cover
Contact Name
Muhammad Yahya Matdoan
Contact Email
keepyahya@gmail.com
Phone
+6282193229395
Journal Mail Official
jurnalparameter@gmail.com
Editorial Address
Jl. Ir. M. Putuhena, Poka-Ambon, 97233, Maluku, Indonesia
Location
Kota ambon,
Maluku
INDONESIA
Parameter: Jurnal Matematika, Statistika dan Terapannya
Published by Universitas Pattimura
Core Subject : Education,
Parameter: Jurnal Matematika, Statistika dan Terapannya is an open access journal (e-journal) published since April 2022. Parameteris published by Department of Mathematics, Faculty of Science and Mathematics, Pattimura. Parameterpublished scientific articles on various aspects related to mathematics and statistics and its application. Articles can be in the form of research results, case studies, or literature reviews.
Articles 124 Documents
Performance Comparison of Neural Network and Long Short-Term Memory for Forecasting Power Usage Effectiveness (PUE) in Data Center Teguh Herlambang; Yuliana Yuliana; Endang Sulistiyani; Firman Yudianto
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 5 No 2 (2026): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/parameterv5i2pp421-436

Abstract

Energy efficiency in data center operations has become a critical issue in the digital era, including for public utilities such as Regional Drinking Water Companies (PDAM). One of the key indicators of data center efficiency is Power Usage Effectiveness (PUE), with PDAM recording a daily average of 2.11. Significant spikes in PUE values during certain months suggest operational dynamics that are not yet fully understood, highlighting the need for a comprehensive analysis of the contributing factors. This study employs Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) algorithms to forecast PUE values. The research process includes data understanding, preprocessing, modeling, evaluation, and forecasting, conducted under three time-based split scenarios: 60%:20%:20%, 40%:20%:40%, and 20%:20%:60%. Among these, the third scenario demonstrated the best performance. The ANN model achieved a Mean Absolute Percentage Error (MAPE) of 10.10%, a Root Mean Square Error (RMSE) of 0.2565, and an accuracy of 85.34%. Meanwhile, the LSTM model recorded a MAPE of 10.62%, RMSE of 0.2600, and accuracy of 85.14%. These results fall within the 10%–20% error range, indicating reliable forecasting performance. The predicted PUE values were 2.38 for ANN and 1.85 for LSTM, both categorized as “Average” in terms of energy efficiency, suggesting room for improvement. The highest energy loads were attributed to cooling systems, specifically air conditioning (AC), air conditioning and mechanical ventilation (ACMV), and uninterruptible power supply (UPS) systems. Therefore, future infrastructure optimization efforts should prioritize improvements in these areas
Feasible Generalized Least Squares Based on Minimum Variance Quadratic Unbiased Estimation for an Unbalanced One-Way Error-Component Panel Model Refa Joyce Semida; Raupong Raupong; Siswanto Siswanto; A. Muthiah Nur Angriany
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 5 No 2 (2026): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/parameterv5i2pp437-452

Abstract

Panel data combine cross-sectional and time-series information, but incomplete firm-year observations produce an unbalanced structure that requires an estimation procedure accommodating unequal observation counts. This study applies a one-way random-effects error-component model to 42 observations from 10 consumer-goods manufacturing firms listed on the Indonesia Stock Exchange during 2017–2021. The firm-specific and idiosyncratic variance components are estimated using Minimum Variance Quadratic Unbiased Estimation (MIVQUE), and the resulting covariance matrix is used to estimate the regression coefficients through feasible generalized least squares (FGLS). The estimated variance components are 0.0063 for the firm-specific effect and 0.0805 for the idiosyncratic disturbance, indicating that approximately 7.26% of the composite disturbance variance is attributable to persistent differences among firms. The fitted model is Yit = 0.0657 − 0.0229DERit+).2089NPMit. The debt-to-equity ratio is negatively associated with stock returns, whereas the net profit margin is positively associated with stock returns. However, neither coefficient is statistically significant at the 5% level, with p-values of 0.0938 and 0.5165, respectively. Therefore, the estimated relationships are interpreted as conditional associations under the assumed random-effects specification rather than as causal effects. This study provides an empirical implementation of MIVQUE-based covariance estimation combined with FGLS for an unbalanced one-way error-component panel model.
Modeling of the Electronic Cigarettes with Awareness Effect Mozart Winston Talakua; Febrianty C. Kuhuwael; Lazarus Kalvein Beay
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 5 No 2 (2026): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

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

Abstract

One of the prevalent behaviors that are frequently observed within societal structures is the habit of smoking. Concurrently with traditional cigarette consumption, there has been a documented rise in the utilization of electronic cigarettes, commonly known as e-cigarettes or vapes. Electronic cigarettes function by vaporizing an e-liquid, typically composed of nicotine, propylene glycol, glycerin, and flavorings, into an inhalable aerosol, namely, potential new smokers (P₁), potential regular smokers (P₂), active conventional smokers (S), electronic cigarette users (E), and individuals who have quit smoking (Q). The analysis entails the calculation of the smoking-free and smoking-endemic equilibrium points via the Cardano method. Additionally, an analysisof the local stability of each equilibrium point is conducted using the eigenvalues of the Jacobian matrix via the Routh-Hurwitz criterion. The results indicate that when the basic reproduction number R_0=0.1961<1, the system converges to a stable, smoking-free equilibrium, suggesting that smoking behavior will eventually disappear from the population. Conversely, when R_0=1.98>1, the system tends towards an asymptotically stable smoking-endemic equilibrium. Sensitivity analysis indicates that an increase in the transition rate from conventional smokers to electronic cigarette users (α) has the most significant influence in reducing the value of R_0. The numerical simulations are provided to confirm the results analysis.
Nonlinear Small Area Poverty Estimation with MARS-Based Feature Reduction Ajriansyah Ajriansyah; Bambang Widjanarko Otok; Sutikno Sutikno
Parameter: Jurnal Matematika, Statistika dan Terapannya Vol 5 No 2 (2026): Parameter: Jurnal Matematika, Statistika dan Terapannya
Publisher : Jurusan Matematika FMIPA Universitas Pattimura

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

Abstract

The use of small area estimation combined with multivariate adaptive regression splines (SAE-MARS) is intended to address the lack of estimation precision in cases with nonlinear patterns. Compared to previous studies,which generally treated MARS solely as a tool to capture nonlinear functions without feature/variable selection, the novelty of this study lies in introducing a stepwise variable reduction procedure based on GCV to eliminate uninformative predictors. Two modeling schemes wereconstructed: using all variables (SAE-MARS-full) and reducing insignificant variables (SAE-MARS-reduced). The SAE-MARS method wasimplemented usingtwo-stage modeling. The first stage formedthe MARS model, and then proceededto the second stage to construct the SAE. SAE-MARS can deliver a sharp reduction in standard error; however,this does not apply globally. The SAE-MARS-reduced model performedslightly better becauseofits simpler structure and high level of model accuracy. Although the decrease in average global RRMSE between the two SAE-MARS models appears modest (13.02% for SAE-MARS-reduced compared to 13.37% for SAE-MARS-full), feature reduction yields a very consistent precision advantage across all regions. Thus, the proposed SAE-MARS-reduced model is empirically proven to effectively handle nonlinear patterns, produce highly precise estimates, and demonstrate that eliminating unimportant variables in the MARS process iscrucial.

Page 13 of 13 | Total Record : 124