Knowledge-Based Intelligent Information and Engineering Systems : 8th International Conference, KES 2004, Wellington, New Zealand, September 20–25, 2004. Proceedings / / edited by Mircea Gh. Negoita

• Record Nr.: UNINA9910144345803321
• Pubbl/distr/stampa: Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2004
• ISBN: 3-540-30132-1
• Edizione: [1st ed. 2004.]
• Descrizione fisica: 1 online resource (CXVI, 1282 p.)
• Collana: Lecture Notes in Artificial Intelligence ; ; 3213
• Disciplina: 006.3
• Soggetti: Artificial intelligence; Application software; Information storage and retrieval; Computers and civilization; Management information systems; Computer science; Artificial Intelligence; Information Systems Applications (incl. Internet); Information Storage and Retrieval; Computer Appl. in Administrative Data Processing; Computers and Society; Management of Computing and Information Systems
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di bibliografia: Includes bibliographical references at the end of each chapters and index.
• Sommario/riassunto: We were very pleased to once again extend to the delegates and, we are pleased to th say, our friends the warmest of welcomes to the 8 International Conference on Knowledge-Based Intelligent Information and Engineering Systems at Wellington - stitute of Technology in Wellington, New Zealand. The KES conferences attract a wide range of interest. The broad focus of the c- ference series is the theory and applications of computational intelligence and em- gent technologies. ; Once purely a research field, intelligent systems have advanced to the point where their abilities have been incorporated into many conventional appli- tion areas. The quest to encapsulate human knowledge and capabilities in domains such as reasoning, problem solving, sensory analysis, and other complex areas has been avidly pursued. This is because it has been demonstrated that these abilities have definite practical applications. The techniques long ago reached the point where they are being exploited to provide commercial advantages for companies and real beneficial effects on profits. KES 2004 provided a valuable mechanism for delegates to obtain a profound view of the latest intelligent systems research into a range of - gorithms, tools and techniques. KES 2004 also gave delegates the chance to come into contact with those applying intelligent systems in diverse commercial areas. The combination of theory and practice represents a uniquely valuable opportunity for - preciating the full spectrum of intelligent-systems activity and the “state of the art”.

Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part III / / edited by De-Shuang Huang, Zhanjun Si, Yijie Pan

• Record Nr.: UNINA9910879579203321
• Pubbl/distr/stampa: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
• ISBN: 981-9755-88-3
• Edizione: [1st ed. 2024.]
• Descrizione fisica: 1 online resource (XVIII, 519 p. 268 illus., 184 illus. in color.)
• Collana: Lecture Notes in Computer Science, , 1611-3349 ; ; 14864
• Disciplina: 006.3
• Soggetti: Computational intelligence; Computer networks; Machine learning; Application software; Computational Intelligence; Computer Communication Networks; Machine Learning; Computer and Information Systems Applications
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part III -- Neural Networks -- Trust Evaluation with Deep Learning in Online Social Networks: A State-of-the-Art Review -- 1 Introduction -- 2 Analysis and Comparison of Related Work -- 2.1 Graph-Based Neural Networks -- 2.2 Other Deep Learning Method -- 3 Challenges and Open Problems -- 4 Research Direction -- 4.1 Trust Evaluation Based on Ensemble Learning with DNN in OSNs -- 4.2 Cross-Origin Trust Evaluation Based on Deep Learning with a Hyperparameter Auto Optimizer in OSNs -- 5 Conclusion -- References -- Deep Neural Network-Based Intrusion Detection in Internet of Things: A State-of-the-Art Review -- 1 Introduction -- 2 Analysis and Comparison of Related Work -- 2.1 Network Traffic-Based Intrusion Detection -- 2.2 Device Behavior-Based Intrusion Detection -- 3 Challenges and Open Problems -- 4 Research Direction -- 4.1 An IDS Based on Federated Learning and Transfer Learning -- 4.2 An IDS Based on Explainable DNNs -- 5 Conclusion -- References -- CNN-SENet: A Convolutional Neural Network Model for Audio Snoring Detection Based on Channel Attention Mechanism -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Convolutional Neural Networks -- 3.2 SENet -- 4 Experiment -- 4.1 Baseline -- 4.2 Datasets -- 4.3 Data Preprocessing -- 4.4 Evaluation Indicators -- 4.5 Experimental Results -- 5 Summary -- References -- Selecting Effective Triplet Contrastive Loss for Domain Alignment -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Problem Formulation and Notations -- 3.2 Triplet Contrastive Loss -- 3.3 Model Structure -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Results and Discussion -- 5 Conclusion -- References -- RCSnet--Flower Classification Network Design Based on Transfer Learning and Channel Attention Mechanism -- 1 Introduction -- 2 Related Work.; 3 Methods -- 3.1 Residual Networks -- 3.2 SENet -- 3.3 Transfer Learning -- 4 Experiment -- 4.1 Baseline -- 4.2 Datasets -- 4.3 Data Preprocessing -- 4.4 Evaluation Indicators -- 4.5 Experimental Results -- 5 Summary -- References -- MDGCL: Message Dropout Graph Contrastive Learning for Recommendation -- 1 Introduction -- 2 Preliminaries -- 2.1 Graph Collaborative Filtering -- 2.2 Graph Contrastive Learning -- 3 Methodology -- 3.1 Analysis of MessageDropout -- 3.2 A Simplified Architecture for GCL -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 5 Conclusion -- References -- Improved CNN Model Using Innovative Adaptive-DropMessage for Gomoku Game -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Adaptive-DropMessage Method -- 3.2 Dilated Depthwise Separable Convolution -- 3.3 Residual Dense Block and SENet Module -- 3.4 Spatial Attention Module -- 3.5 Gomoku-Specific Output Layer -- 4 Experiments and Analysis -- 4.1 Experimental Setup -- 4.2 Game Experiment Results and Analysis -- 5 Conclusion -- References -- A Survey: Feature Fusion Method for Object Detection Field -- 1 Introduction -- 2 Feature Fusion Methods -- 2.1 Simple Topology Fusion Structure -- 2.2 Complex Topology Fusion Structure -- 2.3 Analysis and Summary -- 3 Datasets and Evaluation Indicators -- 3.1 Datasets -- 3.2 Evaluation Indicators -- 4 Trends and Challenges -- 5 Conclusion -- References -- Dual-Branch Collaborative Learning for Visual Question Answering -- 1 Introduction -- 2 Related Work -- 2.1 Visual Question Answering -- 2.2 Graph-Based Visual Relationship Reasoning -- 2.3 Collaborative ; Learning -- 3 Method -- 3.1 Overview -- 3.2 Question Representation and Image Representation -- 3.3 Relational Reasoning Branch -- 3.4 Attention Branch -- 3.5 Dual-Branch Collaborative Learning -- 3.6 Joint Predict -- 4 Experiments.; 4.1 Datasets and Implementation Detail -- 4.2 Ablation Experiment -- 4.3 Comparison with SOTAs -- 4.4 Qualitative Analysis -- 5 Conclusion -- References -- SCAI: A Spectral Data Classification Framework with Adaptive Inference for Rapid and Portable Identification of Chinese Liquors -- 1 Introduction -- 2 Methodology -- 2.1 SCAI: Early-Exit with Self-distillation -- 2.2 SCAI+: SCAI with PA-ResNet -- 3 Experiment -- 3.1 Experiment Instrument -- 3.2 Datasets -- 3.3 Baselines -- 3.4 Common Performance Result -- 3.5 Application Performance Result -- 3.6 Self-distillation Training Analysis -- 4 Conclusion -- References -- EfficientPose: A Lightweight and Efficient Model with Transformer for Human Pose Estimation -- 1 Introduction -- 2 Related Work -- 2.1 Human Pose Estimation -- 2.2 Atrous Convolution and ASPP -- 3 Methods -- 3.1 EfficientPose Architecture -- 3.2 Efficient Bottleneck Block (EBB) -- 3.3 Transformer Encoder -- 3.4 Iterative Training Strategy -- 4 Experiments -- 4.1 Implementation Results -- 4.2 Ablations -- 5 Conclusion -- References -- Enhanced Chinese Named Entity Recognition with Transformer-Based Multi-feature Fusion -- 1 Introduction -- 2 Related Work -- 2.1 Chinese NER Based on Lexical Enhancement -- 2.2 Chinese NER with Fusion of Glyph Features -- 2.3 Feature Fusion in Chinese NER -- 3 Method -- 3.1 Text Representation Layer -- 3.2 Sequence Encoding Layer -- 3.3 Sequence Decoding Layer -- 4 Experiments -- 4.1 Results and Analysis -- 5 Conclusion -- References -- YOLO-Fire: A Fire Detection Algorithm Based on YOLO -- 1 Introduction -- 2 YOLO-Fire -- 2.1 SimpleC3 -- 2.2 Dynamic Upsampler -- 2.3 Focal WIoU-Loss -- 3 Experiments -- 3.1 Implementation Details -- 3.2 Ablation Studies -- 3.3 Experimental Results Analysis -- 4 Conclusion -- References -- From Vision to Sound: The Application of ViT-LSTM in Music Sequence -- 1 Introduction.; 2 Related Work -- 3 Methods -- 3.1 Dataset Definition -- 3.2 Model Construction -- 4 Experiment -- 4.1 Data Processing -- 4.2 Performance Evaluation -- 5 Conclusion -- References -- Graph Convolution Recommendation Algorithm Integrating Multi-relationship Preferences -- 1 Introduction -- 2 Graph Convolution Recommendation Algorithm Integrating Multi-relationship Preferences -- 2.1 User Feature Embedding Propagation -- 2.2 Item Feature Embedding Propagation -- 2.3 Predict -- 2.4 Model Optimization -- 3 Experimental Design and Result Analysis -- 3.1 Experimental Data Set -- 3.2 Evaluation Indicators -- 3.3 Experimental Settings -- 3.4 Experimental Results -- 3.5 Ablation Analysis -- 4 Conclusion -- References -- Temporal Sequential Wave Neural Network for Solving the Optimal Cognitive Subgraph Query Problem -- 1 Introduction -- 2 Definition of the Problem -- 3 Temporal Sequential Wave Neural Network -- 3.1 Design of Temporal Sequential Wave Neural Network -- 3.2 TSWNN Algorithm -- 3.3 Time Complexity Analysis of TSWNN Algorithm -- 4 Example of TSWNN Algorithm -- 5 Experimentation -- 5.1 Experimental Results with Different Number of Nodes -- 5.2 Experimental Results with Different Number of Sides -- 5.3 Experimental Results with Different Limiting Times -- 6 Conclusion -- References -- Joint Prior Relation Enhancement and Non-autoregressive Decoding for Document-Level Event Extraction -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Entity Mention Recognition -- 3.2 Prior Relation Enhancement Encoding -- 3.3 Event Argument Combination Recognition -- 3.4 Event Type Detection -- 3.5 ; Event Record Extraction -- 4 Experiments -- 4.1 Datasets -- 4.2 Baselines and Metric -- 4.3 Main Results -- 4.4 Ablation Study -- 5 Conclusions -- References -- Intrusion Detection System Based on ViTCycleGAN and Rules -- 1 Introduction -- 2 Related Work.; 3 Methodologies -- 3.1 Cycle-Consistent Generative Adversarial Network (CycleGAN) -- 3.2 Vision Transformer -- 3.3 Intrusion Detection System: ViTCycleGAN -- 4 Experiments -- 4.1 Dataset -- 4.2 Data Preprocessing -- 4.3 Performance Evaluation of ViTCyleGAN Intrusion Detection System -- 5 Conclusion -- References -- DFT-3DLaneNet: Dual-Frequency Domain Enhanced Transformer for 3D Lane Detection -- 1 Introduction -- 2 Related Work -- 2.1 2D Lane Detection -- 2.2 3D Lane Detection -- 2.3 Frequency Domain Image Processing -- 3 Method -- 3.1 Frequency Domain Feature Extraction -- 3.2 Dual-Channel High-Frequency Feature Enhancement -- 3.3 Cross-channel Low-Frequency Attention -- 3.4 Dual-Frequency Domain Deformable Attention -- 3.5 Prediction and Loss -- 4 Experiment -- 4.1 Datasets and Metrics -- 4.2 Implementation Details -- 4.3 Comparisons with State-of-the-Arts -- 4.4 Ablation Studies -- 5 Conclusions -- References -- Correlation Matters: A Stock Price Predication Model Based on the Graph Convolutional Network -- 1 Introduction -- 2 Related Work -- 2.1 Stock Price Prediction -- 2.2 Graph Convolutional Network -- 3 Problem Formulation -- 4 StockGCN -- 4.1 Graph Construction -- 4.2 Framework of StockGCN -- 5 Experiments -- 5.1 Datasets -- 5.2 Preprocessing -- 5.3 Baselines -- 5.4 Result Analysis -- 5.5 Ablation Study -- 6 Conclusion -- References -- Coformer: Collaborative Transformer for Medical Image Segmentation -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Encoder -- 3.2 Multi-scale Representation Fusion Module (MRF) -- 3.3 Decoder -- 3.4 Loss Function -- 4 Experiments -- 4.1 Dataset -- 4.2 Implementation Details -- 4.3 Evaluation Results -- 5 Conclusion -- References -- FRMM: Feature Reprojection for Exemplar-Free Class-Incremental Learning -- 1 Introduction -- 2 Methods -- 2.1 Problem Statement and Framework -- 2.2 Feature Reprojection.; 2.3 Ensemble of Two Experts.
• Sommario/riassunto: This 13-volume set LNCS 14862-14874 constitutes - in conjunction with the 6-volume set LNAI 14875-14880 and the two-volume set LNBI 14881-14882 - the refereed proceedings of the 20th International Conference on Intelligent Computing, ICIC 2024, held in Tianjin, China, during August 5-8, 2024. The total of 863 regular papers were carefully reviewed and selected from 2189 submissions. This year, the conference concentrated mainly on the theories and methodologies as well as the emerging applications of intelligent computing. Its aim was to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. Therefore, the theme for this conference was "Advanced Intelligent Computing Technology and Applications". Papers that focused on this theme were solicited, addressing theories, methodologies, and applications in science and technology.