Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : arrus journal of mathematics and applied science

Geographically Weighted Regression with Bi-Square Kernel Weights for Life Expectancy Data in East Java Province Meliyana, Sitti Masyitah; Rusli, R.; Rahman, Abdul
ARRUS Journal of Mathematics and Applied Science Vol. 4 No. 2 (2024)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience3396

Abstract

This study explores the application of Geographically Weighted Regression (GWR) using a Bi-Square Kernel weighting function to analyze life expectancy data across East Java Province. By incorporating spatial heterogeneity, the GWR model provides more accurate and localized insights compared to traditional global regression models. The results indicate significant spatial variability in the effects of poverty rate, healthcare facilities, sanitation, health complaints, and immunization coverage on life expectancy. Based on the analysis of life expectancy estimates in regencies/cities of East Java Province, the Madura region exhibits lower life expectancy compared to other areas, with Bangkalan Regency having the lowest life expectancy at 61.43 years. Additionally, urban areas generally have higher life expectancy than rural areas, with Surabaya City recording the highest life expectancy in East Java at 72.03 years. This disparity can be attributed to differences in the quality of healthcare services and better access to healthcare in urban areas compared to rural ones.
Implementation of Support Vector Regression (SVR) and Double Exponential Smoothing (DES) for Forecasting BRI Stock Prices Meliyana, Sitti Masyitah; Aidid, Muhammad Kasim; Rahmadhani, Amaliyah
ARRUS Journal of Mathematics and Applied Science Vol. 5 No. 2 (2025)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience4282

Abstract

This study aims to forecast the closing stock prices of BRI using Support Vector Regression (SVR) and Double Exponential Smoothing (DES) methods. The data used in this research is secondary data obtained from the Yahoo Finance website, covering the period from January 2020 to November 2023. The analytical steps using the SVR method involve selecting the optimal model by applying Grid Search Optimization to various kernels (linear, polynomial, radial, and sigmoid). The best-performing model was found to be the radial kernel with parameters ? = 0.1, C = 100, and ? = 10, yielding a Mean Absolute Percentage Error (MAPE) of 0.2431%, which was then used for forecasting. For the DES method, the steps involved parameter determination and minimizing the MAPE value, followed by smoothing calculations and forecasting. The optimal parameters obtained were ? = 0.89 and ? = 0.01, resulting in a MAPE value of 1.4832%. Based on the comparison of MAPE values, it can be concluded that the SVR method with a radial kernel (? = 0.1, C = 100, ? = 10) provides the most accurate forecasts for BRI closing stock prices, with the lowest MAPE of 0.2431%.
A Hybrid Neural Network Approach Using SOM and LVQ for Mapping Crime Clusters in Indonesia Rais, Zulkifli; Meliyana, Sitti Masyitah; Hasbullah, Dinda Warfani
ARRUS Journal of Mathematics and Applied Science Vol. 5 No. 2 (2025)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/mathscience4782

Abstract

Crime ratehigh crime rates in Indonesia are one of the important issues that need to be addressed with data-based strategies. This study aims to group provinces in Indonesia based on crime patterns using Self-Organizing Map (SOM) and classify the results using Learning Vector Quantization (LVQ). The results of the clustering analysis using SOM show that the optimal number of clusters is two, as supported by validation using Connectivity, Dunn Index, and Silhouette Score. Cluster 1 consists of 31 provinces with lower crime rates, while Cluster 2 includes 3 provinces with higher crime rates. To improve understanding of the clustering results, classification was carried out using the LVQ method, which produced an accuracy of 91.43%.