Data Management, Analytics and Innovation

Name: Data Management, Analytics and Innovation | Proceedings of ICDMAI 2024, Volume 2
Brand: Springer
Price: 235.39 EUR
Availability: OnlineOnly

Proceedings of ICDMAI 2024, Volume 2

Neha Sharma Amol C. Goje Amlan Chakrabarti Alfred M. Bruckstein(Editor)

Springer (Publisher)

1st Edition

Published on 27. July 2024

XVII, 460 pages

E-Book

PDF with digital watermarking

System requirements

978-981-97-3245-6 (ISBN)

€235.39incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Persons

Dr. Neha Sharma is Data Science Crusader who advocates its application for achieving sustainable goals, solving societal, governmental, and business problems as well as promotes the use of open data. She has more than 24 years of experience and presently working with Tata Consultancy Services and is Founder Secretary, Society for Data Science. Prior to this, she has worked as Director of premier Institute of Pune that run post-graduation courses like MCA and MBA. She is Alumnus of a premier College of Engineering and Technology, Bhubaneshwar, and completed her Ph.D. from prestigious Indian Institute of Technology, Dhanbad. She is Senior IEEE Member, former Secretary-IEEE Pune Section and ACM Distinguished Speaker. She is Astute Academician and has organized several national and international conferences and published several research papers. She is Recipient of "Best Ph.D. Thesis Award" and "Best Paper Presenter at International Conference Award" at National Level.

Dr. Amol C. Goje is President of Society of Data Science and served as Director, Vidya Pratishthan's Institute of Information Technology (VIIT), Baramati, Pune, for last 19 Years. He has a total of over twenty five years of experience in the field of Information and Computer Technology (ICT). He has developed many systems for the University. His main area of interest is to work for underprivileged people in the rural part of India. In his nineteen years as Director, he has designed and implemented numerous path-breaking, innovative, and cost effective solutions. His main innovation is Computer Mobile Van. He has done lot of research work in Information Technology and its application for rural community. In appreciation to his exemplary work, he has received the Ashoka Fellow award in the year 2002. He is engaged as Technical Advisor on many government and non-government organizations.

Amlan Chakrabarti is presently Full Professor and Director of the A.K.Choudhury School of Information Technology, University of Calcutta. He is an M.Tech. from University of Calcutta and did his Doctoral research at the Indian Statistical Institute, Kolkata. He was Post-doctoral Fellow at the School of Engineering, Princeton University, USA, during 2011-2012. He is Recipient of DST BOYSCAST fellowship award in the area of Engineering Science in 2011, Indian National Science Academy Visiting Scientist Fellowship in 2014, JSPS Invitation Research Award from Japan in 2016, Erasmus Mundus Leaders Award from European Union in 2017, Hamied Visiting Fellowship University of Cambridge in 2018 and Shiksha Ratna Award from Govt. of West Bengal, in 2018. He is Team Leader of European Center for Research in Nuclear Science (CERN, Geneva) ALICE-India project for University of Calcutta and also Key Member of the CBM-FAIR project at Darmstadt Germany.

Professor Alfred M. Bruckstein, B.Sc., M.Sc. in EE from the Technion IIT, Haifa, Israel, and Ph.D. in EE, from Stanford University, Stanford, California, USA, is Technion Ollendorff Professor of Science, in the Computer Science Department there, and is Visiting Professor at NTU, Singapore, in the SPMS. He has done research on Neural Coding Processes, and Stochastic Point Processes, Estimation Theory, and Scattering Theory, Signal and Image Processing Topics, Computer Vision and Graphics, and Robotics. Over the years he held visiting positions at Bell Laboratories, Murray Hill, NJ, USA (1987-2001) and TsingHua University, Beijing, China (2002-2023) and made short time visits to many universities and research centers worldwide. At the Technion, he was Dean of the Graduate School and is currently Head of the Technion Excellence Program.

Editor

ISNI: 0000 0000 8431 8016

Content

Intro
Preface
Contents
Editors and Contributors
Comprehensive Survey of Nonverbal Emotion Recognition Techniques
1 Introduction
2 Applications Based on Understanding Nonverbal Emotion
3 Machine/Deep Learning Methods for Recognition of Nonverbal Emotion
3.1 Facial Expressions Recognition Machine/deep Learning Methods
3.2 Hand Gestures Recognition Machine/Deep Learning Methods
3.3 Body Language Recognition Machine/Deep Learning Methods
4 Findings
5 Conclusion
References
A Two-Stage CNN Based Satellite Image Analysis Framework for Estimating Building-Count in Residential Built-Up Area
1 Introduction
2 Review of the Relevant Research Work
3 Background Study
3.1 Mask R-CNN
3.2 Regression Using CNN
4 Proposed Methodology
4.1 Overview of Proposed Methodology
4.2 Mask R-CNN Top-Down Approach for Segmentation of Built Up Area
4.3 CNN Based Regression Model to Estimate Building-Count Within Segmented Built-Up Area
5 Experimental Evaluation of the Proposed Framework
5.1 Dataset Used
5.2 Experimental Setup
5.3 Experimental Evaluation Metric
5.4 Experimental Results and Discussion
6 Conclusion
References
Forecast of Energy Demand Using Temporal Fusion Transformer
1 Introduction
2 Survey of Literature
3 Proposed Work
3.1 Data Collection and Preprocessing
3.2 TFT Model Architecture
3.3 Training and Validation
4 Results
4.1 Forecasts
4.2 Interpreting the Seasonality
4.3 Detecting Some Accidental or Extreme Events
4.4 Ranking the Features
5 Conclusion
References
Mental Health Prediction Using Artificial Intelligence
1 Introduction
2 Literature Survey
3 Design
4 Methodology
5 Results
6 Future Directions and Limitations
7 Conclusion
References
VGGish Deep Learning Model: Audio Feature Extraction and Analysis
1 Introduction
1.1 Feature Extraction
1.2 Dataset
2 Related Work
3 Proposed System
3.1 Preprocessing
3.2 Feature Extraction
3.3 Feature Concatenation and Selection
3.4 Classification
3.5 Output
4 Proposed Algorithm
4.1 Initialization
5 Results
6 Conclusion
References
Stacking Ensemble-Based Approach for Sarcasm Identification with Multiple Contextual Word Embeddings
1 Introduction
2 Related Work
3 Materials and Methods
3.1 Preprocessing
3.2 Contextual Word Embeddings
3.3 Proposed Model
4 Materials and Methods
4.1 Dataset
4.2 Experimental Setup
4.3 Results and Analysis
5 Conclusion
References
Trigger-Based Pothole Detection, and Warning System with RQ and PHR Mapping
1 Introduction
2 Related Work and Comparative Study
3 Methodology
4 Flowcharts
5 Result and Discussions
6 Conclusion
References
Blending Motion Capture and 3D Human Reconstruction Techniques for Enhanced Character Animation
1 Introduction
2 Literature Review
3 Methodology
3.1 Technologies Used for 3D Model Building
3.2 Technology Used for MoCap
3.3 Integration of the Technologies Used
3.4 Constraints of the Proposed System
4 Result
5 Future Scope
References
A Comprehensive Survey of Regression-Based Loss Functions for Time Series Forecasting
1 Introduction
2 Time Series Data
3 Regression Loss Functions
3.1 Mean Absolute Error (MAE)
3.2 Mean Squared Error (MSE)
3.3 Mean Bias Error (MBE)
3.4 Relative Absolute Error (RAE)
3.5 Relative Squared Error (RSE)
3.6 Mean Absolute Percentage Error (MAPE)
3.7 Root Mean Squared Error (RMSE)
3.8 Mean Squared Logarithmic Error (MSLE)
3.9 Root Mean Squared Logarithmic Error (RMSLE)
3.10 Normalized Root Mean Squared Error (NRMSE)
3.11 Relative Root Mean Squared Error (RRMSE)
3.12 Huber Loss
3.13 Log-Cosh Loss
3.14 Quantile Loss
4 Experiments
4.1 Datasets
4.2 Performance Metrics
5 Conclusion
References
Diabetic Retinopathy Detection Using Real-World Datasets of Fundus Images
1 Introduction
1.1 Diabetic Retinopathy
1.2 Severity and Stages
2 Literature Review
2.1 Research Gaps
3 The Dataset
3.1 Retinal Image Collection
4 Related Work
5 Methodology
5.1 Data Distribution of Retinal Image Collection
5.2 Filtering Out Images with Noise
5.3 Image Cropping for Removal of Unnecessary Content
6 Model Architecture
7 Experimental Analysis
8 Results and Discussion
8.1 Deep Learning Models Overview
8.2 Diagnosis & Preventative Measures
9 Comparative Analysis
10 Future Scope
11 Conclusion
References
Deep Learning for MRI-Based Brain Tumour Identification and Classification
1 Introduction
1.1 Viewing Brains
1.2 PET Scans
1.3 CGI
1.4 MRI
1.5 Diffusion Scaling Imaging
2 Literature Survey
3 Proposed Method
3.1 Pre Processing
3.2 Classification
3.3 Characterisation
3.4 Grouping
3.5 Convolution Neural Network
4 Results and Discussion
5 Conclusion
References
Preserving Tamil Brahmi Letters on Ancient Inscriptions: A Novel Preprocessing Technique for Diverse Applications
1 Introduction
2 Literature Review
3 Methodology for Inscription Translation
3.1 Image Blurring
3.2 Binarization
3.3 Edge Detection
4 Results and Discussion
5 Conclusion
References
Analysis of Regular Machine Learning and Ensemble Learning Approaches for Term Insurance Prediction in Banking Data
1 Introduction
2 Literature Review
3 Methodology
3.1 Acquisition of Data
3.2 Analysis
3.3 Data Preprocessing
3.4 Training and Analysis of Models
4 Results
5 Conclusion
References
Platform Independent Satellite Image Processing Using GPGPU
1 Introduction
2 Literature Survey
3 Proposed Methodology
3.1 Operating System Portability and Hardware Independence
3.2 GPU Detection and Parallel Computing
3.3 Change Detection
3.4 Algorithms
4 Results and Discussions
4.1 Evaluation Environment
4.2 Evaluation Result
5 Conclusion
6 Future Scope
References
Blending Psychological Models with Modern HCI Techniques to Develop Artificial Emotional Intelligent "Affective" Systems
1 Introduction
1.1 Understanding Affective Computing
1.2 Human Emotions
1.3 Paper Organization
2 Literature Review
3 HCI Techniques for Utilizing Emotion Models
3.1 HCI Background
3.2 Modern HCI Systems & Interaction Modalities
4 Blending HCI Approaches with Psychological Models and ML Techniques
5 Conclusion
5.1 Future Scope
References
An Enhanced Deep Learning Method to Generate Synthetic Images with Features That are Comparable to Original Images Using Neural Style Transfer
1 Introduction
2 Network Architecture
2.1 Loss
2.2 Content Loss
2.3 Style Loss
3 Results
3.1 Comparative Evaluation
4 Conclusion
References
Improving Sentiment Analysis by Handling Negation on Twitter Data Using Deep Learning Approaches
1 Introduction
1.1 Contributions
1.2 Organization
2 Related Work
3 Proposed Methodology
3.1 WordNet
3.2 Preprocessing
3.3 Negation Handling
3.4 Classification
4 Results
4.1 Dataset Description
4.2 Experimental Results
5 Conclusion
References
Comparative Analysis of Deep Learning Models for Car Part Image Segmentation
1 Introduction
2 Related Works
3 Dataset Description
4 Methodology
4.1 YOLOv8 Segmentation Model
4.2 Detectron2 Mask R-CNN Resnet 101 FPN
4.3 Detectron 2 Mask R-CNN ResNeXt 101 32×8d FPN
5 Experimental Results and Observations
6 Conclusion
References
Boosting Tiny Object Detection in Complex Backgrounds Through Deep Multi-Instance Learning
1 Introduction
2 Literature Survey
2.1 Multi Instance Metric Learning and Bags
3 Methodology
3.1 Dataset Preparation
3.2 Experimental Design
4 Results and Discussion
4.1 Experimental Setup
5 Conclusion
References
Driver Drowsiness Detection System Using YoloV5
1 Introduction
2 Literature Review
3 Methodology
4 Technology Used
4.1 Design and Analysis
5 Result and Experiment
5.1 Design and Analysis
5.2 Preprocessing
5.3 Performance of the Model
5.4 Result and Discussion
6 Future Scope
7 Conclusion
References
Shift of Customer from Unorganised to Organised Sector in Retail: Is Adoption of Technology a Catalyst
1 Introduction
1.1 Background of the Problem
1.2 Research Problem and Relevance
2 Theoretical Framework and Hypothesis Development
3 Research Methodology
4 Result and Analysis
5 Findings and Discussions
6 Conclusion
6.1 Usage and Limitations
References
E-CNN-FFE: An Enhanced Convolutional Neural Network for Facial Feature Extraction and Its Comparative Analysis with FaceNet, DeepID, and LBPH Methods
1 Introduction
2 Literature Review
3 Methodology
4 Implementation
5 Conclusion
References
A Graphical Neural Network-Based Chatbot Model for Assisting Cancer Patients with Dietary Assessment in their Survivorship
1 Introduction
2 Related Work
3 Materials and Methods
3.1 Material
3.2 Software and Hardware Requirements
3.3 Method
4 Results and Discussion
4.1 Time Complexity
5 Conclusion
References
Plant Identification and Disease Detection System Using Deep Convolutional Neural Networks
1 Introduction
1.1 General Introduction
1.2 Problem Statement
2 Literature Review
2.1 System Description
2.2 System Development Method
3 Results and Discussion
3.1 Training Results
3.2 Testing Results
3.3 Project Analysis
4 Conclusion
References
Question Answering in Medical Domain Using Natural Language Processing: A Review
1 Introduction
2 Background
3 State of the Art
3.1 Some of the Most Successful LLMs for Medical QA Include
3.2 These Models Are Very Efficient at Answering a Variety of Medical Questions Including
3.3 These Dataset on Which Models Performed Very Effective Includes [19]
4 Evaluation Metrics
5 Challenges, Risk, and Limitations in Medical Question Answering
5.1 The Challenges Associated with Medical Question Answering Includes
5.2 The Limitation and Risk of LLMs in Medical QA Includes
6 Future Scope
7 Conclusion
References
A Novel Method for Communication-Efficient and Privacy-Preserving AI Model Generation and Optimization Through Federated Learning
1 Introduction
1.1 About Our Federated Learning-Based Framework
1.2 The Contributions
2 Related Work
3 Method
3.1 Efficient Learning with Pruning
3.2 Structured, Unstructured, and Hybrid Pruning
3.3 Why Learning with Pruning in FL is Efficient
3.4 Algorithm
3.5 AI Model Pruning in FL
3.6 L2-Norm
4 Comparative Study Among the Pruning Methods
4.1 Prune a Trained Network and Fine-Tune
4.2 Choose a Trained Network, Prune It with More Pruning
4.3 Take Randomly Initialize Network, Prune It After Training from Scratch
4.4 Performance Evaluation
4.5 Quantizing the Models, Compressing Them Comparing Performance
5 Conclusion
References
A Framework for Analyzing Legal Documents by Leveraging Knowledge Graphs
1 Introduction
2 Literature Survey
3 Proposed Framework
3.1 Data Gathering
3.2 Data Pre-processing
3.3 Section Segmentation
3.4 Entity Extraction
3.5 Relationship Extraction
3.6 Knowledge Graph Construction
3.7 Ontology Development
4 Proposed Benefits
4.1 Quicker Analysis
4.2 Decreased SME Dependency
4.3 Contextual Insights
5 Conclusion
6 Future Roadmap
References
Biomedical Data Management and Analytics in IOMT
1 Introduction
1.1 Synopsis of IoMT
1.2 The Requirements of the IoMT Systems
1.3 Network Architecture of Internet of Medical Things
1.4 Real-Time Analysis Remote Patient Health Monitoring
1.5 Methodology and Analysis
2 Preparation of Medical Data
2.1 Privacy and Security Using Data Fusion
2.2 Requirements of Medical Data Security
2.3 Public Medical Datasets and their Reusability
3 Processing of Medical Data
4 Architecture of Big Medical Data System
4.1 Remote Health Monitoring for Big IoT Data
4.2 Processing of Health Data and Mobility Data
5 Research Opportunities and Challenges
5.1 Practical Solutions with Case Studies
5.2 Technology and Application
5.3 Experimental Evaluation
6 Conclusions and Future Enhancements
References
Inter-State Disparities in Maternal Mortality Ratio in India-Two Decade Analysis
1 Introduction
2 Materials and Method
2.1 Study Design and Source of Data
3 Statistical Analysis
3.1 Outcome Indicator
4 Limitations
5 Results
5.1 Absolute and Relative Reduction-State-Wise Analysis
5.2 Inter-state Disparities in MMR Reduction
6 Discussion
7 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Data Management, Analytics and Innovation

Description

More details

Other editions

Additional editions

Persons

Content

System requirements