Sign inSubmit
Tips: “quotes” for a phrase · author:Lee · a DOI goes straight to its article

30 results for “Class Imbalance”
Set a search alert
Research ArticleOpen accessIn the keywordsComparative Analysis of Fraud Detection Methods in Banking Using Machine Learning TechniquesYoussef Tounsi, Ennouri TaziFraud detection in banking requires algorithms that balance classification performance, computational efficiency, and regulatory interpretability, criteria that are rarely benchmarked together. We present a comprehensive evaluation of nine machine learning approaches (Logistic Regression, Decision Tree, Random Forest, SVM, SGD, XGBoost, CatBoost, LightGBM, and MLP) across three datasets differing in size, imbalance severity, and feature type (synthetic, real-world PCA-anonymized, and large-scale … …Journal of Computer Science, Vol. 22, Issue 6 · 22 Jun 2026 · 1,341 accessesView PDFCite
Research ArticleOpen accessIn the keywordsData Analytics for Imbalanced DatasetMadhura Prabha R, Sasikala SThe primary issue in real-time big data classification is imbalanced datasets. Even though we have many balancing techniques to reduce imbalance ratio which is not suitable for big data that has scalability issues. This study is envisioned to explore different balancing techniques with experimental study. We tried comparing the effectiveness of various balancing strategies, including cutting-edge approaches for severely unbalanced … …Journal of Computer Science, Vol. 20, Issue 2 · 11 Jan 2024 · 5,473 accessesView PDFCite
Review ArticleOpen accessIn the abstractA Systematic Review of Artificial Intelligence and Deep Learning Approaches for Cocoa Pod Disease DetectionHenry Techie-Menson, Michael Asante, Yaw Marfo Missah et al.Cocoa pod diseases destroy an estimated 700,000 metric tons of cocoa annually, threatening 40–50 million smallholder farmers across tropical regions. Accurate field diagnosis remains constrained by symptom similarity, labour-intensive scouting, and limited specialist access in remote communities. This paper presents a PRISMA-guided systematic review of 25 peer-reviewed studies on automated cocoa pod disease detection and classification (2016–2026), addressing architectural approaches, … …Journal of Computer Science, Vol. 22, Issue 8 · 8 Sep 2026 · 733 accessesView PDFCite
Research ArticleOpen accessIn the abstractHybrid Soft Voting Ensemble of XGBoost and DNN for At-Risk Student Performance PredictionEugene Wan, Po Chan Chiu, Mohammad bin Hossin et al.Early identification of at-risk students in higher education is important for timely academic intervention, yet conventional prediction methods often struggle with data imbalance and limited model precision. This study proposes a hybrid soft voting ensemble model that integrates Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) to enhance multi-class student grade prediction (A-F classification) and at-risk student identification. This … …Journal of Computer Science, Vol. 22, Issue 5 · 28 May 2026 · 1,390 accessesView PDFCite
Research ArticleOpen accessIn the abstractEnsemble Learning-Based Hybrid Explainable Intrusion Detection System With SMOTE for Enhanced Detection and Interpretability in CybersecurityMohammad Subhi Al-Batah, Taqieddin AldrousWith cyberattacks becoming increasingly sophisticated, there is a growing need for Intrusion Detection Systems (IDS) that are both accurate and interpretable. This study introduces a hybrid IDS framework that integrates Random Forest (RF) and Light Gradient Boosting Machine (LGBM) classifiers with the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. To enhance transparency and trust, the system also incorporates … …Journal of Computer Science, Vol. 22, Issue 5 · 19 May 2026 · 1,277 accessesView PDFCite
Research ArticleOpen accessIn the abstractHybrid Deep Learning Model for Evaluating Subjective Answers Based on Semantic Textual SimilaritySiddhesh Kudtarkar, Kavita ShirsatSubjective answer evaluation requires accurately identifying semantic similarities between student and reference responses. This study introduces a Hybrid Deep Learning Model (HDLM) that integrates CNN, GRU, and LSTM architectures to assess Semantic Textual Similarity (STS) more effectively. The HDLM employs two parallel branches-CNN-GRU and CNN-LSTM to capture both local syntactic features and long-range contextual dependencies, followed by Manhattan distance for … …Journal of Computer Science, Vol. 22, Issue 4 · 7 Apr 2026 · 1,690 accessesView PDFCite
Research ArticleOpen accessIn the abstractPredictive Mathematical Modeling and Classification of Retail Sales Orders Using AI Machine Learning TechniquesMohammad Subhi Al-Batah, Mowafaq Salem Alzboon, Hamzeh ZureigatThis study presents a systematic mathematical model known as a low-code approach to classifying retail sales orders by size using AI machine learning techniques within the Orange Data Mining platform. Leveraging a real-world sales dataset sourced from Kaggle, we implemented and evaluated ten classification models, including ensemble learners (AdaBoost, Gradient Boosting), probabilistic classifiers (Naïve Bayes), distance-based methods (kNN), and interpretable … …Journal of Computer Science, Vol. 22, Issue 3 · 10 Mar 2026 · 1,567 accessesView PDFCite
Review ArticleOpen accessIn the abstractMachine Learning Advancements for Lung Cancer Detection: An In-Depth Review and Future ProspectsAanchal Vij, Kuldeep Singh Kaswan, Anand NayyarLung cancer is a major cause of cancer-related mortality globally, underscoring the necessity for efficient diagnostic instruments. The review paper summarizes the role of ML and DL in detection, staging, and prognostication of lung cancer. We evaluate the relative efficacy of several models, such as CNNs, SVMs, and ensemble approaches, by analyzing publically accessible imaging and molecular information. We emphasize … …Journal of Computer Science, Vol. 22, Issue 1 · 1 Mar 2026 · 1,794 accessesView PDFCite
Research ArticleOpen accessIn the abstractAdvancing Stroke Lesion Segmentation With U-Net Variants: Classical, Transfer Learning, and MRI Sequence-Specific Customized ApproachesSonia Flora Panesar, Amit P. GanatraIschemic stroke, caused by restricted cerebral blood flow, is a leading cause of death and disability worldwide. Accurate segmentation of stroke lesions in MRI is essential for timely diagnosis but remains labor-intensive when done manually. This study presents a comparative evaluation of three U-Net variants for automated ischemic stroke lesion segmentation using the ISLES 2022 dataset: (1) Classical U-Net with … …Journal of Computer Science, Vol. 22, Issue 2 · 27 Feb 2026 · 1,791 accessesView PDFCite
Research ArticleOpen accessIn the abstractAn Integrated Disease Progression Model to Analyze Electronic Health Records With Multimodal Datasets Using Deep Learning TechniquesThulaganyo Dimakatso, Venumadhav Kuthadi, Rajalakshmi Selvaraj, Othapile DinakenyaneIn contemporary clinical environments, precisely simulating the emergence of disease is an intricate task owing to heterogeneously derived data and variability in the record of diagnoses. The research presents a stable classification model that integrates image data with formalized patient data to track patterns in disease through various stages. The suggested approach combines a multi-stage analytical methodology that includes systematic … …Journal of Computer Science, Vol. 22, Issue 2 · 19 Feb 2026 · 1,678 accessesView PDFCite