Abstract:The development of new pipe connections is one of the important aspects in improving clean water services provided by the Regional Water Company (PDAM). However, the determination of priority areas for pipe network development…
opment at PDAM Tirta Silaupiasa Asahan Regency is still carried out subjectively, so it is less objective and data-based. Therefore, this research aims to apply the K-Medoids clustering algorithm to group development areas of new pipe connections based on their characteristics. The data used consisted of 22 sub-district areas with three input variables, namely the number of prospective new customers, distance to the existing pipe network, and population density. The data was normalized using the Min-Max method, then processed using the K-Medoids algorithm with the number of clusters k = 3 and Euclidean Distance as the distance measure. The clustering results were evaluated using the Silhouette Score method. Based on the test results, the clustering process converged after three iterations with the total cost decreasing from 6.3947 to 5.3436. The clustering produced three groups: Cluster 1 (High Priority) with 1 area, Cluster 2 (Medium Priority) with 16 areas, and Cluster 3 (Low Priority) with 5 areas. The average Silhouette Score obtained was 0.3981, which is included in the reasonable structure category. The system was implemented as a web-based application using PHP and MySQL, so it can help PDAM in determining priority areas for pipe network development objectively and based on data.
Abstract:This study aims to analyze and identify patterns in the educational backgrounds of successful figures using the K-Means clustering method. Educational background is one of the factors that can provide an overview of an individual's…
ndividual's academic journey toward achieving success. However, the diversity of educational fields, levels of education, and academic characteristics of successful figures makes these patterns difficult to analyze manually. Therefore, a data clustering method is needed to help identify similarities in the educational characteristics of successful figures. This study uses a quantitative approach with data collected from various sources regarding the educational backgrounds of successful figures, including education level, field of study, educational institution, and other educational characteristics. The collected data are then processed and transformed to make them suitable for the clustering process. The K-Means method is used to group successful figures based on the similarity of their educational background characteristics. The research process includes data collection, preprocessing, determination of the number of clusters, centroid initialization, calculation of the distance between each data point and the centroid, cluster formation, and evaluation of the clustering results. The clustering results are expected to reveal several groups of educational patterns with similar characteristics and provide information regarding trends in the educational backgrounds of successful figures. This study is expected to serve as a reference for understanding the diversity of educational patterns among successful figures and provide an overview of the relationship between educational characteristics and an individual's journey toward success.
Abstract:Divorce is a social phenomenon whose rate continues to rise in various regions of Indonesia and has become a shared concern for both the government and society, since it may give rise to social, psychological, and economic…
ic consequences for the individuals and families involved. Divorce is generally caused by several interrelated factors, namely economic problems, continuous domestic disputes, infidelity, and domestic violence (KDRT). This study aims to apply the K-Nearest Neighbor (KNN) algorithm to classify the level of divorce (Low, Medium, and High) based on these four causal factors. The data used are secondary data obtained from the Central Bureau of Statistics (BPS) covering ten provinces on Sumatra Island for the 2023-2025 period. Prior to classification, the data were normalized using the Min-Max Normalization method so that every attribute shared a comparable value range. The dataset was divided into 20 training data (2023-2024) and 10 testing data (2025), with the value of K determined using the formula K = √n, resulting in K = 5. The classification process was carried out by calculating the Euclidean Distance between the testing data and the entire training data, then determining the predicted class through majority voting among the five nearest neighbors. The classification model was implemented in a web-based application built with PHP and MySQL that supports dataset import, data normalization, KNN computation, and classification result display. The test results on the ten testing data for 2025 show that the system achieved an overall accuracy of 70%, with the best performance obtained for the Low class (recall of 100%), while the Medium and High classes still experienced misclassification due to the limited amount of training data in those classes. These results indicate that the KNN algorithm is capable of recognizing divorce patterns based on their causal factors and can be used as a decision-support tool related to the analysis of divorce rates on Sumatra Island.
Abstract:Open burning of waste is still one of the problems in waste management because it can produce various air pollutants and has the potential to reduce environmental quality. This study aims to evaluate the ambient air quality…
ity around a simple waste incinerator using a Smokeless Barrel Incinerator (SBI) and analyze the concentrations of sulfur dioxide (SO₂), carbon monoxide (CO), and ozone (O₃) against ambient air quality standards. The study uses a quantitative approach with an experimental method. Sampling was carried out in the parking area of Nahdlatul Ulama University of West Sumatra at a distance of 20 meters from the source of combustion with a downwind position and the height of the tool was about 1.5–2 meters from the ground level. Sampling was carried out for 1 hour. SO₂ and O₃ parameters were analyzed using an impinger system and spectrophotometry methods, while CO was measured using gas analysis instruments according to laboratory methods. The test results showed a concentration of SO₂ of 4.02 μg/m³, CO of 338 μg/m³, and O₃ of 0.067 μg/m³. Based on the reference values used in the study, the three parameters were below the ambient air quality standard. The results showed that under the test conditions, the use of SBI did not cause the concentration of SO₂, CO, and O₃ at the sampling point to exceed the quality standard values. The primary and secondary ventilation systems in SBI have the potential to help improve oxygen supply and combustion processes. However, the results of the study cannot be used to state that SBI is pollutant-free because the parameters of particulate matter, NOₓ, VOCs, PAHs, dioxins-furans, and heavy metals have not been analyzed and direct comparative testing with open combustion has not been carried out.
Abstract:Manual attendance recording at village government offices still leaves several problems, including susceptibility to buddy punching, failure to record the employee's position during check-in, and slow recapitulation. Location-based…
ation-based attendance systems examined in previous studies generally rely on only one or two forms of verification, so the validity of their data remains limited. This study aims to design and build a web-based employee attendance system at the Teluk Dalam Village Office that applies multi-factor verification, comprising the scanning of a secret-token QR code, area restriction (geofencing) through distance calculation using the Haversine formula, identity verification using a PIN, selfie photo capture, and automatic early detection of fraud attempts based on device fingerprint and check-in time proximity. The system was developed using the Waterfall model with framework-less PHP and a MySQL database so that it runs lightly on shared hosting. Testing of the Haversine formula shows that the system is able to consistently distinguish check-ins located inside and outside the office radius, while black-box testing shows that all functions run as designed. By combining five verification layers in a single integrated system within a village government environment, this study not only shifts attendance recording to a digital form but also strengthens data validity and reduces the possibility of attendance manipulation.
Abstract:Partisipasi umat dalam program gereja dapat dilihat melalui kehadiran pada kegiatan dan kontribusi dalam bentuk donasi. Penelitian ini bertujuan mengelompokkan tingkat partisipasi umat pada 18 lingkungan Gereja Katolik Santo…
anto Laurentius Simpang Selayang menggunakan algoritma K-Means. Penelitian menggunakan pendekatan kuantitatif dengan data sekunder yang diperoleh dari administrasi gereja. Variabel yang digunakan adalah jumlah kehadiran (X1) dan jumlah donasi (X2). Data dinormalisasi dengan metode Min-Max, kemudian dihitung jaraknya menggunakan Euclidean Distance, ditentukan anggota cluster, dihitung centroid baru, dan dilakukan iterasi sampai pembagian cluster stabil. Centroid awal menggunakan St. Marta, St. Monika, dan St. Theresia. Iterasi pertama menghasilkan tiga kelompok dengan anggota masing-masing 2, 5, dan 11 lingkungan. Setelah centroid baru dihitung, hasil pada Iterasi 2 tidak mengalami perubahan sehingga proses dinyatakan stabil. Hasil akhir menempatkan Cluster 1 sebagai kelompok partisipasi tinggi, Cluster 2 sebagai kelompok sedang, dan Cluster 3 sebagai kelompok rendah. Hasil pengelompokan dapat digunakan sebagai bahan evaluasi untuk melihat pola partisipasi dan membantu perencanaan program gereja.
Abstract:Abstract: Falls represent a leading cause of injury-related mortality among elderly individuals, demanding reliable automated detection deployable in resource-constrained environments. Existing vision-based approaches predominantly…
edominantly employ machine learning classifiers requiring large labelled datasets, substantial training pipelines, and GPU-class hardware, impeding rapid clinical deployment. This paper presents an explainable, fully rule-based real-time fall detection system implemented in Python using MediaPipe Pose, designed to operate on commodity edge devices without any training dataset. The system comprises three tightly integrated layers: (1) a mathematical formulation layer computing vector-based torso angle, distance-ratio body normalization, and frame-to-frame CoM velocity; (2) a temporal modeling layer combining a deterministic four-state Finite State Machine with a sliding-window motion energy analysis; and (3) a robustness evaluation across three camera viewing angles, two lighting conditions, and three fall types. Experimental validation yields a sensitivity of 91.8%, specificity of 95.8%, and F1-score of 93.1%, with a mean end-to-end detection latency of 140.1 ms on Raspberry Pi 4—satisfying a 200 ms real-time constraint while consuming only 72.5% mean CPU and 284 MB RAM. The rule-based architecture provides full decision auditability without black-box models, aligning with emerging XAI requirements for medical device regulation.
Keywords: Periodic Table of Elements; Chemistry Teaching Materials; Spiritual Values; Discovery Learning.
Abstrak: Kondisi Jatuh merupakan penyebab utama kematian akibat cedera di kalangan lansia, sehingga membutuhkan deteksi otomatis yang andal dan dapat diterapkan di lingkungan dengan keterbatasan sumber daya. Pendekatan berbasis visi yang ada sebagian besar menggunakan pengklasifikasi pembelajaran mesin yang membutuhkan kumpulan data berlabel besar, alur pelatihan yang substansial, dan perangkat keras kelas GPU, yang menghambat penerapan klinis yang cepat. Makalah ini menyajikan sistem deteksi jatuh waktu nyata yang dapat dijelaskan dan sepenuhnya berbasis aturan yang diimplementasikan dalam Python menggunakan MediaPipe Pose, yang dirancang untuk beroperasi pada perangkat edge komoditas tanpa kumpulan data pelatihan apa pun. Sistem ini terdiri dari tiga lapisan yang terintegrasi erat: (1) lapisan formulasi matematika yang menghitung sudut tubuh berbasis vektor, normalisasi tubuh rasio jarak, dan kecepatan CoM antar frame; (2) lapisan pemodelan temporal yang menggabungkan Mesin Keadaan Terbatas empat keadaan deterministik dengan analisis energi gerak jendela geser; dan (3) evaluasi ketahanan di tiga sudut pandang kamera, dua kondisi pencahayaan, dan tiga jenis jatuh. Validasi eksperimental menghasilkan sensitivitas 91,8%, spesifisitas 95,8%, dan skor F1 93,1%, dengan latensi deteksi ujung-ke-ujung rata-rata 140,1 ms pada Raspberry Pi 4—memenuhi batasan waktu nyata 200 ms sambil hanya mengonsumsi 72,5% CPU rata-rata dan 284 MB RAM. Arsitektur berbasis aturan memberikan kemampuan audit keputusan penuh tanpa model kotak hitam, selaras dengan persyaratan XAI yang muncul untuk regulasi perangkat medis.
Kata Kunci: Deteksi jatuh, MediaPipe Pose, komputasi tepi, sistem berbasis aturan, kecerdasan buatan dengan keadaan terbatas, AI yang dapat dijelaskan, perawatan lansia, pemantauan real-time
Abstract:Abstract: The increasing number of Umrah pilgrims requires travel agencies to implement data-driven approaches to improve service quality and support Human Resource Management (HRM). This study aims to segment Umrah pilgrims…
rims using the K-Means clustering algorithm as a basis for HRM strategies. The research follows the Knowledge Discovery in Databases (KDD) process, including data preprocessing, clustering in RapidMiner, and cluster evaluation using the Elbow Method based on performance distance (average within centroid distance). Euclidean Distance was used to measure similarity among data objects. Seven clustering experiments were conducted with k = 2–8, producing performance distance values of 3418.971, 1416.677, 865.316, 479.795, 344.203, 258.804, and 214.562, respectively. The Elbow curve indicates that k = 3 is the optimal number of clusters because it represents the most significant decrease before the curve stabilizes. The resulting clusters provide objective information for supporting staff placement, service task allocation, pilgrim assistance planning, and employee competency development. Therefore, the integration of K-Means and the Elbow Method offers an effective data-driven approach for supporting HRM decision-making in Umrah travel agencies.
Keyword: Elbow Method; Human Resource Management; K-Means Clustering; performance distance; Umrah pilgrims.
Abstrak: Peningkatan jumlah jamaah umrah mendorong biro perjalanan memanfaatkan analisis data untuk meningkatkan kualitas pelayanan dan mendukung pengambilan keputusan pada Manajemen Sumber Daya Manusia (MSDM). Penelitian ini bertujuan melakukan segmentasi jamaah umrah menggunakan algoritma K-Means Clustering sebagai dasar penyusunan strategi MSDM. Metode penelitian mengikuti tahapan Knowledge Discovery in Databases (KDD), meliputi data preprocessing, proses klasterisasi pada RapidMiner, serta evaluasi menggunakan Metode Elbow berdasarkan performance distance (average within centroid distance). Pengukuran kemiripan data dilakukan menggunakan Euclidean Distance. Pengujian dilakukan sebanyak tujuh kali dengan variasi k = 2–8, menghasilkan nilai performance distance berturut-turut 3418,971; 1416,677; 865,316; 479,795; 344,203; 258,804; dan 214,562. Hasil evaluasi menunjukkan bahwa k = 3 merupakan jumlah klaster optimal karena membentuk titik siku (elbow point) dengan penurunan nilai paling signifikan sebelum kurva melandai. Hasil segmentasi dapat dimanfaatkan sebagai dasar penempatan pegawai, pembagian tugas pelayanan, penyusunan tim pendamping jamaah, dan pengembangan kompetensi pegawai secara lebih tepat sasaran.
Kata kunci: jamaah umrah; K-Means Clustering; Manajemen Sumber Daya Manusia; Metode Elbow; performance distance.
Abstract:Abstract: The rapid digital transformation in Indonesian primary education has shifted from an emergency response to a long-term structural necessity. However, primary schools in areas with limited infrastructure, such as…
s UPT SDN 04 Air Pura, still face significant challenges regarding the digital divide and the lack of integrated information systems. This research aims to design and implement a web-based Distance Learning Information System to bridge the gap between academic administration and online learning delivery. Applying the Waterfall development method, this system integrates features for managing student data, attendance, assignments, and digital grade reports within a single platform. Built using PHP, MySQL, and the CodeIgniter framework, the system provides an efficient, accurate, and accessible solution for teachers, students, and school administrators. Black box testing confirms that the system functions fully and effectively, offering a viable solution for sustainable distance learning and improving digital education equity in regions with limited telecommunications infrastructure.
Keywords: Distance Learning, Information System, Web-Based, Primary Education, Waterfall
Abstrak: Transformasi digital dalam pendidikan dasar di Indonesia telah menjadi kebutuhan struktural jangka panjang. Namun, sekolah dasar di wilayah dengan keterbatasan infrastruktur, seperti UPT SDN 04 Air Pura, masih menghadapi tantangan kesenjangan digital dan ketiadaan sistem informasi terintegrasi. Penelitian ini bertujuan untuk merancang dan membangun Sistem Informasi Pembelajaran Jarak Jauh berbasis web guna mengintegrasikan administrasi akademik dan penyampaian materi pembelajaran. Dengan menerapkan metode pengembangan Waterfall, sistem ini mengintegrasikan fitur manajemen data siswa, absensi, tugas, dan raport digital dalam satu platform. Aplikasi yang dibangun menggunakan bahasa pemrograman PHP, basis data MySQL, dan framework CodeIgniter ini terbukti mampu menyediakan solusi yang efisien, akurat, serta mudah diakses bagi guru dan siswa. Hasil pengujian black box menunjukkan bahwa sistem berfungsi secara optimal dan siap mendukung keberlanjutan pembelajaran jarak jauh, sekaligus berkontribusi terhadap pemerataan akses pendidikan digital di tingkat sekolah dasar dengan infrastruktur terbatas.
Kata kunci: Pembelajaran Jarak Jauh, Sistem Informasi, Berbasis Web, Pendidikan Dasar, Waterfall
Abstract:Abstract: Learning three-dimensional (3D) geometric solids remains one of the persistent challenges in mathematics education because students must imagine abstract spatial objects that textbooks can only present in two dimensions.…
imensions. This condition often lowers students' learning interest and hinders their spatial reasoning, particularly at the junior high school level. This study aims to design and develop an interactive learning medium in the form of an Augmented Reality (AR)-based pocket book for teaching geometric solids (cube, cuboid, triangular prism, and quadrilateral pyramid) using the Marker Based Tracking method on the Android platform. The research employed a Research and Development (R&D) approach following the ADDIE model, covering the stages of analysis, design, development, implementation, and evaluation. The application was built using Unity3D as the development engine and Vuforia SDK as the marker recognition library, then tested on mobile devices to measure accuracy, latency, frame rate, device compatibility, and marker-detection distance. The results show that the application can detect markers at a distance of 8-77 cm with a latency of 1000-2000 ms and a frame rate of 15-30 fps, and it runs properly on Android devices from version 7.0 onward. These findings indicate that the pocket book is feasible as an alternative interactive medium to strengthen students' spatial imagination of geometric solids.
Keywords: augmented reality; media pembelajaran; bangun ruang; marker based tracking; android.
Abstrak: Pembelajaran bangun ruang sisi datar masih menjadi salah satu materi matematika yang sulit dipahami siswa karena menuntut kemampuan membayangkan objek tiga dimensi yang di dalam buku teks hanya digambarkan secara dua dimensi. Kondisi ini kerap menurunkan minat belajar sekaligus menghambat kemampuan spasial siswa, terutama di jenjang sekolah menengah pertama. Penelitian ini bertujuan merancang dan mengembangkan media pembelajaran interaktif berupa buku saku berbasis Augmented Reality (AR) untuk materi bangun ruang sisi datar (kubus, balok, prisma segitiga, dan limas segi empat) dengan metode Marker Based Tracking berbasis Android. Penelitian menggunakan pendekatan Research and Development (R&D) dengan model ADDIE yang meliputi tahap analisis, desain, pengembangan, implementasi, dan evaluasi. Aplikasi dibangun menggunakan Unity3D sebagai mesin pengembang dan Vuforia SDK sebagai pustaka pengenal marker, kemudian diuji pada perangkat bergerak untuk mengukur akurasi, latensi, frame rate, kompatibilitas perangkat, dan jarak deteksi marker. Hasil pengujian menunjukkan bahwa aplikasi mampu mendeteksi marker pada jarak 8-77 cm dengan latensi 1000-2000 ms dan frame rate 15-30 fps, serta dapat berjalan baik pada perangkat Android versi 7.0 ke atas. Temuan ini mengindikasikan bahwa buku saku tersebut layak digunakan sebagai media interaktif alternatif untuk memperkuat imajinasi spasial siswa terhadap bangun ruang.
Kata kunci: augmented reality; media pembelajaran; bangun ruang; marker based tracking; android.