Article Per Year (5 Year)
p-Index From 2021 - 2026
5.212
P-Index
This Author published in this journals
All Journal EIGEN MATHEMATICS JOURNAL Mattawang: Jurnal Pengabdian Masyarakat JINAV: Journal of Information and Visualization Quantitative Economics and Management Studies Panrannuangku Jurnal Pengabdian Masyarakat Daengku: Journal of Humanities and Social Sciences Innovation ARRUS Journal of Social Sciences and Humanities ARRUS Journal of Mathematics and Applied Science Ininnawa: Jurnal Pengabdian Masyarakat ARRUS Jurnal Pengabdian Kepada Masyarakat Jurnal Hasil-Hasil Pengabdian dan Pemberdayaan Masyarakat (JHP2M) SMART: Jurnal Pengabdian Kepada Masyarakat Jurnal MediaTIK Journal of Mathematics, Computation and Statistics (JMATHCOS)
Sitti Masyitah Meliyana R.
Universitas Negeri Makassar
Religion Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Physics Public Health Social Sciences Other

Published : 39 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 39 Documents
Search

 1   2   3   4 
Comparative Performance Analysis of Two Clustering Methods for Grouping Indonesian Provinces Based on Forest Area Size Meliyana, Sitti Masyitah; S.A. Dunggio, Anugra; Muhammad, Subhan; Rahman, Abdul
Daengku: Journal of Humanities and Social Sciences Innovation Vol. 5 No. 4 (2025)
Publisher : PT Mattawang Mediatama Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.daengku4439

Abstract

This study aims to compare the performance of two clustering algorithms, K-Means Clustering and K-Medoids Clustering in grouping Indonesian provinces based on forest area by type. The optimal number of clusters was determined using the minimum Davies–Bouldin Index (DBI), while cluster performance was evaluated using the Silhouette Coefficient. Clustering, as one of the key techniques in data mining, automatically classifies data into several groups with similar characteristics. The results reveal differences in the number of clusters produced by the two algorithms. The K-Means method generated four clusters, indicated by its lowest DBI value of 0.515, whereas the K-Medoids method produced three clusters, with a minimum DBI value of 0.559. The clustering performance of K-Means resulted in a Silhouette Coefficient of 0.610, while K-Medoids achieved a higher value of 0.644. Based on these results, the K-Medoids Clustering method with three clusters, demonstrates superior performance in analyzing the grouping of Indonesian provinces by forest area type.
Geographically Weighted Regression (GWR) Modeling in Identifying Factors Affecting the Gender Empowerment Index in Indonesia Meliyana, Sitti Masyitah; Ahmar, Ansari Saleh; Rahman, Abdul
Daengku: Journal of Humanities and Social Sciences Innovation Vol. 5 No. 4 (2025)
Publisher : PT Mattawang Mediatama Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.daengku4449

Abstract

This study aims to analyze the factors influencing the Gender Empowerment Index (GEI) in Indonesia using the Geographically Weighted Regression (GWR) method. The variables used in this study include the proportion of women in managerial positions, women’s income contribution, the proportion of professional workers, reported health complaints, and the proportion of women in parliament. The findings indicate that, among the five independent variables examined, only two variables significantly affect the dependent variable: the proportion of women in managerial positions (X1) and the percentage of women reporting health complaints (X5). This is evidenced by their respective probability values (Pr(>F)) of 0.0045 and 0.0128, which are below the 0.05 significance threshold. This implies that X1 and X5 have a statistically significant influence in the model. The GWR model was found to be the most suitable compared to other models, with an AIC value of 186.72 and an R² of 92.03%, indicating superior model performance in capturing spatial and non-spatial effects across regions.
Performance Evaluation of the K-Means Clustering Method in Grouping Indonesian Provinces Based on Potential Disaster Impact Meliyana, Sitti Masyitah; Dunggio, Anugra S. S.; Ahmar, Ansari Saleh
JINAV: Journal of Information and Visualization Vol. 6 No. 2 (2025)
Publisher : PT Mattawang Mediatama Solution

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

Abstract

This study aims to cluster the provinces in Indonesia based on their level of potential disaster impact, which consists of hazard area, exposed population, physical losses, economic losses, and environmental damage, using the K-Means clustering algorithm and to evaluate the performance of the resulting model. The optimal number of clusters was determined using the Silhouette Coefficient and the Elbow Method with the Within-Cluster Sum of Squares (WSS) approach. The performance evaluation of the K-Means clustering was conducted using the Davies–Bouldin Index (DBI). Based on the selection of the optimal number of clusters, the Silhouette Coefficient produced the highest value at K=3, with a score of 0.699. Similarly, the Elbow Method showed a significant decrease in the mean WSS at K=3, indicating that three clusters were optimal. The performance evaluation using DBI for K=3 resulted in a score of 0.30. According to the principle of DBI evaluation, the closer the DBI value is to zero (without being negative), the better the clustering quality. Therefore, it can be concluded that the K-Means clustering algorithm successfully produced a very good clustering structure in grouping Indonesian provinces based on their potential disaster impact.
Sosialisasi Sekolah Siaga Bencana (SSB) Sebagai Upaya Meningkatkan Kesiapsiagaan Siswa di SMA Athira Makassar Meliyana, Sitti Masyitah; Muthahharah, Isma; Mar'ah, Zakiyah; Hafid, Hardianti; Juhari, Agusalim
Ininnawa : Jurnal Pengabdian Masyarakat Vol. 4 No. 1 (2026): Vol. 4 No. 1 (2026): Volume 04 Nomor 01 (Mei 2026)
Publisher : Program Studi Manajemen FEB UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26858/1khhs667

Abstract

Indonesia is a disaster-prone country, making early preparedness efforts essential, particularly in the school environment. This community service activity aims to improve students’ knowledge and preparedness through the socialization of the Disaster Preparedness School (Sekolah Siaga Bencana/SSB) program at SMA Athira Makassar. The methods used include interactive lectures, discussions, and evacuation simulations, with evaluation conducted using pre-test and post-test. The results show an increase in the average preparedness score from 58.9 in the pre-test to 83.8 in the post-test, indicating an improvement of 24.9 points. The highest increase was found in the understanding of evacuation procedures. These findings indicate that the SSB socialization program is effective in enhancing students’ knowledge and disaster preparedness. Therefore, this activity contributes to fostering a disaster aware culture in schools and can serve as a model for implementing education-based disaster preparedness programs.
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%.
Pemberdayaan Ekonomi Lokal Melalui Budidaya Lebah Trigona di Desa Lantawonua Bombana Isma Muthahharah; Zakiyah Mar’ah; Hardianti Hafid; Sitti Masyitah Meliyana; Farida Islamiah
SMART: Jurnal Pengabdian Kepada Masyarakat Vol 6, No 1 (2026): April
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/smart.v6i1.83144

Abstract

Rendahnya pemanfaatan potensi vegetasi lokal di Desa Lantawonua, Kabupaten Bombana, menjadi isu utama yang melatarbelakangi perlunya diversifikasi ekonomi melalui sektor kreatif. Fokus pengabdian ini adalah pemberdayaan ekonomi keluarga melalui budidaya lebah tanpa sengat (Trigona) dengan memanfaatkan lahan pekarangan dan kebun produktif. Tujuan pengabdian ini adalah untuk meningkatkan keterampilan teknis masyarakat dalam budidaya lebah serta membentuk kemandirian ekonomi melalui kelompok usaha yang terorganisir. Metode pelaksanaan menggunakan pendekatan partisipatif dengan strategi riset aksi yang meliputi sosialisasi pemetaan wilayah vegetasi berbasis visual, pendampingan pembentukan kelompok UPPKA "Measa Laro", pelatihan teknis lapangan, serta sistem monitoring dan evaluasi berkala. Hasil pengabdian menunjukkan adanya peningkatan signifikan pada kapasitas masyarakat dalam mengelola potensi alam secara lestari, dengan tingkat keberhasilan adaptasi koloni lebah mencapai 90%. Kegiatan ini menegaskan bahwa integrasi antara edukasi teknis dan penguatan kelembagaan lokal mampu menciptakan ketahanan ekonomi desa yang berbasis pada kelestarian ekosistem.
PKM Workshop Pembuatan Micromodul Digital untuk Meningkatkan Keterampilan IT dalam Pengajaran Para Guru SMA Negeri 7 Takalar Sitti Masyitah Meliyana; Ruliana; Sudarmin; Rahmat Hidayat; Muh. Qodri Alfairus
ARRUS Jurnal Pengabdian Kepada Masyarakat Vol. 4 No. 2 (2025)
Publisher : PT ARRUS Intelektual Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.abdiku4283

Abstract

Perkembangan teknologi digital menuntut guru untuk memiliki keterampilan dalam memanfaatkan media pembelajaran berbasis teknologi. Namun, guru-guru di SMA Negeri 7 Takalar masih menghadapi kendala dalam pembuatan dan penggunaan micromodul digital yang interaktif. Kegiatan Pengabdian kepada Masyarakat (PKM) ini bertujuan meningkatkan keterampilan teknologi informasi para guru melalui workshop pembuatan micromodul digital menggunakan aplikasi Canva dan Heyzine Flipbook. Metode pelaksanaan meliputi sosialisasi, pelatihan, penerapan teknologi, pendampingan, evaluasi, dan keberlanjutan program. Kegiatan diikuti oleh 25 guru dengan latar belakang mata pelajaran yang beragam. Hasil menunjukkan bahwa 85% peserta mampu membuat micromodul digital sesuai standar, 75% berhasil mengintegrasikannya ke dalam Rencana Pelaksanaan Pembelajaran (RPP), dan 80% merasakan peningkatan interaktivitas pembelajaran di kelas. Kesimpulannya, pelatihan ini efektif meningkatkan keterampilan IT guru dan berdampak pada peningkatan kualitas pembelajaran di SMA Negeri 7 Takalar.
Analysis and Forecasting of Unilever Indonesia Stock Prices Using a Long Short-Term Memory (LSTM) Model Sitti Masyitah Meliyana; Abdul Rahman
Daengku: Journal of Humanities and Social Sciences Innovation Vol. 6 No. 1 (2026)
Publisher : PT Mattawang Mediatama Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.daengku4787

Abstract

This study aims to forecast the stock price of Unilever Indonesia using the Long Short-Term Memory (LSTM) model. The dataset consists of weekly stock price data from May 2015 to May 2025, representing a financial time series with nonlinear and dynamic patterns. The LSTM model is employed due to its capability to capture long-term dependencies in sequential data. To evaluate model performance, the dataset is partitioned into three training–testing scenarios, namely 90:10, 80:20, and 70:30. Model accuracy is assessed using the Mean Absolute Percentage Error (MAPE). The results indicate that the best predictive performance is achieved using the 90:10 data split, yielding the lowest MAPE value of 6.973%, which falls into the highly accurate forecasting category. In comparison, the 70:30, and 80:20 scenarios produce higher MAPE values of 13.732% and 17.263% respectively. These findings demonstrate that increasing the proportion of training data significantly improves the performance of the LSTM model in forecasting stock prices. This study highlights the effectiveness of LSTM in modeling financial time series and provides practical insights for data-driven decision-making in stock market analysis.
Co-Authors Abdul Rahman Abdul Rahman Agusalim Juhari Ahmad Yasir Aras Ahmar, Ansari Saleh Aidid, Muhammad Kasim Alfairus, Muh. Qodri Alok Kumar Panday Angri Lismayani Anisa Nurfadilah Nurdin Annisa, Nurawalia Baso Intang Sappaile Dunggio, Anugra S. S. Elisa, Nur Erman Syarif Farida Islamiah Hardianti Hafid Hasbullah, Dinda Warfani Hastuty Musa Isma Muthahharah Isma Muthahharah Jamaluddin Jamaluddin Lince, Ranak Mar'ah, Zakiyah Mariani Mar’ah, Zakiyah Miguel Botto-Tobar Muhammad Ammar Naufal Muhammad Ansarullah S. Tabbu Muhammad Isbar Pratama Muhammad, Subhan Muthahharah, Isma Nachnoer Arss Parkhimenko Vladimir Anatolievich R. Rusli Rahmadhani, Amaliyah Rahman, Abdul Rahmat Hidayat Rahmat Hidayat Rais, Zulkifli Rezky Amalia Hamka Ruliana Ruliana Ruliana, Ruliana Ruliana, R. Rusli Rusli Rusli Rusli Rustam, Sitti Nail Rustam, Sitti Nailah S. Sudarmin, S. S.A. Dunggio, Anugra Siti Nurazizah Auliah Sitti Nailah Rustam Sitti Nailah Rustam Sudarmin Sudarmin Sudarmin Wahyuni, Maya Sari Yunus, Asmar Zakiyah Mar'ah Zakiyah Mar'ah Zakiyah Mar’ah Zulkifli Rais