Chapter
1 A Cloud-Based Big Data System to Support Visually Impaired People
1.3.1 Internet of Things (IoT)
1.3.3 Face Detection and Recognition
1.3.4 Optical Character Recognition (OCR)
1.5.1 Top-Level Architecture
2 Computational Intelligence in Smart Grid Environment
2.1.1 Power Load Forecasting
2.1.2 Electricity Price Forecasting
2.1.3 Smart Grid Optimization
2.2 Related Work and Open Issues
2.2.1 Power Load Forecasting
2.2.1.1 Stream Forecasting
2.2.2 Prediction of Electricity Spot Prices in Smart Grid
2.2.3 Optimization and Metaheuristics in Big Data and Microgrids
2.3 Overview of Methods Used in Smart Grid Problems
2.3.1 Forecasting Methods
2.3.1.1 Statistical Techniques
2.3.1.2 Artificial Intelligence Techniques
2.3.1.3 Hybrid Techniques (Ensemble Learning)
2.3.2 Optimization Methods
2.3.2.1 Particle Swarm Optimization
2.3.2.2 Artificial Bee Colony
2.3.2.3 Genetic Algorithm
2.4.1 Electricity Price Forecasting
2.4.2 Power Load Forecasting
2.4.2.1 Adaptive Ensemble Learning for Power Load Forecasting
2.4.2.2 Online Support Vector Regression
3 Patient Facial Emotion Recognition and Sentiment Analysis Using Secure Cloud With Hardware Acceleration
3.3.1 Facial Emotion Recognition
3.3.2 Big Data Analytics on the Cloud
3.3.3 Deep Learning Using Convolutional Neural Networks (CNNs)
3.4.1 Face Detection in Images
3.4.2 Facial Emotion Recognition Using CNNs
3.4.3 The CNN Model Training
3.5 System Implementation
3.5.1 A Secure, Multi-tenant Cloud Storage System
3.6.2 GPU Benchmarking and Comparison
3.6.3 Facial Emotion Recognition Accuracy
3.6.4 Model Performance and Power With Hardware Acceleration
3.7 DeepPain: Mapping Patient Emotions to Pain Intensity Levels
3.8 Conclusions and Future Work
4 Novel Computational Intelligence Techniques for Automatic Pain Detection and Pain Intensity Level Estimation From Facial Expressions Using Distributed Computing for Big Data
4.2 Background and History of Computational Techniques
4.2.1 Feature Extraction Techniques
4.2.2 Dimension Reduction Techniques
4.2.3 Machine Learning Techniques for Classification
4.2.4 Distributed Computing for Heavy Computations
4.3 System Architecture for Distributed Computing
4.4 Design of the Novel System for Pain Detection and Pain Intensity Estimation
4.4.2.1 Image Filtering Using Eight Directional Compass Masks
4.4.2.2 Formation of Code Image
4.4.2.3 Formation of Histogram and Feature Vector
4.4.3 Universal Kernel-Based Dimension Reduction System (UKDRS)
4.4.3.1 Universal Kernel-Pearson VII Function
4.4.4 Classification Using ELM-RBF
4.5 Experiments and Results
4.5.2 Evaluation of Classification Results While Detecting Pain
4.5.3 Evaluation of Classification Results in Pain Intensity Level Estimation
4.5.4 Evaluation of Computational Time for Pain Detection and Pain Intensity Level Estimation
4.5.4.1 Image Size vs. Time for Pain Intensity Level Recognition
4.5.5.1 Robustness Against Noise
4.5.5.2 Dimension Reduction
4.5.5.3 Comparison of Pain Detection Results With Other Methods in the Literature
4.6 Conclusion and Future Outlook
5 Computational Intelligence Enabling the Development of Efficient Clinical Decision Support Systems: Case Study of Heart Failure
5.2 Core Components of Diagnoses Based CDSS
5.3 CI Predictor Based on Fuzzy Reasoning Technique
5.4 CI Predictor Based on Multi Layer Perceptron Network
5.5 CI Based CDSS Evaluation Methods
6 Aspect Oriented Modeling of Missing Data Imputation for Internet of Things (IoT) Based Healthcare Infrastructure
6.4 Proposed Missing Data Imputation Service
6.5 Experimentation and Results
7 A Hybrid Computational Intelligence Decision Making Model for Multimedia Cloud Based Applications
7.3.2 Fuzzy Delphi Method
7.3.3 Fuzzy Analytic Hierarchy Process (FAHP)
7.4 The Proposed Hybrid MCDM Model
7.5 A Numeric Application of the Proposed Hybrid Approach
7.6 Conclusion and Future Study
8 Energy-Constrained Workflow Scheduling in Cloud Using E-DSOS Algorithm
8.4 The Application Model
8.5 Experimental Results and Discussion
8.6 Conclusion and Future Work
9 Producing Better Disaster Management Plan in Post-Disaster Situation Using Social Media Mining
9.3.3 Disaster Tweet Ontology
9.3.4 Quantitative Assessment
9.4 Tweet Classification Process
9.4.1 Preprocessing of Tweets
9.4.2 Feature Vector Representation
9.4.2.1 Bag-of-Words Representation
9.4.2.2 Term Frequency-Inverse Document Frequency Representation
9.4.3 Learning Algorithms
9.4.4 Performance Evaluation
9.5 Tweet Classification Algorithms
9.6 Information Extraction
10 Metaheuristic Algorithms: A Comprehensive Review
10.2 Metaheuristics Taxonomies
10.3 Metaphor Based Metaheuristics
10.3.1 Biology Based Metaheuristics
10.3.1.1 Genetic Algorithm (GA)
10.3.1.2 Particle Swarm Optimization (PSO)
10.3.1.3 Water Waves Optimization (WWO)
10.3.1.4 Clonal Selection Algorithm (CLONALG)
10.3.2 Chemistry Based Metaheuristics
10.3.2.1 Chemical Reaction Optimization (CRO)
10.3.2.2 Gases Brownian Motion Optimization (GBMO)
10.3.3 Music Based Metaheuristics
10.3.3.1 Harmony Search (HS)
10.3.3.2 Method of Musical Composition (MMC)
10.3.4 Math Based Metaheuristics
10.3.4.1 Base Optimization Algorithm (BOA)
10.3.4.2 Sine Cosine Algorithm (SCA)
10.3.5 Physics Based Metaheuristics
10.3.5.1 Simulated Annealing (SA)
10.3.5.2 Gravitational Search Algorithm (GSA)
10.3.6 Social and Sport Based Metaheuristics
10.3.6.1 Teaching-Learning-Based Optimization (TLBO)
10.3.6.2 League Championship Algorithm (LCA)
10.4 Non-Metaphor Based Metaheuristics
10.4.2 Variable Neighborhood Search (VNS)
10.4.3 Partial Optimization Metaheuristic Under Special Intensification Conditions (POPMUSIC)
10.5 Variants of Metaheuristics
10.5.1 Upgrading of Metaheuristics
10.5.1.1 Adaptive Metaheuristics
10.5.1.2 Chaotic Metaheuristics
10.5.1.3 Gaussian Based Metaheuristics
10.5.1.4 Metaheuristics Acceleration
10.5.2 Metaheuristics Acclimatization
10.5.2.1 Multi-Objectives Metaheuristics
Non-dominated Sorting Genetic Algorithm (NSGA-II)
Multi-Objective Particle Swarm Optimization With Crowding Distance (MOPSO-CD)
10.5.2.2 Metaheuristics Discretization
10.5.2.3 Metaheuristics Continuousization
10.5.3 Hybridization of Metaheuristics
10.5.3.1 Sequential and Interleaved Hybridization
FPA With Clonal Selection Algorithm (CSA)
10.5.3.2 Metaheuristics in Parallel Schemas
10.6 A Case Study: Weld Beam Design Problem
10.6.1 Weld Beam Design Problem
10.6.2 Experimental Results
10.7 Limitation and New Trends
11 Unsupervised Anomaly Detection for High Dimensional Data-an Exploratory Analysis
11.1.2 Research Contribution
11.2 Preliminary Discussion
11.4 Algorithm Which Do not Consider Subspaces
11.4.2 Approximate Nearest Neighbor Based
11.4.4 Dimension Reduction Based
11.4.5 Feature Selection Based
11.6 Tools and Evaluation
Fraud Detection in Credit Card Transactions
11.8 Proposed Framework DBN-K Means
11.8.1 Experiment and Result
11.8.1.1 Dataset Information
11.8.1.2 Data Preparation
11.8.1.3 Choice of Kernel
11.8.1.4 Choice of Number of Clusters
11.9 Conclusion and Future Work
12 Fog - Driven Healthcare Framework for Security Analysis
12.2.2 Cloud Service Models
12.2.2.1 SaaS (Software-as-a-Service)
12.2.2.2 Platform-as-a-Service
12.2.2.3 Infrastructure-as-a-Service
12.3.1 Secret Key Cryptography (Symmetric Key)
12.3.2 Public Key Cryptography (Asymmetric Key)
12.4 RSA and ECC in Cloud
12.4.1 Performance Comparison of RSA and ECC
12.5.1 Characteristics of Fog Computing
12.5.2 Data Security Issues in Fog Computing (Literature Review)
12.6 Fog Computing Revotilising in Healthcare IoT
12.7.1 RSA Comparison in Cloud and Fog
12.7.1.1 Key Generation Algorithm
12.7.2 ECC Comparison in Cloud and Fog
12.7.2.1 Key Generation Algorithm
12.8 Performance Comparison of RSA and ECC in Fog
12.8.1 Security Comparison of Cloud and Fog
12.10 Conclusion and Future Work
13 Medical Quality of Service Optimization Over Internet of Multimedia Things
13.3 Convergence and Interoperability Between Telemedicine and IoT
13.3.1 Convergence Between Telemedicine and IoT
13.3.2 Interoperability Between Telemedicine and IoT
13.4 Proposed Algorithms for Medical QoS Optimization Over IoT
13.4.1 Modified Lazy Video Transmission Algorithm for Pre-recorded Video Transmission
13.4.2 Online Video Transmission Algorithm for Live Video Transmission
13.4.2.1 Online Video Transmission Algorithm
13.4.2.2 Sliding Window Smoothing in OVTA
13.4.2.3 Slide Length in OVTA
13.4.2.5 Client Buffer Size
13.4.2.6 Lookahead Parameters (P)
13.4.2.7 Server and Client Buffers (Bs and Bc)
13.4.3 Rate Control Video Transmission Algorithm for High Definition Video Transmission
13.5 Medical Quality of Service Mapping Over Joint Telemedicine and IoT
13.6 Experimental Results and Discussion
14 Energy-Efficiency of Tools and Applications on Internet
14.2.1 Energy Consumption of Software
14.2.2 Energy Consumption of Web-Browsers
14.2.3 Energy Consumption of Media Players
14.2.4 Energy Consumption of File Transfer Protocols
14.2.5 Energy Consumption of Wired Secure Protocols
14.2.6 Energy Consumption of Wireless Secure Protocols
14.3 Performance Indicators and Tools for Energy Consumption Measurement
14.3.1 Performance Indicators
14.3.2 Tools for Energy Consumption Measurement
14.5 Experimental Results and Discussion
14.5.2 Experimental Procedures for Windows 7
14.5.3 Experimental Procedures for Linux (Ubuntu 16.04)
14.6 Results and Discussion
14.6.1 Web-Browser Applications for Windows 7 and Ubuntu 16.04
14.6.2 Media Players for Ubuntu 16.04
14.6.3 Media Players for Windows 7
14.6.4 File Transfer Protocols for Windows 7 and Ubuntu 16.04
14.6.5 Wired (SSL/TLS) and Security Protocols for Windows 7 and Ubuntu 16.04
14.6.6 Wireless (WPA2) Security Protocols for Windows 7 and Ubuntu 16.04
14.7 Conclusions and Future Research
15 Transforming Healthcare Via Big Data Analytics
15.1.1 Data-Driven Decision Making
15.1.2 Healthcare Population
15.1.3 The Experience of Patients
15.1.4 Proper Clinical Care
15.1.5.1 Preventative Care Improvement
15.1.5.3 Enhancing the Quality of the Care
15.2 Data Analytics in Healthcare
15.2.1 Lifecycle of Data Analytics in Healthcare
15.2.2 Role of Data Analyst
15.2.3 Healthcare Analytics
15.2.4 Types of Analytics
15.2.4.1 Diagnostic Analytics
15.2.4.2 Descriptive Analytics
15.2.4.3 Predictive Analytics
15.2.4.4 Prescriptive Analytics
15.3 Big Data for Healthcare: Challenges in Deployment
15.3.1 Generate New Knowledge Using Predictive Analytics
15.3.2 Analyze Patient Data in Real-Time Using Big Data Platform Hadoop
15.3.3 Predict Where Emergency Services Are Most Likely to Be Needed
15.3.4 Optimize Care for Patient Populations
15.3.5 Reduce the Cost of Care
15.4.1 Scalable Big Data Analytics
15.4.2 Flattering Management Server-less Insight
15.4.3 Hasty Queries and Scaling Datasets
15.4.4 Unified Cohesive Stream and Batch Processing
15.4.5 Hadoop and Spark in the Cloud Environment
15.4.6 Controlled Databases, Storage of the Object and Its Archival
15.4.7 The Next Arena `The Machine Intelligence'
15.5 Healthcare Essentials: Big Data
15.5.1 Granular Management of Metadata
15.5.2 Management of Privacy
15.5.3 Transformation of Data
15.5.4 Plays Well With Erstwhile
15.5.5 Condense Data Slump
Computational Intelligence for Multimedia Big Data on the Cloud with Engineering Applications
( Intelligent Data-Centric Systems: Sensor Collected Intelligence )
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
