Оглавление
Группа авторов. Advanced Analytics and Deep Learning Models
Table of Contents
List of Table
List of Figures
Guide
Pages
Advanced Analytics and Deep Learning Models
Preface
1. Artificial Intelligence in Language Learning: Practices and Prospects
1.1 Introduction
1.2 Evolution of CALL
1.3 Defining Artificial Intelligence
1.4 Historical Overview of AI in Education and Language Learning
1.5 Implication of Artificial Intelligence in Education
1.5.1 Machine Translation
1.5.2 Chatbots
1.5.3 Automatic Speech Recognition Tools
1.5.4 Autocorrect/Automatic Text Evaluator
1.5.5 Vocabulary Training Applications
1.5.6 Google Docs Speech Recognition
1.5.7 Language MuseTM Activity Palette
1.6 Artificial Intelligence Tools Enhance the Teaching and Learning Processes. 1.6.1 Autonomous Learning
1.6.2 Produce Smart Content
1.6.3 Task Automation
1.6.4 Access to Education for Students with Physical Disabilities
1.7 Conclusion
References
2. Real Estate Price Prediction Using Machine Learning Algorithms
2.1 Introduction
2.2 Literature Review
2.3 Proposed Work. 2.3.1 Methodology
2.3.2 Work Flow
2.3.3 The Dataset
2.3.4 Data Handling. 2.3.4.1 Missing Values and Data Cleaning
2.3.4.2 Feature Engineering
2.3.4.3 Removing Outliers
2.4 Algorithms. 2.4.1 Linear Regression
2.4.2 LASSO Regression
2.4.3 Decision Tree
2.4.4 Support Vector Machine
2.4.5 Random Forest Regressor
2.4.6 XGBoost
2.5 Evaluation Metrics
2.6 Result of Prediction
References
3. Multi-Criteria–Based Entertainment Recommender System Using Clustering Approach
3.1 Introduction
3.2 Work Related Multi-Criteria Recommender System
3.3 Working Principle
3.3.1 Modeling Phase
3.3.2 Prediction Phase
3.3.3 Recommendation Phase
3.3.4 Content-Based Approach
3.3.5 Collaborative Filtering Approach
3.3.6 Knowledge-Based Filtering Approach
3.4 Comparison Among Different Methods
3.4.1 MCRS Exploiting Aspect-Based Sentiment Analysis
3.4.1.1 Discussion and Result
3.4.2 User Preference Learning in Multi-Criteria Recommendation Using Stacked Autoencoders by Tallapally et al
3.4.2.1 Dataset and Evaluation Matrix
3.4.2.2 Training Setting
3.4.2.3 Result
3.4.3 Situation-Aware Multi-Criteria Recommender System: Using Criteria Preferences as Contexts by Zheng
3.4.3.1 Evaluation Setting
3.4.3.2 Experimental Result
3.4.4 Utility-Based Multi-Criteria Recommender Systems by Zheng
3.4.4.1 Experimental Dataset
3.4.4.2 Experimental Result
3.4.5 Multi-Criteria Clustering Approach by Wasid and Ali
3.4.5.1 Experimental Evaluation
3.4.5.2 Result and Analysis
3.5 Advantages of Multi-Criteria Recommender System
3.5.1 Revenue
3.5.2 Customer Satisfaction
3.5.3 Personalization
3.5.4 Discovery
3.5.5 Provide Reports
3.6 Challenges of Multi-Criteria Recommender System
3.6.1 Cold Start Problem
3.6.2 Sparsity Problem
3.6.3 Scalability
3.6.4 Over Specialization Problem
3.6.5 Diversity
3.6.6 Serendipity
3.6.7 Privacy
3.6.8 Shilling Attacks
3.6.9 Gray Sheep
3.7 Conclusion
References
4. Adoption of Machine/Deep Learning in Cloud With a Case Study on Discernment of Cervical Cancer
4.1 Introduction
4.2 Background Study
4.3 Overview of Machine Learning/Deep Learning
4.4 Connection Between Machine Learning/Deep Learning and Cloud Computing
4.5 Machine Learning/Deep Learning Algorithm
4.5.1 Supervised Learning
4.5.2 Unsupervised Learning
4.5.3 Reinforcement or Semi-Supervised Learning
4.5.3.1 Outline of ML Algorithms
4.6 A Project Implementation on Discernment of Cervical Cancer by Using Machine/Deep Learning in Cloud
4.6.1 Proposed Work
4.6.1.1 MRI Dataset
4.6.1.2 Pre Processing
4.6.1.2.1 Image Enhancement
4.6.1.2.2 Image Segmentation
4.6.1.3 Feature Extraction
4.6.2 Design Methodology and Implementation
4.6.3 Results
4.7 Applications
4.7.1 Cognitive Cloud
4.7.2 Chatbots and Smart Personal Assistants
4.7.3 IoT Cloud
4.7.4 Business Intelligence
4.7.5 AI-as-a-Service
4.8 Advantages of Adoption of Cloud in Machine Learning/Deep Learning
4.9 Conclusion
References
5. Machine Learning and Internet of Things–Based Models for Healthcare Monitoring
5.1 Introduction
5.2 Literature Survey
5.3 Interpretable Machine Learning in Healthcare
5.4 Opportunities in Machine Learning for Healthcare
5.5 Why Combining IoT and ML?
5.5.1 ML-IoT Models for Healthcare Monitoring
5.6 Applications of Machine Learning in Medical and Pharma
5.7 Challenges and Future Research Direction
5.8 Conclusion
References
6. Machine Learning–Based Disease Diagnosis and Prediction for E-Healthcare System
6.1 Introduction
6.2 Literature Survey
6.3 Machine Learning Applications in Biomedical Imaging
6.4 Brain Tumor Classification Using Machine Learning and IoT
6.5 Early Detection of Dementia Disease Using Machine Learning and IoT-Based Applications
6.6 IoT and Machine Learning-Based Diseases Prediction and Diagnosis System for EHRs
6.7 Machine Learning Applications for a Real-Time Monitoring of Arrhythmia Patients Using IoT
6.8 IoT and Machine Learning–Based System for Medical Data Mining
6.9 Conclusion and Future Works
References
7. Deep Learning Methods for Data Science
7.1 Introduction
7.2 Convolutional Neural Network
7.2.1 Architecture
7.2.2 Implementation of CNN
7.2.3 Simulation Results
7.2.4 Merits and Demerits
7.2.5 Applications
7.3 Recurrent Neural Network
7.3.1 Architecture
7.3.2 Types of Recurrent Neural Networks
7.3.2.1 Simple Recurrent Neural Networks
7.3.2.2 Long Short-Term Memory Networks
7.3.2.3 Gated Recurrent Units (GRUs)
7.3.3 Merits and Demerits. 7.3.3.1 Merits
7.3.3.2 Demerits
7.3.4 Applications
7.4 Denoising Autoencoder
7.4.1 Architecture
7.4.2 Merits and Demerits
7.4.3 Applications
7.5 Recursive Neural Network (RCNN)
7.5.1 Architecture
7.5.2 Merits and Demerits
7.5.3 Applications
7.6 Deep Reinforcement Learning
7.6.1 Architecture
7.6.2 Merits and Demerits
7.6.3 Applications
7.7 Deep Belief Networks (DBNS)
7.7.1 Architecture
7.7.2 Merits and Demerits
7.7.3 Applications
7.8 Conclusion
References
8. A Proposed LSTM-Based Neuromarketing Model for Consumer Emotional State Evaluation Using EEG
8.1 Introduction
8.2 Background and Motivation
8.2.1 Emotion Model
8.2.2 Neuromarketing and BCI
8.2.3 EEG Signal
8.3 Related Work
8.3.1 Machine Learning
8.3.2 Deep Learning
8.3.2.1 Fast Feed Neural Networks
8.3.2.2 Recurrent Neural Networks
8.3.2.3 Convolutional Neural Networks
8.4 Methodology of Proposed System
8.4.1 DEAP Dataset
8.4.2 Analyzing the Dataset
8.4.3 Long Short-Term Memory
8.4.4 Experimental Setup
8.4.5 Data Set Collection
8.5 Results and Discussions. 8.5.1 LSTM Model Training and Accuracy
8.6 Conclusion
References
9. An Extensive Survey of Applications of Advanced Deep Learning Algorithms on Detection of Neurodegenerative Diseases and the Tackling Procedure in Their Treatment Protocol
9.1 Introduction
9.2 Story of Alzheimer’s Disease
9.3 Datasets. 9.3.1 ADNI
9.3.2 OASIS
9.4 Story of Parkinson’s Disease
9.5 A Review on Learning Algorithms. 9.5.1 Convolutional Neural Network (CNN)
9.5.2 Restricted Boltzmann Machine
9.5.3 Siamese Neural Networks
9.5.4 Residual Network (ResNet)
9.5.5 U-Net
9.5.6 LSTM
9.5.7 Support Vector Machine
9.6 A Review on Methodologies. 9.6.1 Prediction of Alzheimer’s Disease
9.6.2 Prediction of Parkinson’s Disease
9.6.3 Detection of Attacks on Deep Brain Stimulation
9.7 Results and Discussion
9.8 Conclusion
References
10. Emerging Innovations in the Near Future Using Deep Learning Techniques
10.1 Introduction
10.2 Related Work
10.3 Motivation
10.4 Future With Deep Learning/Emerging Innovations in Near Future With Deep Learning
10.4.1 Deep Learning for Image Classification and Processing
10.4.2 Deep Learning for Medical Image Recognition
10.4.3 Computational Intelligence for Facial Recognition
10.4.4 Deep Learning for Clinical and Health Informatics
10.4.5 Fuzzy Logic for Medical Applications
10.4.6 Other Intelligent-Based Methods for Biomedical and Healthcare
10.4.7 Other Applications
10.5 Open Issues and Future Research Directions
10.5.1 Joint Representation Learning From User and Item Content Information
10.5.2 Explainable Recommendation With Deep Learning
10.5.3 Going Deeper for Recommendation
10.5.4 Machine Reasoning for Recommendation
10.5.5 Cross Domain Recommendation With Deep Neural Networks
10.5.6 Deep Multi-Task Learning for Recommendation
10.5.7 Scalability of Deep Neural Networks for Recommendation
10.5.8 Urge for a Better and Unified Evaluation
10.6 Deep Learning: Opportunities and Challenges
10.7 Argument with Machine Learning and Other Available Techniques
10.8 Conclusion With Future Work
Acknowledgement
References
11. Optimization Techniques in Deep Learning Scenarios: An Empirical Comparison
11.1 Introduction
11.1.1 Background and Related Work
11.2 Optimization and Role of Optimizer in DL
11.2.1 Deep Network Architecture
11.2.2 Proper Initialization
11.2.3 Representation, Optimization, and Generalization
11.2.4 Optimization Issues
11.2.5 Stochastic GD Optimization
11.2.6 Stochastic Gradient Descent with Momentum
11.2.7 SGD With Nesterov Momentum
11.3 Various Optimizers in DL Practitioner Scenario
11.3.1 AdaGrad Optimizer
11.3.2 RMSProp
11.3.3 Adam
11.3.4 AdaMax
11.3.5 AMSGrad
11.4 Recent Optimizers in the Pipeline
11.4.1 EVE
11.4.2 RAdam
11.4.3 MAS1 (Mixing ADAM and SGD)
11.4.4 Lottery Ticket Hypothesis
11.5 Experiment and Results. 11.5.1 Web Resource
11.5.2 Resource
11.6 Discussion and Conclusion
References
12. Big Data Platforms
12.1 Visualization in Big Data. 12.1.1 Introduction to Big Data
12.1.2 Techniques of Visualization
12.1.3 Case Study on Data Visualization
12.2 Security in Big Data. 12.2.1 Introduction of Data Breach
12.2.2 Data Security Challenges
12.2.3 Data Breaches
12.2.4 Data Security Achieved
12.2.5 Findings: Case Study of Data Breach
12.3 Conclusion
References
13. Smart City Governance Using Big Data Technologies
13.1 Objective
13.2 Introduction
13.3 Literature Survey
13.4 Smart Governance Status. 13.4.1 International
13.4.2 National
13.5 Methodology and Implementation Approach
13.5.1 Data Generation
13.5.2 Data Acquisition
13.5.3 Data Analytics
13.6 Outcome of the Smart Governance
13.7 Conclusion
References
14. Big Data Analytics With Cloud, Fog, and Edge Computing
14.1 Introduction to Cloud, Fog, and Edge Computing
14.2 Evolution of Computing Terms and Its Related Works
14.3 Motivation
14.4 Importance of Cloud, Fog, and Edge Computing in Various Applications
14.5 Requirement and Importance of Analytics (General) in Cloud, Fog, and Edge Computing
14.6 Existing Tools for Making a Reliable Communication and Discussion of a Use Case (with Respect to Cloud, Fog, and Edge Computing)
14.6.1 CloudSim
14.6.2 SPECI
14.6.3 Green Cloud
14.6.4 OCT (Open Cloud Testbed)
14.6.5 Open Cirrus
14.6.6 GroudSim
14.6.7 Network CloudSim
14.7 Tools Available for Advanced Analytics (for Big Data Stored in Cloud, Fog, and Edge Computing Environment)
14.7.1 Microsoft HDInsight
14.7.2 Skytree
14.7.3 Splice Machine
14.7.4 Spark
14.7.5 Apache SAMOA
14.7.6 Elastic Search
14.7.7 R-Programming
14.8 Importance of Big Data Analytics for Cyber-Security and Privacy for Cloud-IoT Systems
14.8.1 Risk Management
14.8.2 Predictive Models
14.8.3 Secure With Penetration Testing
14.8.4 Bottom Line
14.8.5 Others: Internet of Things-Based Intelligent Applications
14.9 A Use Case with Real World Applications (with Respect to Big Data Analytics) Related to Cloud, Fog, and Edge Computing
14.10 Issues and Challenges Faced by Big Data Analytics (in Cloud, Fog, and Edge Computing Environments)
14.10.1 Cloud Issues
14.11 Opportunities for the Future in Cloud, Fog, and Edge Computing Environments (or Research Gaps)
14.12 Conclusion
References
15. Big Data in Healthcare: Applications and Challenges
15.1 Introduction
15.1.1 Big Data in Healthcare
15.1.2 The 5V’s Healthcare Big Data Characteristics
15.1.2.1 Volume
15.1.2.2 Velocity
15.1.2.3 Variety
15.1.2.4 Veracity
15.1.2.5 Value
15.1.3 Various Varieties of Big Data Analytical (BDA) in Healthcare
15.1.4 Application of Big Data Analytics in Healthcare
15.1.5 Benefits of Big Data in the Health Industry
15.2 Analytical Techniques for Big Data in Healthcare
15.2.1 Platforms and Tools for Healthcare Data
15.3 Challenges
15.3.1 Storage Challenges
15.3.2 Cleaning
15.3.3 Data Quality
15.3.4 Data Security
15.3.5 Missing or Incomplete Data
15.3.6 Information Sharing
15.3.7 Overcoming the Big Data Talent and Cost Limitations
15.3.8 Financial Obstructions
15.3.9 Volume
15.3.10 Technology Adoption
15.4 What is the Eventual Fate of Big Data in Healthcare Services?
15.5 Conclusion
References
16. The Fog/Edge Computing: Challenges, Serious Concerns, and the Road Ahead
16.1 Introduction
16.1.1 Organization of the Work
16.2 Motivation
16.3 Background
16.4 Fog and Edge Computing–Based Applications
16.5 Machine Learning and Internet of Things–Based Cloud, Fog, and Edge Computing Applications
16.6 Threats Mitigated in Fog and Edge Computing–Based Applications
16.7 Critical Challenges and Serious Concerns Toward Fog/Edge Computing and Its Applications
16.8 Possible Countermeasures
16.9 Opportunities for 21st Century Toward Fog and Edge Computing
16.9.1 5G and Edge Computing as Vehicles for Transformation of Mobility in Smart Cities
16.9.2 Artificial Intelligence for Cloud Computing and Edge Computing
16.10 Conclusion
References
Index
Also of Interest. Check out these published and forthcoming titles in the “Next-Generation Computing and Communication Engineering” series from Scrivener Publishing
WILEY END USER LICENSE AGREEMENT
