Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Zachra, Fatimatus
Unknown Affiliation
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Social Sciences Other

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

Found 2 Documents
Search

 1 
Detection of Bias in Machine Learning Models for Predicting Deaths Caused by COVID-19 Zachra, Fatimatus; Basuki, Setio
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 8 No. 1 (2024)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v8i1.1081

Abstract

The COVID-19 pandemic has significantly impacted global health, resulting in numerous fatalities and presenting substantial challenges to national healthcare systems due to a sharp increase in cases. Key to managing this crisis is the rapid and accurate identification of COVID-19 infections, a task that can be enhanced with Machine Learning (ML) techniques. However, ML applications can also generate biased and potentially unfair outcomes for certain demographic groups. This paper introduces a ML model designed for detecting both COVID-19 cases and biases associated with specific patient attributes. The model employs Decision Tree and XGBoost algorithms for case detection, while bias analysis is performed using the DALEX library, which focuses on protected attributes such as age, gender, race, and ethnicity. DALEX works by creating an "explainer" object that represents the model, enabling exploration of the model's functions without requiring in-depth knowledge of its workings. This approach helps pinpoint influential attributes and uncover potential biases within the model. Model performance is assessed through accuracy metrics, with the Decision Tree algorithm achieving the highest accuracy at 99% following Bayesian hyperparameter optimization. However, high accuracy does not ensure fairness, as biases related to protected attributes may still persist.
Assistance in Preparing Engineering Prompts for Muhammadiyah School Teachers to Optimize the Use of ChatGPT in the World of Education: Pendampingan Penyusunan Prompt Engineering Bagi Guru Sekolah Muhammadiyah Untuk Mengoptimalkan Pemanfaatan ChatGPT Di Dunia Pendidikan Basuki, Setio; Faiqurrahman, Mahar; Marthasari, Gita Indah; Indrabayu, Rizky; Zachra, Fatimatus; Effendy, Nico Ardia
Dinamisia : Jurnal Pengabdian Kepada Masyarakat Vol. 8 No. 3 (2024): Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/dinamisia.v8i3.19522

Abstract

ChatGPT, a widely used Large Language Model (LLM), enhances productivity in various sectors, including education. However, its extensive usage often lacks proficiency in writing effective prompts, resulting in less optimal, biased, and hallucinated outputs. This community service initiative by Universitas Muhammadiyah Malang (UMM) aims to educate teachers on prompt engineering, enabling them to (i) write effective prompts to utilize ChatGPT's potential, (ii) educate about potential biases and hallucinations of ChatGPT, and (iii) integrate ChatGPT into educational practices with integrity. Partnering with three Muhammadiyah Schools, the program trains 7-8 teachers from each institution. The training covers five key areas: (a) prompt engineering introduction, (b) building optimal prompts, (c) leveraging ChatGPT in teaching and learning, (d) prompt engineering for educational material creation, and (e) ethics of LLM usage in professional and academic settings. The effectiveness of this program is evaluated through pre-test and post-test questionnaires. Results indicate a significant improvement in prompt engineering proficiency, rising from 35.3% (pre-test) to 87.5% (post-test), and in the utilization of ChatGPT for learning support, increasing from 23.5% (pre-test) to 81.3% (post-test).
Co-Authors Basuki, Setio Effendy, Nico Ardia Faiqurrahman, Mahar Gita Indah Marthasari Indrabayu, Rizky