Research ArticleOpen accessIn the abstractExplainable MedAttn-ResNet50 for Automated Kidney Tumor Classification from CT Images With Grad-CAM VisualizationD. Vetrithangam, Pramod Kumar, Shilpasree S. et al.Kidney tumor classification from CT imaging remains challenging due to CT-specific intensity variations, tumor heterogeneity, and limited clinically meaningful interpretability in existing deep learning models. To address these limitations, we propose an Explainable MedAttn-ResNet50 framework that integrates radiology-driven preprocessing, multi-scale feature extraction, and medical attention mechanisms within a unified architecture. The preprocessing pipeline applies radiology-inspired intensity normalization, contrast enhancement, and … …Journal of Computer Science, Vol. 22, Issue 8 · 13 Aug 2026 · 1,120 accessesView PDFCite
Research ArticleOpen accessIn the abstractReal-Time Monitoring and Injury Risk Warning Algorithm Based on Data Fusion of Motor Muscle ContractionGuomin Wang, Jingying HuangThe existing sports injury warning algorithms are difficult to achieve dynamic injury risk modeling based on individual muscle characteristics while ensuring real-time fusion efficiency of multimodal signals. This article proposes a real-time muscle contraction state perception and injury risk warning algorithm based on adaptive weighted feature fusion and lightweight temporal modeling. The system synchronously collected surface electromyography (sEMG), Inertial Measurement … …American Journal of Biochemistry and Biotechnology, Vol. 22, Issue 3 · 10 Aug 2026 · 1,089 accessesView PDFCite
Research ArticleOpen accessIn the abstractAnchoring Public Health Forecasts: High-Precision Obesity Prevalence Estimation Via Hybrid Geodemographic Ensemble RegressionTrenton Ward, Isaac OsunmakindeObesity remains a major driver of chronic disease and rising healthcare costs in the United States. Yet, most existing predictive models rely on single-model classifiers and rarely incorporate spatial structure or ensemble-based regression, thereby limiting their ability to capture geodemographic variation. This study introduces a hybrid unsupervised–supervised ensemble framework that integrates K-Means spatial profiling with a Stacking Regressor to address … …Journal of Computer Science, Vol. 22, Issue 7 · 31 Jul 2026 · 632 accessesView PDFCite
Research ArticleOpen accessIn the abstractHybrid Data Security Approach Based on GAN Teganographyand AES-RSA Encryption in a Distributed SystemDerrick Méthode Bagaza, Abraham Walake, Mamoudou Kourouma, Blaise Omer YenkeData security in distributed environments has become a major challenge due to the dispersion of resources, the expansion of the attack surface, and the increasing sophistication of cyber threats. Although traditional mechanisms such as data encryption, multi-factor authentication, and access control systems help to strengthen information protection, these approaches still have certain limitations when faced with advanced attacks and human … …Journal of Computer Science, Vol. 22, Issue 8 · 28 Jul 2026 · 1,062 accessesView PDFCite
Research ArticleOpen accessIn the abstractGait Analysis Combining Sports Biomechanics and ImagingChao ZhuAiming at the problems of marker positioning error, soft tissue interference, and insufficient personalized modeling ability in traditional gait analysis, this study proposes a gait assessment method that integrates sports biomechanics and multimodal imaging analysis. Firstly, based on the public OU-ISIR gait database, a Convolutional Neural Network (CNN) is used to extract the key gait features in the human silhouette … …American Journal of Biochemistry and Biotechnology, Vol. 22, Issue 2 · 20 Jul 2026 · 850 accessesView PDFCite
Research ArticleOpen accessIn the abstractDesigning the Future: A Blockchain-Based Framework for Transparent and Secure ElectionsJayesh Solanki, Divyakant MevaBlockchain-based electronic voting systems have been identified as a solution to enhance the transparency, security, and efficiency of modern electoral processes. However, the existing system has three major problems, which include scalability, privacy issues, and cybersecurity attacks. The researcher proposed an innovative solution to develop an electronic voting system with enhanced security, scalability, and transparency of voters' information. This paper … …Journal of Computer Science, Vol. 22, Issue 6 · 16 Jun 2026 · 1,291 accessesView PDFCite
Research ArticleOpen accessIn the abstractSEAchain: A Privacy-Preserving Dual-Credential Model on BlockchainS. Balachander, A. MuruganAll facets of daily life are now impacted by transaction data. The complex and heterogeneous network created by millions of users, devices, online services, and applications makes digital identity management more difficult. Users can maintain control over their personal information via distributed identity, a potentially useful model for resolving identity issues. Nevertheless, current state-of-the-art techniques are inappropriate because of persistent … …Journal of Computer Science, Vol. 22, Issue 5 · 25 May 2026 · 1,310 accessesView PDFCite
Research ArticleOpen accessIn the abstractA Comparative SCAPS-1D Study of Lead-Free CsSnCl₃-Based Perovskite SCs Employing Different ETLsRony Tota, Shak Mahmudul Hasan, Md. Morsalin et al.Cesium tin chloride (CsSnCl3) has drawn considerable interest as a non-toxic absorber candidate for next-generation photovoltaic devices, offering an attractive combination of affordability, thermal robustness, and competitive conversion performance suitable for clean-energy deployment. In the present work, the photovoltaic behaviour of CsSnCl₃-based SCs was numerically examined using the SCAPS-1D software. Three distinct device stacks were constructed by varying the ETL, … …American Journal of Engineering and Applied Sciences, Vol. 19, Issue 1 · 22 May 2026 · 1,737 accessesView PDFCite
Research ArticleOpen accessIn the abstractUncertainty-Aware Ensemble Models for Improved Defect Detection in Noisy DataMadhavi Perla, Gadi Lava Raju, A Radha Krishna et al.Software defect prediction plays a crucial role in ensuring software quality and reliability, especially as modern systems become more complex and data rich. This study introduces an uncertainty-aware ensemble learning framework aimed at improving defect classification performance in noisy and imbalanced datasets, particularly those from the PROMISE and NASA KC1 repositories. The proposed model integrates multiple classifiers in a multi-learner … …Journal of Computer Science, Vol. 22, Issue 4 · 27 Apr 2026 · 1,542 accessesView PDFCite