Claim Missing Document
Check
Articles

Found 3 Documents
Search

Prediksi Kecepatan Angin untuk Mengetahui Potensi Sumber Energi Alternatif menggunakan Model Regresi Lasso: Studi Kasus Kota Makassar pada Tahun 2024 Siti Nurjanah; Yoan Purbolingga; Dila Marta Putri; Asde Rahmawati; Fahrizal Fahrizal; Bastul Wajhi Akramunnas
Jurnal Penelitian Rumpun Ilmu Teknik Vol. 3 No. 1 (2024): Februari : Jurnal Penelitian Rumpun Ilmu Teknik
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juprit.v3i1.3501

Abstract

This research explores the potential of wind energy as an alternative energy source in Makassar City. The researcher used daily climate data from BMKG Martim Paotere Meteorological Station Makassar City for 2023 to January 2024. The research method uses the Lasso regression model to predict wind speed. The results of data processing, through tests with an MSE value of 0.334 and an R2 value of 0.97, show the high validity of the model. Wind speed predictions for 2024 were then generated and converted into estimates of the electrical power that could be generated. Based on this prediction, the maximum wind speed reached 10.76 m/s, with the maximum electrical power reaching 1597 Watts. The results of this study indicate that Makassar City has considerable potential to be developed as a Wind Power Plant location as an alternative source of electrical energy. This potential can contribute to reducing dependence on conventional energy in Makassar City.
Pengembangan Semangka Dayun sebagai Produk Unggulan Melalui Indikasi Geografis untuk Perlindungan Hak Kekayaan Intelektual Sukamarriko Andrikasmi; Ledy Diana; Mubarak Mubarak; Reny Fitri Yani; Hussein Al Muhtadeebillah; Dian Pratiwi; Siti Nurjanah; Fahrur Rozi
Unri Conference Series: Community Engagement Vol 7 (2025): Seminar Nasional Pemberdayaan Masyarakat
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31258/unricsce.7.444-448

Abstract

This community service activity aims to encourage the development of Dayun Watermelon as a superior regional product while providing legal protection through the Geographical Indication (GI) scheme as a form of Intellectual Property Rights (IPR). Dayun Watermelon has unique taste, quality, and cultivation techniques that are passed down from generation to generation, so it has the potential to become a regional asset with high economic and cultural value. The implementation was conducted through socialization regarding the importance of IPR protection, technical training in preparing Geographical Indication documents, mentoring farmer groups in building institutions, and facilitating cooperation with local governments and related stakeholders. The results indicate an increase in farmer and community understanding regarding the benefits of Geographical Indication protection, the formation of a collective understanding to maintain product quality, and the initial steps in preparing IPR application documents. This activity is expected to strengthen the competitiveness of Dayun Watermelon, improve farmer welfare, and protect local identity through a sustainable IPR protection system.
Sistem Deteksi Kantuk Pengemudi berbasis DLIB Facial Landmark dan Rasio Kedipan Mata menggunakan OPENCV secara Real-time M Ikhsan; Siti Nurjanah; Dila Marta Putri; Ika Mayla Sari; Hudaya Muna Putra; Ririn Violina; Radinal Dwiki Novendra; Yoan Purbolingga
Journal of System & Technology (SYSTEC) Vol. 2 No. 1 (2026): Journal of System & Technology (June Edition)
Publisher : Jurusan Teknik Elektro, Fakultas Teknik, Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kecelakaan lalu lintas akibat kondisi mengantuk saat berkendara merupakan permasalahan keselamatan yang serius dan belum terselesaikan secara tuntas. Penelitian ini mengimplementasikan sistem deteksi kantuk pengemudi secara real-time berbasis kecerdasan buatan dengan memanfaatkan OpenCV untuk akuisisi video dari webcam dan pustaka Dlib untuk ekstraksi 68 titik facial landmark. Kontribusi utama penelitian ini adalah pengembangan sistem tiga-kelas (active, drowsy, sleep) menggunakan mekanisme pencacah frame dengan ambang batas empat frame berturut-turut, yang beroperasi tanpa GPU khusus disertai alarm audio otomatis. Berbeda dengan penelitian terdahulu yang umumnya hanya membedakan dua kondisi, sistem ini menambahkan kelas 'active' sebagai konfirmasi eksplisit kondisi pengemudi yang waspada. Pengujian terhadap 30 percobaan menghasilkan akurasi 90%, recall rata-rata 0,90, dan rata-rata waktu respons alarm 0,65 detik. Hasil ini menunjukkan bahwa pendekatan berbasis rasio keterbukaan mata dan pencacah frame efektif sebagai prototipe sistem deteksi kantuk ringan syang dapat direproduksi pada perangkat komputasi konvensional.