
Proceedings of the 12th International Conference on Soft Computing for Problem Solving
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book provides an insight into 12th International Conference on Soft Computing for Problem Solving (SocProS 2023), organized by The Department of Applied Mathematics and Scientific Computing, Saharanpur Campus of Indian Institute of Technology, Roorkee, India, in conjunction with Continuing Education Center during 11-13 August 2023. This book presents the latest achievements and innovations in the interdisciplinary areas of soft computing, machine learning, and data science. It covers original research papers in the areas of algorithms (artificial neural network, deep learning, statistical methods, genetic algorithm, and particle swarm optimization) and applications (data mining and clustering, computer vision, medical and health care, finance, data envelopment analysis, business, and forecasting applications). This book is beneficial for young as well as experienced researchers dealing across complex and intricate real-world problems for which finding a solution by traditional methods is a difficult task.
More details
Other editions
Additional editions

Persons
Prof. Millie Pant (MP) is a professor in the Department of Applied Mathematics and Scientific Computing (DAMSC), Saharanpur Campus of Indian Institute of Technology Roorkee, joint faculty at the Mehta Family School of Data Science and Artificial Intelligence at the Indian Institute of Technology Roorkee and adjunct faculty at AIT Thailand, Bangkok. Her expertise is in optimization algorithms, soft computing techniques, image processing, and decision-making processes. She has published more than 200 research articles in various journals and conferences of national and international repute. She has more than 8000 Google Scholar citations, and her H-index is 44. She has supervised 14 Ph.D. students and currently 10 students are doing Ph.D. under her supervision. She has completed 4 bilateral sponsored projects with Germany and Russia, UK and Czech Republic and two national projects sponsored by DST and DRDO. She has conducted several short-term courses sponsored by Deloitte, TSW, DST, and QIP in the areas of optimization, evolutionary algorithms, and artificial intelligence. She is one of the founder chairs for SocProS conferences and has been the chair of several other conferences as well.
Dr. Kusum Deep, is a full Professor (HAG), with the Department of Mathematics as well as Joint Faculty at the Mehta Family School of Data Science and Artificial Intelligence at the Indian Institute of Technology Roorkee, India. Also, she is a Visiting Professor, Liverpool Hope University, UK, University of Technology Sydney, Australia and University of Wollongong, Australia. With B.Sc Hons & M.Sc Hons. School from Centre for Advanced Studies, Panjab University, Chandigarh, she is an M.Phil Gold Medalist. She earned her PhD from UOR (now Indian Institute of Technology Roorkee) in 1988. She has been a national scholarship holder and a Post-Doctoral from Loughborough University, UK assisted by International Bursary funded by Commission of European Communities, Brussels. She has won numerous awards like Khosla Research Award, UGC Career Award, Starred Performer of IITR Faculty, best paper awards by Railway Bulletin of Indian Railways, special facilitation in memory of late Prof. M. C. Puri, AIAP Excellence Award. She is one of the four women from IIT Roorkee to feature in the ebook "Women in STEM-2021" celebrating the contributions made by 50 Indian women in STEM published by Confederation of Indian Industries. According to Stanford University, she falls within top 2 % of the scientists in the world for 2019 and 2020. In 2021 she bagged the prestigious POWER grant awarded by SERB-DST, Govt. of India. In 2022 she is leading a collaborative consultancy project with Deloitte. On September 5, 2022, she was awarded Uttarakhand State Level "Excellence in Research of the Year 2022 Award, jointly organized in collaboration with DIVYA HIMGIRI (Premier Weekly News Magazine of Uttarakhand), VMSB Uttarakhand Technical University, Uttarakhand State Council for Science & Technology (UCOST) and Society for Research & Development in Science, Technology and Agriculture (SRADSTA). According to the 9th edition of Research.com ranking of the best researchers in the arena of Computer Science she holds a national rank 100 and world rank 10112. He google scholar citations are 6501, h-index is 39 and i10-index is 105. She has authored two books, supervised 20 PhDs, and published 125 research papers. She is a Senior Member of ORSI, CSI, IMS and ISIM. She is one of the the Editors of Engineering Applications of Artificial Intelligence, Elsevier and many reputed journals. She is the Founder President of Soft Computing Research Society, India. She is the General Chair of series of International Conference on Soft Computing for Problems Solving (SocProS). She has a vast teaching experience in Mathematics, Operations Research, Numerical and Analytical Optimization, Artificial Intelligence, Data Science, Parallel Computing, Computer Programming, Numerical Methods, etc. Her research interests are nature inspired optimization techniques, particularly Evolutionary Algorithms, and Swarm Intelligence Techniques and their applications to solve real life problems as well as artificial intelligence and data science.
Prof. Atulya K. Nagar holds the Foundation Chair as Professor of Mathematical Sciences and is the Pro Vice-Chancellor (Research) at Liverpool Hope University, United Kingdom. He received a prestigious Commonwealth Fellowship for pursuing his doctorate (DPhil) in Applied Nonlinear Mathematics, which he earned from the University of York (UK) in 1996. He holds BSc (Hons), MSc, and MPhil (with distinction) in Mathematical Physics from the MDS University of Ajmer, India. Prof Nagar is a fellow of the Institute of Mathematics and Its applications (FIMA) and a fellow of the Higher Education Academy (FHEA). His research expertise is in the area of Applied Non-linear Analysis, Natural Computing and Systems Engineering.
Content
- Intro
- Preface
- Contents
- Editors and Contributors
- MIM-ViT: Deepfake Detection Using Masked Image Modelling and Vision Transformer
- 1 Introduction
- 2 Related Work
- 2.1 Deepfake Generation
- 2.2 Deepfake Detection
- 2.3 Research Gaps in Existing Work
- 3 Proposed Architecture
- 3.1 Dataset
- 3.2 Preprocessing
- 3.3 Face Quality Testing
- 3.4 Model
- 4 Experimental Setup
- 5 Results and Discussion
- 5.1 Performance Metrics
- 5.2 Experiments
- 6 Conclusion and Future Scope
- References
- A Study on Generalized Hough Transform for Detecting Fuzzy Lines
- 1 Introduction
- 2 Preliminaries
- 2.1 Classical Hough Transform
- 3 Fuzzy Hough Transform
- 3.1 Generalized Version of Fuzzy Hough Transform
- 3.2 Fuzzy Line Detection Using FHT
- 4 Similarity Measure Between Two Fuzzy Lines
- 4.1 Distance Measure Between Two Fuzzy Lines
- 5 Experimental Results
- 6 Conclusion
- References
- 'KSK' Algorithm for Optimizing DCS Performance Using 'R'
- 1 Introduction
- 2 Literature Review
- 3 Objective
- 4 Technique
- 5 Flowchart of Algorithm
- 6 Implementation
- 7 Comparison
- 8 Conclusion
- References
- A Knee-Based Multi-objective Optimization for Gait Cycle of 25-DOF NAO Humanoid Robot
- 1 Introduction
- 2 Past Studies
- 3 Knee-Based Optimization Methodology
- 3.1 Angle-Based Focus
- 3.2 Utility-Based Focus
- 4 Problem Definition
- 5 Multi-Objective Optimization Formulation
- 6 Results and Discussion
- 7 Conclusions
- References
- Estimating Severity for Knee Osteoarthritis Radiographs Using Deep Learning and Machine Learning Algorithms
- 1 Introduction
- 2 Literature Review
- 3 Methods and Materials Used
- 3.1 Dataset Used
- 3.2 Dataset Pre-processing
- 3.3 Extracting Relevant Features
- 3.4 Classification
- 3.5 Investigating Parameters
- 4 Experimental Analysis
- 5 Conclusion
- References
- Knee-Osteoarthritis Detection Using Deep Learning
- 1 Introduction
- 2 Literature Review
- 3 Proposed Model
- 4 Methodology
- 4.1 Image Preprocessing
- 4.2 Application of CNN Algorithm
- 4.3 Dataset
- 4.4 Training
- 5 Results
- 6 Implementation of Online Tool
- 7 Benefits
- 8 Conclusion and Future Scope
- References
- Hybrid Method for Named Entity Recognition in Kumauni Language Using Machine Learning
- 1 Introduction
- 1.1 NER and Its Approaches
- 1.2 Applications of Named Entity Recognition
- 2 Review of Literature
- 3 Background Study
- 4 Problem Formulation
- 5 Research Objectives
- 6 Research Methodology
- 6.1 CRF
- 6.2 CNN
- 6.3 Bi-LSTM
- 7 Proposed Methodology
- 8 Results and Discussion
- 8.1 Dataset Description
- 8.2 Performance Measure
- 9 Results and Discussion
- 10 Comparative Analysis
- 11 Conclusion and Future Work
- References
- Implementation of Basic Mathematical Operations on Openpower-ISA of Libresoc
- 1 Introduction
- 2 Literature Survey
- 3 Methodology and Implementation
- 4 Results and Discussions
- 4.1 Implementation for Addition Operation
- 4.2 Implementation for Subtraction Operation on the Decoder Test Cases of Openpower-ISA
- 4.3 Implementation for Multiplication Operation
- 4.4 Implementation for Division Operation
- 5 Conclusion
- 6 Future Scope
- References
- Machine Learning-Based Node Localization in IoT-Assisted WSN: An Initial Framework for Real-Time Applications
- 1 Introduction
- 1.1 Main Contributions
- 2 Related Work
- 3 Localization in IoT
- 4 Machine Learning-Based Localization in IoT Context
- 5 Proposed Framework for ML-Based Localization in IoT-Assisted WSN
- 5.1 Offline Phase
- 5.2 Model Selection and Training
- 5.3 Online Phase
- 5.4 Node Localization
- 6 Conclusion
- 7 Future Scope
- References
- Implementing Blockchain Technology in Healthcare: An Overview, Key Requirements, and Challenges
- 1 Introduction
- 2 Literature Review
- 3 Proposed Model
- 4 Future Scope
- 5 Conclusion
- References
- Path Planning for Autonomous Ground Vehicles by Applying Modified Harris Hawks Optimization Technique
- 1 Introduction
- 2 Problem Description and System Modeling
- 3 Modified Harris Hawks Optimization (MHHO) Algorithm
- 4 Simulation Results and Discussions
- 4.1 Performance of the Modified HHO Optimization Algorithm
- 4.2 Performance of MHHO Optimization Algorithm in Path Planning Algorithms
- 5 Conclusion and Future Scope
- References
- Glaucoma Classification Using Improved Pretrained Model
- 1 Introduction
- 2 Related Work
- 3 Proposed Methodology
- 3.1 Phase 1: RIM-1 DL Dataset
- 3.2 Phase 2: Preprocessing
- 3.3 Phase 3: Transfer Learning
- 3.4 Phase 4: Hybrid Model Development
- 4 Results and Discussion
- 5 Conclusion
- References
- Performance Optimization of a Waste Heat-Operated Tri-generation Cycle Under Different Energy Situations
- 1 Introduction
- 2 System Description and Performance Evaluation
- 2.1 Description of the Cycle
- 2.2 Assumptions Required During Simulation
- 2.3 Performance Evaluation of the Cycle
- 3 Optimization Strategy Used in the Study
- 3.1 Dragonfly Optimization Algorithm
- 3.2 Flowchart of the Optimization Strategy
- 4 Results
- 4.1 Calculation of Suitable Range of GF, PF, and SF
- 4.2 Optimized Results for Residential or Goods Storage Facilities
- 5 Conclusion
- References
- Organizational Supply Chain Risk Assessment Using Machine Learning and Backpropagation Neural Network
- 1 Introduction
- 2 Literature Review
- 3 Research and Analysis on the Model Construction for Supply Chain Risk Assessment
- 3.1 Research Methodology
- 3.2 Backpropagation Neural Network Model
- 4 Simulation Result
- 5 Conclusion
- References
- An Approach to Find Critical Path Using Trapezoidal Picture Fuzzy Numbers
- 1 Introduction
- 2 Preliminaries
- 2.1 Trapezoidal Picture Fuzzy Numbers
- 2.2 Operations on Trapezoidal Picture Fuzzy Numbers ch15ddd
- 2.3 Comparison of TPFNs Based on: Expected Values ch15ddd
- 3 Trapezoidal Picture Fuzzy Critical Path Method
- 4 Conclusion and Future Research
- References
- Comparative Analysis of Machine Learning and Deep Learning Algorithms for Automatic Sleep Staging Using EEG Signals
- 1 Introduction
- 2 Literature Review
- 2.1 Machine Learning
- 2.2 Deep Learning
- 2.3 Limitation
- 2.4 Contribution
- 3 Proposed Methodology
- 3.1 Dataset
- 3.2 Pre-processing
- 3.3 Feature Extraction and Selection
- 3.4 Classification Algorithm
- 3.5 Performance Evaluation
- 4 Result Analysis
- 4.1 Machine Learning Evaluation
- 4.2 Deep Learning Evaluation
- 5 Conclusion and Future Work
- References
- Randomized Shuffled Hierarchical Partitioning Technique for Enhancing Efficiency of Swarm Algorithms
- 1 Introduction
- 2 Literature Review
- 2.1 Hierarchical Partitioning
- 2.2 Modified Hierarchical Partitioning
- 2.3 Random Partitioning
- 2.4 Self-adaptive Multi-population Technique with Random Partitioning (SAMPR)
- 3 Proposed Variants
- 3.1 Shuffled Hierarchical Partitioning (SHier)
- 3.2 Randomized Hierarchical Partitioning (RHier)
- 3.3 Randomized Shuffled Hierarchical Partitioning (RSHier)
- 4 Results and Discussion
- 4.1 Comparison Among the Proposed Techniques with HIER and mHIER
- 4.2 Testing the Applicability of RSHier Over Multiple Swarm Algorithms
- 4.3 Comparison Over CEC 2014 Function Set
- 4.4 Studying Diversity and Convergence Improvements
- 5 Conclusion
- References
- A Novel Approach to Solve the Interval-Valued Fermatean Fuzzy Transportation Problem
- 1 Introduction
- 2 Preliminaries
- 3 Mathematical Formulation
- 3.1 Interval-Valued Transportation Problem (IVTP)
- 3.2 Equivalent Crisp Transportation Problem Using Order Relation leqRC
- 4 Solution Methodology
- 5 Numerical Example
- 5.1 Discussion
- 6 Conclusion and Future Research Scope
- References
- An Ensemble of PSO and Artificial Electric Field Algorithm for Computationally Expensive Optimization Problems
- 1 Introduction
- 2 Literature Review
- 3 Ensemble of PSO and AEFA
- 3.1 PSO
- 3.2 AEFA
- 3.3 Proposed Algorithm
- 3.4 Time and Space Complexity of the PSAEF Algorithm
- 3.5 Advantages and Disadvantages of the Proposed PSAEF Algorithm
- 4 Results and Discussions
- 5 Component-Wise Comparison
- 6 Conclusion and Future Scope
- References
- Popularity Prediction of Online Social Media Content: A Bibliometric Analysis
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 4 Results
- 4.1 Document and Source Type
- 4.2 Evolution of Publication Over Years
- 4.3 Keyword Analysis
- 4.4 Analysis of Authorship
- 4.5 Analysis of the Author's Main Affiliation
- 4.6 Analysis of the Author's Countries
- 4.7 Citation Analysis
- 4.8 Analysis of Journals
- 5 Conclusion
- References
- Development of an Autonomous Driving Car Prototype Using FPGA
- 1 Introduction
- 2 Literature Survey
- 3 Proposed System
- 3.1 Architecture
- 3.2 Algorithms Used
- 4 Proposed Features
- 4.1 Lane Detection
- 4.2 Object Detection
- 4.3 Collision Avoidance
- 5 Result
- 5.1 Testing and Validation
- 6 Suggested Improvements
- 7 Future Scope
- 8 Conclusion
- References
- Custom CDGNet Architecture for Precise Human Part Semantic Segmentation
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 4 Experimental Analysis
- 4.1 Dataset Used
- 4.2 Evaluation Metrics
- 4.3 Quantitative Analysis
- 5 Conclusion and Future Work
- References
- Dissipative and Non-dissipative Cell Balancing SoC Constant Current, Voltage Charging of Li-Ion Battery for EV Application
- 1 Introduction
- 2 Lithium-Ion Battery
- 2.1 Cell Balancing
- 2.2 Cell Balancing Function
- 3 Battery Calculation
- 3.1 Battery Characteristics
- 4 Battery State of Charge (SoC)
- 4.1 Current Integration
- 4.2 Formula for Estimation Coulomb Counting
- 4.3 SoC Estimation
- 4.4 % Depth of Discharge
- 4.5 State of Health
- 4.6 C-Rate
- 4.7 Battery Voltage
- 4.8 Battery Current
- 5 Simulation Results
- 5.1 Constant Current Charging
- 5.2 Constant Voltage Control
- 5.3 Cell Balancing
- 5.4 State of Charge (SoC)
- 6 Conclusion
- References
- Auto-Detection of Field-Level Dependencies in Data Workflow on a Distributed Platform
- 1 Introduction
- 2 HPCC Systems and ECL
- 3 ECL IR (Intermediate Representation)
- 4 Design and Implementation
- 4.1 Generation of ECL IR
- 4.2 Forward Tracing
- 4.3 Backward Tracing
- 4.4 Graph Representation
- 5 Programming Languages and Their Usage
- 5.1 ECL
- 5.2 C++ 17
- 5.3 JavaScript
- 6 Experimental Results and Testing
- 6.1 Evaluation
- 6.2 Testing
- 6.3 Example Outputs
- 7 Conclusion
- 7.1 Limitations and Future Enhancements
- References
- The Behavioral Factors Affecting Online Purchase Intention Among Young Adults
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Proposed Conceptual Model
- 3.2 Development of Questionnaire
- 4 Analysis and Results
- 4.1 Data Collection and Preprocessing
- 4.2 Analysis and Model Revision
- 5 Conclusion
- References
- Workload Forecasting Model for Resource Management in Cloud Data Center
- 1 Introduction
- 2 Related Work
- 3 Proposed Model
- 3.1 Workload Traces
- 3.2 Learning Algorithms
- 3.3 Evaluation Criteria
- 4 Experiment
- 5 Result Analysis
- 6 Conclusion and Future Work
- References
- Unveiling the Mystery of Membrane Potential in a Neuron
- 1 Introduction
- 2 Overview of Ionic Mechanisms Underlying Membrane Potential
- 3 Previous Work on Analysis of Membrane Potential Using Morris Lecar Model
- 4 Mathematical Framework
- 4.1 Model Paramerization
- 4.2 Simulation Method
- 5 Results
- 5.1 Comparison of the Dynamics of Membrane Voltage and Its Double Derivative Under Base Conditions
- 5.2 Varying the Stimulating Current
- 5.3 Varying the Calcium Conductance
- 5.4 Varying the Potassium Conductance
- 5.5 Varying the Temperature Dependent Component
- 6 Discussions and Conclusions
- 7 Future Research
- References
- A Cascading-Failure-Aware Distributed Computing System with Performance Sharing: Reliability and Robustness Analysis
- 1 Introduction and Related Works
- 2 Methodology
- 3 Results and Discussion
- 4 Conclusion
- References
- MineralVisio: A Deep Learning Based Mineral Identification System
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 About the Dataset
- 3.2 Data Preprocessing
- 3.3 Model Development
- 3.4 Evaluation Metrics
- 4 Results and Discussions
- 5 Conclusion
- References
- A Hybrid Approach for Depression Classification Using BERT and SVM
- 1 Introduction
- 2 Literature Survey
- 3 Preliminaries
- 4 Methodology
- 4.1 Dataset
- 4.2 Feature Extraction
- 4.3 Classification
- 4.4 Experimental Results
- 4.5 Performance
- 5 Conclusion and Future Work
- References
- Enhancing Word Sense Disambiguation Performance on WiC-TSV Dataset Using BERT-LSTM Model
- 1 Introduction
- 1.1 Objective
- 1.2 Organization of Paper
- 2 Literature Review
- 3 Methodology
- 3.1 Objective
- 3.2 Data Augmentation
- 3.3 Model Architecture
- 4 Experiment and Result Analysis
- 4.1 Dataset
- 4.2 Experiment
- 4.3 Result Analysis
- 5 Experiment and Result Analysis
- References
- Unleashing Deep Reinforcement Learning: A Promising Alternative for Imbalanced Dataset Classification
- 1 Introduction
- 2 Related Work
- 3 Imbalanced Datasets
- 3.1 Breast Cancer BreakHis Dataset
- 3.2 Stroke Prediction Dataset
- 4 Algorithm Implementation
- 4.1 Deep Reinforcement Learning Algorithm (DQNimb)
- 4.2 SMOTE
- 4.3 SVM-SMOTE
- 4.4 Adaptive Synthetic Sampling (ADASYN)
- 4.5 Deep Neural Network
- 5 Methodology
- 5.1 Methodology Adopted for Breast Cancer Detection
- 5.2 Methodology Adopted for Stroke Prediction
- 6 Experimentation Results
- 7 Conclusion
- References
- MetroPT Predictive Maintenance Using Logistic Regression and Random Forest with Isolation Forest Preprocessing
- 1 Introduction
- 2 Dataset Used
- 3 Methodology
- 3.1 Isolation Forest Preprocessing
- 3.2 Proposed Work
- 4 Results
- 4.1 Random Forest Classifier
- 4.2 Logistic Regression
- 4.3 Output
- 4.4 Discussions
- 4.5 Conclusions
- References
- Pothole Detection of Road Pavement by Modified MobileNetV2 for Transfer Learning
- 1 Introduction
- 2 Related Work
- 3 Modified MobileNetV2 Architecture
- 4 Dataset
- 5 Proposed Methodology
- 6 Results and Discussion
- 7 Conclusion
- References
- Malware Classification Using Deep Learning Approaches
- 1 Introduction
- 1.1 Overview
- 1.2 Role of Artificial Intelligence in Malware Classification
- 2 Related Work
- 3 Methodology
- 3.1 Dataset Collection
- 3.2 Preprocessing of Dataset
- 3.3 Class Decomposition
- 3.4 DTC-Net Architecture
- 4 Results and Discussions
- 5 Conclusion
- References
- Identifying Outliers Using Voronoi Circles
- 1 Introduction
- 2 Related Works
- 3 Basic Concepts and Preliminaries
- 3.1 Convex Hull
- 3.2 Voronoi Diagram
- 3.3 Empty Circles
- 3.4 K-Nearest Neighbors Algorithm
- 3.5 PCA
- 4 Proposed Model
- 4.1 Algorithmic Approach
- 5 Results
- 5.1 Case Study-1
- 5.2 Case Study-2
- 6 Conclusions
- References
- Brain Tumor Detection by Fusion Techniques
- 1 Introduction
- 2 Related Work
- 3 Materials and methods
- 3.1 Methodology
- 3.2 Proposed Network Architecture
- 4 Results and Discussion
- 5 Conclusion and Future Scope
- References
- Fault Prediction in Software Systems Using Saliency Maps in Machine Learning
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Input Parameters
- 3.2 Steps for Detecting Failure in Autonomous Cars Using Saliency Map
- 4 PilotNet Model
- 5 Saliency Maps and Failure Predictor Model
- 6 Free Lane Boundary Detection Integration
- 7 Result Analysis and Implementation
- 7.1 Analysis of Driving Scenes Using Steering Wheel Angle
- 7.2 Illustration of Mean Absolute Error
- 7.3 Performance of the Predictive Model
- 8 Conclusion and Future Work
- References
- On Two-Dimensional Approximate Pattern Matching Using Fuzzy Automata
- 1 Introduction
- 2 Preliminaries
- 2.1 One-Dimensional Pattern Matching
- 2.2 Approximate Fuzzy Pattern Matching
- 2.3 Two-Dimensional Pattern Matching
- 3 One-Dimensional Approximate Fuzzy Multiple Pattern Matching Using Fuzzified Aho-Corasick Automata
- 4 Two-Dimensional Fuzzy Approximate Pattern Matching Using FACA
- 5 Conclusion
- References
- Detecting URL Phishing Using BERT and DistilBERT Classifiers
- 1 Introduction
- 2 Literature Review and Background
- 2.1 Literature Review
- 2.2 Background
- 3 Proposed Methodology
- 4 Experiment Results
- 4.1 Experiment-1: Bert Classifier
- 4.2 Experiment-2: DistilBERT Classifier
- 4.3 Comparative Analysis
- 5 Conclusion
- References
- An Efficient Credit Card Fraud Detection Using SMOTE Under Machine Learning Environment
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Dataset
- 3.2 Oversampling Using SMOTE
- 3.3 Train-Test Split
- 3.4 Machine Learning Algorithms
- 3.5 Assessment of Accuracy
- 4 Result and Analysis
- 4.1 Without SMOTE
- 4.2 With SMOTE
- 5 Conclusion
- References
- In Hospital Mortality Risk Prediction for HF Patients Using SMOTE and Various Machine Learning Algorithms
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Data Extraction
- 3.2 Data Pre-processing
- 3.3 Decision Tree
- 3.4 Random Forest
- 3.5 XGBoost
- 3.6 K-Nearest Neighbor
- 3.7 Linear Discriminant Analysis
- 4 Result and Analysis
- 4.1 Without SMOTE
- 4.2 With SMOTE
- 5 Conclusion
- References
- A Comparative Scrutiny on Machine Learning and Deep Learning Approaches for Fraudulent Transaction Discovery in Credit Card Data
- 1 Related Work
- 2 Proposed Solution
- 2.1 Processing Steps
- 2.2 Dataset
- 2.3 Data Preprocessing
- 2.4 Algorithms
- 2.5 Evaluation Metrics
- 3 Experimental Results and Discussion
- 4 Conclusion and Future Work
- References
- Ensemble Multi-label Feature Selection Using Weighted Harmonic Mean
- 1 Introduction
- 1.1 Related Studies
- 1.2 Highlights
- 2 Preliminaries
- 2.1 Multi-label Learning
- 2.2 Ensemble Feature Selection
- 2.3 Weighted Harmonic Mean
- 3 Proposed Method
- 4 Experimental Studies
- 4.1 Datasets
- 4.2 Classifier Settings
- 4.3 Evaluation Measures
- 4.4 Base Methods
- 4.5 Comparing Methods
- 4.6 Results and Discussion
- 4.7 Stability Analysis
- 4.8 Statistical Test
- 5 Conclusion
- References
- Enhancing Industry 5.0: Leveraging Data Analytics with IBM Infosphere DataStage and Qlik Sense for Sustainable Entrepreneurship
- 1 Introduction
- 1.1 IBM Infosphere
- 1.2 Qlik Sense
- 2 Research Gap
- 3 Motivation
- 4 Research Methodology
- 4.1 ETL Process
- 4.2 Schema Design
- 5 Analysis/Result
- 6 Conclusion
- References
- Power Quality Improvement of Grid Tied Hybrid Power System by Using ANFIS Controller
- 1 Introduction
- 2 Fuzzy MPPT System
- 2.1 PV-WIND Power System Design
- 2.2 MPPT
- 2.3 Grid Synchronization
- 2.4 ANFIS Controller
- 2.5 Inverter Control
- 3 Results and Discussion
- 4 Conclusions and Future Scope
- References
- Metaheuristic and Exact Approaches for Cost Optimization in Multi-Echelon Multimodal Transportation Network
- 1 Introduction
- 2 Description of Multi-Echelon Multimodal Transportation Problem
- 2.1 Mathematical Optimization Model for Multimodal Transportation Network
- 2.2 Solution Methodology to Multimodal Transportation Problem
- 3 Results and Discussion
- 3.1 Case Scenarios for Multimodal Transportation Problem
- 3.2 Computational Experiments for Multimodal Transportation Problem
- 4 Conclusion and Future Directions of Research
- References
- Successive Iteration Approach for Solvability of Second-Order Semilinear Fuzzy Systems
- 1 Introduction
- 2 Fundamental Backgrounds
- 3 Solvability of the System
- 4 Example
- 5 Conclusion
- References
- Prediction of Breast Cancer Grade Using Explainable Machine Learning
- 1 Introduction
- 2 Methods
- 2.1 Data
- 2.2 Data Pre-processing
- 2.3 Models
- 2.4 Kaplan-Meier Model
- 2.5 Cox Proportional Hazard (CPH)
- 2.6 Extreme Gradient Boosting (XGB)
- 3 Evaluation
- 3.1 Concordance Index (C-Index)
- 3.2 Explainability
- 4 Results
- 5 Discussion
- 6 Conclusion
- References
- A Novel Approach for Traffic Rules Violation Detection Using Deep Learning
- 1 Introduction
- 2 Literature Survey
- 2.1 Vehicle Detection and Classification
- 2.2 Helmet Detection
- 2.3 License Plate Detection
- 3 Proposed Methodology
- 3.1 Frames Extraction
- 3.2 Vehicle Detection and Classification
- 3.3 Helmet Detection
- 3.4 Image Super-Resolution
- 3.5 License Plate Detection
- 4 Architectural Design
- 5 Experimental Setup
- 5.1 System Specifications
- 5.2 Dataset
- 6 Results and Analysis
- 6.1 Helmet Detection
- 6.2 Number Plate Detection
- 6.3 Benchmark Analysis
- 7 Conclusion
- 8 Future Work
- References
- Integrating Thermal Mechanisms with Machine Learning for Accurate State of Health Estimation in Lithium-Ion Batteries
- 1 Introduction
- 1.1 Battery Modelling
- 1.2 State of Health (SOH)
- 1.3 Li-Ion Battery Ageing
- 1.4 Thermal Stress
- 2 Dataset Description
- 2.1 Dataset Creation
- 2.2 Data Preprocessing
- 2.3 Feature Selection
- 2.4 Proposed Methodology
- 3 Machine Learning Models and Algorithms
- 3.1 Support Vector Regression (SVR)
- 3.2 Random Forest Regressor (RF)
- 3.3 K-Nearest Neighbour Regressor Algorithm (K-NN)
- 3.4 Gradient Boosting Regressor (Gr. Boost Regr.)
- 3.5 Artificial Neural Networks (ANN)
- 4 Experiment Results
- 5 Validation Analysis
- 6 Conclusion
- References
- CNN-Based Audio Word Comparison: Exploring MobileNet for Similarity Assessment
- 1 Introduction
- 2 Related Work
- 2.1 Study Related to Sound and Its Spectrogram Features
- 2.2 Mel Spectrogram
- 3 Tools and Materials
- 3.1 Google Speech Command Dataset
- 3.2 Librosa
- 4 Methodology
- 4.1 Overview of Related Work
- 4.2 Data-Preprocessing
- 4.3 Deep Learning Model: MobileNet
- 4.4 Collection of Real-Time Samples for Testing Model
- 4.5 Cosine Similarity
- 5 Implementation
- 5.1 Benchmarks for Real-Time Collected Dataset
- 6 Results and Discussion
- 7 Future Work
- 8 Conclusion
- References
- A Novel Bi-objective Credibilistic Mean-Semivariance Portfolio Selection Problem with Coherent Triangular Fuzzy Numbers
- 1 Introduction
- 2 Preliminaries
- 3 Model Formulation
- 4 Empirical Results and its Analysis
- 5 Conclusion
- References
- Speech-to-Speech Translation Using Transformer Neural Network
- 1 Introduction
- 2 Literature Review
- 3 Methodology and Implementation
- 3.1 Dataset
- 3.2 Proposed Methodology
- 4 Implementation
- 5 Results and Conclusions
- 6 Future Scope
- References
- Stock Price Prediction Using ARIMA, LR and LSTM
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Data Source
- 3.2 ARIMA Model
- 3.3 LSTM Model
- 3.4 Linear Regression
- 3.5 RMSE
- 3.6 MAPE
- 4 Result and Analysis
- 5 Conclusion
- References
- A Novel Solution for Fuzzy Wave Equation
- 1 Introduction
- 2 Definitions, Notations, and Preliminaries
- 2.1 Special Fuzzy Numbers
- 2.2 Continuity and Differentiability of Fuzzy Function
- 3 Main Results
- 3.1 Fuzzy Adomian Decomposition Analysis
- 3.2 Fuzzy Homotopy Perturbation Technique
- 3.3 Fuzzy Laplace Transformation
- 4 Numerical Results and Discussion
- 5 Conclusion
- References
- A Hybrid Model for Rain Prediction Using Machine Learning Algorithm
- 1 Introduction
- 2 Literature Review
- 3 Proposed Method
- 3.1 Split Data
- 3.2 Feature Selection
- 3.3 RFC and GBC Train
- 3.4 Combined RFC and GBC
- 3.5 Train LR
- 3.6 Test Model
- 3.7 Random Forest Classifier (RFC)
- 3.8 Gradient Boosting Classifier (GBC)
- 3.9 Linear Regression (LR)
- 4 About the Dataset
- 5 Result and Discussion
- 6 Conclusions and Future Scope
- References
- An Ecologically Sustainable Omnichannel Fresh Food Distribution Model Considering Freshness-Keeping Effort and Carbon Emissions
- 1 Introduction and State of the Art
- 2 Problem Description and Formulation
- 3 Case Study
- 4 Discussion
- 5 Conclusion
- References
- A Framework to Detect Social Distancing Violation and Mask Use in Public Places
- 1 Introduction
- 2 Literature Survey
- 3 Methodology
- 4 Results and Discussion
- 5 Conclusion
- References
- Application of Regression Analysis of Student Failure Rate
- 1 Introduction
- 2 Literature Review
- 3 Proposed Model
- 3.1 Data Loading
- 3.2 Data Preprocessing
- 3.3 Exploratory Data Analysis
- 3.4 Model Selection
- 3.5 Model Tuning
- 4 Dataset
- 5 Implementation
- 5.1 Linear Regression
- 5.2 Decision Tree
- 6 Result
- 7 Conclusion and Future Scope
- References
- Machine Learning-Based Sound Event Detection: A Case Study for Noise Identification in Classroom Environment
- 1 Introduction
- 2 Literature Review
- 3 Methodology
- 3.1 Pre-processing
- 3.2 Feature Representation and Extraction
- 3.3 CNN
- 3.4 Proposed Framework for Deep Feature Extraction
- 4 Experiments and Results
- 4.1 Datasets
- 4.2 Permitted Noise Levels in Academic Environment
- 4.3 Experiment and Analysis
- 4.4 Application of Proposed Sound Event Detection
- 5 Discussion
- References
- Performance Analysis of Indian States and Union Territories for Covid-19 Management Through DEA and Machine Learning
- 1 Introduction
- 2 Literature Review
- 3 Exploratory Data Analysis (EDA)
- 4 Methodology
- 4.1 Super-Efficiency Data Envelopment Analysis (SE-DEA) Model
- 4.2 Machine Learning Techniques
- 5 Data Collection and Preprocessing
- 6 Results and Discussion
- 6.1 Performance of the States and UTs Without Taking Literacy Rate into Consideration
- 6.2 Performance of the States and UTs with Taking Literacy Rate into Consideration
- 6.3 Relation Between the Literacy Rate and Efficiency Score
- 6.4 An Analysis of the Results of 10 Most Populated States
- 7 Conclusion
- References
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.