cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota tangerang selatan,
Banten
INDONESIA
Jurnal Matematika Sains dan Teknologi
Published by Universitas Terbuka
ISSN : 14111934     EISSN : 24429147     DOI : -
Core Subject : Education, Agriculture,
Agriculture, Biological Sciences & Forestry Mathematics Other
Merupakan media informasi dan komunikasi para praktisi, peneliti, dan akademisi yang berkecimpung dan menaruh minat serta perhatian pada pengembangan Matematika, ilmu pengetahuan dan teknologi. Diterbitkan oleh Lembaga Penelitian dan Pengabdian kepada Masyarakat, Universitas Terbuka.
Arjuna Subject : -
Articles 418 Documents
 38   39   40   41   42 
The Implementation of Random Under-Sampling and Synthetic Minority Oevrsampling Techniques to Evaluate the Performance of the Classification and Regression Tree Method Rifandi Pratama Putra Kasadi; Nurwan Nurwan; La Ode Nashar; Djihad Wungguli; Siti Nurmardia Abdussamad
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 1 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i1.11381.2025

Abstract

Class imbalance in datasets poses a significant challenge in the application of classification models, including the Classification and Regression Tree (CART) method. This study aims to evaluate the performance of CART combined with two data balancing techniques: Random Under Sampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE). The data set used in this research is the Heart Failure Clinical Records from Kaggle.com, which exhibits an imbalance where the number of deceased patients is 1,568 records (minority class) and the number of survivors is 3,432 records (majority class), with a total of 5,000 records. The RUS technique reduced the total number of records to 2,526, with each class containing 1,263 records. Conversely, after applying SMOTE, the total number of records increased to 5,474, with each class containing 2,737 records. Model performance evaluation was conducted using precision, recall, and F1-score metrics, both before and after implementing data balancing techniques. The results of the study showed that combining CART with SMOTE produced better performance in recognizing the minority class compared to RUS, achieving accuracy and F1-score of 88.203% and 88.195%, respectively. Meanwhile, RUS achieved an accuracy of 86.345% and an F1-score of 86.332%. Therefore, the use of SMOTE improved model accuracy by approximately 1.85% and F1-score by 1.86% compared to RUS. This study makes a significant contribution to improving prediction accuracy on imbalanced datasets and enriches scientific references related to the application of the CART method and data balancing techniques.
Hierarchical Bayes Application for Small Area Estimation with Error Measurement on Child Poverty in Sumatera Island Aisha Arthamevia; Zahra Rizky Fadilah; Rasya Az Zahra; Sausan Salsabila; Renandika Salsabiila Agistasari; Nofita Istiana
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 2 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i2.11540.2025

Abstract

Child poverty on Sumatera Island remains a significant issue, as four provinces recorded child poverty rates above the national average in 2021, increasing to five provinces in 2022. To support more effective and targeted policies, reliable estimates at the district/city level are required; however, direct estimates from the March 2023 Susenas data showed low precision, with 37 of 154 districts/cities having a Relative Standard Error (RSE) greater than 25%. To improve accuracy, this study applied Small Area Estimation using a Hierarchical Bayes model with Measurement Error on the Beta distribution (SAE HB ME Beta). Empirical findings revealed serious precision problems, particularly in Kepulauan Bangka Belitung, where all districts had RSE values above 25%, and in West Sumatera, which ranked second with more districts exceeding the threshold than those below it, including the highest overall RSE. When the model was initially estimated jointly for all provinces, one district in West Sumatera still had an RSE above 25% and estimates for Kepulauan Bangka Belitung failed to satisfy the internal consistency criterion. To address this heterogeneity, the model was re-estimated separately for West Sumatera and Kepulauan Bangka Belitung and for the remaining provinces. The final results show that all districts/cities achieved RSE ≤ 25% and met internal consistency requirements, indicating that the proposed approach improves the precision and reliability of district-level child poverty estimates across Sumatera Island.
Application of The Grasshopper Optimization Algorithm for Route Optimization in Food Pickup-Delivery Ananda Rizky Ardha Saputra; Helen Burhan; Yudi Satria
Jurnal Matematika Sains dan Teknologi Vol. 27 No. 1 (2026): in Progress
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v27i1.12923.2026

Abstract

Food pickup and delivery is one of the services provided by online transportation platforms, where couriers collect food orders from restaurants and deliver them to customers. As the demand for this service continues to increase, a larger number of couriers is required to meet customer requests. To address this challenge, a double-order scheme is introduced, allowing a single courier to simultaneously handle two orders destined for nearby customers. In this study, the double-order scheme is employed to optimize food delivery routes with the objectives of minimizing operational costs while maintaining food quality within the specified delivery time windows. This optimization problem is formulated as the Pickup and Delivery Problem with Time Windows (PDPTW). The Grasshopper Optimization Algorithm (GOA), a metaheuristic optimization method inspired by the foraging behavior of grasshoppers, is used to solve the problem. GOA simulates how grasshoppers search for food and communicate food locations to one another through a chemical signal known as the 4-VA pheromone. The proposed method was evaluated using simulation data consisting of 50 customer orders, 300 iterations, and a population of 10 grasshoppers. The results demonstrate that the proposed approach can reduce operational costs by up to 33.71% and decrease the number of active couriers by 50% compared with the conventional single-order delivery scheme.
Parametric and Non-Parametric Approaches to the Analysis of Adolscents' Knowledge and Attitudes on Tuberculosis Findasari Findasari; Fitriana Kartikasari; Ivanna Isty Nursani; Ndaru Atmi Purnami
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 2 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i2.13409.2025

Abstract

Pulmonary tuberculosis (TB) remains a major public health problem in Indonesia. Improving adolescents’ knowledge and attitudes through school-based health education is essential to support TB prevention efforts. This study aimed to assess changes in knowledge and attitudes toward pulmonary tuberculosis following an audiovisual-based health education intervention. A quantitative pre-experimental one-group pretest–posttest design was conducted among 103 Grade XI students in a senior high school in Kudus Regency, Central Java. Data were collected using structured questionnaires. Normality was assessed prior to analysis; as most variables violated the normality assumption (p < 0.05), the Wilcoxon Signed-Rank Test was used as the primary statistical method, while the paired t-test was performed as a supplementary comparison analysis. The results showed a significant increase in knowledge scores from a median of 26 to 28 (Z = –4.865, p < 0.001, r = 0.48) and a significant improvement in attitude scores (Z = –7.383, p < 0.001, r = 0.73). The paired t-test produced consistent results, with a mean increase of 1.835 points in knowledge (95% CI: 1.177–2.493; Cohen’s d = 0.545) and 3.417 points in attitudes (95% CI: 2.717–4.118; Cohen’s d = 0.954). Normalized gain analysis indicated that improvement in knowledge was categorized as low, whereas improvement in attitudes reached the medium category. In conclusion, audiovisual-based health education was associated with positive changes in adolescents’ knowledge and attitudes regarding pulmonary tuberculosis. However, because the study was conducted in a single school using a pre-experimental design, the findings should be generalized with caution. Further controlled studies involving more diverse populations are recommended.
Forecasting National Rice Production Using Autoregressive Distributed LAG and K-Means Clustering Dara Sakina; Alfi Hidayatullah; Yuliana Kartika Permadani; Nasrudin Nasrudin
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 2 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i2.13428.2025

Abstract

Indonesia as an agricultural country faces various obstacles in its development. The increasing population, decreasing agricultural land area, and differences in potential in each province are the biggest problems in rice production. The limitations of research in general in presenting differences in rice production characteristics between provinces are the urgency discussed in this study. The purpose of this study is to develop a rice production forecasting model in Indonesia using the ARDL approach combined with the K-Means clustering technique. The variables used in this study are rice production, harvested area, and farmers’ terms of trade (NTP). Forecasting is carried out for the period 2024 with the aim of obtaining an accurate estimate of rice production in Indonesia. The results show that the ARDL model integrated with K-Means clustering provides highly accurate rice production forecasts, as indicated by low MAPE and RMSE values. In particular, Cluster 2 achieves the best performance with a MAPE of 0.36% and an RMSE of 3,860.40, followed by Cluster 1 (MAPE 2.17%; RMSE 33,192.31) and Cluster 3 (MAPE 5.88%; RMSE 40,577.10). In contrast, the national ARDL model without clustering records much larger errors (MAPE 14.71%; RMSE 582,062.00), confirming that clustering substantially improves forecasting accuracy and produces prediction patterns that closely match actual rice production.
Credit Risk Prediction Using LightGBM with Time-Aware Validation and Shap Interpretation Sony Alfauzan
Jurnal Matematika Sains dan Teknologi Vol. 27 No. 1 (2026): in Progress
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v27i1.13616.2026

Abstract

Accurate credit scoring is critical for financial stability, yet modern machine learning models often operate as "black boxes," creating a significant challenge for regulatory compliance and business trust. This research addresses this problem by developing a comprehensive, transparent, and robust framework for credit risk prediction. The primary objective was to build a high-performance model that is not only accurate but also fully interpretable and stable over time. The research method involved using a public loan dataset (2007-2014) with 466,285 loan records to train a Light Gradient Boosting Machine (LightGBM). To ensure real-world applicability and prevent temporal data leakage, a rigorous time-aware validation strategy was employed, splitting the data into a historical training set (2007-2013) and a future out-of-time (OOT) test set (2014). The SHapley Additive exPlanations (SHAP) framework was integrated to provide clear explanations for every prediction. The main research results demonstrate the model's strong predictive capability, achieving an AUC-ROC of 0.711 and a KS-statistic of 0.309 on the OOT dataset. The model's stability was confirmed with a low Population Stability Index (0.0685). Furthermore, SHAP analysis revealed that predictions were driven by financially intuitive factors like interest rate and annual income. The study concludes by presenting a complete workflow that successfully bridges the gap between high-performance modeling and the practical need for transparent, business-aligned risk management tools.
Application of Firth’s Logistic Regression in Analyzing Employment Status of Educated Women in Riau Kayla Azka Dhiya Tsabithah; Liza Kurnia Sari
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 2 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i2.13672.2025

Abstract

The ongoing demographic bonus in Indonesia provides a strategic opportunity to promote inclusive development. To optimize this potential, the involvement of educated women is crucial and not just rely on the contribution of men. However, the women’s Labor Force Participation Rate (LFPR) has remained stagnant over the past two decades and gender inequality in employment persists to this day. Riau Province requires the most attention, as in the last three years it has recorded the lowest women’s LFPR nationally. Interestingly, data show that the proportion of educated women who are employed is actually lower than that of less educated women. This study applies Firth’s logistic regression to analyse the employment status of educated women in Riau Province in 2024. The method is employed to reduce estimation bias that may arise from data imbalance. The results indicate that ICT use, age, marital status, and place of residence have significant effects. These findings can support the development of more effective strategies to increase the employment status of educated women, particularly by strengthening ICT access and considering sociodemographic characteristics.
Modeling Air Quality Index in Indonesia Using Smoothing Splines and Truncated Splines Regression Nadhia Az Zahra; Khoirin Nisa; Misgiyati Misgiyati; Nusyirwan Nusyirwan
Jurnal Matematika Sains dan Teknologi Vol. 26 No. 2 (2025)
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/jmst.v26i2.14574.2025

Abstract

The Air Quality Index (AQI) is a composite indicator that reflects regional air quality conditions and is influenced by multiple determinants with complex and nonlinear relationships. In such circumstances, parametric regression may be restrictive because it requires a predetermined functional form. This study applies spline based nonparametric regression using smoothing splines and truncated splines to model AQI in Indonesia and to compare the performance of both approaches. AQI is treated as the response variable, while population density, land cover area within and outside forest areas, and the number of motor vehicles are considered as predictor variables. For smoothing splines, the optimal smoothing parameter is selected using Generalized Cross Validation, whereas truncated splines are estimated using Ordinary Least Squares under various knot configurations and selected based on the minimum Generalized Cross Validation value. Model performance is evaluated using Generalized Cross Validation, Mean Squared Error, and Adjusted R squared. The study aims to identify the most appropriate model and to determine key factors influencing AQI variation in Indonesia, thereby providing empirical support for environmental policy making. The results show that the smoothing spline model provides better performance than the truncated spline model, with a lower Mean Squared Error (MSE) of 0.0716 and a higher Adjusted R² of 0.794. These results indicate that smoothing splines are more effective in capturing the nonlinear relationships influencing AQI variation in Indonesia.

Page 42 of 42 | Total Record : 418

 38   39   40   41   42 

Filter by Year

2003 2026


Reset
Filter By Issues
All Issue Vol. 27 No. 1 (2026): in Progress Vol. 26 No. 2 (2025) Vol. 26 No. 1 (2025) Vol. 25 No. 2 (2024) Vol. 25 No. 1 (2024) Vol. 24 No. 2 (2023) Vol. 24 No. 1 (2023) Vol. 23 No. 2 (2022) Vol. 23 No. 1 (2022) Vol. 22 No. 2 (2021) Vol. 22 No. 1 (2021) Vol. 21 No. 2 (2020) Vol. 21 No. 1 (2020) Vol. 20 No. 2 (2019) Vol 20 No 2 (2019) Vol. 20 No. 1 (2019) Vol 20 No 1 (2019) Vol 20 No 1 (2019) Vol 19 No 2 (2018) Vol. 19 No. 2 (2018) Vol 19 No 1 (2018) Vol. 19 No. 1 (2018) Vol 18 No 2 (2017) Vol. 18 No. 2 (2017) Vol 18 No 1 (2017) Vol. 18 No. 1 (2017) Vol 17 No 2 (2016) Vol. 17 No. 2 (2016) Vol 17 No 1 (2016) Vol. 17 No. 1 (2016) Vol. 16 No. 2 (2015) Vol 16 No 2 (2015) Vol 16 No 1 (2015) Vol. 16 No. 1 (2015) Vol 15 No 2 (2014) Vol. 15 No. 2 (2014) Vol 15 No 1 (2014) Vol. 15 No. 1 (2014) Vol. 14 No. 2 (2013) Vol 14 No 2 (2013) Vol 14 No 1 (2013) Vol. 14 No. 1 (2013) Vol. 13 No. 2 (2012) Vol 13 No 2 (2012) Vol 13 No 1 (2012) Vol. 13 No. 1 (2012) Vol 12 No 2 (2011) Vol. 12 No. 2 (2011) Vol. 12 No. 1 (2011) Vol 12 No 1 (2011) Vol. 11 No. 2 (2010) Vol 11 No 2 (2010) Vol. 11 No. 1 (2010) Vol 11 No 1 (2010) Vol. 10 No. 2 (2009) Vol 10 No 2 (2009) Vol. 10 No. 1 (2009) Vol 9 No 2 (2008) Vol. 9 No. 2 (2008) Vol 9 No 1 (2008) Vol. 9 No. 1 (2008) Vol 8 No 2 (2007) Vol. 8 No. 2 (2007) Vol. 8 No. 1 (2007) Vol 8 No 1 (2007) Vol. 7 No. 2 (2006) Vol 7 No 2 (2006) Vol 7 No 1 (2006) Vol. 7 No. 1 (2006) Vol 6 No 2 (2005) Vol. 6 No. 2 (2005) Vol. 6 No. 1 (2005) Vol 6 No 1 (2005) Vol 5 No 2 (2004) Vol. 5 No. 2 (2004) Vol. 5 No. 1 (2004) Vol 5 No 1 (2004) Vol. 4 No. 2 (2003) Vol. 4 No. 1 (2003) Vol 4 No 1 (2003) More Issue