Claim Missing Document
Check
Articles

Found 35 Documents
Search

Implementation of YOLOv5 Algorithm for Classification and Detection of Car Types Using Deep Learning Syafirly, Muhammad Rifqi Rajwa; Firmansyah, Ravi Rangga Wahyu; Nurdiansyah, Ahmad; Megana, Agis Adienia Haqi; Wirawan, I Made
Techné : Jurnal Ilmiah Elektroteknika Vol. 24 No. 1 (2025)
Publisher : Fakultas Teknik Elektronika dan Komputer Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31358/techne.v24i1.571

Abstract

Perkembangan teknologi computer vision dan deep learning telah membuka peluang baru dalam klasifikasi kendaraan, namun menghadapi tantangan dalam kompleksitas desain dan variasi visual mobil. Penelitian ini berfokus pada implementasi algoritma YOLO (You Only Look Once) V5 untuk mengklasifikasikan jenis mobil, yang bertujuan untuk mengembangkan model yang akurat, kuat, dan efektif dalam membedakan kategori mobil. Dataset yang digunakan dalam penelitian ini, yang bersumber dari Kaggle, dataset terdiri dari 1.000 gambar di empat kategori mobil (convertible, double cabin, sport, dan van), dengan 80% data digunakan untuk pelatihan, 10% untuk validasi, dan 10% untuk pengujian. Metodologinya mencakup prapemrosesan data, pelatihan model YOLOv5, dan evaluasi performa menggunakan metrik seperti akurasi, presisi, perolehan, dan skor F1. Hasilnya menunjukkan bahwa model tersebut dapat mengklasifikasikan jenis mobil dengan accuracy 96%, precision 96,6%, recall 97%, dan F1-score 97%, sehingga menunjukkan performa yang baik untuk setiap kategori mobil. Kata kunci: Klasifikasi, YOLOv5, Computer vision, Deteksi, Mobil.
Development of Programmable Logic Controller (PLC) Trainer Learning Media for Industrial Automation Widinata, Fandi; Wirawan, I Made
Edunesia : Jurnal Ilmiah Pendidikan Vol. 6 No. 2 (2025)
Publisher : research, training and philanthropy institution Natural Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51276/edu.v6i2.1229

Abstract

This research aims to develop learning media through PLC trainers and job sheets to support practical learning in the subject of Programmed Control Systems at Vocational High School (SMK) Negeri 1 Singosari. The background of this research is the limited real practice media, where students previously only relied on simulations, causing a gap between understanding theory and practical skills. The development model used in this research follows the ADDIE framework, which consists of five stages: Analysis, Design, Development, Implementation, and Evaluation. Data was collected through interviews, observations, expert validation, and user trials involving 11th-grade students of Industrial Automation Engineering of SMK Negeri 1 Singosari. The results showed that the trainer and jobsheet developed were declared "very feasible" based on the validation of media experts (95.8%), material experts (93.8%), and student trials in small groups (95.6%) and large groups (96.6%). Revisions were made based on expert input, such as adding diodes for safety and evaluation questions on the jobsheet, which improved trial results. The implication of this research shows that integrated and contextual learning media can bridge the gap between theory and practice, improve students' technical competence, and support the achievement of learning objectives.
Pengembangan oven dengan kontrol elektronik untuk peningkatan kapasitas dan kualitas produksi kue bolu Muladi, Muladi; Rahmawati, Yuni; Wirawan, I Made; Hidayat, Samsul; Dwi Septian, Fachur Rozy; Isrofil, Fiqhy
Jurnal Inovasi Hasil Pengabdian Masyarakat (JIPEMAS) Vol 4 No 2 (2021)
Publisher : University of Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/jipemas.v4i2.9166

Abstract

Community service with SME Sakinah Bakery is carried out to increase the production capacity and quality. Sakinah Bakery produces sponge cake and pastries that are very popular within the community and spread across 500 vendor shops in Malang City and Regency. Consumer demands has not been fully fulfilled due to low production capacity. About 10% of the product are undercooked or overcooked. These low quality products reduce the taste and aroma, breaks easily and becomes mushy quickly. Based on surveys and interviews, partner needs an large capacity oven that can produce well-cooked biscuits. The production tool that determine the cake ripeness is oven. This problem is overcomed by making an oven with electronic controls to stabilize the temperature and baking time. Temperature control with sensor feedback mounted on the combustion chamber forms a stable closed loop control system. Proper heating is obtained by controlling the LPG main valve. The three furnaces are spread out to get an even heating. The oven was able to increase 60% the production capacity per bake. The number of fail product decreases by 5.19% indicated that the product quality increases. Technology transfer in the form of training is carried out to maintain the quality.
IMPLEMENTASI MESIN PEMERAS MINUMAN EMPON EMPON INSTAN FOOD GRADE GUNA MENJAGA HIGIENITAS DAN KUALITAS USAHA MIKRO KECIL MENENGAH MELATI LOSARI Wirawan, I Made; Sujito, Sujito; Afandi, Arif Nur; Hadi, Mokh. Sholihul; Habibi, Muhammad Afnan
Jurnal Pengabdian Pendidikan Masyarakat (JPPM) Vol 4 No 2 (2023): Jurnal Pengabdian Pendidikan Masyarakat Vol 4 No 2 (2023)
Publisher : LPPM UNIVERSITAS MUHAMMADIYAH MUARA BUNGO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52060/jppm.v4i2.1356

Abstract

The product produced by MSMEs Melati Losari is an instant empon empon drink that has many benefits. Problems that can be identified in the field of production are limitations in the process of squeezing the empon empon drink. MSMEs Melati Losari so far still uses manual equipment and methods, namely by placing it between the cloth and then threading it using human power. Thus it takes quite a long time in the process of producing the empon empon drink. The long process reduces productivity in processing this product. From the conditions above, the method and results of this community service are providing appropriate technology by applying an empon- empon drink squeezer machine, which aims to reduce interference during the squeeze process. This empon-empon squeezer is designed to make it easier for users and has a size that is small so that it can be stored easily and has press technology to make it easier during the process of squeezing instant empon-empon drinks. This empon- empon squeezer already uses stainless material to so that the instant empon empon drink during the squeezing process maintains the authentic taste and color of the processed empon empon ingredients. And can meet the recommended food safety standards (food grade) as well as carry out training on the use of tools and maintenance, so that these tools can increase the efficiency, and hygiene of empon empon beverage products, products with high hygiene can improve the quality and quantity of instant empon empon drink production MSMEs Melati Losari.
Comparative Evaluation of Machine Learning Models for Heavy Crude Oil Viscosity Prediction Using Repeated Nested Cross-Validation and Independent Holdout Testing Enggie Hendrawan Saputra; Ilham Ari Elbaith Zaeni; Didik Dwi Prasetya; Azlan Mohd Zain; Welly Antonius; I Made Wirawan
Indonesian Journal of Data and Science Vol. 7 No. 2 (2026): Indonesian Journal of Data and Science
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v7i2.455

Abstract

Introduction: Accurate prediction of heavy crude oil viscosity is important for reservoir engineering, production planning, and flow assurance because viscosity strongly affects fluid mobility and transport behavior. This study comparatively evaluates established machine learning models under a rigorous validation protocol rather than proposing a new predictive framework. Method: A published Middle Eastern heavy crude-oil dataset containing 196 development measurements and 47 independent holdout measurements was used. Linear Regression, Support Vector Regression, Random Forest, Gradient Boosting, and the Beggs–Robinson correlation were evaluated using repeated nested cross-validation with five outer folds repeated twice and five inner folds. Preprocessing and hyperparameter selection were embedded within the validation pipeline, while the untouched holdout set was used only for final evaluation. Results and Discussion: Gradient Boosting achieved the best internal performance with R² = 0.99313 and RMSE = 11.41 cP. On the independent holdout set, it achieved R² = 0.99308, RMSE = 8.43 cP, MAE = 6.64 cP, and MAPE = 0.78%, outperforming Random Forest and Support Vector Regression. Residual diagnostics showed no detectable heteroscedasticity, while permutation importance identified temperature and C7+ as the dominant predictors. Conclusion: Gradient Boosting provides highly accurate viscosity predictions within the sampled domain; however, the absence of row-level oil identifiers and external reservoir data limits conclusions regarding oil-disjoint and field-level generalization.
Co-Authors A.N. Afandi Abdul Syukor Mohamad Jaya Abdullah Iskandar Syah Agung Witjoro Ahmad Fahmi Ahmad Lutfi Hidayatulloh Ahmad Nurdiansyah, Ahmad Aji Prasetya Wibawa Amalia Beladinna Arifa Anggi Kusuma Irawan Anik Nur Handayani Argeshwara, Dityo Kreshna Aries Alfian Prasetyo Aripriharta - Arisatya Bharotoyakti Arrohman, Maulana Ludfi Arya Mahesa Jenar Ashar, Muhammad Atmaja, Muhammad Bayu Setya Wahyu Azlan Mohd Zain Bayu Koen Anggoro Dessy Rif’a Anzani Didik Dwi Prasetya Dila Umnia Soraya Dwi Septian, Fachur Rozy Dyah Lestari Ega Gefrie Febriawan Emmy Dyah Sulistyowati Enggie Hendrawan Saputra Fachur Rozy Dwi Septian Ferina Ayu Pusparani Fiqhy Isrofil Firmansyah, Ravi Rangga Wahyu FX Yuswantoro Dwi Irawan Gisra Rahmadhita Handrawan Hary Suswanto Hendra Susanto Heru Wahyu Herwanto Ifa Ibriza Rahmatun Nisa Indrasari, Novita Tri Indrazno Siradjuddin Irawan, Anggi Kusuma Isrofil, Fiqhy Isyatul Karimah Kornelius Kamargo/Irawan Dwi Wahyono Kornelius Kamargo Kusumawardana, Arya Latt, Aung Ko M. Alfian Mizar Mahfud Jiono Marizan Sulaiman Maulia Wijiyanti Hidayah Megana, Agis Adienia Haqi Meriatami, Alfeina Zakkya Moh. Zainul Falah Mokh Sholihul Hadi Mokhammad Nasrulloh Muhammad Afnan Habibi Muhammad Iqbal Akbar Muhammad Rama Setiyadi Muhammad Rodhi Faiz Muladi Nasmi Herlina Sari Novendra, Irvandy Ilza Nurrohman, Andrian Bima Oheo K. Haris Osamu Fukuda Pandri Pandiatmi Puji Santoso Puji Santoso Pundhi Yuliawati Raffi Taufik Gushardana Rajib Muhammad Basthony Retno Indah Rokhmawati Ridwan Shalahuddin Rozan Hermansyah Samsul Hidayat Samsul Hidayat Setiadi Cahyono Putro Shalahuddin, Ridwan Shidiqi, Maulana As Sinarep Sinarep Siti Sendari Slamet Wibawanto Soenar Soekopitojo Suci Lestari Sugiono, Bhima Satria Rizky Sujita Sujita Sujito . Sujito Sujito Suteja Suteja Syaad Patmanthara Syafirly, Muhammad Rifqi Rajwa Tri Atmadji Sutikno Triyanna Widiyaningtyas Wahyu Sakti Gunawan Irianto Welly Antonius Widinata, Fandi Widiyanintyas, Triyanna Yuliawati, Pundhi Yuni Rahmawati Yusuf Ahyar Sutaryono Zaeni, Ilham Ari Elbaith Zakiyah Amalia