Distributed computing and intelligent technology : 18th international conference, ICDCIT 2022, Bhubaneswar, India, January 19-23, 2022 : proceedings

This book constitutes the proceedings of the 18th International Conference on Distributed Computing and Intelligent Technology, ICDCIT 2022, held in Bhubaneswar, India, in January 20212. The 11 full papers presented together with 4 short papers were carefully reviewed and selected from 50 submissions. There are also 4 invited papers included. The papers were organized in topical sections named: invited papers, distributed computing and intelligent technology. Preface Organization Contents Invited Papers Modern AI/ML Methods for Healthcare: Opportunities and Challenges 1 Introduction 2 AI in Medical Diagnosis 2.1 Cardiology 2.2 Pulmonology 2.3 Dermatology 2.4 Neurology and Psychiatry 2.5 Oncology 3 AI in Medical Prognosis 3.1 Cancer Progression Studies 3.2 Mortality Prediction Studies 4 AI in Medical Treatment 5 AI in COVID-19 5.1 AI Based COVID-19 Diagnosis 5.2 AI Based COVID-19 Prognosis 5.3 Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction 5.4 COVID-19 Risk Stratification and Mortality Prediction in Hospitalized Indian Patients 6 Summary and Outlook References An Introduction to Graph Neural Networks from a Distributed Computing Perspective 1 Introduction 2 Model and Background 2.1 Preliminaries 2.2 Graph Neural Networks 2.3 Comparison to Distributed Algorithms 2.4 Applications of GNNs 3 Limits of GNNs: The WL-Test 3.1 Different Aggregation Methods 3.2 The Weisfeiler-Lehman Algorithm 3.3 The WL-Test and GNNs 4 More Expressive GNNs 4.1 Port Numbers 4.2 Domain-Specific Extra Features 4.3 Random Features 4.4 GNNs with Dropouts 4.5 Metagraph-Based Approaches 5 Conclusion References Towards Temporally Uncertain Explainable AI Planning 1 Introduction 1.1 Explainable AI Planning in Literature 2 Contrastive Explanations in Plan Exploration 2.1 Planning Model and Capability 2.2 Iterative Plan Exploration 2.3 Temporal, Numeric, and Probabilistic Model Restrictions 3 Optimisation Under Temporal Uncertainty 3.1 Temporal Networks and Controllability 3.2 PSTN Strong Controllability and Risk in Literature 3.3 On Pareto Optimal Schedules to PSTNs 4 Discussion and Conclusion References The Impact of Synchronization in Parallel Stochastic Gradient Descent 1 Introduction 2 Preliminaries 2.1 SGD and Machine Learning 2.2 Performance Metrics 3 Parallel SGD 3.1 Synchronous SGD 3.2 Asynchronous Parallel SGD 4 Problems and Challenges with Parallel SGD 4.1 Scalability 4.2 Convergence Under Asynchrony 4.3 Benchmarking and Evaluation 5 Our Work on Parallelizing SGD 5.1 Convergence of Staleness-Adaptive SGD 5.2 A Framework for Lock-Freedom and Consistency 6 Conclusions References Distributed Computing A Distributed Algorithm for Constructing an Independent Dominating Set 1 Introduction 2 Preliminaries and Problem Definition 3 The Proposed Algorithm 3.1 Construction of the Dominating Set (Step 1) 3.2 Construction of Vertex Cover (Step 2) 3.3 Independent Set Construction and Graph Shrinking (Step 3) 4 Experimental Evaluation 5 Concluding Remarks References An Approach to Cost Minimization with EC2 Spot Instances Using VM Based Migration Policy 1 Introduction 2 Related Work 3 Problem Statement 4 Proposed Algorithmic Modelling 5 Implementation 6 Data Aggregation and Preprocessing 7 Results and Analysis 7.1 Cost Analysis 7.2 Sliding Window Duration Analysis 7.3 SLA Violation Analysis 8 Limitations and Future Work 9 Conclusion References Transforming Medical Resource Utilization Process to Verifiable Timed Automata Models in Cyber-Physical Systems 1 Introduction 2 Background and Related Work 2.1 Usefulness of UPPAAL in Healthcare Applications 2.2 Model-Based Development: Tools and Programming Languages 2.3 Defining Formalism Using Temporal Logic 3 Design and Modeling of Medical Resource Utilization Process 3.1 Case Study of Caregiver Assignment 3.2 Model Implementation Using UPPAAL 3.3 Concurrent Execution of Patient and Caregiver Processes in UPPAAL 3.4 Model Verification 4 Conclusion References An SDN Implemented Adaptive Load Balancing Scheme for Mobile Networks 1 Introduction 1.1 SDN Overview 2 Problem Formulation 3 Self-adaptive Load Balancing Scheme for MANET 3.1 Description of SALB Scheme 4 Experimental Evaluation 4.1 Methodology 4.2 Performance Evaluation 4.3 Accuracy Verification 5 Conclusion References Rewriting Logic and Petri Nets: A Natural Model for Reconfigurable Distributed Systems 1 Introduction 2 PT Nets 2.1 Multisets 2.2 Place/Transition (PT) Nets with Inhibitor Arcs 3 Rewriting Logic and the Maude system 4 Running Example: A Fault-Tolerant MS 5 Formalization of Rewritable PT Systems with Maude 5.1 Base Notions and Properties of Rewritable PT Systems 6 Examples of Formal Verification 6.1 Exploiting PT Net Structural Analysis 7 Conclusion References MCDPS: An Improved Global Scheduling Algorithm for Multiprocessor Mixed-Criticality Systems 1 Introduction 2 System Model 2.1 Literature Survey 3 Our Algorithm 3.1 Special Case: At Least K HI-Criticality Tasks Meet Their Deadline in HI-Criticality Scenario 4 Results and Discussion 5 Conclusion References Replication Based Fault Tolerance Approach for Cloud 1 Introduction 2 Related Works 3 Problem Description 4 Proposed Algorithm 5 Result 6 Conclusion References Intelligent Technology A Comparative Study on MFCC and Fundamental Frequency Based Speech Emotion Classification 1 Introduction 2 Literature Review 3 Methodology 3.1 Database 3.2 Features 3.3 Support Vector Machines 4 Results 5 Conclusion References Efficient Traffic Routing in Smart Cities to Minimize Evacuation Time During Disasters 1 Introduction 2 Basic Ideas 3 Formulation of the Problem 3.1 Optimal Traffic Distribution for Flow Type 1 3.2 Optimal Traffic Distribution for Flow Type 2 3.3 Optimal Traffic Distribution for Flow Type 3 4 Algorithm 5 Simulation Results 6 Conclusion References Early Detection of Parkinson’s Disease as a Pre-diagnosis Tool Using Various Classification Techniques on Vocal Features 1 Introduction 2 Related Works 3 Methodology 3.1 Signal Acquisition 3.2 Signal Pre-processing 3.3 Feature Engineering 3.4 Classification Algorithms 3.5 Training and Test Case Classification 4 Results 5 Conclusion 6 Application 7 Future Work References Extracting Emotion Quotient of Viral Information Over Twitter 1 Introduction 1.1 Motivation and Research Questions 2 Related Work 2.1 Sentiment Analysis Over Soft Data (Reviews/Posts/Viral Information) 2.2 Emotion Quotients (EQs) Over Soft Data 3 Proposed Strategy 3.1 Conceptual Framework 3.2 Generating Sentiment Level (SL) and Emotional Quotient (EQ) 3.3 System Use-Cases of Sentiment and Emotional Analytics 3.4 Working Example 4 Performance Assessment and Evaluation 4.1 Data Settings 4.2 Performance on Sentiments and Emotion Quotients (EQs) Estimation 4.3 Accuracy on Sentiment and Emotional Quotient Generation 4.4 Overall Retrieval Performance 5 Conclusion References A Novel Modified Harmonic Mean Combined with Cohesion Score for Multi-document Summarization 1 Introduction 1.1 Motivation 1.2 Contribution 2 Proposed Approach 2.1 Generating Extractive Gold Summaries 3 Experimental Framework 3.1 ROUGE-N Score Evaluation 3.2 Performance Comparison on DUC-2002 Dataset 3.3 Performance Comparison on DUC-2006 Dataset 3.4 Performance Comparisons Using Summary Readability 4 Conclusion References Multi-channel Deep Model for Classification of Alzheimer’s Disease Using Transfer Learning 1 Introduction 2 Related Works 3 Methods and Materials 3.1 Data Selection 3.2 Data Preprocessing 3.3 Slice Selection 3.4 Multi-channel Network Architecture 3.5 Ensemble of Multi-channel Model 4 Results and Discussions 4.1 Effect of Base Models and Optimal Value of N 5 Conclusion References Deep Learning and Linguistic Feature Based Automatic Multiple Choice Question Generation from Text 1 Introduction 2 Related Work 3 Methodology 3.1 Extraction 3.2 Summarization 3.3 SynQG 3.4 Distractor Generation 3.5 Paraphrasing 4 Experiments and Results 5 Conclusion References A Deep Multi-kernel Uniform Capsule Approach for Hate Speech Detection 1 Introduction 2 Related Work 3 Methods 3.1 Data Sets 3.2 Classification Model 4 Experiments 4.1 Experimental Setup 4.2 Results 5 Conclusion References Author Index