Jurnal Komputer Antartika

Prediksi Hasil Produksi Ikan Lele Menggunakan Algoritma Artificial Neural Network

Akbar Febriansyah Putra — 2026-09-30

Produksi ikan lele merupakan salah satu kegiatan budidaya yang memiliki nilai ekonomi dan memerlukan perencanaan hasil panen yang tepat. Pengelolaan data produksi yang masih dilakukan secara manual dapat menyulitkan proses memperkirakan hasil produksi secara akurat. Penelitian ini bertujuan membangun model prediksi hasil produksi ikan lele menggunakan algoritma Artificial Neural Network (ANN). Penelitian menggunakan pendekatan kuantitatif dengan metode Machine Learning. Dataset yang digunakan berjumlah 10.000 data, terdiri atas 8.000 data training dan 2.000 data testing. Variabel input yang digunakan meliputi jumlah bibit, berat awal, total pakan, suhu air, pH air, dan survival rate, sedangkan hasil produksi ikan lele digunakan sebagai variabel output. Tahapan penelitian meliputi pengumpulan data, data preparation, normalisasi, pembagian dataset, pemodelan ANN, dan evaluasi. Pemodelan dilakukan menggunakan perangkat lunak RapidMiner dengan arsitektur Multi-Layer Perceptron dan metode backpropagation. Hasil pengujian menghasilkan nilai Root Mean Squared Error (RMSE) sebesar 235,001. Hasil penelitian menunjukkan bahwa ANN mampu mempelajari hubungan antara variabel input dan hasil produksi ikan lele sehingga dapat digunakan sebagai pendekatan untuk membantu proses estimasi dan perencanaan produksi berbasis data.

Catfish production is an important aquaculture activity with economic value and requires accurate production planning. Manual production data management can make it difficult to estimate production outcomes accurately. This study aims to develop a catfish production prediction model using an Artificial Neural Network (ANN) algorithm. This study employed a quantitative approach using Machine Learning. The dataset consisted of 10,000 records, including 8,000 training data and 2,000 testing data. The input variables included the number of seeds, initial weight, total feed, water temperature, water pH, and survival rate, while catfish production was used as the output variable. The research stages consisted of data collection, data preparation, normalization, dataset division, ANN modeling, and evaluation. The modeling process was performed using RapidMiner with a Multi-Layer Perceptron architecture and the backpropagation method. The evaluation resulted in a Root Mean Squared Error (RMSE) value of 235.001. The results indicate that ANN can learn the relationship between the input variables and catfish production and can therefore be used as an approach to support data-based production estimation and planning.

Penambangan Data Berbasis Pembelajaran Mesin untuk Pengelompokan Wilayah Beresiko Stunting di Kabupaten Bandung

Widhy Juliawan — 2026-10-02

Stunting merupakan masalah pertumbuhan yang bersifat multidimensional sehingga penentuan prioritas wilayah memerlukan pembacaan serentak atas faktor kesehatan, lingkungan, layanan, dan demografi. Penelitian ini bertujuan mengelompokkan 31 kecamatan di Kabupaten Bandung berdasarkan kemiripan pola kerentanan terkait stunting. Data sekunder tahun 2024 dihimpun dari Profil Kesehatan Kabupaten Bandung dan Satu Data Kabupaten Bandung, sedangkan geometri kecamatan menggunakan batas administrasi Badan Informasi Geospasial edisi 2022. Tujuh fitur yang digunakan adalah prevalensi berat badan lahir rendah, sanitasi tidak aman, air minum tidak layak, rumah tangga non-PHBS, rasio Posyandu, rasio puskesmas, dan logaritma kepadatan penduduk. Seluruh fitur distandardisasi dan diarahkan agar nilai Z lebih tinggi menunjukkan kerentanan relatif lebih besar. Algoritma K-Means diuji untuk k=2–6. Pemilihan jumlah klaster mempertimbangkan elbow, silhouette, Davies–Bouldin, Calinski–Harabasz, keseimbangan ukuran, stabilitas 100 seed, dan leave-one-out. Solusi k=2 dipilih dengan silhouette 0,222, stabilitas seed ARI 1,000, dan ukuran klaster 15 serta 16 kecamatan. Klaster A menunjukkan pola kepadatan–air minum–keterbatasan layanan, sedangkan Klaster B menunjukkan pola BBLR–perilaku kesehatan. Prevalensi stunting tertimbang masing-masing klaster adalah 7,76% dan 10,19%. Namun, perbedaan distribusi prevalensi kecamatan tidak signifikan (Mann–Whitney U=139,0; p=0,465; Cliff’s delta=0,158). Hasil ini mendukung penggunaan klaster sebagai tipologi eksploratif untuk merancang intervensi yang berbeda antar pola, bukan sebagai klasifikasi risiko tinggi dan rendah yang bersifat definitif.

Stunting is a multidimensional growth problem; therefore, determining priority areas requires a simultaneous assessment of health, environmental, service, and demographic factors. This study aims to classify 31 sub-districts in Bandung Regency based on similarities in stunting-related vulnerability patterns. Secondary data for 2024 were collected from the Bandung Regency Health Profile and Satu Data Kabupaten Bandung, while sub-district geometries were obtained from the 2022 administrative boundaries provided by the Geospatial Information Agency. Seven features were employed, consisting of low birth weight prevalence, unsafe sanitation, inadequate drinking water access, non-PHBS households, Posyandu ratio, Puskesmas ratio, and the logarithm of population density. All features were standardized and transformed so that higher Z-scores represented greater relative vulnerability. The K-Means algorithm was evaluated for k=2–6 clusters. The optimal number of clusters was determined by considering the elbow method, silhouette score, Davies–Bouldin index, Calinski–Harabasz index, cluster size balance, 100-seed stability analysis, and leave-one-out validation. The k=2 solution was selected, achieving a silhouette score of 0.222, ARI seed stability of 1.000, and balanced cluster sizes of 15 and 16 sub-districts. Cluster A represents a density–drinking water–service limitation pattern, whereas Cluster B reflects a low birth weight–health behavior pattern. The weighted stunting prevalence of each cluster was 7.76% and 10.19%, respectively. However, the distribution of sub-district-level stunting prevalence between clusters was not statistically significant (Mann–Whitney U=139.0; p=0.465; Cliff’s delta=0.158). These findings support the use of Clustering as an exploratory typology for designing differentiated interventions based on vulnerability patterns rather than as a definitive classification of high- and low-risk areas.

Perancangan Dan Simulasi Sistem Lampu Otomatis Berbasis Esp32 Menggunakan Sensor LDR dan PIR untuk Analisis Potensi Penghematan Energi Pada Simulator Wokwi

Yoga Aimar Rosyid — 2026-10-07

Penggunaan lampu yang tidak disesuaikan dengan kondisi pencahayaan lingkungan dan aktivitas pengguna dapat menyebabkan konsumsi energi yang kurang efisien. Penelitian ini bertujuan merancang dan menyimulasikan sistem lampu otomatis berbasis ESP32 menggunakan sensor Light Dependent Resistor (LDR) dan Passive Infrared (PIR), mengevaluasi kinerja sistem dalam merespons kondisi pencahayaan dan gerakan, serta menganalisis potensi penghematan energi menggunakan simulator Wokwi. Penelitian menggunakan metode eksperimen berbasis simulasi dengan pendekatan deskriptif kuantitatif dan model pengembangan Prototype. Sensor LDR digunakan untuk mengklasifikasikan kondisi terang atau gelap, sedangkan PIR digunakan untuk mendeteksi gerakan. Pengujian black-box dilakukan pada 16 kasus uji yang masing-masing diulang tiga kali sehingga diperoleh 48 pelaksanaan pengujian. Seluruh pengujian menghasilkan keluaran sesuai harapan dengan tingkat keberhasilan 100%. Pada skenario dinamis EN-04, rata-rata durasi nyala lampu sebesar 20,155 detik dari pengamatan 60 detik. Dengan asumsi daya lampu 10 watt, sistem otomatis menghasilkan estimasi konsumsi energi 0,05599 Wh dibandingkan 0,16667 Wh pada sistem konvensional, sehingga diperoleh potensi penghematan sebesar 66,41%. Hasil tersebut merupakan estimasi berbasis simulasi dan bukan pengukuran konsumsi energi aktual pada perangkat fisik.

The use of lighting that is not adjusted to ambient lighting conditions and user activity may result in inefficient energy consumption. This study aims to design and simulate an ESP32-based automatic lighting system using a Light Dependent Resistor (LDR) sensor and a Passive Infrared (PIR) sensor, evaluate the system's performance in responding to lighting conditions and motion detection, and analyze its potential energy savings using the Wokwi simulator. The study employed a simulation-based experimental method with a descriptive quantitative approach and the Prototype development model. The LDR sensor was used to classify lighting conditions as bright or dark, while the PIR sensor was used to detect motion as a representation of user activity. The system applied an LDR threshold value of 2000 and a 10-second delay mechanism using the millis() function. Functional testing was conducted using the black-box testing method on 16 test cases, each repeated three times, resulting in a total of 48 test executions. All 48 test executions produced outputs consistent with the expected responses, resulting in a system success rate of 100%. Verification of the duration-recording mechanism showed a difference of 0 ms between the program results and manual calculations. In the dynamic EN-04 scenario, the lamp operated for an average of 20.155 seconds during a 60-second observation period. Assuming a lamp power of 10 watts, the conventional system required an estimated energy consumption of 0.16667 Wh, whereas the automatic system required 0.05599 Wh, corresponding to an estimated energy reduction of 0.11068 Wh or a potential saving of 66.41%. These findings indicate that the integration of ESP32, LDR, PIR, and a delay mechanism can control lighting according to ambient conditions and detected motion while potentially reducing operating duration and energy consumption. The energy results are simulation-based estimates and do not represent actual energy consumption in a physical implementation.

Rancang Bangun Sistem POS Berbasis Web dengan Protokol HTTPS dan Adaptive Interface Pada UMKM Jajanan Kampung Uni Yen

Rian Agust — 2026-10-08

Penelitian ini bertujuan untuk merancang dan membangun sistem Point of Sale (POS) berbasis web pada UMKM Jajanan Kampung Uni Yen guna mendukung efisiensi transaksi, keamanan data, dan fleksibilitas penggunaan. Permasalahan yang dihadapi meliputi proses transaksi yang masih dilakukan secara manual, sering terjadi kesalahan pencatatan, serta belum adanya sistem keamanan data yang memadai. Metode pengembangan sistem yang digunakan adalah Waterfall yang meliputi tahap analisis, perancangan, implementasi, dan pengujian. Sistem dikembangkan dengan menerapkan protokol Hypertext Transfer Protocol Secure (HTTPS) untuk mengamankan komunikasi data serta algoritma Adaptive Interface berbasis rule-based untuk menyesuaikan tampilan sistem pada berbagai perangkat. Hasil penelitian menunjukkan bahwa sistem POS berbasis web yang dibangun mampu mendukung proses transaksi melalui otomatisasi perhitungan, pencatatan transaksi, pengelolaan stok, penyusunan laporan penjualan secara terintergrasi, meningkatkan akurasi data, serta dapat digunakan secara fleksibel pada perangkat desktop, tablet, dan smartphone. Selain itu, penerapan HTTPS mendukung keamanan data transaksi dan pengguna. Dengan demikian, sistem yang dikembangkan dapat menjadi solusi yang efektif dalam mendukung efisiensi operasional dan kualitas pelayanan pada UMKM.

This study aims to design and develop a web-based Point of Sale (POS) system for Jajanan Kampung Uni Yen MSME to support transaction efficiency, data security, and flexibility of use. The problems faced include manual transaction processes, frequent recording errors, and the lack of an adequate data security system. The system development method used is the Waterfall method, which consists of the analysis, design, implementation, and testing stages. The system was developed by implementing the Hypertext Transfer Protocol Secure (HTTPS) protocol to secure data communication and a rule-based Adaptive Interface algorithm to adjust the system interface across various devices. The results show that the developed web-based POS system is capable of supporting transaction processes through automated calculations, transaction recording, stock management, and integrated sales report generation, improving data accuracy, and providing flexible use on desktop, tablet, and smartphone devices. In addition, the implementation of HTTPS supports the security of transaction and user data. Therefore, the developed system can serve as an effective solution to support operational efficiency and service quality in MSMEs.