Claim Missing Document
Check
Articles

Found 2 Documents
Search

Takallam: An Android Application to Enhance Literacy of Arabic Expression Ummi Azizah Rachmawati; Aya Yahya; Puspa Setia Pratiwi; Sri Puji Utami; Febri Ufaira Hasan; Rama Abirami K.
Izdihar : Journal of Arabic Language Teaching, Linguistics, and Literature Vol. 7 No. 3 (2024): Izdihar: Journal of Arabic Language Teaching, Linguistics, and Literature
Publisher : Arabic Education Department, Islamic Studies Faculty, Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/jiz.v7i3.34762

Abstract

The Arabic language holds great significance in Islamic culture. Arabic is traditionally learned through in-person instruction in classrooms or scientific gatherings, while another method involves memorizing words from books or dictionaries. However, this memorization technique is often less effective due to the repetitive reading required. An alternative approach to learning Arabic is through information system media. In this research, the researchers developed a multimedia application to facilitate learning basic Arabic conversations. The research follows the Prototyping methodology, which involves building and refining a system model. This process includes seven steps: collecting requirements, developing prototypes, evaluating prototypes, coding, testing, system evaluation, and implementation. The Android-based mobile application, developed using Android Studio, incorporates multimedia features. The outcome of this research is the development of the Takallam app, designed to help users learn basic Arabic conversation. Takallam includes interactive dialogues, practical phrases, and engaging quizzes, with cartoon animations to enhance the learning experience and make practice more enjoyable. The System Usability Scale test yielded an average score of 74, and Beta Testing showed an 80% feasibility rate, confirming that the application meets the required criteria.
Reinforcement Learning for Personalised Critical Care Treatment using Scalable Parallel Computing Chandra Prasetyo Utomo; Kohei Ichikawa; Nashuha Insani; Kundjanasith Thonglek; Kang Xingyuan; Chaerita Maulani; Ummi Azizah Rachmawati
Advance Sustainable Science Engineering and Technology Vol. 8 No. 2 (2026): February-April
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v8i2.2080

Abstract

Sepsis is one of the leading causes of death in intensive care units. Many patients do not receive timely or effective treatment, which lowers their chances of survival. We developed a reinforcement learning–based framework to provide personalised treatment recommendations for sepsis patients. The model creates simple patient representations from treatment responses, groups patients with similar patterns, and learns the best treatment policy for each group. To reduce long training time, we use parallel and distributed computing. Using the MIMIC-III database and off-policy evaluation with weighted importance sampling, our method achieves a policy value of 79.933, higher than the clinician policy (47.654) and a general AI policy (57.658). A higher policy value indicates a lower mortality risk. These results show that our method can support faster, more accurate, and more effective treatment decisions in the ICU.