11902nam 22006615 450 991084708040332120240628122032.0981-9989-37-X10.1007/978-981-99-8937-9(CKB)31253144200041(MiAaPQ)EBC31233423(Au-PeEL)EBL31233423(MiAaPQ)EBC31266869(Au-PeEL)EBL31266869(DE-He213)978-981-99-8937-9(EXLCZ)993125314420004120240329d2024 u| 0engur|||||||||||txtrdacontentcrdamediacrrdacarrierProceedings of the 2nd International Conference on Big Data, IoT and Machine Learning BIM 2023 /edited by Mohammad Shamsul Arefin, M. Shamim Kaiser, Touhid Bhuiyan, Nilanjan Dey, Mufti Mahmud1st ed. 2024.Singapore :Springer Nature Singapore :Imprint: Springer,2024.1 online resource (1053 pages)Lecture Notes in Networks and Systems,2367-3389 ;867981-9989-36-1 Includes bibliographical references and index.Intro -- Organization -- Preface -- Contents -- Editors and Contributors -- Informatics for Emerging Applications -- A Deep Learning Approach to Predict Cryptocurrency Price by Evaluating Sentiment and Stock Market Correlations -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Proposed System -- 3.2 Data Preprocessing -- 3.3 Model for Cryptocurrency Data -- 3.4 Model for Sentiment Analysis -- 4 Evaluation -- 4.1 Dataset Description -- 4.2 Experimentation and Result Analysis -- 5 Conclusion -- References -- Dominance by Stability: A Framework for Top k Dominating Query on Incomplete Data -- 1 Introduction -- 2 Related Works -- 3 Top-k Dominating Query by Stability (TKDS) -- 3.1 Bucketing -- 3.2 Dominating Score Computation -- 3.3 Bucket Implementation -- 3.4 Top-k Query Processing -- 4 Performance Evaluation -- 4.1 Dataset -- 4.2 Result Analysis -- 5 Conclusion -- References -- Phylogeny Reconstruction Using k-mer Derived Transition Features -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 k-mer Length, Distribution Vector, and Position List Generation -- 3.2 Standard Deviation, Median, and Transition Spatial Features -- 3.3 Phylogenetic Distance and Tree Reconstruction -- 4 Experimental Results -- 4.1 Datasets and Configurations -- 4.2 Soundness of k-mer Length l and Scalability of the Method -- 4.3 Benchmark Test Performance -- 4.4 Performance with Respect to State-of-the-Art Methods -- 4.5 Discussion -- 5 Conclusion -- References -- Developing an Interpretable Machine Learning Model for Divorce Prediction -- 1 Introduction -- 2 Related Works -- 3 Understandable AI Model for Divorce Prediction -- 3.1 Proposed Methodology -- 3.2 Evaluation Metrics -- 3.3 Dataset Description -- 4 Result and Discussion -- 4.1 Performance Analysis of Individual Classifier -- 4.2 SHAP Value Analysis -- 5 Conclusion and Future Work.References -- Riot Perception and Safety Navigation of Autonomous Vehicles Using Deep Learning -- 1 Introduction -- 2 Literature Review -- 3 Dataset Description and Preprocessing -- 4 Methodology -- 4.1 Model Architecture -- 4.2 Training YOLOv8 -- 5 Result and Discussions -- 6 Implementation and Future Work -- 7 Conclusion -- References -- An Explainable AI Enable Approach to Reveal Feature Influences on Social Media Customer Purchase Decisions -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Overview of the Proposed Methodology -- 3.2 Description of the Dataset -- 3.3 Techniques for Dataset Preprocessing -- 3.4 ML Algorithms for Analysis -- 3.5 Performance Measure Metrics -- 3.6 Details of XAI Tools -- 4 Result and Analysis -- 4.1 Performance of the ML Algorithms to Predict Social Media Customer Purchase Decision -- 4.2 Explainability of RF by the XAI Tools -- 5 Conclusion and Future Works -- References -- Field Programmable Gate Array in DNA Computing -- 1 Introduction -- 2 Background -- 2.1 DNA Computing -- 2.2 DNA Basic Operations -- 3 FPGA Logic Block -- 3.1 Architecture of Basic Components -- 3.2 Working Procedure -- 4 FPGA Logic Block Algorithm -- 5 Conclusion -- References -- XAI-Driven Model Explainability and Prediction of P2P Bank Loan Default Network -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Overview of Proposed Methodology -- 3.2 Description of the Dataset -- 3.3 Feature Selection Procedure -- 3.4 Data Balancing in Highly Imbalanced Dataset -- 3.5 Description of the ML Algorithms for Prediction -- 3.6 Performance Measure Techniques -- 3.7 Description of the Explainable AI Tools -- 4 Result and Analysis -- 5 Conclusion and Future Works -- References -- Design Implication of a Compact-Sized, Low-Fidelity Rover for Tough Terrain Exploration -- 1 Introduction -- 2 Comparative Study.3 Foundational Concepts and Technologies -- 3.1 Embedded System and Robotics -- 3.2 Navigation System in Miniature Robots -- 3.3 Low-Fidelity Robot -- 3.4 Mini Rover -- 4 Systematic Approach -- 4.1 Task Outline -- 5 Implementation -- 5.1 System Design -- 5.2 Mathematical Calculation -- 6 Discussions and Analysis -- 7 Conclusion -- References -- VioNet: An Enhanced Violence Detection Approach for Videos Using a Fusion Model of Vision Transformer with Bi-LSTM and 3D Convolutional Neural Networks -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 4 Result and Discussion -- 4.1 Dataset -- 4.2 Implementation Details -- 4.3 Performance Evaluation -- 4.4 Comparison with Other Methods -- 5 Conclusion -- References -- Rank Your Summaries: Enhancing Bengali Text Summarization Via Ranking-Based Approach -- 1 Introduction -- 2 Bengali Summary Ranker -- 2.1 Proposed Approach -- 2.2 Models -- 3 Evaluation -- 3.1 Datasets -- 3.2 Hyper-Parameter Settings -- 3.3 Evaluation Metrics -- 3.4 Experimental Results -- 4 Result Analysis -- 4.1 Quantitative Analysis -- 4.2 Qualitative Analysis -- 5 Related Works -- 6 Conclusion -- References -- An Efficient Machine Learning Classification Model for Rainfall Prediction in Bangladesh -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Predicted Models -- 3.2 Models Setting and Analysis Steps -- 3.3 Flow Diagram of This Study -- 3.4 Experiment Dataset -- 3.5 Data Preprocess -- 4 Results and Discussion -- 4.1 Actual and Predicted Results -- 4.2 Models Performance Table -- 4.3 Graphical Representation -- 5 Conclusions and Future Work -- References -- Study on the Analysis and Prediction of Drug Addiction Among University Students of Bangladesh Using Machine Learning -- 1 Introduction -- 1.1 Data Collection -- 1.2 Assuring the Quality -- 1.3 Choosing an Algorithm -- 1.4 Limitations -- 1.5 Ethical Consideration.2 Literature Review -- 3 Background Study -- 3.1 K-Nearest Neighbor -- 3.2 Logistic Regression -- 3.3 Gaussian Naïve Bayes -- 3.4 Support Vector Machine -- 3.5 Random Forest -- 3.6 Neural Network (Multilayer Perceptron) -- 4 Methodology -- 4.1 Data Assemblage and Dataset -- 4.2 Visualization -- 4.3 Algorithm Analysis -- 5 Experiment Results -- 6 Conclusion and Future Work -- References -- Artificial Intelligence for Imaging Applications -- A Deep CNN-Based Approach for Revolutionizing Bengali Handwritten Numeral Recognition -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Dataset Acquisition and Description -- 3.2 Data Augmentation -- 3.3 Convolutional Neural Network -- 3.4 Proposed Architecture -- 4 Experiment and Result Analysis -- 4.1 Data Preprocessing -- 4.2 Experimental Settings -- 4.3 Result Analysis -- 4.4 Evaluating Different Route Configurations -- 4.5 Comparison with Prior Works -- 5 Conclusion -- References -- Performance Analysis of Multiple Deep Learning Models for Image Retrieval Problems -- 1 Introduction -- 2 Related Work -- 2.1 Literature Review -- 2.2 Deep Learning Methods -- 3 Research Methodology -- 3.1 Image Acquisition -- 3.2 Model Adaptation -- 3.3 Implementation and Training -- 4 Experimental Result and Analysis -- 5 Conclusion -- References -- Advancing Lung Cancer Diagnosis Through Deep Learning and Grad-CAM-Based Visualization Techniques -- 1 Introduction -- 2 Literature Review -- 3 Materials and Methodology -- 3.1 Dataset Description -- 3.2 Data Preprocessing -- 3.3 Proposed Workflow -- 3.4 Model Architecture -- 3.5 Grad-CAM Visualization -- 4 Result Analysis -- 4.1 Method Evaluation Metrics -- 4.2 Comparison with Pre-Trained Other Models -- 4.3 Comparison with Related Works -- 4.4 Obtained Result -- 5 Discussion -- 6 Conclusion -- References.A Novel Approach to Detect Stroke from 2D Images Using Deep Learning -- 1 Introduction -- 2 Related Works -- 3 Data Sets Characteristics -- 4 Proposed Methodology -- 5 Result and Discussion -- 5.1 Batch Size -- 5.2 Impact of Learning Rate -- 5.3 Adam Optimizer -- 5.4 Kernel Size -- 5.5 Comparison with Current Studies -- 6 Conclusion and Future Work -- References -- Enhancing Pneumonia Diagnosis: An Ensemble of Deep CNN Architectures for Accurate Chest X-Ray Image Analysis -- 1 Introduction -- 2 Literature Review -- 3 Proposed Method -- 4 Dataset -- 5 Image Pre-processing -- 5.1 Resizing -- 5.2 Augmentation -- 5.3 Normalization -- 6 Deep CNN Model Architectures Using Transfer Learning -- 6.1 Convolutional Neural Network Model Architectures -- 6.2 Transfer Learning: Fine Tuning -- 7 Ensemble Learning -- 8 Results and Discussion -- 8.1 Output of Single Model -- 8.2 Output of Ensemble Model -- 9 Conclusion -- References -- Dataset for Road Roughness Assessment Using Image Classification Techniques and Deep Learning Models: A Case Study on Bangladeshi National Highways -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Data Collection -- 3.2 Data Preprocessing -- 3.3 Dataset Comparison -- 3.4 Model Training -- 3.5 Feature Map Extraction -- 3.6 Analysis -- 4 Conclusion -- References -- Noise-Aware-Based Texture Descriptor, Evaluation Adjacent Distance Local Ternary Pattern EAdLTP for Image Classification -- 1 Introduction -- 2 Background Study -- 2.1 Local Binary Pattern LBP -- 2.2 Local Ternary Pattern LTP -- 3 Noise-Aware-Based Evaluation Window-Based Adjacent Distance Local Ternary Pattern EAdLTP -- 3.1 Encoding the Value of xp -- 3.2 Calculating the Value of Adjacent Distance Local Ternary Pattern EAdLTP -- 4 Experiment Analysis -- 5 Conclusion -- References -- Sentiment Analysis from YouTube Video Using Bi-LSTM-GRU Classification.1 Introduction.This book gathers a collection of high-quality peer-reviewed research papers presented at the International Conference on Big Data, IoT and Machine Learning (BIM 2023), organised by Jahangirnagar University, Bangladesh, and Daffodil International University, Bangladesh, held in Dhaka, Bangladesh, during 6–8 September 2023. The book covers research papers in the field of big data, IoT and machine learning. The book is helpful for active researchers and practitioners in the field.Lecture Notes in Networks and Systems,2367-3389 ;867Internet of thingsBig dataArtificial intelligenceInternet of ThingsBig DataArtificial IntelligenceInternet of things.Big data.Artificial intelligence.Internet of Things.Big Data.Artificial Intelligence.005.7Arefin Mohammad ShamsulMiAaPQMiAaPQMiAaPQBOOK9910847080403321Proceedings of the 2nd International Conference on Big Data, IoT and Machine Learning4242132UNINA