Intro
Preface
Organization
Contents
Artificial Intelligence and Data Science
AttR2U-Net: Deep Attention Based Approach for Melanoma Skin Cancer Image Segmentation
1 Introduction
2 Background and Related Work
2.1 R2U-Net Architecture
2.2 Attention Mechanism
3 AttR2U-Net Configurations
3.1 AttR2U-Net-V1
3.2 AttR2U-Net-V2
3.3 AttR2U-Net-V3
4 Experiments and Results
4.1 ISIC Dataset
4.2 Experimental Results
5 Conclusion
References
Causality Analysis Method and Model Related to Why-Question Answering in Business Intelligence Context

1 Introduction
2 Causality Analysis Approaches
3 Proposed Causality Perception Model in BI Context
4 Proposed Causality Analysis Method
5 Experimental Study
5.1 Granger Causality Tests
5.2 Association Rules Algorithms Results
6 Conclusion and Future Works
References
Markovian Segmentation of Non-stationary Data Corrupted by Non-stationary Noise
1 Introduction
2 Two-jumping Conditional Triplet Markov Models
2.1 Two-jumping Conditional Triplet Markov Chain
2.2 Two-jumping Conditional Triplet Markov Field
3 Performance Evaluation

3.1 Segmentation of Simulated Images
3.2 Segmentation of Synthetic Images
3.3 Results and Discussion
4 Conclusion
References
Aster: A DSL for Engineering Self-Adaptive Systems
1 Introduction
2 Illustrative Example
3 Modeling the Aircraft Arrival Planning System
3.1 Architecture of the Aircraft Arrival Planning System
3.2 Aster Syntax
4 The Aircraft Arrival Planning System Formal Semantics
4.1 A Petri Net-Based Semantics for Aster
4.2 Generating Formal Specifications
4.3 The Aircraft Arrival System Semantics
5 Conclusion
References

Co-rating Aware Evidential User-Based Collaborative Filtering Recommender System
1 Introduction
2 Dempster-Shafer Theory Basic Concepts
3 Evidential Collaborative Filtering
3.1 A Brief Overview of ECF Research
3.2 Evidential K-Nearest Neighbors
4 Problem Formulation
5 Experimental Evaluation
5.1 Dataset
5.2 Metrics
5.3 Results
6 Conclusion and Perspectives
References
Graph Representation Learning for Covid-19 Drug Repurposing
1 Introduction
2 Related Work
3 Materials and Methods
3.1 Computational Workflow
3.2 Data Collection
3.3 Method

4 Results
4.1 Model Training
4.2 Model Evaluation
4.3 Drugs Ranking and Validation
5 Conclusion
References
A Scalable Adaptive Sampling Based Approach for Big Data Classification
1 Introduction
2 Prior Works in Big Data Sampling
3 Scalable Adaptive Sampling Based on ScaSRS, BLB and Chebyshev Inequality
3.1 Selecting Data with ScaSRS Algorithm
3.2 Learning and Creating Model
3.3 Calculating the Variance
3.4 Improved Sample Accuracy Using Active Learning
3.5 SGDAS Algorithm
4 Results and Discussion
4.1 Test Dataset
4.2 Empirical Results