)
		5.7.3 Peak Signal to Noise Ratio (PSNR)
	5.8 Conclusion
	Acknowledgment
	References
Chapter 6: Song Recommendation Using Computational Techniques Based on Mood Detection
	6.1 Introduction
	6.2 Literature Survey
	6.3 Machine Learning
		6.3.1 Support Vector Machine
		6.3.2 Naïve Bayes
		6.3.3 Random Forest
	6.4 Deep Learning
		6.4.1 Convolutional Neural Network
		6.4.2 Artificial Neural Network (ANN)
		6.4.3 Long Short-Term Memory (LSTM)
	6.5 Other Methodologies
	6.6 Conclusion
	References
Chapter 7: Deep Learning Classification of Retinal Images for the Early Detection of Diabetic Retinopathy Disease
	7.1 Introduction
	7.2 Classification of the Diabetic Retinopathy
	7.3 Related Study
	7.4 Methodology
		7.4.1 Dataset
		7.4.2 Instruction for the Grading
		7.4.3 Development of the Algorithm
		7.4.4 Purpose of CNN
		7.4.5 EfficientNet
		7.4.6 Evolution of Algorithm
		7.4.7 Performance Analysis
	7.5 Result and Discussion
		7.5.1 Data Analysis
		7.5.2 Convolutional Neural Network
		7.5.3 EfficientNet Model
		7.5.4 Model Prediction
		7.5.5 Accuracy
	7.6 Conclusion
	Acknowledgement
	References
Chapter 8: Protecting and Analyzing Big Data on Cloud Platforms
	8.1 Introduction to Big Data and Cloud Computing
		8.1.1 Cloud Computing Service Models
		8.1.2 Deployment Models of Cloud
	8.2 Big Data and Cloud Relationship
		8.2.1 Hadoop: The Big Data Software
		8.2.2 Models Between the Big Data and Cloud
	8.3 Need for Retrieving Information from Widespread Big Data on the Web
	8.4 Security of Big Data in Cloud Computing
	8.5 Challenges for Information Retrieval in Big Data and Cloud
	8.6 Classification of Big Data Security
		8.6.1 Infrastructure Security
		8.6.2 Data Privacy
		8.6.3 Data Management
		8.6.4 Integrity and Reactive Security
	8.7 Encryption Decryption Algorithm for the Analytics of Big Data in Cloud
		8.7.1 Homomorphic Encryption Algorithm
		8.7.2 Verifiable Computation Algorithm (Outsource Computing)
		8.7.3 Message Digest Algorithm
		8.7.4 Key Rotation Algorithm
		8.7.5 Data Encryption Algorithm (DES) Algorithm
		8.7.6 Rijndael Encryption Algorithm
	8.8 Advanced Security by Homomorphic Cryptosystems
		8.8.1 Fully Homomorphic Encryption
		8.8.2 Partially Homomorphic Encryption
	8.9 Case Study with Results
		8.9.1 AES Encryption Performance
			8.9.1.1 Algorithm
			8.9.1.2 Speed
		8.9.2 ElGamal Encryption Performance
			8.9.2.1 Algorithm
			8.9.2.2 Speed
	8.10 Conclusion
	References
Chapter 9: Using Flutter to Develop a Hybrid Application of Augmented Reality
	9.1 Introduction
	9.2 Literature Review
	9.3 Implementation
	9.4 Application Architecture and Construction
		9.4.1 Front-End Development
		9.4.2 Back-End Development
	9.5 Results
	9.6 Conclusion
	Notes
	References
Chapter 10: Computational Intelligence Techniques for Recommendation System in Big Data
	10.1 Introduction to Big Data and Recommendation System
	10.2 Analyzing Big Data for Recommendation System
		10.2.1 User Profile
			10.2.1.1 Profile Representation Technique
			10.2.1.2 Initial Profile Generation
			10.2.1.3 Relevance Feedback
			10.2.1.4 Profile Learning Technique
			10.2.1.5 Profile Adaption Technique
		10.2.2 Profile Exploitation
			10.2.2.1 Information Filtering Methods
				10.2.2.1.1 Demographic filtering
				10.2.2.1.2 Content-Based Filtering
				10.2.2.1.3 Collaborative Filtering
				10.2.2.1.4 Hybrid Approach
	10.3 Evaluation of Recommender System
		10.3.1 Predicting Ratings
		10.3.2 Recommending Useful Items
		10.3.3 Optimizing Utility
	10.4 Book Recommendation System: An Example
		10.4.1 Collaborative Filtering Technique in Book Recommendation System
		10.4.2 Content-Based Filtering Technique in Book Recommendation System
		10.4.3 Hybrid Technique
	10.5 A Comparison between Content-Based Filtering Techniques and Collaborative Filtering Techniques
	10.6 Case Studies
		10.6.1 Last.fm
		10.6.2 MovieLens
	10.7 Conclusion
	References
Chapter 11: Predicting Melanoma Tumor Size through Machine Learning Approaches
	11.1 Introduction
	11.2 Methodology
		11.2.1 Data Collection
		11.2.2 Data Preprocessing and Feature Engineering
		11.2.3 Model Selection
			11.2.3.1 XGBoost
			11.2.3.2 LightGBM
			11.2.3.3 Extra Tree Regressor
			11.2.3.4 Bagging Regressor
			11.2.3.5 Catboost Regressor
		11.2.4 Hyperparameter Tuning
		11.2.5 Repeated K-Fold Cross-Validation
	11.3 Result
		11.3.1 Bayesian Optimization
		11.3.2 Experimental Result and Comparison
	11.4 Conclusion
	References
Chapter 12: A Fuzzy-Based Approach for Characterization and Identification of Sentiments
	12.1 Introduction
	12.2 Literature Survey
	12.3 Overview of the Proposed Framework
	12.4 Materials
		12.4.1 Linguistic Resources
		12.4.2 Dataset
	12.5 Methodology
		12.5.1 Corpus Filtering and Preprocessing
		12.5.2 Word Study
		12.5.3 Sentiment Analysis Using Fuzzy Logic
			12.5.3.1 Developing Fuzzy Rules and Membership Function
			12.5.3.2 Establishing Rule Strength
			12.5.3.3 Aggregating Rule Strength and Output Membership Function
			12.5.3.4 Defuzzification
	12.6 Results
	12.7 Conclusion
	References
Chapter 13: Fingerprint Alterations Type Detection and Gender Recognition Using Convolutional Neural Networks and Transfer Learning
	13.1 Introduction
	13.2 Related Work
	13.3 Contributions
	13.4 Materials and Methods
		13.4.1 Dataset
		13.4.2 Methods
			13.4.2.1 AlexNet
			13.4.2.2 AkaNet
			13.4.2.3 VGG-16
	13.5 Results
		13.5.1 Classification Accuracies
		13.5.2 Alteration Detection
		13.5.3 Alteration Type Detection
		13.5.4 Gender Recognition
	13.6 Conclusion
	References
Chapter 14: Content-Based Image Retrieval Using Intelligent Techniques
	14.1 Introduction
	14.2 State of the Art
	14.3 CBIR Using Intelligence Techniques
		14.3.1 The Proposed Method
		14.3.2 Experiment and Results
		14.3.3 Retrieval Result
		14.3.4 Performance Comparison
	14.4 Conclusion and Future Scope
	References
Index