Claim Missing Document
Check
Articles

CLUSTERING DATA METEOROLOGI WILAYAH INDONESIA TIMUR DENGAN METODE K-MEANS DAN FUZZY C-MEANS Gion Andrian; Desi Arisandi; Teny Handhayani
INTI Nusa Mandiri Vol. 18 No. 2 (2024): INTI Periode Februari 2024
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i2.5039

Abstract

Climate change is a global issue that affect human life and the environment. Signs of climate change can be observed from long-term meteorological data. This research uses clustering techniques with the K-Means and Fuzzy C-Means methods to group cities in the Eastern Indonesia region based on numerical daily time series meteorological data from 1 January 2010 to 31 August 2023. The variables are minimum temperature, maximum temperature, temperature average, humidity, rainfall, duration of sunlight, maximum wind speed, and average wind speed. The dataset was collected from 28 meteorological stations. The K-Means and Fuzzy C-Means methods obtained the same results, namely the highest silhouette value of 0.218 with the number of clusters k = 2. In general, the annual trend shows an increase in temperature and a decrease in wind speed which are signs of climate change. This research is an early study of climate change in East Indonesia. The results of this research are expected to contribute to the study of climate change in Indonesia.
IMPLEMENTASI METODE CLUSTERING UNTUK PEMETAAN WILAYAH PRODUKSI DAN EKSPOR KOPI DI INDONESIA Arya Dwi Saputra; Jefri Jaya; Teny Handhayani; Manatap Sitorus Dolok Lauro
INTI Nusa Mandiri Vol. 20 No. 1 (2025): INTI Periode Agustus 2025
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v20i1.6903

Abstract

Coffee is one of the main agricultural commodities in Indonesia, but the distribution of production and export contribution is still uneven. This study aims to map the patterns of coffee production and export in Indonesia using clustering methods, namely K-Means and Hierarchical Agglomerative Clustering (AHC). The data used includes coffee production by province and regency (2015–2022), as well as coffee export data by destination country (2016–2023), obtained from BDSP and BPS. The system is developed in the form of an interactive website that allows users to upload datasets, select clustering methods, and view analysis results in the form of tables, graphs, and interactive maps. Clustering quality is evaluated using the Silhouette Score and Davies-Bouldin Index (DBI). The testing results show that the optimal number of clusters is two for all datasets, with the highest Silhouette score reaching 0.85 and the lowest DBI of 0.21, indicating good clustering quality. AHC is more effective in analyzing export and provincial-level production data, while K-Means performs better for regency-level data. This system is expected to provide insights into the distribution patterns of coffee production and exports and support decision-making in the agricultural sector, particularly for coffee commodities.
CLUSTERING WILAYAH KEMISKINAN MULTIDIMENSI DI INDONESIA MENGGUNAKAN ALGORITMA FUZZY C-MEANS DAN OPTICS Nicholas Eugene Supardi; Teny Handhayani; Irvan Lewenusa
INTI Nusa Mandiri Vol. 20 No. 2 (2026): INTI Periode Februari 2026
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v20i2.7814

Abstract

A multidimensional approach to mapping poverty in Indonesia necessitates the use of the Human Development Index (HDI), Poverty Line, and Expenditure per Capita. This study aims to evaluate the performance of two clustering algorithms with distinct paradigms the centroid-based Fuzzy C-Means (FCM) and the density-based OPTICS in profiling poverty across 501 regencies and cities. Experimental results indicate that OPTICS achieved high internal validity, with a Silhouette Score of 0.7301 and a Davies-Bouldin Index (DBI) of 0.329. Significantly, OPTICS identified 94% of the data as noise. This finding reveals a fundamental characteristic: the distribution of socio-economic data in Indonesia is highly heterogeneous and sparse, lacking inherently dense cluster structures. Conversely, FCM, employing a soft clustering approach, successfully accommodates the ambiguity of data boundaries and provides comprehensive segmentation across all regions. Despite yielding lower validity metrics (Silhouette Score 0.3894), FCM was selected as the final model because it satisfies the practical requirements of the application, which demands complete coverage mapping. This study concludes that a soft clustering approach is more applicable than density-based clustering for analyzing highly heterogeneous data such as that found in Indonesia
A Hybrid Linear Regression Model with Mean Reversion and Alligator Indicators for Short-Term Forex Price Trend Prediction Irvan Lewenusa; Teny Handhayani
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.5.5514

Abstract

The foreign exchange (forex) market is characterized by high liquidity and rapid price fluctuations, which pose significant challenges for short-term price trend prediction using conventional statistical models. This study aims to develop a more reliable forecasting approach by addressing the limitations of standalone linear regression under volatile market conditions. To achieve this objective, a hybrid modelling framework is proposed that integrates Linear Regression with Mean Reversion principles and the Alligator technical indicator. Historical data OHLC data for three major currency pairs (AUDUSD, EURUSD, GBPUSD) were acquired from the Metatrader 5 platform, covering period from January to May 2025 with a 5-minute timeframe. The model performance was evaluated using monthly and weekly forecasting scenarios, supported by standard regression error metrics and back testing validation. The results show that compared to a baseline model using linear regression only, the proposed hybrid approach provides substantially improved predictive reliability in weekly forecasting scenarios, achieving average R2 values above 0.85 across all evaluated currency pairs. In addition, the hybrid framework facilitates clearer and more reliable buy and sell decision making by combining quantitative trend estimation with deviation base correction signals and trend structure confirmation. From a Computer Science perspective, this study contributes to predictive time series modelling and algorithmic trading research by demonstrating that hybrid integration of machine learning and technical indicators enhances model stability, interpretability, and decision support capability for short-term forex forecasting.
PEMBUATAN WEBSITE UNTUK UMKM GUDEG JOGJA DIAJENG Reinerius S. D. Kristiantoro; Teny Handhayani; Wasino; Desi Arisandi; Irvan Lewenuisa; Jeanny Pragantha
Jurnal Serina Abdimas Vol 4 No 3 (2026): Jurnal Serina Abdimas
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/jsa.v4i3.38026

Abstract

Gudeg Jogja Diajeng is a culinary business that still faces challenges in its ordering process because the current system is conducted manually through direct visits and the WhatsApp instant messaging application. This process causes several problems, such as delays in service when the number of orders increases, the risk of recording errors, and difficulties in managing transaction data. This Community Service Program aims to assist Gudeg Jogja Diajeng in implementing digital transformation through the development of an online ordering website as an effort to support economic growth by increasing MSME productivity and competitiveness. The implementation method includes identifying partner problems, analyzing system requirements, collecting data, designing the website, developing the program code, testing the system, and providing website operation training for the partner. The developed website provides various features, including stock and price management, menu management, transaction reports, and customer features such as Micro, Small, and Medium Enterprises (MSMEs) information, menu listings, shopping cart, ordering, and payment processes. System testing was conducted using the User Acceptance Test (UAT) method and the System Usability Scale (SUS) evaluation to determine the level of user acceptance and system usability. The SUS evaluation result obtained a score of 82.16, indicating that the website has good usability and is well accepted by users. The implementation of this online ordering website is expected to improve operational efficiency, facilitate customers in conducting transactions, expand marketing reach, and support the sustainability and growth of Gudeg Jogja Diajeng MSME through the utilization of digital technology. ABSTRAK UMKM Gudeg Jogja Diajeng merupakan salah satu usaha kuliner yang masih menghadapi kendala dalam proses pemesanan karena sistem yang digunakan masih dilakukan secara manual melalui kunjungan langsung maupun aplikasi pesan instan WhatsApp. Proses tersebut menyebabkan beberapa permasalahan, seperti keterlambatan pelayanan saat jumlah pesanan meningkat, risiko kesalahan pencatatan, serta kesulitan dalam pengelolaan data transaksi. Kegiatan Pengabdian kepada Masyarakat (PKM) ini bertujuan untuk membantu UMKM Gudeg Jogja Diajeng dalam melakukan transformasi digital melalui pengembangan website pemesanan daring sebagai upaya mendukung pencapaian pertumbuhan ekonomi melalui peningkatan produktivitas dan daya saing UMKM. Metode pelaksanaan kegiatan meliputi identifikasi permasalahan mitra, analisis kebutuhan sistem, pengumpulan data, perancangan website, pembuatan kode program, pengujian sistem, serta pelatihan penggunaan website kepada mitra. Website yang dikembangkan menyediakan berbagai fitur, yaitu pengelolaan stok dan harga, pengelolaan menu, laporan transaksi, serta fitur pelanggan berupa informasi UMKM, daftar menu, keranjang belanja, pemesanan, dan pembayaran. Pengujian sistem dilakukan menggunakan metode User Acceptance Test (UAT) dan evaluasi System Usability Scale (SUS) untuk mengetahui tingkat penerimaan dan kemudahan penggunaan sistem. Hasil evaluasi SUS memperoleh skor sebesar 82,16, yang menunjukkan bahwa website memiliki tingkat usability yang baik dan dapat diterima oleh pengguna. Implementasi website pemesanan daring ini diharapkan mampu meningkatkan efisiensi operasional, mempermudah pelanggan dalam melakukan transaksi, memperluas jangkauan pemasaran, serta mendukung keberlanjutan dan pertumbuhan UMKM Gudeg Jogja Diajeng melalui pemanfaatan teknologi digital.
Pembuatan aplikasi seluler berbasis kecerdasan buatan untuk pemantauan tumbuh kembang anak Teny Handhayani; Puspa Indah; Meirista Wulandari; Rakha Naufal Sujana; Benny Dwiyanto; Desi Arisandi; Wasino Wasino; Jeanny Pragantha
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 10, No 5 (2026): October (In Progress)
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v10i5.42024

Abstract

Abstrak Masyarakat kawasan perkotaan (urban) dihadapkan pada tantangan mobilitas tinggi dan maraknya misinformasi kesehatan, yang berdampak pada kesenjangan literasi terkait tumbuh kembang balita. Selama ini, pemantauan gizi anak seringkali hanya mengandalkan intuisi orang tua atau kunjungan Posyandu yang kerap terlewatkan. Kegiatan Pengabdian kepada Masyarakat (PKM) ini bertujuan untuk memecahkan masalah tersebut dengan mengembangkan dan mengimplementasikan aplikasi pemantauan tumbuh kembang balita berbasis Android bagi mitra. Metode pelaksanaan kegiatan mencakup observasi, wawancara, perancangan aplikasi cerdas, pengujian sistem, dan sosialisasi kepada 15 responden ibu balita. Sistem ini mengintegrasikan kecerdasan buatan menggunakan model machine learning Light Gradient Boosting Machine (LightGBM) dan Extreme Gradient Boosting (XGBoost) untuk mengklasifikasikan status gizi (malnutrisi, kurang gizi, normal, kelebihan gizi) serta mendeteksi indikasi stunting. Hasil evaluasi algoritma menunjukkan performa yang sangat baik, di mana LightGBM mencapai tingkat akurasi 93%–99% dan XGBoost mencapai 92%–98%. Implementasi aplikasi yang dirancang dengan penyimpanan data lokal (offline) ini berhasil menjamin keamanan privasi pengguna sekaligus mengubah kebiasaan warga dari pemantauan berbasis intuisi menjadi pencatatan berbasis data medis yang tervalidasi. Kehadiran aplikasi ini terbukti meningkatkan kemandirian dan literasi ibu-ibu urban dalam mendeteksi risiko malnutrisi sejak dini, sekaligus mendukung pencapaian Sustainable Development Goals (SDGs) poin ke-3 (kehidupan sehat dan sejahtera) dan ke-4 (pendidikan berkualitas). Kata kunci: aplikasi mobile; machine learning; pemantauan gizi balita; stunting; kesehatan masyarakat urban Abstract Urban communities face the challenges of high mobility and widespread health misinformation, which impacts the literacy gap related to toddler growth and development. To date, child nutrition monitoring often relies solely on parental intuition or often-missed Posyandu visits. This Community Service (PKM) activity aims to solve this problem by developing and implementing an Android-based toddler growth and development monitoring application for partners. The implementation method includes observation, interviews, intelligent application design, system testing, and outreach to 15 respondents who are mothers of toddlers. This system integrates artificial intelligence using the Light Gradient Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost) machine learning models to classify nutritional status (malnutrition, undernutrition, normal, overnutrition) and detect indications of stunting. The algorithm evaluation results showed excellent performance, with LightGBM achieving an accuracy level of 93%–99% and XGBoost reaching 92%–98%. The implementation of this application, designed with local (offline) data storage, has successfully guaranteed user privacy and shifted residents' habits from intuitive-based monitoring to validated medical data-based recording. The application has been proven to increase the independence and literacy of urban mothers in detecting the risk of malnutrition early, while also supporting the achievement of Sustainable Development Goals (SDGs) points 3 (healthy and prosperous lives) and 4 (quality education). Keywords: mobile applications; machine learning; toddler nutrition monitoring; stunting; urban public health
Co-Authors Adela Calista Adela Tania Agus Budi Dharmawan Akmal Farouqi Andre Andre Andre Andre, Andre Andrew Castello Purba Andrian, Gion Andry Winata Angelica Christina Arya Bintang Saputra Arya Dwi Saputra Arya Dwi Saputra Benny Dwiyanto Brando Dharma Saputra Cecillia Chung Chairisni Lubis Cherissa Aeryn Djaya Christina, Angelica Daffa Hilmi Aji Dara Kharisma Limparan Darius Andana Haris David Jansen Dayanti, Afina Putri Desi Arisandi Desi Arisandi Desi Arisandi Desi Arisandi Desi Arisandi Duncan Ariel Dwi Saputra, Arya Dyah Erny Herwindiati Ericko, Teddy Faradila Herfiyana Farhan Adithya Putra Farhan Afrial Fawaz Fenny Jong Gabriella Adeline Halim Georgia Sugisandhea Gion Andrian Gion Andrian Hendryli, Janson Herfiyana, Faradila Huang, Jervis Irvan Lewenuisa Irvan Lewenusa Irvan Lewenusa Irvan Lewenusa Irvan Lewenusa, Irvan Janson Hendryli Janson Hendryli Jason Jason Sunaryo Jaya, Jefri Jayadi, Bryan Valentino Jeanny Pragantha Jeanny Pragantha Jeanny Pragantha Jeanny Pragantha Jefri Jaya Jefri Jaya Jeremia Pinnywan Immanuel Jochsen, Erico Jordi Pradipta Kusuma Jourdan Stanley Julius Juan Karnadi, Benny Kelvin Wijaya Kelvin Wijaya Kusuma, Jordi Pradipta Lely Hiryanto Lim, Maggie Lubis, M.Kom., Chairisni Mahendra, Izam Susilo Mahendra, Izam Susilo Manatap Dolok Lauro Manatap Dolok Lauro, Manatap Dolok Manatap Sitorus Manatap Sitorus Dolok Lauro Marcel Yusuf Rumlawang Arpipi Marchel Yusuf Rumlawang Arpipi Mathew Judianto Matthew Oni Matthew Russel Paul Meirista Wulandari Mikael Reichi Sopany Mohammad Faraditya Eka Putra Monica Ong Muhammad Isnaini Syaifudin Naufal Firdausyan Nicholas Eugene Supardi Nicko Kurniawan Novario Jaya Perdana Oni, Matthew Owen Djoenaedi Owen Maytrio Phratama Paulus Samotana Zalukhu Peter James Tedja Phratama, Owen Maytrio Purba, Andrew Castello Puspa Indah Raffy Sonata Rakha Naufal Sujana Reinerius S. D. Kristiantoro Sandy Permadi Sormin Sitorus Dolok Lauro , Manatap Sopany, Mikael Reichi Sumarlie , Devid Sumarlie, Aurellia Clearesta Tanudy, Clara Tasya Syamsudin Tommy Wijaya Putra Tony Tony Veri Vincent Alexander Wasino Wasino Wasino Wasino . Wasino Wasino William William Winata, Andry Yudistira Permana Zyad Rusdi