10688nam 22004693 450 991087469460332120240721090305.0981-9735-26-2(MiAaPQ)EBC31534307(Au-PeEL)EBL31534307(CKB)33030842500041(EXLCZ)993303084250004120240721d2024 uy 0engurcnu||||||||txtrdacontentcrdamediacrrdacarrierProceedings of International Conference on Computational Intelligence Icci 20231st ed.Singapore :Springer,2024.©2024.1 online resource (714 pages)Algorithms for Intelligent Systems Series981-9735-25-4 Intro -- Preface -- Contents -- About the Editors -- 1 Modeling the Optical Gain of Erbium-Doped Fiber Amplifiers in Strong Cross-Gain Modulation Regime Employing Artificial Neural Networks -- 1 Introduction -- 2 Literature Review -- 3 ANN-Based Model of EDFAs -- 3.1 Device to Be Modeled -- 3.2 ANN Model of an EDFA -- 4 Training and Optimization of the ANN-Based Model -- 4.1 Training of the Model -- 4.2 Model Optimization -- 5 Accuracy Assessment -- 6 Conclusions -- References -- 2 The Fuzzy Logic Model for Machining Data Selection -- 1 Introduction -- 2 Fuzzy Methodology -- 2.1 Fuzzy Expressions -- 2.2 Universe Partitioning -- 2.3 Fuzzy Rules -- 2.4 Fuzzy Relationship -- 2.5 Rule Combination -- 3 Results and Discussion -- 3.1 Average Speed Calculation and Cutting Speed -- 4 Conclusion -- References -- 3 Design of a Fuzzy Controller Applied to Level Control in Industrial Processes -- 1 Introduction -- 2 Design Proposal -- 2.1 Design Description -- 2.2 Design Engineering -- 3 Experimental Tests -- 3.1 Numerical Simulation -- 3.2 Implementation -- 3.3 Results and Discussions -- 4 Conclusions -- References -- 4 Hybrid Weighted Ensemble Model for the Early Diagnosis of Parkinson's Disease Using Voice Features -- 1 Introduction -- 2 Related Works -- 2.1 Survey Based on Recent Existing System Using the Same Dataset as Proposed System -- 2.2 Survey Based on Machine Learning (ML) Techniques of Early Diagnosis of PD Based on Voice Feature Modality -- 2.3 Survey Based on Ensemble Techniques, Feature Selection and Dimensionality Reduction Techniques for Voice Feature Dataset of PD Early Diagnosis -- 3 Research Methodologies -- 3.1 Dataset Description -- 3.2 Train and Test Data Split -- 3.3 Hybrid Weighted Ensemble Classifier Construction -- 3.4 Testing and Evaluation -- 4 Results -- 5 Conclusion and Future Scope -- References.5 Ensuring Transparency in Takeovers: Evaluating Information Retrieval in the Indian Financial Market -- 1 Introduction -- 2 Problem Statement and Related Work -- 2.1 Financial Data Mining -- 2.2 Large Language Models -- 2.3 Information Retrieval -- 2.4 Information Retrieval Benchmarking -- 3 Methodology -- 3.1 Dataset Preparation -- 3.2 Sample Questions -- 4 Results -- 4.1 Evaluation Metrics -- 4.2 Results from BEIR -- 4.3 Limitations -- 4.4 Future Proposed Work -- 5 Conclusion -- References -- 6 An Intrusion Detection System Using Machine Learning to Secure the Internet of Drones -- 1 Introduction -- 2 Literature Review -- 3 Dataset Used -- 4 Methodology -- 4.1 Data Preprocessing and Encoding -- 4.2 Data Collection and Understanding -- 4.3 Feature Extraction -- 4.4 Data Scaling and Normalization -- 4.5 Encoding Categorical Data -- 4.6 Handling Imbalanced Data -- 5 Experimental Results -- 5.1 Training and Validation -- 5.2 Performance Analysis -- 5.3 Evaluation -- 6 Discussion, Limitation, and Future Work -- 7 Conclusion -- References -- 7 Advancements in CT Image Reconstruction: An Exploration of Conventional and Deep Learning-Driven Approaches -- 1 Introduction -- 2 Literature Survey -- 2.1 CT Image Reconstruction Challenges -- 3 Conclusion -- References -- 8 Machine Learning-Assisted Food Quality Index Determination for Healthcare -- 1 Introduction -- 2 Related Works -- 3 Proposed Work -- 3.1 Dense Convolutional Networks (DenseNets) -- 3.2 Deep Residual Networks (ResNets) -- 3.3 Evaluation Metrics and Parameters -- 3.4 3-Classification Experiment -- 3.5 18-Classification Experiment -- 4 Implementation and Results -- 4.1 Dataset and Preprocessing -- 4.2 Performance Metrics -- 4.3 Performance Analysis -- 5 Conclusion -- References -- 9 Comparing Various DC-DC Converters for Recharging EV Batteries -- 1 Introduction.2 Classification of EV Chargers -- 3 Converter Topologies for EV Battery Chargers -- 4 On-Board Battery Chargers -- 4.1 Front-End-Type Converters -- 4.2 Back-End Converters -- 5 Verification and Discussion -- 6 Conclusion -- References -- 10 A Survey on Detection of Man-In-The-Middle Attack in IoMT Using Machine Learning Techniques -- 1 Introduction -- 2 Man-In-The-Middle Attack -- 2.1 Types of Man-In-The-Middle Attack -- 3 Spoofing-Based Man-In-The-Middle Attack -- 3.1 ARP Spoofing -- 3.2 DNS Spoofing -- 3.3 DHCP Spoofing -- 3.4 IP Spoofing -- 4 Related Study -- 4.1 Comparative Analysis of Strategies -- 5 Challenges and Limitations of Man-In-The-Middle Attack -- 5.1 Intercepting Communication -- 5.2 Identity Spoofing -- 5.3 Data Tampering -- 5.4 Session Hijacking -- 5.5 SSL Stripping -- 5.6 Weak Encryption -- 5.7 Public Wi-Fi Vulnerabilities -- 5.8 Device Vulnerabilities -- 5.9 Phishing Attack -- 5.10 Complexity of Detection -- 5.11 Insider Threats -- 5.12 End-To-End Encryption: -- 6 Conclusion -- References -- 11 An Application of Deep Learning Using Leaky Rectified Linear Unit and Hyperbolic Tangent in Non-destructive Testing -- 1 Introduction -- 2 Methodology to Develop Mathematical Model Using Artificial Neural Network -- 3 Application of Mathematical Model in Non-Destructive Testing -- 4 Results -- 5 Conclusions -- References -- 12 An Approach of Deep Clustering Applied for Customer Segmentation to Escalate Businesses -- 1 Introduction -- 2 Background Study -- 2.1 Mall Customer Segmentation -- 2.2 Clustering -- 2.3 K-Means Clustering -- 2.4 Density-Based Spatial Clustering for Application with Noise (DBSCAN) -- 2.5 Deep Clustering -- 3 Proposed Methodology -- 3.1 Data Extraction -- 3.2 Problem Mapping -- 3.3 Model Preparation -- 3.4 Density-Based Spatial Clustering for Application with Noise (DBSCAN) -- 3.5 K-Means Clustering.3.6 Deep Clustering -- 3.7 Supreme Approach -- 4 Results and Discussion -- 5 Conclusion -- References -- 13 Binary Probing: A Novel Approach for Efficient Hash Table Operations -- 1 Introduction -- 2 Analysis of Existing Algorithms -- 2.1 Separate Chaining -- 2.2 Linear Probing -- 2.3 Quadratic Probing -- 2.4 Double Hashing -- 3 Our Approach -- 4 Algorithmic Execution -- 5 Algorithm Flowchart -- 6 Results and Discussion -- 6.1 Time Complexity Analysis -- 6.2 Comparison with Other Algorithms -- 7 Conclusion -- References -- 14 Transformer-Based Reinforcement Learning for Forex Trading -- 1 Introduction -- 1.1 Literature Survey -- 2 System Architecture and Design -- 2.1 System Architecture -- 2.2 Scale Method -- 2.3 Transformer -- 2.4 Deep Q-LEARNING -- 3 Algorithm Development and Implementation -- 3.1 Training the Transformer Model -- 4 Results and Discussions -- 4.1 Prediction System Implementation -- 5 Conclusion -- References -- 15 AI in Mechanical Design: Generate Specific Components -- 1 Introduction -- 1.1 What is AI? -- 2 AI Methodology -- 3 Case Studies -- 3.1 Generate Simple Components -- 3.2 Generate Complex Shapes -- 4 Conclusions -- References -- 16 Harnessing EEG Signals to Detect Schizophrenia: A Deep Learning Approach -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dataset -- 3.2 Pre-processing of Data -- 3.3 Architecture of the Proposed CNN Model -- 3.4 Evaluation Metrics -- 4 Validation of Model -- 5 Conclusion and Future Scope -- References -- 17 Solution of ECG Inverse Problem Using Artificial Neural Network -- 1 Introduction -- 2 Methodology -- 3 Experimental Results -- 4 Discussion -- 5 Conclusion -- References -- 18 The Impact of Artificial Intelligence Technology in Learning Zones -- 1 Introduction -- 2 Methodology -- 3 Literature Review -- 4 Discussion -- 5 Conclusion -- References.19 From Stateless to Stateful: A Comparative Analysis of Stateful Serverless Computing Frameworks -- 1 Introduction -- 1.1 Motivation -- 1.2 Contribution -- 2 Why Stateful Serverless? -- 3 Existing Stateful Serverless Systems -- 3.1 Cloudburst -- 3.2 Azure Durable Functions -- 3.3 Apache Flink StateFun -- 3.4 Beldi -- 4 Comparative Analysis of SSS's -- 5 Literature Review -- 6 Challenges and Limitation of Existing Stateful Serverless -- 7 Conclusion and Future Work -- References -- 20 Predicting High-Risk Perinatal Complication Using Semi-supervised Machine Learning -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Dataset Collection -- 3.2 Preprocessing -- 3.3 Modeling -- 4 Simulation and Discussion -- 5 Conclusion and Future Work -- References -- 21 An Online Learning and Problem Solving (OLPS) EEG Database for Mental Workload Assessment and Its Initial Benchmark Classification Performance -- 1 Introduction -- 2 Methodology -- 2.1 Design of Experiment -- 2.2 One Dimensional Convolutional Neural Network -- 2.3 Evaluation Metric -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- 22 Optimizing Healthcare Billing Processes Through Machine Learning Using Diagnosis-Related Groups -- 1 Introduction -- 2 Description of the Classification Problem -- 2.1 Problem Model -- 2.2 Classification and Optimization Methods -- 3 Optimization Framework and Test Cases -- 3.1 Used Software and Hardware -- 3.2 Data Preparation -- 3.3 Model Selection and Hyperparameter Tuning -- 4 Results -- 5 Conclusions -- References -- 23 Convolutional Neural Networks-Based Evaluation of Disease Severity in Grape Plant Using Colored and Grayscale Leaf Images -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset Utilized -- 2.2 Research Methodology -- 2.3 CNN Architectures and Implementation Details -- 3 Results and Discussion.4 Conclusion and Future Direction.Algorithms for Intelligent Systems SeriesTiwari Ritu1373693Saraswat Mukesh1373695Pavone Mario1749796MiAaPQMiAaPQMiAaPQBOOK9910874694603321Proceedings of International Conference on Computational Intelligence4184151UNINA