Claim Missing Document
Check
Articles

Found 13 Documents
Search

Sistem Deteksi Perokok di Area Publik Menggunakan YOLOv8 Harun, Ahmad; Fariza, Arna; Setiawardhana, Setiawardhana
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 11, No 2 (2025): Volume 11 No 2
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v11i2.94182

Abstract

Merokok merupakan salah satu penyebab utama kematian yang dapat dicegah, baik bagi perokok aktif maupun pasif. Paparan asap rokok, bahkan dalam jumlah kecil, tetap berbahaya dan menimbulkan dampak serius, terutama bagi anak-anak. Meskipun berbagai regulasi telah diterapkan untuk melarang aktivitas merokok di ruang publik, seperti Perda Kota Medan No. 3 Tahun 2014, implementasinya masih menghadapi tantangan seperti keterbatasan anggaran, lemahnya pengawasan, dan rendahnya kesadaran masyarakat. Penelitian ini mengusulkan sistem deteksi perokok berbasis deep learning menggunakan model YOLOv8 untuk mendeteksi keberadaan aktivitas merokok dalam video pengawasan. Lima varian model YOLOv8 diuji, yaitu YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, dan YOLOv8x. Hasil pelatihan menunjukkan bahwa YOLOv8m dan YOLOv8l memperoleh nilai mAP tertinggi sebesar 0,987. Namun, pada pengujian implementasi menggunakan video CCTV Full HD dengan ketinggian kamera 2 meter dan jarak maximal 3 meter, YOLOv8s menunjukkan performa terbaik dengan akurasi 100% pada pencahayaan baik dan 95% pada pencahayaan kurang, serta kecepatan inferensi yang lebih tinggi. Dengan demikian, YOLOv8s merupakan varian model yang paling optimal untuk implementasi sistem deteksi perokok di ruang publik.
Nutrition Temperature and TDS Control System with Fuzzy Logic on Pak Choy Hydroponics (Brassica rapa subsp. chinensis) Sanaba, Utari; Rokhana, Rika; Setiawardhana, Setiawardhana; Wijayanto, Ardik
Jurnal Rekayasa Elektrika Vol 20, No 3 (2024)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v20i3.34322

Abstract

Hydroponics is a method of cultivation that does not use soil as a medium, allowing it to be applied in limited spaces such as urban households. One of the vegetable plants that can be grown using hydroponics is pak choy (Brassica rapa subsp. chinensis). To produce healthy pak choy plants that can efficiently absorb nutrients in a hydroponic system, several factors need to be considered, such as the level of Total Dissolved Solids (TDS) in the nutrient solution, nutrient solution temperature, and air humidity in the hydroponic environment. The ideal nutrient solution temperature for hydroponic plants falls within the range of 25-27C. In this system, a monitoring and control system will be designed to optimize the growth of pak choy plants in a Deep Flow Technique (DFT) hydroponic system. In this system, the nutrient solution temperature will be controlled with a set point of 25C using an on/off control for a peltier device. To maintain the TDS level at a set point of 1200 ppm in the nutrient solution, fuzzy logic control will be employed, generating timer-based control signals for the nutrient pump A, nutrient pump B, and water pump. The monitoring system will be displayed on an Internet of Things (IoT) dashboard platform, such as ThingSpeak.
EVALUASI KINERJA MODEL ARIMA DALAM PERAMALAN KONSUMSI ENERGI GEDUNG BERTINGKAT Yusvida, Rizka; Windarko, Novie Ayub; Setiawardhana, Setiawardhana
BRILIANT: Jurnal Riset dan Konseptual Vol 10 No 3 (2025): Volume 10 Nomor 3, Agustus 2025
Publisher : Universitas Nahdlatul Ulama Blitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28926/briliant.v10i3.1967

Abstract

In an effort to manage and optimize the use of energy in these buildings, the ARIMA model (Autoregressive Integrated Moving Average) emerged as a very important analytical tool. The primary objective of this research is to investigate and explore how ARIMA parameter settings can be modified to improve the accuracy of energy consumption predictions on stairwell buildings. Based on an in-depth analysis of existing literature as well as empirical data, it was found that the ARIMA model, by leveraging time row kastasioneran and the use of univariate data, showed great potential in producing highly accurate short-term predictions. In this study, it was found that by performing the correct configuration of ARIMA parameters, the model was able to a level of accuracy with MAPE of 5,317% and RMSE of 8,7. These results show an excellent level of conformity, indicating that the ARIMA model can be effectively used to improve the accuracy of prediction of energy consumption in stairwell buildings. The findings of this study confirm that with proper adjustment of parameters, ARIMA can be a very useful tool in more efficient energy management in the building sector, which can ultimately contribute to reducing unnecessary energy consumption as well as improving overall energy efficiency.