Claim Missing Document
Check
Articles

Found 26 Documents
Search

Optimalisasi Tata Kelola Pelayanan Administrasi Desa Berbasis Digital di Desa Limbato Kecamatan Tilamuta Kabupaten Boalemo Abdussamad, Juriko; Abdussamad, Zuchri; Abdussamad, Siti Nurcahyati; Abdussamad, Siti Nurmardia
Jurnal Sibermas (Sinergi Pemberdayaan Masyarakat) Vol 14, No 1 (2025): Jurnal Sibermas (Sinergi Pemberdayaan Masyarakat)
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/sibermas.v14i1.29055

Abstract

Desa Limbato, Kecamatan Tilamuta, Kabupaten Boalemo, menghadapi tantangan dalam penyelenggaraan pelayanan administrasi desa, khususnya terkait keterbatasan sumber daya manusia, sarana, prasarana, dan rendahnya penerapan digitalisasi layanan. Padahal, desa ini memiliki potensi besar dengan mayoritas penduduk berpendidikan sarjana dan capaian nominasi nasional PHBS. Untuk mengatasi permasalahan tersebut, dilaksanakan program pengabdian masyarakat melalui KKN-MBKM Terintegrasi dengan fokus optimalisasi tata kelola pelayanan administrasi berbasis digital. Metode yang digunakan meliputi sosialisasi, pelatihan pembuatan dan penggunaan website desa, serta simulasi layanan administrasi digital bagi aparatur desa selama 4 bulan. Hasil kegiatan menunjukkan bahwa aparatur desa mampu mengelola layanan administrasi secara digital, meningkatkan efisiensi pelayanan, serta memperluas akses informasi publik melalui website desa. Keberhasilan program ini diharapkan dapat mempercepat transformasi digital pemerintahan desa dan menjadi inspirasi bagi desa-desa lain di Kabupaten Boalemo dalam mewujudkan pelayanan publik yang efektif, efisien, dan transparan.
Implementasi Metode Bidirectional LSTM Dengan Word Embedding FastText Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim Wewengkang, Hanz Franklyn Bachruddin; Wungguli, Djihad; Yahya, Nisky Imansyah; Hasan, Isran K.; Abdussamad, Siti Nurmardia
Jurnal Riset Mahasiswa Matematika Vol 4, No 5 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i5.33358

Abstract

Aplikasi transportasi online kini menjadi bagian penting dalam kehidupan masyarakat Indonesia. Maxim, sebagai salah satu penyedia layanan, perlu memahami persepsi pengguna untuk meningkatkan kualitas layanannya. Penelitian ini menerapkan metode Bidirectional Long Short-Term Memory (BiLSTM) untuk melakukan klasifikasi sentimen terhadap ulasan pengguna aplikasi Maxim di Google Play Store. Untuk memperkuat representasi kata, digunakan word embedding FastText yang mampu menangkap informasi sub-kata secara lebih baik. Data penelitian diperoleh melalui scraping menggunakan package google-play-scraper pada Python. Model BiLSTM yang dilatih dengan konfigurasi hyperparameter optimal berhasil mengklasifikasikan sentimen ulasan secara efektif, dengan hasil accuracy 94%, precision 96%, recall 95%, dan f1-score 95%. Hasil ini menunjukkan bahwa kombinasi BiLSTM dan FastText mampu mendeteksi sentimen positif dan negatif secara akurat dan seimbang, serta relevan untuk mendukung evaluasi kualitas layanan berbasis opini pengguna.
FORECASTING STOCK PRICES OF PT. BANK RAKYAT INDONESIA USING THE HYBRID ARIMA-BACKPROPAGATION NEURAL NETWORK METHOD Alaina, Silvana Rahmayanti; Hasan, Isran K.; Abdussamad, Siti Nurmardia
VARIANCE: Journal of Statistics and Its Applications Vol 7 No 1 (2025): VARIANCE: Journal of Statistics and Its Applications
Publisher : Statistics Study Programme, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/variancevol7iss1page39-48

Abstract

PT. Bank Rakyat Indonesia (Persero) Tbk is classified as a blue-chip stock. Although investing in BRI shares has the potential to generate profits, stock price fluctuations can pose risks, making forecasting necessary. The ARIMA model is frequently used to predict such fluctuations, but struggles to capture non-linear patterns. ARIMA is combined with an Artificial Neural Network (ANN), specifically the Backpropagation Neural Network, to address this issue and improve forecasting accuracy. Although Backpropagation is weak in slow convergence, this can be overcome using the Conjugate Gradient Powell Beale (CGB) algorithm. The research results show that the closing stock price data of BRI from January 2023 to February 2024 produced an ARIMA (1,1,1)-Backpropagation [4-4-1] model with higher accuracy, achieving a MAPE of 2.516% and RMSE of 200.1592, Relative to the standalone ARIMA (1,1,1) model, which had a MAPE of 6.203% and RMSE of 421.5896.
Pemodelan Multiple Discriminant Analysis Pada Perilaku Impulsive Buying Pengguna Shopee Pada Tanggal Cantik Naue, Siti Nurmeylisya; Yahya, Lailany; Abdussamad, Siti Nurmardia; Payu, Muhammad Rezky Friesta; Nasib, Salmun K
Griya Journal of Mathematics Education and Application Vol. 5 No. 2 (2025): Juni 2025
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v5i2.632

Abstract

Impulsive buying is a consumer behavior that makes purchases without prior planning. Impulsive buying is one of the consumer behavior phenomena that is increasingly widespread, especially on e‑commerce platforms such as Shopee during massive promotions on beautiful dates. Multiple Discriminant Analysis (MDA) is a method that has the advantage of classifying individuals into groups based on several predictor variables. The purpose of this study is to classify consumers into groups or categories based on their tendency to make impulse purchases on beautiful dates by analyzing the factors that influence them. The results of this study indicate that the beautiful date can affect the behavior of impulsive buying. The discriminant function model formed is able to distinguish categories of impulsive buying behavior with a good classification accuracy rate of 86.25% and the model shows that price is the most dominant or influential factor in distinguishing the category of impulsive buying of Shopee users on beautiful dates. This means that MDA Modeling is very helpful in classifying respondents into groups or categories based on the factors that influence them.
Penerapan Ensemble K-modes Pada Pengelompokkan Kelurahan di Kota Gorontalo Berdasarkan Kecanduan Game Online Remaja Taufik, Mohamad Alfiransyah; Achmad, Novianita; Abdussamad, Siti Nurmardia; Wungguli, Djihad; Yahya, Nisky Imansyah
Griya Journal of Mathematics Education and Application Vol. 5 No. 2 (2025): Juni 2025
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v5i2.633

Abstract

The swift advancement of digital technology has resulted in a heightened frequency of online game usage among teenagers, raising concerns about potential addiction. This study aims to cluster urban villages in Gorontalo City based on the characteristics of online game addiction in adolescents, to support the formulation of more effective preventive policies. The method used is ensemble clustering with K-modes algorithm approach, which is effective for mixed numeric and categorical data. Data were obtained through a survey of adolescents aged 10-24 years in all urban villages, including indicators of lack of attention from close people, self-control, lack of activities, stress or depression, social environment, parenting, length of time playing online games, frequency of playing online games and many favorite online games. The clustering results obtained 3 optimum clusters, where cluster 1 consists of 7 neighborhoods, cluster 2 consists of 17 neighborhoods and cluster 3 consists of 26 neighborhoods. Cluster 1 is a group of neighborhoods with a low risk and addiction level, cluster 2 with a moderate tendency, and cluster 3 with a high tendency.
Density based spatial clustering of application with noise using flower pollination algorithm for leptospirosis clustering Karim, Finansiya S. Abd.; Rahmi, Emli; Abdussamad, Siti Nurmardia; Hasan, Isran K.; Yahya, Nisky Imansyah
PYTHAGORAS : Jurnal Program Studi Pendidikan Matematika Vol 14, No 1 (2025): PYTHAGORAS: Jurnal Program Studi Pendidikan Matematika
Publisher : UNIVERSITAS RIAU KEPULAUAN, BATAM, INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33373/pyth.v14i1.7505

Abstract

Leptospirosis is an important health problem in Indonesia, with most cases found in East Java and Central Java provinces. This study aims to identify the distribution pattern of leptospirosis in the two provinces using a clustering approach. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method is used to cluster areas based on leptospirosis spread factors, but DBSCAN requires optimal parameter determination for accurate results. Therefore, this research implements Flower Pollination Algorithm (FPA) to optimize the epsilon (ϵ) and minimum points (MinPts) parameters in DBSCAN. This research uses secondary data obtained from data on the Number of Natural Disaster Events by Regency / City in East Java and Central Java Provinces in 2023 and data on Population Density by Regency / City in East Java and Central Java Provinces in 2023. The population in this study uses all observations, namely all people in the districts and cities in East Java and Central Java. The sampling technique is saturated sampling, that is, the entire population in the study is sampled. The clustering results using FPA-DBSCAN resulted in two main clusters, with 30 districts/municipalities detected as noise, 23 districts/municipalities belonging to cluster 0, and 20 districts/municipalities in cluster 1. The validation test using Silhouette Coefficient showed a value of 0.1892, indicating that the clustering is quite valid. The results of this clustering can serve as a strategic reference for local governments in optimizing disease surveillance and targeted health interventions.
Prediksi Wisatawan Mancanegara di Indonesia Menggunakan Metode SARIMAX dengan Efek Variasi Kalender Libur Nasional Pakaya, Desya Neydi Putri; Achmad, Novianita; Hasan, Isran K; Wungguli, Djihad; Abdussamad, Siti Nurmardia
Jurnal Riset Mahasiswa Matematika Vol 4, No 6 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i6.34937

Abstract

Fluctuations in the number of foreign tourist arrivals often produce outlier values that can interfere with the accuracy of the forecasting model. This study uses a boxplot approach to detect outliers, followed by Natural Logarithm (ln) transformation as a treatment step. The Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) method is applied by considering three exogenous variables that show the effect of variations in the National Holiday calendar in the form of Nyepi Day, Idul Fitri Day and year-end holidays. The results of the analysis show that the three variables have a positive effect on the increase in the number of foreign tourist arrivals, where Nyepi Day makes the largest contribution compared to the other two holiday periods. Model 2 (0,1,1)(1,0,1)[12] was selected as the most optimal model based on the evaluation results of several models that have been compared. This model shows excellent performance, indicated by the Mean Absolute Percentage Error (MAPE) value of 3.75\% which indicates that the model has very high prediction accuracy. So that the SARIMAX model is effective in modeling and predicting the number of foreign tourist visits in Indonesia.
PENERAPAN HYBRID SEVEN TOOLS ANALYSIS DAN FAILURE MODE AND EFFECTS ANALISIS DALAM STATISTICAL PROSES Sulista Kamah; Novianita Achmad; Siti Nurmardia Abdussamad
JURNAL ILMIAH EKONOMI DAN MANAJEMEN Vol. 3 No. 7 (2025): Juli
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jiem.v3i7.5843

Abstract

Kawan Gypsum adalah usaha rumahan ini bergerak pada bidang jasa yangme layani penjualan serta pemasangan gypsum bagi rumah rumah, pertokoan, out let atau gedung gedung yang nantinya digunakan untuk mempercantik arsitektur dalam rumah. Penelitian ini bertujuan untuk menganalisis penerapan seven tools analysis Dan failure mode and effects analisis dalam SPC pada jenis Kecacatan Pada Produksi Profil Gypsum Di Kawan Gypsum. Metode seven tools untuk mengiden tifikasi kualitas produk profil Kawan Gypsum. Penelitian ini menggunakan data primer yang diperoleh melalui angket, wawancara, dukumentasi dan observasi. Populasi dalam penelitian ini mencakup seluru hasil produksi pada kawan Gyp sum. Sampel pada penelitian ini dengan menggunakan metode sampling purposive yaitu suatu metode pengambilan sampel dalam penelitian dimana peneliti bijak sana memilih sampel berdasarkan kriteriakriteria tertentu yang dianggap sesuai dengan tujuan penelitian. Hasil Failure Mode and Effects Analysis memperoleh ni lai RPN tertinggi untuk cacat produksi profil gypsum adalah 392, yang disebabkan oleh faktor manusia dan faktor metode, yaitu kelelahan dan kurang konsentrasi, penyimpanan yang tidak benar dan finishing yang tidak tepat, posisi kedua de ngan RPN berjumlah 343 yang disebabkan oleh faktor manusia yaitu kesalahan dalam proses pengeringan, posisi ketiga ditempati oleh RPN berjumlah 336 dari faktor lingkungan yaitu aliran udara yang tidak merata, posisi keempat ditempati oleh RPN berjumlah 294 dari faktor mesin yaitu penuangan yang kurang efisien, dan posisi kelima ditempati oleh RPN berjumlah 288 dari faktor bahan dan fak tor mesin yaitu minyak cetakan atau bahan pelapis yang tidak sesuai dan sistem penuangan yang tidak konsisten.
PANEL DATA REGRESSION ANALYSIS FOR MODELING THE HUMAN DEVELOPMENT INDEX IN NORTH SULAWESI PROVINCE Abdussamad, Siti Nurmardia; Adityaningrum, Amanda; Payu, Muhammad Rezky Friesta
Parameter: Journal of Statistics Vol. 4 No. 1 (2024)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/27765660.2024.v4.i1.17138

Abstract

The regression analysis is a technique used in hypothesis testing to determine the impact of one variable on another. This study uses Panel Data Regression Analysis, which combines cross-sectional and time series data. This study aims to analyze the impact of Life Expectancy, Income Per Capita, Expected School Years, and Average School Years on the Human Development Index. According to the result of the analysis, the Common Effect Model (CEM), which used Ordinary Least Squares (OLS) estimation, was the most suitable model. The equation obtained is . Moreover, according to the significance test, all independent variables were significantly related to the dependent variable
Evaluation of Implementation Context Based Clustering In Fuzzy Geographically Weighted Clustering-Particle Swarm Optimization Algorithm Abdussamad, Siti Nurmardia; Astutik, Suci; Effendi, Achmad
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 14 No. 1 (2020)
Publisher : Faculty of Engineering, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jeeccis.v14i1.609

Abstract

This paper contains an evaluation of the implementation Context Based Clustering method into Fuzzy Geographically Weighted Clustering-Particle Swarm Optimization (FGWC-PSO) algorithm on 11 variable from data factors causing the spread of dengue in East Java. Integration of Particle Swarm Optimization as a metaheuristic algorithm makes the computation run longer so, the solution in this paper is FGWC-PSO will be combined with context based clustering to produce a hybrid method (CFGWC-PSO) which can shorten the computational time of the clustering algorithm. Context based clustering in this paper will use 3 ways, namely by using random values, using Fuzzy C-Means (FCM), and using mean and standard deviations. CFGWC-PSO algorithm using number of clusters = 2 and CFGWC-PSO will be evaluated using IFV index, based on processing results found that the best clustering algorithm is CFGWC-PSO using FCM