00809nam0 22002291i 450 UON0013610520231205102821.37320020107d1967 |0itac50 bamalIN|||| 1||||NamovakamK. K. Kurup[s.l.][s.n.]196788 p.19 cmSI VI MMSUBCONT. INDIANO - LETTERATURE DRAVIDICHE MINORI - MALAYALAMAKURUPK. K. N.UONV012741641239ITSOL20240220RICASIBA - SISTEMA BIBLIOTECARIO DI ATENEOUONSIUON00136105SIBA - SISTEMA BIBLIOTECARIO DI ATENEOSI SI VI MM 439 SI SA 64861 5 439 Namovakam1315712UNIOR12828nam 22006855 450 991088699790332120251003105535.03-031-70248-410.1007/978-3-031-70248-8(CKB)34868733800041(MiAaPQ)EBC31652222(Au-PeEL)EBL31652222(DE-He213)978-3-031-70248-8(EXLCZ)993486873380004120240907d2024 u| 0engur|||||||||||txtrdacontentcrdamediacrrdacarrierAdvances in Computational Collective Intelligence 16th International Conference, ICCCI 2024, Leipzig, Germany, September 9–11, 2024, Proceedings, Part I /edited by Ngoc-Than Nguyen, Bogdan Franczyk, André Ludwig, Manuel Nunez, Jan Treur, Gottfried Vossen, Adrianna Kozierkiewicz1st ed. 2024.Cham :Springer Nature Switzerland :Imprint: Springer,2024.1 online resource (430 pages)Communications in Computer and Information Science,1865-0937 ;21653-031-70247-6 Includes bibliographical references and index.Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Collective Intelligence and Collective Decision-Making -- Formalization of Agent-Based Model of Group Learning -- 1 Introduction -- 2 Environment -- 2.1 Students and Teachers -- 2.2 Phases of Learning -- 3 Model -- 3.1 Agents -- 3.2 Groups -- 3.3 Agent's Knowledge -- 3.4 Agent Characteristics -- 4 Example -- 5 Conclusion -- References -- Music Genre Classification Using Hybrid Committees and Voting Mechanisms -- 1 Introduction -- 1.1 Related Work -- 1.2 Contribution -- 2 Outline of the System -- 2.1 Used Dataset -- 2.2 Used Classifiers -- 3 Voting Systems -- 4 Experimental Results -- 4.1 Classifiers -- 4.2 Classifiers Committee -- 5 Conclusions and Future Work -- References -- Towards Practical Large Scale Traffic Model of Electric Transportation -- 1 Introduction -- 2 Related Works -- 3 Basic Concepts in Simulation -- 4 Agent Model -- 5 Results -- 6 Conclusions -- References -- A Systematic Literature Review on Affective Computing Techniques for Workplace Stress Detection -- 1 Introduction -- 2 Background and Related Works -- 2.1 Stress at Work -- 2.2 Related Works -- 3 Systematic Research Papers Collection Methodology -- 4 SLR Results -- 4.1 RQ1: Which Context for Stress at Work Assessment? -- 4.2 RQ2: Which Method of Data Collection for Stress Assessment? -- 4.3 RQ3: How is Collected Stress-Related Data Analyzed? -- 5 RQ4: What Challenges and How Are They Addressed? -- 6 Conclusion -- References -- Rough Set Decision Rules for Usage-Based Churn Modeling in Mobile Telecommunications -- 1 Introduction -- 2 Methodology and Basic Concepts -- 3 Experiments Results and Comparisons -- 3.1 Source Data and Features -- 3.2 Classification Quality Evaluation -- 3.3 Analysis of Rough Set Rules Generation -- 4 Conclusions -- References -- Deep Learning Techniques.CNN Classifier for Helicobacter Pylori Detection in Immunohistochemically Stained Gastric WSI -- 1 Introduction -- 1.1 State-of-the-Art -- 2 Detection of H. Pylori Using CNN -- 3 Experiments -- 3.1 Results -- 4 Conclusions -- References -- Complete Convolutional Neural Networks Environment for Computer Vision Problems With Nvidia Drive AGX Xavier -- 1 Introduction -- 2 Related Work -- 3 Problem Description -- 4 Methods -- 4.1 Environment Concept -- 4.2 Working Hours -- 4.3 Outside Working Hours -- 5 Experiment -- 6 Discussion -- 7 Future Work -- 8 Conclusions -- References -- The Development of an Application-Specific Instruction Set Processor Specialized on a Convolutional Neural Network Trained on MNIST -- 1 Introduction -- 2 Related Work -- 3 Methods -- 4 Obtained Results -- 5 Future Work -- 6 Conclusions -- References -- Detection and Localization of Covid-19 on Chest Radiographs by Deep Learning Algorithms -- 1 Introduction -- 2 Related Word -- 3 Materials and Methods -- 3.1 Dataset -- 3.2 Proposed Method -- 4 Results -- 4.1 Experimentation 1: Binary Classification -- 4.2 Experimentation 2: Three-Class Classification -- 4.3 Experimentation 3: Ensemble Learning -- 4.4 Localization and Visualization of Lesions for Radiographs Classified as COVID and Pneumonia -- 5 Conclusions -- References -- Big Textual Data Analytics Using Transformer-Based Deep Learning for Decision Making -- 1 Introduction -- 1.1 Context and Issues -- 1.2 Contribution -- 1.3 Paper Organization -- 2 Releated Work -- 3 Proposed Decision-Making Approach -- 3.1 Pre-Processing : Big Data Analytics -- 3.2 Classification : Deep Learning -- 4 Experimental Study of the Proposed Approach -- 4.1 Evaluation Environment -- 4.2 Experimental Study and Results Study -- 5 Conclusions -- 5.1 Summary -- 5.2 Prospects -- References.Multistep Time Series Forecasting of Energy Consumption Based on Stacked Deep LSTM Network Architecture -- 1 Introduction -- 2 Deep Neural Networks for Time-Series Forecasting: Related Work -- 3 Stacking LSTMs for Time Series Forecasting -- 4 Model Optimization -- 5 Experiments and Results -- 5.1 Model Architecture -- 5.2 Training and Validation -- 5.3 Future Forecasting -- 6 Conclusion -- References -- On the Effect of Quantization on Deep Neural Networks Performance -- 1 Introduction -- 2 Related Work -- 2.1 Neural Network Quantization -- 2.2 Performance of Quantized Models -- 3 Performance Evaluation -- 3.1 Evaluation Performance Techniques -- 4 Experiments -- 4.1 Evaluation Metrics -- 4.2 Clean Accuracy -- 4.3 Uncertainty Quantification -- 4.4 Sensitivity Analysis -- 4.5 Adversarial Attacks -- 5 Conclusion -- References -- Natural Language Processing -- Three-Stage Extraction of Spatial Relationships Using Markers -- 1 Introduction -- 2 Related Works -- 3 Datasets -- 4 Approach Used -- 4.1 Selection of SIs -- 4.2 SI-Driven Selection of TRs and LDs -- 4.3 Building Sample Representation -- 4.4 Classification -- 5 Discussion and Extension -- 6 Experiments -- 6.1 Evaluation Settings -- 6.2 CLEF2017-mSpRL -- 6.3 SpaceEval -- 6.4 PST -- 7 Results -- 8 Ablation Study -- 9 Limitations -- 10 Conclusion -- References -- A Quadruplication Multilingual and Multilevel Topic Seeding Approach Towards a Bottom-Up Graph Generation and Enhancement -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Step 1: Data Preparation -- 3.2 Step 2: Initial Training -- 3.3 Steps 3: Second Training -- 3.4 Step 4 and 5: Third and Fourth Training -- 4 Experimentation -- 4.1 Experimentation Settings -- 4.2 Experimental Results and Discussion -- 5 Conclusion and Future Work -- References -- Question Answering System to Answer Questions About Technical Documentation.1 Introduction -- 2 Related Work -- 3 Dataset -- 4 Proposed Solution -- 4.1 Indexing Pipeline -- 4.2 Query Pipeline -- 5 Results -- 5.1 Retriever Evaluation -- 5.2 Reader Evaluation -- 6 Solution Variants -- 7 Qualitative Analysis -- 8 Discussion -- References -- Interpretable Dense Embedding for Large-Scale Textual Data via Fast Fuzzy Clustering -- 1 Introduction -- 2 Related Works -- 3 Description of the Proposed Text Vectorization Method -- 3.1 Forming the Target Dictionary -- 3.2 Grouping Words According to Their Semantic and Thematic Relatedness -- 3.3 Fuzzy Clustering of Word Vectors -- 3.4 The Process of Text Embedding Construction -- 4 Experimental Setup -- 4.1 Description of the Text Corpus -- 4.2 First Step: Text Preprocessing and Dictionary Construction -- 4.3 Second Step: Grouping of the Dictionary Words According to Their Thematic Relatedness -- 4.4 Third Step: Merging of the Clusters to Obtain Thematic Categories -- 4.5 Fourth Step: Construction of Text Embeddings -- 4.6 Assessing the Quality of the Proposed Embeddings in Solving the Task of Thematic Categorization of Publications -- 5 Experimental Results -- 5.1 Random Simulation of k Neighbors -- 5.2 Sparse Vector Representation Based on the Word Frequencies -- 5.3 Text Embeddings Based on Neural Networks Model -- 5.4 Proposed Text Embeddings -- 5.5 Conclusions -- References -- M2DS: Multilingual Dataset for Multi-document Summarisation -- 1 Introduction -- 2 Related Work -- 2.1 Major MDS Datasets Across Diverse Domains -- 2.2 Existing MDS Models -- 2.3 Prior Work on Multilingual MDS -- 2.4 Existing Multilingual Text Summarisation Datasets -- 3 M2DS Dataset -- 3.1 Dataset Development -- 3.2 Dataset Composition -- 3.3 Dataset Comparison -- 4 Experiments -- 4.1 Pre-trained Model Selection -- 4.2 Baselines -- 5 Analysis and Discussion -- 6 Conclusion and Future Directions -- References.uMentor: LLM-Powered Chatbot for Harnessing Technology Books in Digital Library -- 1 Introduction -- 2 Background and Related Works -- 3 Proposed Method -- 3.1 Approach Direction -- 3.2 Instruction Dataset Preparation -- 3.3 LLM Fine-Tuning Process -- 3.4 AI-Powered Academic Mentor -- 4 Experiments and Evaluation -- 4.1 Experiment Environment -- 4.2 Experiment Results -- 4.3 Evaluation and Discussion -- 4.4 LLM Ablation Study and Analysis -- 5 Conclusions -- References -- Advancements in Text Subjectivity Analysis: From Simple Approaches to BERT-Based Models and Generalization Assessments -- 1 Introduction -- 2 Related Work -- 3 Models -- 3.1 Our Pipeline -- 3.2 Pre-built Models -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Experimental Results -- 5 Discussion -- 6 Conclusion -- 7 Appendix -- References -- Hybrid Approach Text Generation for Low-Resource Language -- 1 Introduction -- 2 Related Works -- 3 Problems of Text Generation in the Turkish and Kazakh Languages -- 4 Description of the Hybrid Text Generation Approach in the Low Resource Language -- 4.1 Data Collection and Processing -- 4.2 Structural and Semantic Properties of Text in Kazakh Language -- 5 Practical Results -- 6 Conclusion and Future Work -- References -- Data Mining and Machine Learning -- ROCKET with Dynamic Convolution for Time Series Classification -- 1 Introduction -- 2 Background -- 2.1 Problem Formulation -- 2.2 Dynamic Time Warping -- 2.3 Dynamic Convolution -- 2.4 ROCKET -- 3 DynamicROCKET -- 4 Experimental Evaluation -- 4.1 Data -- 4.2 Baselines -- 4.3 Experimental Protocol -- 4.4 Implementation -- 4.5 Results -- 4.6 Discussion -- 5 Conclusions and Outlook -- References -- Prediction of the Delay Time of Public Transportation Using Machine Learning -- 1 Introduction -- 2 Related Works -- 3 Research Methodology -- 3.1 Data Processing.3.2 Methods.This two-volume set CCIS 2165-2166 constitutes the refereed proceedings of the 16th International Conference on Computational Collective Intelligence, ICCCI 2024, held in Leipzig, Germany, during September 9–11, 2024. The 67 full papers included in this book were carefully reviewed and selected from 234 submissions. The main track, covering the methodology and applications of CCI, included: collective decision-making, data fusion, deep learning techniques, natural language processing, data mining and machine learning, social networks and intelligent systems, optimization, computer vision, knowledge engineering and application, as well as Internet of Things: technologies and applications. The special sessions, covering some specific topics of particular interest, included: cooperative strategies for decision making and optimization, security and reliability of information, networks and social media, anomalies detection, machine learning, deep learning, digital image processing, artificial intelligence, speech communication, IOT applications, natural language processing, innovative applications in data science.Communications in Computer and Information Science,1865-0937 ;2165Computer networksEducationData processingApplication softwareComputer visionComputer Communication NetworksComputers and EducationComputer and Information Systems ApplicationsComputer VisionComputer networks.EducationData processing.Application software.Computer vision.Computer Communication Networks.Computers and Education.Computer and Information Systems Applications.Computer Vision.006.3Nguyen Ngoc-ThanMiAaPQMiAaPQMiAaPQBOOK9910886997903321Advances in Computational Collective Intelligence2158878UNINA