Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Technology and System Information
Jumadi Parenreng
Universitas Negeri Makassar
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Development Model of an AI-Based Context-Aware System on Smartphones Using Explainable AI (XAI) and Reinforcement Learning Approaches Haekal Ramadhan; Muhammad Yahya; Jumadi Parenreng
Journal of Technology and System Information Vol. 3 No. 1 (2026): January
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jtsi.v3i1.5662

Abstract

This study analyzes requirements and designs an Artificial Intelligence (AI)-based context-aware smartphone system to support lecturers’ work focus. It addresses the problem of disruptive notifications that ignore user context, which can reduce concentration during teaching and academic tasks. The research applies a modified Research and Development (R&D) approach, integrating Explainable Artificial Intelligence (XAI) and Reinforcement Learning (RL) to enable adaptive and transparent notification management. The process includes requirements analysis, system design, expert validation, and a small-scale trial with 10 respondents. Results show that the system meets its core function as a context-aware application, with minor interface improvements suggested by experts. User evaluations indicate generally positive performance across usability, effectiveness, efficiency, satisfaction, transparency, and reliability, all categorized as “good.” Reliability and data consistency were also confirmed through statistical testing. The main contribution of this study is the development of an AI-based, context-aware notification management model that combines RL for adaptive decision-making and XAI for transparency, specifically tailored to lecturers’ work contexts. This model offers a practical and theoretically grounded solution to improve focus and productivity, and it is feasible for further large-scale  implementation and testing.
Co-Authors Haekal Ramadhan Muhammad Yahya