Search
51 articles for “class imbalance”
-
Class Imbalance Reduction and Training Data Selection for Cross Project Defect Prediction
Abstract: The research aims to predict errors in a targeted project using data from other projects. This project is named as the Cross-Project Defect Prediction (CPDP). There are a number of ways available to improve the predictable performance of CPDP models. However, there is no comparison of modern methods. Predictability facilitates the rational distribution of testing resources by detecting software modules that may be problematic before releasing products. If a project …
Published in Journal of Software Engineering Tools & Technology Trends · Vol. 9, Issue 3, 2022 · pp. 12–20 Read article
-
A Review: Identification of Credit Card Fraud Using Machine Learning and Anomaly Detection Approach’s on Imbalanced Data
Abstract: Credit cards are among the most widely used payment methods in today's culture, and online purchases have become quite popular. Credit card fraud has emerged as a problem in this industry as a direct result of its popularity. The issue of credit card fraud is becoming a global problem. Credit card fraud has increased due to the widespread use of these payment methods. Thanks to credit card use, e-commerce has …
Published in Recent Trends in Programming languages · Vol. 10, Issue 3, 2023 · pp. 27–40 Read article
-
Real-time DDoS Attack Prediction in SDN Environments Using Machine Learning
Abstract: The ever-growing reliance on sdn-based services necessitates robust security measures against Distributed Denial-of-Service (DDoS) attacks that threaten service availability. This project investigates the development of a real-time prediction system for DDoS attacks in sdn environments, leveraging the power of machine learning. The proposed system employs a Decision Tree classification algorithm implemented in Python. To ensure accurate attack identification, the system meticulously addresses data preprocessing challenges inherent in network traffic datasets. …
Published in Journal Of Network security · Vol. 13, Issue 1, 2025 · pp. 16–27 Read article
-
Knowledge discovery in software defect datasets using learning algorithms
Abstract: In this paper, the learning impact on various classification models were studied which were built using binary class-imbalanced data. Before the learning process, some preprocessing techniques were applied to training datasets for removing the redundancy. Nowadays feature selection and sampling techniques become an essential tool for many data mining task because learning algorithms do not perform well with defective datasets, dimensionality reduction problem arises. Sampling technique is also used to …
Published in Journal of Software Engineering Tools & Technology Trends · Vol. 5, Issue 2, 2018 · pp. 18–26 Read article
-
A Comprehensive Analysis of Machine Learning Models for Credit Card Fraud Detection
Abstract: This paper presents an indepth comparison of various machine learning models—Logistic Regression, Support Vector Classification (SVC), and Neural Networks (NN)—in the context of credit card fraud detection. The analysis spans multiple performance metrics, including accuracy, F1 score, precision, recall, and computational efficiency. Logistic Regression demonstrates competitive performance in terms of accuracy, but its poor precision renders it unsuitable for fraud detection tasks. Conversely, the Neural Network exhibits balanced precision and …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 3, 2025 Read article
-
Soil Analysis Mechanisms for Smart Agriculture-A Review
Abstract: Agriculture, Horticulture, as the single biggest client of freshwater on a worldwide premise and as a significant reason for corruption of surface and groundwater assets through disintegration and synthetic overflow, has cause to be worried about the worldwide ramifications of water quality. The related agro food preparing industry is likewise a huge wellspring of natural contamination in many nations. Hydroponics is currently perceived as a significant issue in freshwater, estuarine …
Published in Recent Trends in Sensor Research & Technology · Vol. 8, Issue 3, 2021 · pp. 6–10 Read article
-
Vehicle Insurance Fraud Detection Using Supervised Neural Network Model
Abstract: Vehicle insurance fraud is a serious problem that causes huge financial losses to insurance companies. In recent years, developing fraud detection models using machine-learning techniques has been of great interest. This study proposes a novel approach for vehicle insurance fraud detection using Supervised Neural network model on the Kaggle Vehicle Insurance Fraud Detection dataset. The initial step in this study involves performing data pre-processing and feature extraction on the dataset, …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 10, Issue 1, 2023 · pp. 32–39 Read article
-
Strategy for Improving Software Maintenance Using Machine Learning for Security Requirements: A Review
Abstract: Within the area of software technical education, the significance of software defect discovery has increased as a research focus to enhance program reliability. By maximizing testing resources and assisting developers in identifying potential problems using program defect predictions, program dependability is increased. Applying software engineering (SE) techniques to critical and intricate systems, like networking and security systems, is imperative. Traditional methods of predicting software maintainability have limitations, particularly in balancing …
Published in International Journal of Information Security Engineering · Vol. 2, Issue 2, 2024 · pp. 36–48 Read article
-
Eye Disease Classification Using K-means Clustering Algorithm and Ensemble Classification Approach
Abstract: In this study, we present a comprehensive approach for the classification of eye diseases, specifically targeting normal, cataract, glaucoma, and diabetic retinopathy conditions. This research uses a dataset from Kaggle, which provides a wide and varied collection of retinal images to ensure good representation. The methodology encompasses advanced image processing and machine learning techniques to ensure accurate diagnosis and prediction. The preprocessing phase involves a series of image enhancement techniques …
Published in International Journal of Bioinformatics and Computational Biology · Vol. 3, Issue 2, 2025 · pp. 15–27 Read article
-
Advancements in Intrusion Detection: Tackling Imbalanced Network Traffic with Machine Learning and Deep Learning Techniques
Abstract: Malicious cyberattacks can frequently hide enormous amounts of typical data in unbalanced network traffic. It is very stealthy and obfuscating in cyberspace, which makes it challenging for Network Intrusion Detection Systems (NIDS) to guarantee the precision and promptness of detection. This essay investigates. Machine learning and deep learning are utilized for intrusion detection in imbalanced network traffic. It offers a novel method for addressing the problem of class imbalance termed …
Published in Recent Trends in Electronics Communication Systems · Vol. 11, Issue 2, 2024 · pp. 18–24 Read article
-
Disease Prediction Using Ensemble Learning Models: A Comprehensive Approach
Abstract: In recent years, ensemble learning techniques have become pivotal in advancing predictive analytics within healthcare, particularly for early disease detection. The inherent variability and complexity of medical data, often characterized by high dimensionality, class imbalance, and noise, make it challenging for standalone classifiers to maintain high predictive accuracy. Ensemble learning, by integrating multiple models through bagging, boosting, or stacking, offers a more robust and generalizable approach. This study explores the …
Published in Journal of Communication Engineering & Systems · Vol. 15, Issue 3, 2025 · pp. 26–33 Read article
-
A Comprehensive Analysis of Classification Methods for Churn Prediction in Financial Services
Abstract: Persistent issues that affect long-term revenue in the banking sector include excessive client attrition. Customary churn models depend on measures related to customer satisfaction, which often result in low predictive accuracy due to their subjective nature. This study proposes an effective early warning model to address customer churn in financial services. Data is preprocessed through cleaning, one-hot encoding, Z-score normalization, and Min-max scaling. To handle class imbalance, the SMOTE algorithm …
Published in Journal of Advanced Database Management & Systems · Vol. 12, Issue 2, 2025 · pp. 47–61 Read article
-
Predictive Analytics and Adaptive Learning: A Machine Learning Framework for Reducing Learning Gaps
Abstract: Most contemporary digital learning environments encounter persistent challenges when it comes to accurately identifying students who are at-risk of academic underperformance. These challenges often arise due to limited visibility in learners’ engagement levels and gaps in conceptual understanding, particularly during the early stages of a course. To address this issue, the present study proposes an early prediction framework that leverages comprehensive student-related data through the application of machine learning techniques. …
Published in International Journal of Algorithms Design and Analysis Review · Vol. 4, Issue 1, 2026 · pp. 16–21 Read article
-
Explainable Machine Learning Integrated with Polymer-Based Diagnostic Technologies for Liver Health Classification
Abstract: Early and reliable assessment of liver health is essential for timely treatment, yet most machine-learning approaches face limitations such as class imbalance and low clinical interpretability. This study proposes a polymer-integrated, explainable machine-learning framework that combines SMOTE-based data balancing, Logistic Regression, and XAI techniques (SHAP and LIME) for transparent liver-health classification. In addition to ML modelling, the study emphasizes the emerging role of polymer-based biosensors, microfluidic polymer chips, polymer nanomaterials, …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 631–643 Read article
-
Stacked Generalization-Based Deep Learning Approach for Pneumonia Detection
Abstract: The proposed work focuses on a stacked generalization-based approach for diagnosing pneumonia from chest X-ray images. It utilizes regularization, early stopping, and data augmentation to deal with overfitting. It uses safe level SMOTE to deal with class imbalance and attention-based feature fusion to adaptively weigh features based on their importance. It uses two publicly available datasets (RSNA and Kermany) with ground truth provided by expert radiologists. The proposed work used …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 3, 2025 · pp. 20–31 Read article
-
Prediction of Customer Churn Using Machine Learning Classification Models
Abstract: Customer churn prediction is a critical task in both the telecommunication and medical industries, where retaining customers or patients is essential for ensuring long-term profitability and maintaining high-quality service. To address this, a range of machine learning models—including logistic regression, decision trees, random forests, gradient boosting machines, and support vector machines—were employed to accurately forecast churn behavior. Prior to model training, the dataset underwent thorough preprocessing, which included handling missing …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 2, 2025 · pp. 86–92 Read article
-
Depression Detection Using AI with Chatbot Support
Abstract: Depression is a major global health concern and a significant contributor to suicide rates worldwide. India reports a high number of suicide cases, making the early detection of mental distress and depression essential for timely intervention. This research presents an AI-based system for depression detection that integrates deep learning, natural language processing (NLP), and a chatbot for user support. The system analyzes facial expressions using convolutional neural networks (CNNs) and …
Published in Research & Reviews: A Journal of Embedded System & Applications · Vol. 14, Issue 1, 2025 · pp. 01–08 Read article
-
A Comprehensive Review of Machine Learning and Explainable AI Techniques for Disease Prediction Systems
Abstract: Large amounts of diverse medical data have been produced because of the quick development of digital healthcare systems, offering substantial chances to use machine learning methods for clinical decision support and illness prediction. By identifying intricate patterns in clinical data, machine learning-based models have shown great promise in early disease detection, risk assessment, and personalised healthcare. However, issues with transparency, interpretability, and reliability have been brought up by the growing …
Published in International Journal of Biomedical Innovations and Engineering · Vol. 4, Issue 1, 2026 · pp. 20–28 Read article
-
Deep Learning for Earth Observation Using Satellite Imagery: A Comprehensive Review
Abstract: Earth observation (EO) satellites provide continuous, large-scale information about the Earth's land, oceans, atmosphere, vegetation, infrastructure, and environmental conditions. The rapid growth of multispectral, hyperspectral, synthetic aperture radar (SAR), thermal, and high- resolution satellite missions has generated large volumes of heterogeneous spatial and temporal data. Conventional image-processing and machine-learning techniques often require manually designed features and may have difficulty representing the complex spatial, spectral, temporal, and multimodal characteristics of satellite …
Published in Research & Reviews : Journal of Space Science & Technology · Vol. 15, Issue 2, 2026 Read article
-
Automated Microstructure Classification with Class-Specific Segmentation for Titanium Based Composite Materials
Abstract: In engineering, characterisation of microstructure is required to determine and forecast behaviour of titanium alloys. Our proposal in this work has been a deep-learning-based framework in the automatic classification and segmentation of Titanium Based Composite Material. The framework then uses EfficientNetB0 backbone, where we have chosen the backbone to scale the performance of classification and the computational efficiency with the assistance of the transfer learning and the compound scaling. In …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 424–433 Read article