iosr-JCE  Volume-28 ~ Issue-4 ~ Jul. - Aug. 2026

Abstract: Hate speech on social media causes real harm to real people. Yet automatic detectors still struggle with two problems: messy training data, and models that look good on paper but fail on new data. This paper presents a simple, data-first approach to hate speech detection. We clean the text, balance the classes, and add more training examples before we train any model. We then feed this clean data into HateBERT, a version of BERT trained further on abusive language, followed by a 2-layer bidirectional LSTM (BiLSTM). The model is trained with a standard loss function, with no extra tricks. We test this setup against twelve other combinations of embeddings (MiniLM, RoBERTa.....

Key Word: Hate speech detection, HateBERT, bidirectional LSTM, data-centric AI, noise reduction, Easy Data Augmentation, embedding comparison, model overfitting, Davidson dataset, Jigsaw Toxic Comments, social media text classification.

[1]. T. Davidson, D. Warmsley, M. Macy, And I. Weber, "Automated Hate Speech Detection And The Problem Of Offensive Language," In Proc. 11th Int. Aaai Conf. On Web And Social Media (Icwsm), 2017.
[2]. C. J. Adams, J. Sorensen, J. Elliott, L. Dixon, M. Mcdonald, N. Cukierski, And W. Cukierski, "Toxic Comment Classification Challenge," Kaggle / Jigsaw, 2018.
[3]. T. Caselli, V. Basile, J. Mitrović, And M. Granitzer, "Hatebert: Retraining Bert For Abusive Language Detection In English," In Proc. 5th Workshop On Online Abuse And Harms (Woah), Acl, 2021.
[4]. J. Wei And K. Zou, "Eda: Easy Data Augmentation Techniques For Boosting Performance On Text Classification Tasks," In Proc. Emnlp-Ijcnlp, 2019.
[5]. S. Hochreiter And J. Schmidhuber, "Long Short-Term Memory," Neural Computation, Vol. 9, No. 8, Pp. 1735–1780, 1997..

Abstract: Reliable person identification is critical for modern security systems, yet unimodal biometric methods often suffer from noise, environmental variations, and user-related differences. To overcome these limitations, this paper presents a robust deep learning–based multimodal biometric system for person identification using deep feature fusion of iris and retina traits. Separate convolutional neural networks are used to extract highly discriminative features from iris and retinal images, capturing complementary information from each modality. The extracted....

Key Word: Multimodal Biometrics, Iris Recognition, Retina Recognition, Deep Learning, Feature Fusion

[1]. L. Hong And A. K. Jain, "Integrating Faces And Fingerprints For Personal Identification," Ieee Transactions On Pattern Analysis And Machine Intelligence, Vol. 20, No. 12, Pp. 1295–1307, Dec. 1998.
[2]. R. Frischholz And U. Dieckmann, "Bioid: A Multimodal Biometric Identification System," Computer, Vol. 33, No. 2, Pp. 64–68, Feb. 2000.
[3]. A. Ross And A. K. Jain, "Information Fusion In Biometrics," Pattern Recognition Letters, Vol. 24, No. 13, Pp. 2115–2125, 2003.
[4]. J. Fierrez-Aguilar, J. Ortega-Garcia, D. Garcia-Romero, And J. Gonzalez-Rodriguez, "A Comparative Evaluation Of Fusion Strategies For Multimodal Biometric Verification," In Proc. 4th Int. Conf. Audio-Video-Based Biometric Person Authentication (Avbpa), Lncs, Vol. 2688, 2003, Pp. 830–837.
[5]. T. Wang, T. Tan, And A. K. Jain, "Combining Face And Iris Biometrics For Identity Verification," In Proc. 4th Int. Conf. Audio-Video-Based Biometric Person Authentication (Avbpa), Lncs, Vol. 2688, 2003, Pp. 805–813.

Abstract: Background: Rendering photorealistic 3D scenes has long been a compromise between image quality and computational speed. Early splatting methods proposed the idea of projecting elements onto a 2D plane, and later approaches with neural networks, such as NeRF (around 2020), made it possible to achieve high-quality rendering of scenes at the cost of significant computational costs, which limited their use in real time. Photogrammetry....

Key Word: 3D Reconstruction, Computer Graphics, Gaussian Splatting, Neural Rendering, Point Cloud, Real-Time Rendering.

[1]. Entertainment Weekly. "Toy Wonder." (2010, June 29). Available At:
Https://Archive.Ph/20121205204251/Http://Www.Ew.Com/Ew/Article/0,,299897,00.Html
[2]. Price, D. (2008). The Pixar Touch: The Making Of A Company. New York: Alfred A. Knopf, P. 138.
[3]. Siva, L. (2023). Understanding And Exploring 3D Gaussian Splatting: A Comprehensive Overview. Medium. Available At:
Https://Logessiva.Medium.Com/Understanding-And-Exploring-3d-Gaussian-Splatting-A-Comprehensive-Overview-B4004f28ef1c
[4]. Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020). Nerf: Representing Scenes As Neural Radiance Fields For View Synthesis. Available At: Https://Www.Matthewtancik.Com/Nerf
[5]. Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G. (2023). 3D Gaussian Splatting For Real-Time Radiance Field Rendering. ACM Transactions On Graphics. Available At: Https://Repo-Sam.Inria.Fr/Fungraph/3d-Gaussian-Splatting/..

Abstract: This study analyzes the impact of the COVID-19 pandemic on student retention in higher education in Mexico, focusing on engineering courses in Programming and Numerical Methods over the period 2015–2025. A longitudinal design was employed using institutional academic records corresponding to enrollment capacity and actual student attendance across different academic terms (winter, spring, and autumn). Student retention was used as an inverse indicator of dropout rates, allowing the evaluation of academic continuity before, during, and after the pandemic.....

Key Word: COVID-19, higher education, student retention, engineering education, longitudinal study, Mexico

[1]. Aragón-Nogales, R., Vargas-Almanza, I., & Miranda-Novales, M. G. (2019). COVID-19 By SARS-Cov-2: The New Health Emergency. Revista Mexicana De Pediatría, 86(6).
[2]. Asadullah, M. N. (2024). Back To School After COVID-19 Pandemic: Resumption Or Transitional Disruption. International Journal Of Educational Development. Https://Doi.Org/10.1016/J.Ijedudev.2024.103086[3]. Badillo, D. (15 De Marzo De 2025). A 5 Años De La Pandemia COVID-19. Está Claro Que El Mundo Lo Hizo Mal Y México Aún Peor, Expertos. El Economista. Https://Www.Eleconomista.Com.Mx/Politica/5-Anos-Pandemia-Covid-19-Claro-Mundo-Hizo-Mal-Mexico-Aun-Peor-Expertos-20250315-750669.Html
[4]. Cervantes-Muñoz, C., Mora-Ríos, J., Saltijeral-Méndez, T., & Ramos-Lira, L. (2022). Implications Of The COVID-19 Lockdown For The Emotional Well-Being Of The Adult Population In Mexico. Salud Mental.
Https://Doi.Org/10.17711/Sm.0185-3325.2022.024
[5]. El Economista. (9 De Mayo De 2023). Covid-19 Cuánto Duró La Pandemia En México.

Abstract: Intelligent Medical Record Systems are becoming important in modern healthcare because they help healthcare professionals manage patient information and improve clinical decision-making. However, many existing systems only store patient records and do not provide intelligent support for predicting diseases or explaining medical recommendations. In many hospitals in Nigeria and other developing countries, delayed diagnosis, poor record management, lack of real-time alerts, and limited explainability of Artificial Intelligence (AI) models affect the quality of healthcare delivery. This study presents an Explainable AI-Driven Framework for Real-Time Clinical Decision Support in Intelligent Medical Record Systems. The framework is designed to assist healthcare.....

Key Word: Explainable Artificial Intelligence, Clinical Decision Support System, Intelligent Medical Record System, Machine Learning, Real-Time Healthcare, SHAP, LIME.

[1]. Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., Depristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019). A Guide To Deep Learning In Healthcare. Nature Medicine, 25(1), 24–29.
[2]. Holzinger, A., Saranti, A., Molnar, C., Biecek, P., & Samek, W. (2022). Explainable AI Methods For Healthcare. Artificial Intelligence In Medicine, 126, 102309.
[3]. Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2021). Artificial Intelligence In Healthcare: Past, Present And Future. Stroke And Vascular Neurology, 6(2), 230–243.
[4]. Lundberg, S. M., Erion, G., Chen, H., Degrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S. I. (2020). From Local Explanations To Global Understanding With Explainable AI For Trees. Nature Machine Intelligence, 2(1), 56–67.
[5]. Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine Learning In Medicine. New England Journal Of Medicine, 380(14), 1347–1358..

Abstract: IT help desks get numerous tickets per day the range of incidents is quite diverse from small device issues up to disruptions of business critical services. Proper prioritization is crucial since the higher the incident impact, the faster it should be escalated. However the manual process of prioritization may lead to inconsistencies since different service desk agents assess urgency and impact differently. In this paper, the design and implementation of the proposed IT help desk ticket prioritization system based on rules are discussed. The proposed approach determines the ticket priority based on four input factor impact, urgency, business.....

Key Word: IT Service Management, Help Desk, Incident Management, Ticket Prioritization, Rule-Based System, IT Support..

[1]. A. Mandal, S. Agarwal, N. Malhotra, G. Sridhara, A. Ray, And D. Swarup, “Improving It Support By Enhancing Incident Management Process With Multi-Modal Analysis,” Arxiv Preprint Arxiv:1908.01351, 2019.
[2]. Axelos. Itil Foundation: Itil 4 Edition. London: Tso, 2019.
[3]. C. Ramya, S. P. Paramesh, And K. S. Shreedhara, “Classifying The Unstructured It Service Desk Tickets Using Ensemble Of Classifiers,” Arxiv Preprint Arxiv:2103.15822, 2021.
[4]. Iso/Iec 20000-1:2018. Information Technology — Service Management — Part 1: Service Management System Requirements. International Organization For Standardization, 2018.
[5]. M. T. Lê And A. Ait-Bachir, “Learning To Prioritize It Tickets: A Comparative Evaluation Of Embedding-Based Approaches And Fine-Tuned Transformer Models,” Arxiv Preprint Arxiv:2512.17916, 2025..

Abstract: The direction of the industry has shifted toward cloud computing, as this technology is now part of most online services. Cloud computing provides various advantages, such as cost savings. There are different providers available, and users need to select the most suitable ones for their applications. Therefore, it is essential that the suppliers align with the consumers' objectives and provide standard evaluation tools to assess the features of their services....

Key Word: Cloud Computing; Security; Scalability; Availability; Usability; Amazon Web Service (AWS); Microsoft Azure.

[1] Peter Mell And T. Grance, “The NIST Definition Of Cloud Computing,” Pp. 1–3, 2011.
[2] Z. Haoxing And C. System, Cloud Computing: Concepts, Technology & Architecture, 4th Ed. Pearson Education, 2024.
[3] F. Khoda Parast, C. Sindhav, S. Nikam, H. Izadi Yekta, K. B. Kent, And S. Hakak, “Cloud Computing Security: A Survey Of Service-Based Models,” Comput. Secur., Vol. 114, Pp. 1–18, 2022.
[4] F. Palumbo, G. Aceto, A. Botta, D. Ciuonzo, V. Persico, And A. Pescapé, “Characterization And Analysis Of Cloud-To-User Latency: The Case Of Azure And AWS,” Comput. Networks, Vol. 184, No. November, 2021.
[5] J. Scheuner And P. Leitner, “Function-As-A-Service Performance Evaluation: A Multivocal Literature Review,” J. Syst. Softw., Vol. 170, P. 110708, 2020