Claim Missing Document
Check
Articles

Found 3 Documents
Search

PENERAPAN DETEKSI KECACATAN BUAH JERUK MENGGUNAKAN MODEL DEEP LEARNING YOLOV5 Rinanto, Noorman; Aldi Febriansyah; Adianto; Muhammad Khoirul Hasin; Putri Nur Rahayu
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.8897

Abstract

Penentuan kualitas buah jeruk secara manual cenderung tidak konsisten serta memerlukan waktu dan tenaga yang signifikan. Oleh karena itu, penelitian ini bertujuan untuk merancang sistem otomatis dalam mendeteksi kecacatan buah jeruk dengan memanfaatkan model deep learning YOLOv5. Dataset citra buah jeruk dikumpulkan berdasarkan variasi tingkat kematangan, yaitu matang, asam, dan busuk, kemudian diberi label menggunakan platform Roboflow dan dibagi menjadi data pelatihan, validasi, serta pengujian. Proses pelatihan dilakukan melalui platform Google Colab dengan menerapkan dua varian model, yaitu YOLOv5s dan YOLOv5n. Berdasarkan hasil evaluasi, model YOLOv5s menunjukkan akurasi deteksi yang sangat tinggi dengan nilai mAP@0.5 di atas 99% dan mAP@0.5:0.95 mendekati 98%. Sementara itu, YOLOv5n memiliki keunggulan dalam hal kecepatan inferensi meskipun akurasinya sedikit lebih rendah. Pengujian secara real-time menggunakan webcam menunjukkan bahwa kedua model mampu mengenali serta mengklasifikasikan buah jeruk secara tepat, Pengujian real-time menggunakan kamera menghasilkan akurasi 93,33% untuk YOLOv5s dan 86,67% untuk YOLOv5n, sistem ini memiliki potensi besar dalam mendukung proses otomatisasi penilaian mutu buah, meningkatkan efisiensi kerja, dan mengurangi human error dalam proses sortasi.
Implementation of YOLOv5s for Automatic Waste Category Classification in Digital Waste Bank Systems Rinanto, Noorman; Mat Syai’in; Agus Khumaidi; Muhammad Khoirul Hasin; Lilik Subiyanto; Vivin Setiani; Firstama Yusuf Noor; Harun Ismail
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 20 No. 1 (2026)
Publisher : Faculty of Engineering, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jeeccis.v20i1.1894

Abstract

The increasing volume of organic waste in campuses or households demands innovative solutions for waste management and classification. This study proposes an automated classification system based on deep learning using the YOLOv5s algorithm to detect 14 categories of inorganic waste in real-time. The dataset consists of over 3.500 labeled images, annotated via Makesense.ai and augmented using Roboflow. The model was trained on Google Collaboratory for 100 epochs using the YOLOv5s architecture and evaluated based on precision, recall, F1-score, and mean Average Precision (mAP). Training result show mAP@0.5 approaching 100% and mAP@0.5:0.95 around 85%, with an average confidence score of 88.30% during real-time testing using a webcam. These findings demonstrate that YOLOv5s can accurately and efficiently classify waste objects, offering strong potential for integration into digital waste bank systems to enhance the efficiency and transparency of waste management processes.
Automatic identification system big data‑driven maritime traffic density prediction in surabaya port using PCA and k‑means clustering Arfianto, Afif Zuhri; Haj, Muhammad Izzul; Muhammad Khoirul Hasin; Noorman Rinanto; Imam Sutrisno; Dimas Pristovani Riananda; Dwi Sasmita Aji Pambudi
Journal of Soft Computing Exploration Vol. 7 No. 1 (2026): March 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i1.22

Abstract

The management of maritime traffic directly determines the level of operational efficiency and safety achievable at major ports, including Tanjung Perak in Surabaya, which serves as a critical logistics node for eastern Indonesia. This study presents a comprehensive analysis of maritime traffic density prediction using Automatic Identification System (AIS) big data combined with Principal Component Analysis (PCA) and K-Means clustering techniques. The dataset comprises 1,173 vessel movements recorded in December 2025, encompassing various vessel types, port operations, and voyage characteristics. Through dimensionality reduction using PCA and unsupervised clustering with K-Means, we identified 10 distinct traffic patterns representing different operational profiles. The analysis revealed significant temporal patterns, with peak traffic occurring at 14:00 (79 vessels) and lowest traffic at 02:00 (18 vessels). The clustering results achieved a silhouette score of 0.3863, effectively segmenting vessels based on voyage distance, capacity, speed, draught, and temporal features. The results of this research offer practical guidance for port authorities seeking to improve resource allocation, traffic management, and operational efficiency based on empirical evidence.