Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Advanced Computer Knowledge and Algorithms Gameology and Multimedia Expert
Nasrullah Rahimi
Kunduz University
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
The Role of Artificial Intelligence in Mathematics Education: A Systematic Literature Review of Teaching, Learning, Assessment, and Future Challenges Zaidullah Zaheed; Nasrullah Rahimi; Shahwali Shahidi
Journal of Advanced Computer Knowledge and Algorithms Vol. 3 No. 4 (2026): Journal of Advanced Computer Knowledge and Algorithms - October 2026
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v3i4.30450

Abstract

Artificial intelligence (AI) is reshaping how mathematics is taught, learned, and assessed, yet the evidence is scattered across computing, learning-sciences, and education research. This study aims to synthesise what is known about the role of AI in mathematics education and to identify the challenges that will shape its next decade. A PRISMA-informed systematic literature review protocol was applied to a curated corpus of 40 peer-reviewed studies, meta-analyses, benchmark papers, and authoritative books published between 1984 and 2024. The corpus was coded against four research questions covering AI techniques, teaching and learning applications, assessment and feedback, and open challenges, and was synthesised into a conceptual model linking AI technologies, pedagogical functions, learning outcomes, and governance. The results show that intelligent tutoring and adaptive practice systems have the strongest evidence base, with reported effects that are large in controlled studies (0.3 to 0.8 standard deviations) but shrink to roughly 0.2 at scale. Learner-modelling algorithms such as knowledge tracing underpin personalisation, whereas large language models have shifted attention to conversational tutoring and automated feedback, although their mathematical reliability remains uneven. Persistent challenges include algorithmic bias, privacy, invalid generated solutions, over-reliance, and limited teacher involvement. The review concludes that AI is most effective when it complements teachers, provides step-level feedback, and is governed by transparent, verifiable algorithms. The findings offer a research and design agenda for developers, educators, and policymakers.
A Comparative Study of LBPH, FaceNet, and ArcFace for Robust Face Verification Under Challenging Conditions Wali Mohammad Wadeed; Nasrullah Rahimi
Gameology and Multimedia Expert Vol. 3 No. 4 (2026): Gameology and Multimedia Expert - October 2026
Publisher : Department of Informatics Faculty of Engineering Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/game.v3i4.29730

Abstract

Face verification is an essential component of biometric authentication, surveillance, and access control systems. However, the reliability of face recognition models can decrease significantly under challenging conditions such as poor illumination, motion blur, and partial facial occlusion. Therefore, a reliable and systematic evaluation of face verification methods is important for selecting appropriate approaches for practical applications. This study employs a quantitative, experimental, and comparative research design to evaluate three face verification methods representing different stages of the field: the traditional texture-based Local Binary Patterns Histograms (LBPH), the deep metric-learning model FaceNet, and the angular-margin-based ArcFace. To ensure a fair comparison, identical preprocessing procedures, verification protocols, and evaluation settings are applied across three widely used benchmark datasets: LFW, AgeDB, and CPLFW. The models are evaluated using accuracy, ROC-AUC, Equal Error Rate (EER), False Acceptance Rate (FAR), False Rejection Rate (FRR), and computational cost. The experimental findings demonstrate that FaceNet and ArcFace substantially outperform the traditional LBPH method across the evaluated benchmarks. Among the three approaches, ArcFace consistently achieves the highest verification accuracy and demonstrates greater robustness under challenging conditions. Overall, the findings indicate that modern deep learning-based methods, particularly ArcFace, provide a more reliable and effective solution for face verification applications requiring high accuracy and robustness, although computational requirements should also be considered when selecting a method for practical deployment
Co-Authors Shahwali Shahidi Wali Mohammad Wadeed Zaidullah Zaheed