Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Profesi Pendidikan Journal of Mathematics Instruction, Social Research and Opinion Saqbe : Jurnal Sains dan Pembelajarannya Jurnal Elektronika dan Telekomunikasi
Indra Maulana
Institut Prima Bangsa
Humanities Education Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Comparative Performance of Regression and Ensemble Learning Algorithms in Precision Irrigation Forecasting of Sweet Potato Muthia Rahmah; Indra Maulana
Jurnal Elektronika dan Telekomunikasi Vol. 25 No. 2 (2025)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.799

Abstract

Precision irrigation is essential for sustainable agriculture under increasing water scarcity. This study compared regression and ensemble learning algorithms for forecasting irrigation requirements in sweet potato, a crop characterized by high variability in water demand. An Internet of Things (IoT)-based prototype was deployed to collect real-time data on soil moisture, temperature, humidity, light intensity, and atmospheric pressure over 42 hours and 50 minutes (August 4-5, 2025), encompassing two complete diurnal cycles at 10-minute intervals and yielding 243 temporal observations. Following preprocessing and feature engineering with lag-based temporal features, the final dataset comprised 240 samples (192 training, 48 testing) using chronological time-based splitting to prevent data leakage. Five algorithms, Support Vector Regression (SVR), AdaBoost, Extreme Gradient Boosting (XGBoost), Random Forest Regressor (RFR), and CatBoost, were evaluated under default and hyperparameter-tuned configurations using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²) as evaluation metrics. Tuned Random Forest achieved superior performance (R² = 0.9802, RMSE = 9.58, MAE = 6.08), followed by default Random Forest (R² = 0.9786) and default CatBoost (R² = 0.9687). XGBoost demonstrated strong performance (R² = 0.9670 tuned) but exhibited overfitting tendencies with near-perfect training scores. SVR improved substantially after tuning (R² = 0.328 to 0.797), although it remained inferior to ensemble methods. Overall, ensemble methods, particularly XGBoost and Random Forest, demonstrated superior efficacy for sweet potato irrigation forecasting. These findings underscore the potential of IoT-integrated machine learning to enhance water-use efficiency and support sustainable smart farming practices.
Validation of Pre-Service STEM Teachers’ Acceptance and Use of Generative Artificial Intelligence Scale: Rasch Model Elsima Nainggolan; Saraswathy A/p Ramasundrum; Indra Maulana
Saqbe: Jurnal Sains dan Pembelajarannya Vol. 2 No. 1 (2025): Saqbe : Sains dan Pembelajarannya (Maret 2025)
Publisher : Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Generation Z pre-service STEM teachers, recognized as digital natives, possess strong potential to adopt Generative Artificial Intelligence (GAI) in educational contexts and advance its meaningful integration. Accordingly, this study aims to validate an instrument designed to measure their acceptance of and use of GAI. A quantitative cross-sectional survey was administered to 401 pre-service STEM teachers using a UTAUT2–TPB–based instrument. Data were collected via Google Forms and analyzed using Rasch modeling (Winsteps 3.7.3). The results confirm that the instrument possesses strong psychometric properties under the Rasch model. Analysis demonstrated high person (0.94) and item (0.97) reliabilities, well-defined separation indices, and acceptable item fit values, indicating that the scale effectively differentiates respondents and maintains stability across items. The unidimensionality test further supported that the instrument measures a single, coherent construct, reinforcing its internal structural integrity. Overall, these findings verify that the instrument is valid and reliable for assessing GAI acceptance and use among pre-service STEM teachers. The study offers both theoretical and practical contributions by providing a rigorously tested measurement tool to evaluate readiness for GAI adoption and integration in teacher education.
Validation of Instrument to Measure Pre-Service Science Teachers Digital Skills: Rasch Model Indra Maulana; Evi Syarah; Elsima Nainggolan; Hilman Qudratuddarsi
Jurnal Ilmiah Profesi Pendidikan Vol. 11 No. 2 (2026): Mei
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jipp.v11i2.4794

Abstract

This study aimed to validate an instrument for measuring digital skills among pre-service science teachers using the Rasch model framework. A total of 349 Generation Z participants were surveyed from three year levels. Data were collected through Google Forms and analyzed using Winsteps 3.7.3. The Rasch model provided insights into item reliability, person reliability, separation indices, unidimensionality, item fit statistics, and differential item functioning (DIF). Results demonstrated strong psychometric robustness, with person reliability of 0.95, item reliability of 0.98, and Cronbach’s alpha of 0.97. Wright Map analysis indicated appropriate alignment between item difficulty and respondents’ abilities. Item fit statistics fell within the acceptable range, supporting internal validity. Unidimensionality analysis confirmed that the instrument measured a single construct, while DIF analysis showed no significant bias across gender or year of study. Overall, the instrument proved reliable, valid, and equitable in assessing digital skills among science pre-service teachers, offering a valuable tool for teacher education and digital competence assessment.
Gadget Use Intensity and Learning Concentration Among Junior High School Students: The Mediating Role of Learning Motivation Adithia Sandy Nugraha; Indra Maulana
Journal of Mathematics Instruction, Social Research and Opinion Vol. 5 No. 3 (2026): September
Publisher : MASI Mandiri Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58421/misro.v5i3.2142

Abstract

The increasing use of digital devices among adolescents has raised concerns regarding its potential influence on students’ learning concentration, while limited evidence has examined the mediating role of learning motivation among junior high school students. Therefore, this study aimed to investigate the effect of gadget use intensity on students’ learning concentration and examine the mediating role of learning motivation. This quantitative explanatory study involved 105 junior high school students from Cirebon Regency and Cirebon City, Indonesia. Data were collected using a four-point Likert scale questionnaire consisting of 17 valid items and analyzed using descriptive statistics, classical assumption tests, and mediation analysis with Hayes’ PROCESS Macro Model 4 in SPSS. The results showed that gadget use intensity had no significant effect on either learning motivation or learning concentration. In contrast, learning motivation significantly improved students’ learning concentration. Furthermore, learning motivation did not mediate the relationship between gadget use intensity and learning concentration. These findings indicate that improving students’ learning concentration depends more on strengthening learning motivation than merely reducing gadget use intensity. Therefore, schools and teachers should prioritize instructional strategies that enhance students’ motivation while encouraging responsible and educationally meaningful gadget use.
Co-Authors Adithia Sandy Nugraha Elsima Nainggolan Elsima Nainggolan Evi Syarah Hilman Qudratuddarsi Muthia Rahmah Saraswathy A/p Ramasundrum