Info
- Utilizzare la checkbox di selezione a fianco di ciascun documento per attivare le funzionalità di stampa, invio email, download nei formati disponibili del (i) record.
AI in Multidimensional Signals Analysis and Processing : Proceedings of The 3DIT-MSP&DL 2024
| AI in Multidimensional Signals Analysis and Processing : Proceedings of The 3DIT-MSP&DL 2024 |
| Autore | Jain Lakhmi C |
| Edizione | [1st ed.] |
| Pubbl/distr/stampa | Singapore : , : Springer, , 2025 |
| Descrizione fisica | 1 online resource (429 pages) |
| Disciplina | 621.367 |
| Altri autori (Persone) |
KountchevaRoumiana
LiuYingkai |
| Collana | Smart Innovation, Systems and Technologies Series |
| ISBN | 981-9654-08-4 |
| Formato | Materiale a stampa  |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Record Nr. | UNINA-9911028660803321 |
Jain Lakhmi C
|
||
| Singapore : , : Springer, , 2025 | ||
| Materiale a stampa | ||
| Lo trovi qui: Univ. Federico II | ||
| ||
Intelligent 3D Technologies and Augmented Reality : Proceedings of the Fifth International Conference on 3D Imaging Technologies—Multidimensional Signal Processing and Deep Learning, Volume 2 / / edited by Roumen Kountchev (deceased), Srikanta Patnaik, Yingkai Liu, Roumiana Kountcheva
| Intelligent 3D Technologies and Augmented Reality : Proceedings of the Fifth International Conference on 3D Imaging Technologies—Multidimensional Signal Processing and Deep Learning, Volume 2 / / edited by Roumen Kountchev (deceased), Srikanta Patnaik, Yingkai Liu, Roumiana Kountcheva |
| Autore | Kountchev (deceased) Roumen |
| Edizione | [1st ed. 2024.] |
| Pubbl/distr/stampa | Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024 |
| Descrizione fisica | 1 online resource (342 pages) |
| Disciplina | 006.3 |
| Altri autori (Persone) |
PatnaikSrikanta
LiuYingkai KountchevaRoumiana |
| Collana | Smart Innovation, Systems and Technologies |
| Soggetto topico |
Computational intelligence
Artificial intelligence Signal processing Multimedia systems Computational Intelligence Artificial Intelligence Signal, Speech and Image Processing Multimedia Information Systems |
| ISBN | 981-9751-84-5 |
| Formato | Materiale a stampa |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Nota di contenuto | 1. Virtual reality image generation and enhancement based on real-time model simplification -- 2. Deep Landscape Design Evaluation System with Multi-scale Visual Attention Mechanism -- 3. The Role and Effect of Deep Learning in Landscape Design Innovation -- 4. Application of 3D Image Technology and Deep Learning in Landscape Design -- 5. The Influence of University Yoga Course Based on VR Technology on university students' Physical Fitness and Special Sports Skills -- 6. Enhancing Mobile Robot Path Planning through Advanced Deep Reinforcement Learning -- 7. Innovative Application of VR Technology in Ceramic Art Design Exhibition -- 8. Deep Learning-based Species Classification using Joint ResNet and Data Augmentation -- 9. Simulation and Application of Digital Display Model Based on Computer Vision and Virtual Reality -- 10. Chinese Image Description Generation Model Based on Recurrent Fusion Encoding. |
| Record Nr. | UNINA-9910886089703321 |
|
Kountchev (deceased) Roumen
|
||
| Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024 | ||
| Materiale a stampa | ||
| Lo trovi qui: Univ. Federico II | ||
| ||
Multidimensional Signal Processing : Proceedings of the Fifth International Conference on 3D Imaging Technologies--Multidimensional Signal Processing and Deep Learning, Volume 1
| Multidimensional Signal Processing : Proceedings of the Fifth International Conference on 3D Imaging Technologies--Multidimensional Signal Processing and Deep Learning, Volume 1 |
| Autore | Kountchev Roumen |
| Edizione | [1st ed.] |
| Pubbl/distr/stampa | Singapore : , : Springer, , 2024 |
| Descrizione fisica | 1 online resource (400 pages) |
| Altri autori (Persone) |
PatnaikSrikanta
LiuYingkai KountchevaRoumiana |
| Collana | Smart Innovation, Systems and Technologies Series |
| ISBN |
9789819751815
9819751810 |
| Formato | Materiale a stampa |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Nota di contenuto |
Intro -- Preface -- Contents -- About the Editors -- Part I Multidimensional Signal Processing -- 1 Evaluation of Ultrasonic Doppler Signal Quality Based on Deep Learning -- 1.1 Introduction -- 1.2 Related Work -- 1.3 Materials and Methods -- 1.3.1 Short-Time Average Magnitude Difference Function -- 1.3.2 Signal Preprocessing -- 1.3.3 DataSet Creation -- 1.4 The Proposed Model -- 1.4.1 The Network Architecture -- 1.4.2 Convolutional Neural Network -- 1.4.3 Long Short-Term Memory -- 1.5 Results -- 1.5.1 Performance Metrics -- 1.5.2 Experimental Setup -- 1.5.3 Performance Evaluations -- 1.6 Conclusions -- References -- 2 Tensor Compression Based on Tensor Train Decomposition -- 2.1 Background -- 2.2 Basic Principle -- 2.2.1 Singular Value Decomposition SVD -- 2.2.2 Tensor and Tensor Decomposition -- 2.2.3 Higher-Order Singular Value Decomposition (HOSVD) -- 2.2.4 Tensor Train Decomposition (TTD) -- 2.3 Experiments and Analysis of Results -- 2.4 Conclusion -- References -- 3 Digital Twin Technology Approach Based on the Hierarchical IDP Tensor Decomposition -- 3.1 Introduction -- 3.2 AI-Based Model for Industry Applications -- 3.3 New Approaches for Hierarchical Data Analysis -- 3.3.1 Hierarchical Decomposition of a Single 3D Tensor Through IDP Based on Neural Networks (NN) with Convolutional Auto-Encoders (CAE) -- 3.3.2 Brief Description of the Convolutional Auto-Encoder -- 3.3.3 Hierarchical Tensor Sequence Decomposition Through Branched Inverse Difference Pyramid, Based on Convolutional Auto-Encoders -- 3.4 Digital Twin Approach Based on the Hierarchical IDP Tensor Decomposition -- 3.5 Conclusions -- References -- 4 Modeling Technology for Complex Dynamic Operating Environment of Power Grid Based on Digital Twins -- 4.1 Introduction -- 4.2 Digital Twin Technology for Power Grids -- 4.3 Digital Modeling and Model Mapping.
4.4 Multi-mode Data Fusion in Complex and Dynamic Working Environment of Power Grid -- 4.5 Multi-source Comprehensive Reconstruction and Entity Hierarchical Processing of Power Grid Environment -- 4.6 Dynamic Update of Station Panoramic Digital Twin Model -- 4.7 Structured Spatiotemporal Big Data Construction Technology Based on Real-Life Twins -- 4.8 Conclusion -- References -- 5 Design of a Digital Twin Platform Based on Distributed Computing and Resource Optimization Algorithms -- 5.1 Introduction -- 5.2 Design of Digital Twin Platform -- 5.2.1 Design Principles -- 5.2.2 Architecture -- 5.3 Database Design -- 5.4 Experimental Evaluation -- 5.5 Conclusions -- References -- 6 Deep Learning Network Optimization Combining 3D Imaging and Multidimensional Signal Processing -- 6.1 Introduction -- 6.1.1 Research Background and Significance -- 6.1.2 Research Status at Home and Abroad -- 6.1.3 Research Content and Innovation Points of This Article -- 6.2 Theoretical Basis -- 6.2.1 Overview of Deep Learning -- 6.2.2 Three-Dimensional Imaging Technology -- 6.2.3 Multidimensional Signal Processing -- 6.3 Methodology -- 6.3.1 Network Architecture Design -- 6.3.2 Preprocessing of 3D Imaging Data -- 6.3.3 Application of Multidimensional Signal Processing Technology -- 6.4 Experimental Design and Results -- 6.4.1 Experimental Environment and Data Set Description -- 6.4.2 Experimental Methods and Procedures -- 6.4.3 Experimental Results -- 6.5 Result Analysis and Discussion -- 6.5.1 Network Performance Analysis -- 6.5.2 Validity Verification of Experimental Results -- 6.5.3 Discussion of Existing Problems and Limitations -- References -- 7 Time Series Prediction Application of Deep Learning in Multidimensional Signal Processing -- 7.1 Introduction -- 7.1.1 Research Background and Importance. 7.1.2 Challenges of Time Series Forecasting and the Potential of Deep Learning -- 7.1.3 Overview of the Main Contributions and Structure of the Paper -- 7.2 Theoretical Background -- 7.2.1 Basic Concepts of Time Series Forecasting -- 7.2.2 Application of Deep Learning in Time Series Analysis -- 7.2.3 Characteristics and Challenges of Multidimensional Signal Processing -- 7.3 Methodology -- 7.3.1 Formal Definition of the Research Problem -- 7.3.2 Selected Deep Learning Model -- 7.3.3 Data Preprocessing and Feature Extraction -- 7.3.4 Model Training and Parameter Optimization -- 7.3.5 Evaluation Criteria -- 7.3.6 Experimental Setup -- 7.3.7 Result Display -- 7.4 Conclusion -- 7.4.1 Research Summary -- 7.4.2 Limitations of the Study -- 7.4.3 Suggestions for Future Research -- References -- 8 Improving Abstractive Summarization with Graph Sequence Model -- 8.1 Introduction -- 8.2 Related Work -- 8.3 Research with Abstractive Summarization Based on Graph Sequence Model -- 8.3.1 A Subsection Sample -- 8.3.2 Text Sequence Construction Diagram Input -- 8.3.3 Calculation of the LINE with Second-Order Proximity -- 8.3.4 Maximizing Possible Output of the Language Decoder -- 8.4 Experiment and Result -- 8.5 Conclusion -- References -- 9 Advancing Semantic Segmentation and Interpretation of 3D Images Through Integrated Deep Learning and Natural Language Processing Techniques -- 9.1 Introduction -- 9.2 Theoretical Basis -- 9.3 Application of Deep Learning Methods in 3D Image Segmentation -- 9.3.1 Basic Structure and Principles of Convolutional Neural Network (CNN) -- 9.3.2 Feature Extraction and Processing of Three-Dimensional Images -- 9.3.3 Design and Implementation of Segmentation Algorithm -- 9.4 Application of Natural Language Processing in Three-Dimensional Image Interpretation -- 9.4.1 Language Model and Natural Language Understanding. 9.4.2 Conversion Method from Image Segmentation to Language Description -- 9.4.3 Implementation and Optimization of Semantic Interpretation -- 9.5 Design and Implementation of Fusion Methods -- 9.5.1 System Architecture and Workflow -- 9.5.2 Integration Strategy of Deep Learning and Natural Language Processing -- 9.5.3 Optimization and Adjustment of Algorithms -- 9.5.4 Comprehensive Experimental Design and Results -- 9.6 Application Cases and Actual Effect Analysis -- 9.6.1 Application Scenario Description -- 9.6.2 System Performance in Practical Applications -- 9.6.3 Case Studies and Analysis -- 9.7 Conclusion -- References -- 10 Children's Toy Product Design Based on Augmented Reality Technology -- 10.1 Introduction -- 10.2 Forms of Application of Augmented Reality Technology in Children's Toy Design -- 10.2.1 Process Optimization and Information Presentation -- 10.2.2 Enhancing Interactivity and Engagement -- 10.2.3 Entertainment and Personalized Experience -- 10.3 Application Strategies of Augmented Reality Technology in Children's Toy Design -- 10.3.1 Personalized Expression -- 10.3.2 Contextualized Display -- 10.3.3 Socialized Sharing -- 10.3.4 Educational Guidance -- 10.4 Application of Augmented Reality Technology in Children's Toy Design -- 10.4.1 Survey Research Proposal -- 10.4.2 Survey Results -- 10.4.3 "Bunny Run" Design -- 10.4.4 Little Bunny AR Application Development -- 10.4.5 Toy Design Results Show -- 10.5 Conclusion -- References -- Part II Feature Fusion and Human Action Analysis -- 11 Based on the Neural Network Classification of Human Behavior Research -- 11.1 Introduction -- 11.2 Model -- 11.2.1 Behavior Recognition Based on Two-Stream Convolutional Networks -- 11.2.2 Extraction of Optical Flow -- 11.2.3 Two-Flow Hybrid Neural Network with Static and Dynamic Features -- 11.3 Experiment -- 11.3.1 Experimental Environment. 11.3.2 Model Implementation Details -- 11.3.3 Experimental Result -- 11.4 Conclusion -- References -- 12 Development of an Independent Adversarial Sample Detection Model, Based on Image Features -- 12.1 Introduction -- 12.2 Related Work -- 12.3 System Design -- 12.4 Analysis of Performance -- 12.5 Conclusions -- 12.6 Discussion -- References -- 13 Visualization and Analysis of CNN Adversarial Training -- 13.1 Introduction -- 13.2 Methodology -- 13.2.1 Dataset Description and Preprocessing -- 13.2.2 Proposed Approach -- 13.2.3 Implementation Details -- 13.3 Results and Discussion -- 13.3.1 Interim Output -- 13.3.2 Distribution -- 13.3.3 Adversarial Training -- 13.4 Conclusion -- References -- 14 Video Violence Detection Method Based on Multi-Feature and Graph Convolutional Network -- 14.1 Introduction -- 14.2 Proposed Violence Detection System -- 14.2.1 Data Process -- 14.2.2 Feature Extraction -- 14.2.3 Feature Fusion -- 14.2.4 GCN-Based Method -- 14.3 Experiments -- 14.3.1 Implementation and Evaluation Methods -- 14.3.2 Experimental Results -- 14.4 Conclusion -- References -- 15 Enhancing Realized Volatility Prediction: An Exploration into LightGBM Baseline Models -- 15.1 Introduction -- 15.2 Methodology -- 15.2.1 Dataset Description and Preprocessing -- 15.2.2 Proposed Approach -- 15.3 Results and Discussion -- 15.3.1 Model Evaluation -- 15.3.2 Model Performance and Analysis -- 15.3.3 Computational Efficiency -- 15.3.4 Discussion -- 15.3.5 Conclusion -- References -- 16 Terminal Anomaly Discovery Technology Based on Service Behavior Deviation -- 16.1 Introduction -- 16.2 Related Technology -- 16.2.1 Multivariate Gaussian Mixture Distribution -- 16.3 Gramian Angular Field -- 16.4 Terminal Anomaly Evaluation Model -- 16.4.1 Business Timing Symbolization Based on Multivariate Gaussian Mixture Distribution. 16.4.2 Multi-Dimensionalization of Time Series Data Based on Gramian Angular Field. |
| Record Nr. | UNINA-9910917783903321 |
|
Kountchev Roumen
|
||
| Singapore : , : Springer, , 2024 | ||
| Materiale a stampa | ||
| Lo trovi qui: Univ. Federico II | ||
| ||