arXiv subjects

Md Biplob Hosen

Publications and source records attributed to Md Biplob Hosen.

4 recordsLinked to original sources

arXiv2026

HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering

Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or act on the complex clinical information contained in these records. The ArchEHR-QA 2026 shared task addresses this challenge by focusing on grounded question answering over EHRs, and this paper presents the system developed by the HealthNLP_Retrievers team for this task. The proposed approach uses a multi-stage cascaded pipeline powered by the Gemini 2.5 Pro large language model to interpret patient-authored questions and retrieve relevant evidence from lengthy clinical notes. Our architecture comprises four integrated modules: (1) a few-shot query reformulation unit which summarizes verbose patient queries; (2) a heuristic-based evidence scorer which ranks clinical sentences to prioritize recall; (3) a grounded response generator which synthesizes professional-caliber answers restricted strictly to identified evidence; and (4) a high-precision many-to-many alignment framework which links generated answers to supporting clinical sentences. This cascaded approach achieved competitive results. Across the individual tracks, the system ranked 1st in question interpretation, 5th in answer generation, 7th in evidence identification, and 9th in answer-evidence alignment. These results show that integrating large language models within a structured multi-stage pipeline improves grounding, precision, and the professional quality of patient-oriented health communication. To support reproducibility, our source code is publicly available in our GitHub repository

cs.CL↗

arXiv2025

Explainable AI and Machine Learning for Exam-based Student Evaluation: Causal and Predictive Analysis of Socio-academic and Economic Factors

Academic performance depends on a multivariable nexus of socio-academic and financial factors. This study investigates these influences to develop effective strategies for optimizing students' CGPA. To achieve this, we reviewed various literature to identify key influencing factors and constructed an initial hypothetical causal graph based on the findings. Additionally, an online survey was conducted, where 1,050 students participated, providing comprehensive data for analysis. Rigorous data preprocessing techniques, including cleaning and visualization, ensured data quality before analysis. Causal analysis validated the relationships among variables, offering deeper insights into their direct and indirect effects on CGPA. Regression models were implemented for CGPA prediction, while classification models categorized students based on performance levels. Ridge Regression demonstrated strong predictive accuracy, achieving a Mean Absolute Error of 0.12 and a Mean Squared Error of 0.023. Random Forest outperformed in classification, attaining an F1-score near perfection and an accuracy of 98.68%. Explainable AI techniques such as SHAP, LIME, and Interpret enhanced model interpretability, highlighting critical factors such as study hours, scholarships, parental education, and prior academic performance. The study culminated in the development of a web-based application that provides students with personalized insights, allowing them to predict academic performance, identify areas for improvement, and make informed decisions to enhance their outcomes.

cs.LG↗

arXiv2025

From Code to Career: Assessing Competitive Programmers for Industry Placement

In today's fast-paced tech industry, there is a growing need for tools that evaluate a programmer's job readiness based on their coding performance. This study focuses on predicting the potential of Codeforces users to secure various levels of software engineering jobs. The primary objective is to analyze how a user's competitive programming activity correlates with their chances of obtaining positions, ranging from entry-level roles to jobs at major tech companies. We collect user data using the Codeforces API, process key performance metrics, and build a prediction model using a Random Forest classifier. The model categorizes users into four levels of employability, ranging from those needing further development to those ready for top-tier tech jobs. The system is implemented using Flask and deployed on Render for real-time predictions. Our evaluation demonstrates that the approach effectively distinguishes between different skill levels based on coding proficiency and participation. This work lays a foundation for the use of machine learning in career assessment and could be extended to predict job readiness in broader technical fields.

cs.SE↗

arXiv2025

Dynamic Encryption-Based Cloud Security Model using Facial Image and Password-based Key Generation for Multimedia Data

In this cloud-dependent era, various security techniques, such as encryption, steganography, and hybrid approaches, have been utilized in cloud computing to enhance security, maintain enormous storage capacity, and provide ease of access. However, the absence of data type-specific encryption and decryption procedures renders multimedia data vulnerable. To address this issue, this study presents a dynamic encryption-based security architecture that adapts encryption methods to any file type, using keys generated from facial images and passwords. Four diverse datasets are created, each with a consistent size of 2GB, containing varying combinations of image, audio (MP3 and MPEG), video, text, CSV, PPT, and PDF files, to implement the proposed methodology. AES is used to encrypt image data, AES-CTR is employed for audio or video data to meet real-time streaming needs, and Blowfish is used for other types of data. Performance analysis on all four datasets is conducted using AWS servers, where DATASET-1 demonstrates the best performance compared to the others.

cs.CR↗