Kooperativer Bibliotheksverbund

UID:

Umfang: XI, 658 p. 280 illus., 218 illus. in color. , online resource.

Ausgabe: 1st ed. 2024.

ISBN: 9783031664311

Serie: Lecture Notes in Networks and Systems, 1067

Inhalt: This volume is a collection of meticulously crafted, insightful, and state-of-the-art papers presented at the Intelligent Systems Conference 2024, held in Amsterdam, The Netherlands, on 5-6 September 2024. The conference received an overwhelming response, with a total of 535 submissions. After a rigorous double-blind peer review process, 181 papers were selected for presentation. These papers span a wide range of scientific topics, including Artificial Intelligence, Computer Vision, Robotics, Intelligent Systems, and more. We hope that readers find this volume both interesting and valuable. Furthermore, we expect that the conference and its proceedings will inspire further research and technological advancements in these critical areas of study. Thank you for engaging with this collection of works from the Intelligent Systems Conference 2024. Your interest and support contribute significantly to the ongoing progress and innovation in the field of intelligent systems.

Anmerkung: Diagnosis of Alzheimer's Disease with Deep Neural Networks -- MAMTCPN: Moise+ Automated Mapping to Colored Petri Net -- The Problem of Many Vehicles: An Explainable System for Autonomous Multi-Agent Accidents -- Enhancing Spinal Health: Personalized Exoskeleton for Preventing and Rehabilitating Heavy Lifting-Related Conditions.

In: Springer Nature eBook

Weitere Ausg.: Printed edition: ISBN 9783031664304

Weitere Ausg.: Printed edition: ISBN 9783031664328

Sprache: Englisch

DOI: 10.1007/978-3-031-66431-1

URL: https://doi.org/10.1007/978-3-031-66431-1

UID:

Umfang: 1 online resource (668 pages)

Ausgabe: 1st ed.

ISBN: 9783031664311

Serie: Lecture Notes in Networks and Systems Series ; v.1067

Anmerkung: Intro -- Preface -- Contents -- Diagnosis of Alzheimer's Disease with Deep Neural Networks -- 1 Introduction -- 2 Related Work -- 3 Dataset -- 4 Data Preprocessing -- 4.1 Spatial Normalization -- 4.2 Skull Stripping -- 4.3 Creating 2D Datasets -- 4.4 Store Datasets in TFRecords -- 5 Model Implementation -- 5.1 2D Models -- 5.2 3D Models -- 6 Data Augmentation -- 7 Analysis of Results -- 8 Conclusions and Future Work -- References -- MAMTCPN: Moise+ Automated Mapping to Colored Petri Net -- 1 Introduction -- 2 Background -- 3 Related Works -- 4 Mapping Tool Description -- 5 Scenario Example -- 6 Conclusion -- References -- The Problem of Many Vehicles: An Explainable System for Autonomous Multi-agent Accidents -- 1 Introduction -- 2 The Problem of Many Hands -- 3 Causal Responsibility -- 4 Full Time Causal Graph (FTCG) -- 5 Related Work -- 6 Framework Overview -- 6.1 Multi-agent Scenario Creation -- 6.2 Individual Multi-explanation Generation and Counterfactual Filtering -- 6.3 Combined Causal Explanation -- 7 Evaluation and Results -- 7.1 Evaluation Metrics -- 7.2 Results and Discussion -- 8 Conclusion and Future Work -- References -- Enhancing Spinal Health: Personalized Exoskeleton for Preventing and Rehabilitating Heavy Lifting-Related Conditions -- 1 Introduction -- 2 Materials -- 3 Methods -- 3.1 Exoskeleton Development -- 3.2 Data Storage and Continuous Monitoring -- 4 Results -- 4.1 SVM Algorithm Training -- 4.2 Final Exoskeleton Prototype Modeling -- 5 Discussion -- 6 Conclusion -- References -- Urban Visual Pollution Detection in Public Realm Using Artificial Intelligence: A Case Study of Riyadh Area, Saudi Arabia -- 1 Introduction -- 2 Related Works -- 3 Data Set -- 4 Methodology -- 5 Artificial Intelligence-Based Model -- 5.1 Random Forest -- 5.2 Support Vector Machine -- 6 Our Design -- 6.1 Intelligence Amplification. , 6.2 Feature Development -- 6.3 Working of Our Design -- 7 Data Set Cleaning -- 7.1 Scaling Image -- 7.2 Background Removal -- 7.3 Testing and Training -- 7.4 Comparison of Data and Methodology -- 7.5 Comparison Results -- 8 Objectives of Proposed Methods -- 9 Features-Based Analysis -- 10 Conclusion -- References -- Particle Swarm Optimization for Tuning PID Parameters to Control General Systems -- 1 Introduction -- 1.1 Identification of an 2nd Order Overshooting System -- 1.2 Identification of a PTn System -- 1.3 Controller Parameters Calculated After the Minimized ITAE Criterion -- 2 Particle Swarm Optimization -- 2.1 Hyperparameters -- 2.2 Formula -- 3 Methods -- 3.1 Reference Values -- 3.2 Time Complexity -- 3.3 Search Space -- 3.4 Implementation PSO -- 3.5 Database -- 3.6 Evaluations -- 4 Results -- 4.1 Search Space 0-10 -- 4.2 Search Space 0-100 -- 4.3 Comparison of Time Responses -- 5 Conclusion and Further Work -- References -- RecipeRadar: An AI-Powered Recipe Recommendation System -- 1 Introduction -- 2 Related Work -- 2.1 Previous Study -- 2.2 Limitations -- 3 Our Methodology -- 3.1 Data Preparation -- 3.2 Model Construction -- 4 Results -- 4.1 Model Evaluation -- 4.2 Visualization -- 4.3 Comparative Analysis: Previous Studies vs. Our Model -- 4.4 Chatbot Design -- 5 Conclusion -- 6 Future Work -- References -- Factors Influencing Organizational Adoption of Artificial Intelligence and Corporate Social Responsibility in a Solar System World -- 1 Introduction -- 2 Literature Review -- 2.1 The Firm-Level Adoption of AI -- 2.2 AI and Its Adoption for Social Good -- 2.3 AI Adoption and CSR -- 3 Methodology -- 4 Findings and Discussion -- 5 Conclusion -- References -- Formal Definition of Interpretability and Explainability in XAI -- 1 Introduction -- 2 Analysis of Explicability and Interpretability Terminology in Machine Learning. , 3 Proposed Formal Definition -- 3.1 Fundamental Distinction Between Explainability and Interpretability -- 3.2 Formalization -- 4 Explainability Properties -- 5 Classification of Explainability vs. Interpretability in ML -- 5.1 Methods of Global/Local Explainability -- 5.2 Intrinsic vs. Extrinsic Explainability -- 5.3 Specific vs. Agnostic Explainability in Machine Learning -- 6 Interpretability Methods in Machine Learning -- 6.1 Transparent Models in Machine Learning -- 6.2 XIA Interpretability Technique -- 6.3 Comparison of XIA Interpretability Techniques -- 7 Conclusion -- References -- Fall Detection with Neural Networks -- 1 Introduction -- 2 Literature Review -- 2.1 Database -- 2.2 Motion Sensors -- 2.3 Card Raspberry Pi 4 -- 2.4 Neural Networks -- 3 System Development -- 3.1 Database Acquisition -- 3.2 Processing -- 3.3 Network Training -- 3.4 Network Evaluation -- 3.5 Raspberry Pi Implementation -- 4 Procedure -- 5 Experimental Results -- 6 Discussion -- 7 Conclusion -- References -- Intelligent Digitalization and Immersive Experience in Cross-Border e-Commerce Environment (I): The Formation Pathway and Underlying "Mediator" of Consumer Brand Attachment -- 1 Introduction -- 2 Literature Review -- 2.1 CBEC and Branding -- 2.2 Independent Variable: User-Generated Content -- 2.3 Dependent Variable: Brand Attachment -- 2.4 Correlations Between User-Generated Content and Brand Attachment -- 2.5 Brand Involvement -- 2.6 Summary -- 3 Research Hypotheses and Models -- 3.1 Hypothesis of UGC Quality and BA via the Mediating Role of BI -- 4 Samples -- 5 Methodology -- 5.1 Variable Measurements -- 5.2 Methods of Test -- 6 Findings -- 6.1 Reliability and Validity -- 6.2 Hypothesis Test -- 6.3 Robustness Test -- 6.4 Summary -- 7 Discussions -- 8 Summary and Implications -- 8.1 Conclusion -- 8.2 Implications -- 8.3 Limitations and Future Research. , References -- AI and Inclusivity: Co-designing for Disability Empowerment -- 1 Introduction -- 2 AI Systems and Their Impact on Disability -- 2.1 AI's Role in Disability Empowerment -- 2.2 Challenges at the Intersection of AI and Disability -- 3 Collaborative Innovation: Embracing Co-design in AI for Inclusive Solution -- 3.1 Co-design in Action: Case Studies -- 3.2 Inclusive Co-design Principles -- 4 Conclusions and Future Perspective -- References -- Artificial Intelligence in Detecting Signs of Depression Among Social Networks Users -- 1 Introduction -- 2 Social Depression Detection Framework Phases -- 2.1 Data Collection and Annotation -- 2.2 Data Preprocessing -- 2.3 Model Selection and Training -- 2.4 Model Evaluation -- 3 Comparative Study of Existing Works -- 3.1 Research Conduct -- 3.2 Comparing Data Collection and Annotation Phase -- 3.3 Comparing Data Preprocessing Phase -- 3.4 Comparing Classification Models Trained -- 3.5 Comparing Models Performances -- 4 Overview of the Whole Phases and Discussion -- 4.1 Overview of the Whole Phases -- 4.2 Discussion -- 5 Conclusion -- References -- Artificial Intelligence Tools for Wind Turbine Blade Monitoring -- 1 Introduction -- 2 Monitoring System Scheme -- 3 Simulation and Results -- 4 Conclusion -- References -- Idiomatizing Python Source Code Using Different Recurrent Architectures -- 1 Introduction -- 2 Related Work -- 3 Encoder-Decoder Architectural Possibilities -- 3.1 Base Recurrent Model -- 3.2 The Choice of RNN Type -- 3.3 Using Multiple Parallel RNNs for Encoding -- 3.4 Stacking RNNs for Encoding -- 3.5 Applying Convolution as the First Step of Encoding -- 3.6 Using Convolution and Pooling to Initialize Encoder RNN -- 3.7 Pass Through the Input Twice -- 3.8 Using Two Parallel RNNs for Decoding -- 3.9 Combining These Approaches -- 4 Experimental Setup and Evaluation -- 5 Discussion. , 6 Conclusion -- References -- Sampling vs. Metasampling Based on Straightforward Hilbert Representation of Isolation Kernel -- 1 Introduction -- 2 Related Work -- 3 Background -- 3.1 Kernel ABC -- 3.2 Straightforward Hilbert Representation of Isolation Kernel -- 4 Metasampling Based on SHRIKe -- 5 Experiments -- 5.1 Methods and Tools -- 5.2 Gaussian Model -- 5.3 Cancer Cell Evolution -- 6 Conclusion -- References -- CBR Evaluation Pyramid: A Pragmatic Process for Evaluating Case-Based Reasoning Systems -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 The CBR Evaluation Pyramid -- 3.2 Why a Pyramid or Layered Framework? -- 3.3 Evaluation Approach -- 3.4 Operationalizing the Evaluation -- 4 Discussion -- 5 Contributions -- 6 Conclusion and Future Work -- References -- Tank Road 1929: Design and Evaluation of Immersive Social Environments for Context-Based Learning -- 1 Introduction -- 1.1 Research Question -- 1.2 Research Objectives -- 1.3 Key Terms -- 2 Literature Review -- 2.1 Living in History Through VR -- 2.2 Interactions Within Virtual Environments -- 3 Developing the Experiment -- 3.1 The Case for Tank Road, Singapore -- 3.2 Experiment Design -- 3.3 Applying Propositions for Immersive Social Environments -- 3.4 Reconstructing Tank Road -- 3.5 Conducting Tank Road 1929 -- 4 Results and Analysis -- 4.1 Preconceived Notions -- 4.2 During the Experiment -- 4.3 Learnt Knowledge -- 4.4 On VR Experience -- 5 Conclusion and Discussion -- 5.1 Results Summary -- 5.2 Project Limitations -- 5.3 Areas Identified for Future Research Work -- References -- Models for Real-Time Emotion Classification: FER-2013 Dataset -- 1 Introduction -- 2 Related Work -- 2.1 Models Trained with FER-2013 -- 3 CNN Models -- 3.1 Adapted Models -- 3.2 Hyperparameter Tuning -- 4 Experiments -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Experiment Results. , 5 Analysis and Discussion.

Weitere Ausg.: Print version: Arai, Kohei Intelligent Systems and Applications Cham : Springer,c2024 ISBN 9783031664304

Sprache: Englisch

UID:

Umfang: 1 online resource (668 pages)

Ausgabe: 1st ed. 2024.

ISBN: 9783031664311

Serie: Lecture Notes in Networks and Systems, 1067

Inhalt: This volume is a collection of meticulously crafted, insightful, and state-of-the-art papers presented at the Intelligent Systems Conference 2024, held in Amsterdam, The Netherlands, on 5-6 September 2024. The conference received an overwhelming response, with a total of 535 submissions. After a rigorous double-blind peer review process, 181 papers were selected for presentation. These papers span a wide range of scientific topics, including Artificial Intelligence, Computer Vision, Robotics, Intelligent Systems, and more. We hope that readers find this volume both interesting and valuable. Furthermore, we expect that the conference and its proceedings will inspire further research and technological advancements in these critical areas of study. Thank you for engaging with this collection of works from the Intelligent Systems Conference 2024. Your interest and support contribute significantly to the ongoing progress and innovation in the field of intelligent systems.

Anmerkung: Diagnosis of Alzheimer’s Disease with Deep Neural Networks -- MAMTCPN: Moise+ Automated Mapping to Colored Petri Net -- The Problem of Many Vehicles: An Explainable System for Autonomous Multi-Agent Accidents -- Enhancing Spinal Health: Personalized Exoskeleton for Preventing and Rehabilitating Heavy Lifting-Related Conditions.

Weitere Ausg.: Print version: Arai, Kohei Intelligent Systems and Applications Cham : Springer,c2024 ISBN 9783031664304

Sprache: Englisch

DOI: 10.1007/978-3-031-66431-1