cover
Contact Name
Muh. Isbar Pratama
Contact Email
isbarpratama@unm.ac.id
Phone
+6285399692435
Journal Mail Official
jmathcos@unm.ac.id
Editorial Address
Kampus Parangtambung UNM, Jl. Dg. Tata Raya Prodi Matematika Lt. 3 Gd FG Jurusan Matematika FMIPA
Location
Kota makassar,
Sulawesi selatan
INDONESIA
Journal of Mathematics, Computation and Statistics (JMATHCOS)
ISSN : 24769487     EISSN : 27210863     DOI : https://doi.org/10.35580/jmathcos
Core Subject : Education,
Fokus yang didasarkan tidak hanya untuk penelitian dan juga teori-teori pengetahuan yang tidak menerbitkan plagiarism. Ruang lingkup jurnal ini adalah teori matematika, matematika terapan, program perhitungan, perhitungan matematika, statistik, dan statistik matematika.
Articles 269 Documents
Projective Geometry Analysis of the Boyang Traditional House Based on Building Numbering of House Theory Ja'faruddin Ja'faruddin; Alimuddin Tampa; Muh. Ishaq Firdaus; Nur Insani Maiwa
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/Jmathcos12954

Abstract

This study positions ethnomathematics as a framework for understanding mathematics as an embedded component of cultural practices and indigenous knowledge systems. Indonesia’s rich ethnic diversity provides a wide spectrum of traditional architectural forms containing implicit mathematical structures. This research aims to investigate the architectural structure of the Boyang traditional house through the perspective of projective geometry and House Theory, particularly in the construction of house diagrams, building numbering systems, and the formulation of projective coordinates. The study employed a descriptive qualitative approach by representing one-point, two-point, and three-point perspective views into projective geometric diagrams. The findings reveal that the Boyang house can be classified as a Type IV simple house based on House Theory classification. Furthermore, the resulting building numbers are identified as . The analysis demonstrates that the architectural structure of the Boyang house can be formally modeled within the framework of projective geometry, thereby illustrating the existence of mathematical reasoning embedded in local architectural traditions. These findings contribute to the development of ethnomathematics by strengthening the integration between formal mathematical concepts and cultural heritage studies, while also providing a theoretical foundation for interdisciplinary research in mathematics, architecture, and indigenous cultural studies.
A Markowitz–ARMA–GARCH–Copula Overlay for Jakarta Islamic Index Portfolios: A Complexity–Benefit Comparison with the Markowitz Model Irfani Azis; Nina Valentika; Nunung Kusdaniyama; Euis Aprianti; Tegar Aji Sukma Bestari
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/Jmathcos12760

Abstract

This study develops and evaluates a Markowitz–ARMA–GARCH–Copula (MAGC) overlay for Islamic stock portfolios constructed from constituents of the Jakarta Islamic Index (JII) over the period May 2020–April 2025. The Markowitz mean–variance model is used as the baseline allocation approach to form an initial buy-and-hold portfolio. The MAGC overlay is then applied to incorporate daily volatility dynamics and copula-based dependence modeling into the evaluation and refinement of portfolio risk. ARMA–GARCH models are used to capture autocorrelation and time-varying volatility in stock returns, while the copula approach is employed to model cross-asset dependence without relying on the assumption of multivariate normality. Portfolio performance is assessed using expected return, total risk, Value at Risk (VaR), and Expected Shortfall (ES). The results show that the MAGC portfolio is broadly comparable to the Markowitz portfolio, with a slightly higher expected return (0.000350 vs. 0.000346), marginally lower volatility (0.011717 vs. 0.011721), and modest reductions in VaR (0.017890 vs. 0.018080) and ES (0.025380 vs. 0.025430). However, the bootstrap comparison indicates that these differences are not statistically significant. Therefore, the MAGC overlay provides only modest risk refinement rather than clear superiority over Markowitz. Overall, the findings suggest that the conventional Markowitz model remains a competitive and parsimonious baseline for buy-and-hold JII portfolio construction, while MAGC may serve as an additional tail-risk diagnostic tool for investment managers.
A Modified Simulated Annealing Algorithm for Clusterwise Linear Regression Model Estimation Luh Putu Widya Adnyani; Bagus Sartono; Asep Saefuddin; I Made Sumertajaya; Gerry Alfa Dito; Krittiya Duangmanee
Journal of Mathematics, Computations and Statistics Vol. 9 No. 2 (2026): Volume 09 Issue 02 (June 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/Jmathcos12907

Abstract

Heterogeneous data require modeling methods that capture structural differences across subpopulations rather than imposing a single global relationship. Clusterwise linear regression (CLR) is able to provide this flexibility despite the high computational cost. Although effective, classical simulated annealing (SA) algorithms is sensitive to initial parameters and prone to premature convergence. This study proposes an improved SA-based approach by incorporating a simple stochastic modification. Rather than consistently relocating the observation with the largest residual, the algorithm randomly selects an observation from the top-(m) largest residuals at each iteration.. This mechanism allows the algorithm to explore more possible solutions while still moving toward better results. The proposed method was evaluated through simulation studies and an application to district-level poverty data in Indonesia. The results show that the modified algorithm generally provides better clustering accuracy and smaller parameter bias than the standard simulated annealing algorithm in clusterwise regression models. The real-data application also identified nine clusters with different socio-economic characteristics, showing the importance of using analytical approaches and policies that account for regional diversity.
A Python-Based Implementation of Dijkstra's Algorithm for Optimal Freight Routing in Weighted Graph Networks (Case Study: Banjarnegara-Semarang) Jundulloh Mubarok; Mulyono Mulyono
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/31926k15

Abstract

This study aims to determine the optimal freight route using a Python-based implementation of Dijkstra Algorithm in a weighted graph network, with a case study of Banjarnegara-Semarang. The network is modeled as a directed graph where nodes represent regions and edges represent distances (km). The dataset consists of 19 nodes and 38 edges. Computation is performed using Python (NetworkX) to obtain the shortest path efficiently. The results show that the optimal route is Banjarnegara–Wonosobo-Kendal-Semarang with a total distance of 146.20 km. This approach is faster and more accurate than manual calculations and supports efficient logistics decision-making.
Robust Multi-Criteria Optimization for Energy Stocks Selection on the Indonesian Stock Exchange Using a Weighted Scoring Model Sahrudin Sahrudin; Hendra Cipta
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/j2sk2n30

Abstract

Pemilihan saham terbaik merupakan masalah pengambilan keputusan multi-kriteria yang dipengaruhi oleh ketidakpastian data keuangan. Studi ini bertujuan untuk menentukan saham terbaik di sektor energi yang terdaftar di Bursa Efek Indonesia menggunakan Weighted Scoring Model (WSM) dan pendekatan Robust Multi-Criteria Optimization. Studi ini menggunakan lima kriteria fundamental, yaitu Laba Per Saham (EPS), Rasio Harga terhadap Laba (PER), Return on Equity (ROE), Rasio Utang terhadap Ekuitas (DER), dan Dividend Yield (DY). Bobot kriteria ditentukan berdasarkan tingkat pertumbuhannya selama periode observasi, diikuti dengan normalisasi dan perhitungan nilai preferensi menggunakan WSM. Pendekatan robust diterapkan pada tingkat ketidakpastian ±5%, ±10%, dan ±15%. Hasil menunjukkan bahwa ITMG menempati peringkat pertama dalam model deterministik dengan nilai preferensi 0,4722 dan mempertahankan peringkat pertama di semua skenario robust. Hasil ini menunjukkan bahwa ITMG adalah alternatif saham terbaik dan menunjukkan ketahanan terhadap perubahan data dalam tingkat ketidakpastian yang diuji.
Analysis and Simulation of SIR Model with Time Delay as a Solution to Addiction Tiktok Students of Bulukumba 4th State Middle School Based on Wisdom Local in Bulukumba Sitti Satriana; Rahmat Syam; Syafruddin Side
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/1jzmzd49

Abstract

This research is an applied research discussing the analysis and simulation of the spread of TikTok addiction disease using the SIR (Susceptible Infectious Recovered) mathematical model with a delay time to determine the model of the spread of TikTok addiction disease, analyze the equilibrium and stability points in the model, the effect of delay time on model stability and the effect of local wisdom-based interventions in reducing the number of TikTok addictions. The data used comes from SMP Negeri 4 Bulukumba
Application of Geographically and Temporally Weighted Regression to Under-Five Diarrhea Cases in East Java Nurul Aulya Bakri; Suwardi Annas; Aswi Aswi
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/rdfs5k14

Abstract

Under-five diarrhea remains an important indicator of environmental health conditions. In East Java Province, Indonesia, the incidence varies across districts and over time, indicating spatial dependence and temporal dynamics. This study aims to analyse spatial–temporal variation and examine the influence of environmental, health, and sociodemographic factors using the Geographically and Temporally Weighted Regression (GTWR) approach. Spatial panel data from 38 districts/cities during 2019–2023 were analysed, including variables on exclusive breastfeeding, sanitation, vitamin A, immunisation, drinking water facilities, and population density. Moran’s I and heterogeneity tests were applied, followed by GTWR estimation using adaptive space–time weighting. The results reveal significant spatial autocorrelation and heterogeneity, with variable effects differing across regions and periods. Vitamin A supplementation and population density show consistent positive associations, while safe drinking water exhibits a protective effect. GTWR outperforms multiple linear regression, as indicated by lower AIC and higher R² values. In conclusion, GTWR provides a more accurate representation of diarrhea patterns. It is recommended that interventions be tailored to local conditions by considering spatial and temporal variations.
Robust Improved GTWR for Spatiotemporal Heterogeneity with Outlier Effects Luri Zahara; I Gede Nyoman Mindra Jaya; Defi Yusti Faidah
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/cqg4ms14

Abstract

Spatiotemporal data often exhibit strong heterogeneity, where relationships between predictors and responses vary across locations and time. Standard regression frameworks struggle with this non-stationarity, and although the Improved Geographically and Temporally Weighted Regression (I-GTWR) addresses spatiotemporal heterogeneity through localized weighting, its reliance on Least Squares makes it highly sensitive to outliers. Contaminated observations propagate through the kernel weighting structure, leading to biased parameter estimates and distorted coefficient surfaces. To address this weakness, this study proposes a Robust I-GTWR framework that integrates M, S, and MM-estimators to downweight extreme values while retaining the model’s adaptive spatiotemporal structure. A controlled simulation was designed to generate heterogeneous spatiotemporal coefficient fields and introduce high-leverage contamination at selected locations and years. Model performance was assessed using bias and RMSE. Results show that robust variants consistently produce lower error and narrower uncertainty distributions than standard I-GTWR, particularly under moderate-to-severe contamination. The method was further applied to tuberculosis incidence and six covariates across 27 regencies/cities in West Java from 2020–2024. Model comparison using AIC selected the M-estimator as the optimal specification. The resulting coefficient surfaces reveal persistent spatiotemporal heterogeneity, effects of population density, HIV prevalence, and sanitation vary substantially across regencies/cities and evolve over time. These findings confirm that robust estimation enhances stability without sacrificing the ability to detect non-stationary processes, making Robust I-GTWR a more reliable approach for contaminated spatiotemporal data and geographically targeted disease control strategies. The method was further applied to tuberculosis incidence and six covariates across 27 regencies/cities in West Java from 2020–2024. Model comparison based on AIC indicated that the M-estimator provided the best performance among the robust specifications, achieving the lowest AIC value of 1902.742. The resulting coefficient surfaces revealed substantial spatiotemporal heterogeneity, where the effects of population density, HIV prevalence, and sanitation conditions varied considerably across regencies/cities and over time. These findings demonstrate that the Robust I-GTWR framework improves model stability in the presence of potential outliers while preserving the ability to capture non-stationary disease transmission patterns, providing more reliable insights for geographically targeted tuberculosis control strategies.
Prediction of the Bioactive Potential of Moringa Oleifera Compound Using Supervised and Unsupervised Learning Approaches Putri Indi Rahayu; Fardinah Fardinah; Asrirawan Asrirawan; Nur Arfah; Putri Ramadhani
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/spc9p810

Abstract

Indonesia is recognized as one of the world’s megadiverse countries because of its rich biodiversity, including many medicinal plants such as Moringa oleifera. This plant has long been used in traditional medicine and is known to contain various bioactive compounds with potential pharmacological properties. However, the exploration and utilization of these compounds, especially those with antibiotic activity, are still limited. One major challenges in drug discovery is the identification and validation of bioactive compounds, which usually require extensive laboratory experiments, high costs, and long periods of time. In addition, conventional experimental method often depend on advanced laboratory facilities and  specialized expertise. To overcome these limitations, computational approaches based on machine learning have emerged as promising alternatives for accelerating the discovery of potential drug compounds. Therefore, this study aims to develop and implement machine learning based computational methods to predict the antibiotic potential of bioactive compounds found in Moringa oleifera. The analysis applies both supervised and unsupervised learning approaches to identify molecular patterns, classify compound characteristics, and evaluate the relationships among bioactive compounds based on their structural properties. The results show that the proposed approaches can improve the prediction performance of antibiotic activity and identifying several potential candidate compounds that may act as promising antibiotic agents. Furthermore, combination supervised and unsupervised learning techniques provides deeper insights into the molecular characteristics of the compounds. These findings demonstrate that computational methods can serve as efficient and reliable strategies to support and accelerate natural product based drug discovery and development.
Graph-Theoretic Analysis of Weighted Neighborhood Graphs for Spatial Soil Nutrient Prediction Nurul Maulida Surbakti; Sisti Nadia Amalia; Muhammad Ashari; Riza Pahlwan
Journal of Mathematics, Computations and Statistics Vol. 9 No. 3 (2026): Volume 09 Issue 03 (September 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/fazqcb69

Abstract

Soil nutrient prediction is a spatial modeling problem because nutrient values observed at nearby locations may share common spatial structure. This study develops a graph-theoretic analysis of weighted neighborhood graphs for Graph Convolutional Network (GCN)-based prediction of synthetic nitrogen (N), phosphorus (P), and potassium (K) patterns. Ten independent Monte Carlo realizations of 100 sampling locations were generated from a uniform distribution on the unit square. For each realization, weighted k-nearest-neighbor (kNN) and epsilon-neighborhood graphs were constructed using an exponential distance-decay kernel. Graph structure was quantified using the number of edges, average degree, density, number of connected components, and algebraic connectivity. Separate transductive GCN regressors were trained for N, P, and K using  train-validation-test splits, target standardization based only on the training set, early stopping, and repeated random seeds. Binary GCN, multilayer perceptron (MLP), Random Forest, and inverse-distance weighting (IDW) were included as baselines. Among the tested graph configurations, kNN with  gave the lowest mean test error , whereas kNN with  produced a marginally higher mean . Weighted GCN improved numerically over binary GCN overall , with a significant paired improvement in MAE under a Wilcoxon test , although MLP remained slightly stronger overall . Across graph configurations, density was negatively associated with test  indicating that excessive neighborhood mixing can reduce predictive performance in these controlled settings. Nutrient-specific analysis showed that phosphorus was the most difficult target, while residual Moran’s I values were close to zero. Within the controlled synthetic scenarios, weighted neighborhood graphs provided a useful and interpretable representation for GCN-based spatial nutrient modeling. Future work should evaluate the framework on field measurements using spatial block validation and environmental covariates.