Big Data Technologies and Applications. 11th and 12th EAI International Conference, BDTA 2021 and BDTA 2022, Virtual Event, December 2021 and 2022 Proceedings

Preface
Conference Organization - BDTA 2021
Conference Organization - BDTA 2022
Contents
Software Engineering and Blockchain Technologies
Using Requirements Clustering to Discover Dependent Requirements for Hidden Impact Analysis
	1 Introduction
	2 Requirements Management
	3 Requirements Clustering
		3.1 Hierarchical Clustering
		3.2 Clustering Using K-Means
	4 Determining the Good Number of Clusters
		4.1 Suggested Model for Calculating Good Number of K Clusters
	5 K Clustering Model Implementation
		5.1 Detailed Model Data Examination
	6 Clustering Model Results
	7 Conclusions
	References
A Proposed Keyword-Based Feature Extraction Approach for Labeling and Classifying Egyptian Mobile Apps Arabic Slang User Requirements Reviews
	1 Introduction
	2 Literature Review
	3 A Proposed Keyword-Based Feature Extraction Approach for Identifying and Classifying of User Requirements from Egyptian Mobile Apps Arabic Slang Reviews (MASR)
		3.1 Phase One: Egyptian Mobile Apps Arabic Slang Reviews (MASR) Collection
		3.2 Phase Two: Keyword-Based Feature Requirement Identification and Classification Approach (KBRIC) for Egyptian (MASR)
		3.3 Phase Three: Automated Supervised Single/Multi-label Classification
		3.4 Phase Four: Evaluation
	4 Results and Discussion
	5 Conclusion and Future Work
	References
A Comparative Study for Anonymizing Datasets with Multiple Sensitive Attributes and Multiple Records
	1 Introduction
		1.1 Our Main Contributions Are as Follows
	2 Related Work
	3 Problem Setting and Privacy Model
	4 Anonymization Algorithms and Methods
	5 1: M-Generalization Algorithm:
	6 Experiments and Analysis Result
		6.1 Information Loss and Data Utility
		6.2 Efficiency
	7 Conclusion and Future Work
	References
A Proposed Framework for Cloud Immunization Information System: Challenges and Opportunities
	1 Introduction
		1.1 Distinction Between Electronic Immunization Registries (EIR) and IIS
		1.2 Purpose of Immunization Information System
		1.3 The Need for an Immunization Information System
	2 The Proposed Framework
		2.1 Cloud Infrastructure
		2.2 Cloud Interoperability
		2.3 Data Sources
		2.4 Registration
		2.5 Public Health
		2.6 The Service Providers
	3 Immunization Information System Challenges and Opportunities
	4 Conclusion
	References
The Role of Block Chain Technology in Reducing Corruption Within the Local Governance in Egypt
	1 Introduction
	2 Literature Review
	3 Defining and Diagnosing Corruption at Local Level
		3.1 Causes of Corruption
		3.2 Procurement Procedures in Local Governments
	4 Improve Transparency and Accountability
	5 Applying Blockchain to Track Procurement Workflows:
	6 ALGORITHM: Smart Contract Place Bid
	7 Conclusion
	References
A Data Brokering Architecture to Guarantee Nonfunctional Requirements in IoT Applications
	1 Introduction
	2 Existing Architecture
		2.1 Volume
		2.2 Variety
		2.3 Velocity
		2.4 Value Extraction
	3 The Proposed New Architecture
	4 Benefits of the New Architecture
	5 Discussion
	6 Conclusion
	References
Machine Learning and Big Data Applications
A Proposed Virtual Learning Model Based on Statistical Analysis of Educational Data of Egypt
	1 Introduction
		1.1 Stages of Learning in Artificial Intelligence
		1.2 Types of Artificial Intelligence
	2 Literature Review
	3 Impact on Learning, Teaching, and Education
	4 Data Analysis of the Educational Data (Case Study of Education in Egypt)
	5 Results and Discussions
	6 A Proposed Virtual Learning Model
	7 Conclusion
	References
Diagnosis Hepatitis B Using Machine and Deep Learning: Survey
	1 Introduction
	2 Background
		2.1 Hepatitis B Definition and Structure
		2.2 Hepatitis B (CHB) Stages
		2.3 Machine Learning
		2.4 Deep Learning
	3 Disease Diagnosis Using Deep Learning and Machine Learning
		3.1 Applying Machine Learning to Identify Liver Problems
		3.2 Deep Learning for Liver Disease Prediction
	4 Diagnosis Hepatitis B Using Machine and Deep Learning: Survey
		4.1 Hepatitis B Using Machine Learning Algorithms
		4.2 Hepatitis B Using Deep Learning Algorithms
	5 Discussion and Limitations (Future Work)
	6 Conclusion
	References
Using Grasshopper Optimization in Big Data
	1 Introduction
	2 Grasshopper Optimization Algorithm
	3 Developments on GOA
		3.1 Grasshopper Optimization Algorithm in Binary
		3.2 Grasshopper Optimization Algorithm Modifications
		3.3 Chaotic Grasshopper Optimization Algorithm
		3.4 Grasshopper Optimization Algorithm Hybridizations
	4 Applications of Grasshopper Optimization Algorithm
		4.1 GOA in Medical Domain
		4.2 GOA in Industry Domain
		4.3 GOA in Agriculture Domain
		4.4 GOA in Education Domain
	5 Conclusion and Future Work
	References
A Semi-supervised Learning Application for Hand Posture Classification
	1 Introduction
	2 Literature Review
	3 Methodology and Implementation
		3.1 Dataset Selection and Pre-processing
		3.2 Tri-training
		3.3 Co-forest
	4 Results and Discussions
		4.1 Evaluation Metrics
	5 Conclusion and Future Work
	References
Explore the Relationship Between Procedural Score Feedback and Subsequent Time Allocation and Learning Outcomes of Learners in a Massive Open Online Course (MOOC)
	1 Introduction
	2 Theoretical Foundation
		2.1 Feedback and Score Feedback
		2.2 Study Time Allocation
		2.3 Learned Industriousness Theory
	3 Hypotheses Development
		3.1 Procedural Score Feedback (PSF) and Learning Outcomes (LO)
		3.2 Study Time Allocation (STA) and Learning Outcomes (LO)
		3.3 Procedural Score Feedback (PSF) and Study Time Allocation (STA)
	4 Methodology
		4.1 Research Context and Participants
		4.2 Research Design
		4.3 Coding Scheme
	5 Data Analysis and Results
		5.1 Sample
		5.2 Measurement Model Evaluation
		5.3 Model Fit Indices
		5.4 Structural Model Evaluation
		5.5 Mediation Analysis
	6 Discussion
	7 Implications for Theory and Practice
	8 Conclusion and Future Work
	References
DoS Attacks Detection in the Network of Drones: An Efficient Decision Tree-Based Model
	1 Introduction
	2 Related Work
	3 Overview of Denial of Service Attack
	4 Proposed DoS Attack Detection Method
	5 Results and Discussion
		5.1 Dataset
		5.2 Scenario 1: Impact of Data Cleaning on Performance
		5.3 Scenario 2: Best Value of the DT Parameter “Max-Depth”
		5.4 Scenario 3: Investigating Other Classifiers (KNN and Random Forest)
		5.5 Analysis of Model Latency
	6 Conclusions and Future Works
	References
Deep Learning Applications and Bio-inspired Optimization
Detecting Fake News Spreaders on Twitter Through Follower Networks
	1 Introduction
	2 Background and Related Work
		2.1 Fake News
		2.2 Fake News Spreaders
		2.3 Twitter
		2.4 Influence/Trust Network
		2.5 BERT Transformer
	3 Proposed Approach
	4 Data Gathering and Pre-processing
		4.1 Twitter Scraping
		4.2 Building the Twitter Follower Network
		4.3 Fake News Data Labeling
	5 User\'s Impact Factor Formulation
	6 Results
		6.1 BERT Classifier
		6.2 User\'s Impact Factor
	7 Conclusion
	8 Future Steps
	References
NODDLE: Node2vec Based Deep Learning Model for Link Prediction
	1 Introduction
	2 Related Work
		2.1 Heuristic Similarity Metrics
		2.2 Machine Learning and Deep Learning
	3 Proposed Approach
		3.1 Problem Statement
		3.2 Data Preparation
		3.3 NODDLE (Integration of NOde2vec and Deep Learning mEthod)
	4 Experiment
		4.1 Datasets
		4.2 Experimental Results and Discussions
	5 Conclusion
	References
Hybrid Coral Reef Optimization Algorithm Employed Local Search Technique for Job Shop Scheduling Problems
	1 Introduction
	2 Related Work
	3 Materials and Methods
		3.1 Representation of JSSP for CRO
		3.2 Objective Function
		3.3 Local Search: Simulated Annealing (SA)
		3.4 Proposal Approaches
	4 Experiment Results and Discussion
		4.1 Parameters Used in the Algorithm
		4.2 Experiment Results
		4.3 Improvement of Search Efficiency
	5 Conclusions
	References
Efficient Human Activity Recognition Based on Grouped Representations of Multimodal Wearable Data
	1 Introduction
	2 Background
	3 Proposed Approach
		3.1 Re-sampling Dataset
		3.2 Specific Features Grouping and Data Abstraction
	4 Datasets
		4.1 Target Activities
		4.2 Datasets Presentation
	5 Evaluation Method
		5.1 Evaluation of Preliminary Re-sampling
		5.2 Evaluation of Grouped Abstraction
		5.3 Classification Method and Evaluation Metrics
	6 Results
		6.1 Re-sampling Performance
		6.2 Grouped Abstraction Performance
		6.3 Visualization of Grouped Abstraction
	7 Discussion
	8 Conclusion
	References
Artificial Intelligence and Data Mining in Education
Pose+Context: A Model for Recognizing Non-verbal Teaching Behavior of Normal College Student
	1 Introduction
	2 Related Work
		2.1 Category of Teachers’ Non-verbal Behaviors
		2.2 Human Pose Estimation and OpenPose
	3 The Pose+Context Model
	4 Experiment
		4.1 Dataset Construction
		4.2 Evaluation Metric
		4.3 Experiment Results
	5 Application
	6 Conclusions and Future Work
	References
Dropout Prediction in MOOC Combining Behavioral Sequence Characteristics
	1 Introduction
	2 Related Work
	3 Dataset
	4 Proposed Method
		4.1 Overview of the Method
		4.2 Data Preprocessing
		4.3 Mining Features
		4.4 Feature Extraction and Modeling
	5 Experiment
		5.1 Experiment Settings
		5.2 Results and Discussion
	6 Conclusion
	References
CVO: Curriculum Vitae Optimization by Recommending Keywords to Undergraduate Students
	1 Introduction
	2 Related Work
		2.1 Candidate Skills Selection
		2.2 Clustering of CVs
		2.3 Recommendation Systems
	3 Methodology
		3.1 Dataframe
		3.2 Data Processing
		3.3 Clustering
		3.4 Classification
	4 Experimental Results
		4.1 Cosine Similarity
		4.2 Recommendation System
	5 Conclusion
	References
Hardware and Software Solutions for Big Data Storing and Management
Big Data in Healthcare Institutions: An Architecture Proposal
	1 Introduction
	2 Main Concepts
		2.1 Big Data in Healthcare Institutions
		2.2 Big Data Engine - Hadoop
	3 Proposed Architecture
		3.1 Structure
		3.2 Hands-On: Proposed Process
	4 Discussion and Conclusions
	References
New Domains and Novel Applications Related to Big Data Technologies
Analysis of Knowledge Map on Rural Culture Tourism in China
	1 Introduction
	2 Data Sources and Research Methods
		2.1 Data Source
		2.2 Research Methods
	3 Analysis of the Trend in Rural Cultural Tourism Research in China
		3.1 Distribution of Years
		3.2 Institutional Distribution Characteristics
		3.3 Analysis of Authors
	4 Analysis on the Research Hotspots of Rural Cultural Tourism in China
		4.1 Keywords Co-word Analysis
		4.2 Keyword Mutation Detection
		4.3 Time Zone Analysis of Keywords
		4.4 Analysis of Keywords Clustering Map
	5 Conclusion and Discussion
	References
A Visual Analysis of E-Government Research in China Based on Co-word Clustering
	1 Introduction
	2 Data Sources and Research Methodology
		2.1 Data Sources and Preparation
		2.2 Method
	3 Analysis and Discussion
		3.1 High Frequency Keyword Word Frequency Statistics and Analysis
		3.2 High Frequency Keyword Co-word Analysis
		3.3 High Frequency Keyword Clustering Analysis
	4 Findings
		4.1 Researches on the Development Trend of E-Government
		4.2 Research on the Integration of E-Government and New Media
		4.3 Research on E-Governance in the Information Society
		4.4 Research on Government Information Management and Data Governance
	5 Summary
	References
Research on Virtual Simulation Teaching Platform Based on Convergent Media
	1 Preface
	2 Achieve Functions of Convergence Media Experiment Platform
	3 Construction of a Converged Media Experiment Platform
		3.1 General Frame Design
		3.2 News Production Design
		3.3 Media Aggregation Module
		3.4 Design of Media Resource Management System
	4 Conclusion
	References:
Author Index