Article Per Year (5 Year)
p-Index From 2021 - 2026
2.495
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Program Kreativitas Mahasiswa - Karsa Cipta Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JURNAL MEDIA INFORMATIKA BUDIDARMA Technomedia Journal JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) EDUMATIC: Jurnal Pendidikan Informatika JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) eProceedings of Engineering LOGIC: Jurnal Penelitian Informatika
Gamma Kosala
Telkom University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Advancing Vehicle Logo Detection with DETR to Handle Small Logos and Low-Quality Images Ubaidillah, Rifky Fahrizal; Sulistiyo, Mahmud Dwi; Kosala, Gamma; Rachmawati, Ema; Haryadi, Deny
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 4 (2025): August 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i4.6236

Abstract

Image-based vehicle logo detection is an important component in the implementation of vehicle information recognition technology, which supports the development of intelligent transportation systems. Vehicle logos, as elements that represent the identities of vehicle brands and models, play a significant role in completing vehicle identity data. The information obtained from this logo can be utilized to solve various traffic problems, such as vehicle document counterfeiting and theft, and for better traffic planning and management purposes. However, the main challenge in developing an accurate logo detection system lies in the wide variety of shapes, sizes, and positions of logos in different types of vehicles. In addition, the generally small size of logos, especially on certain vehicles, often makes it difficult for computer-based detection systems to recognize logos consistently, thus affecting the overall performance of the detection model. In this research, the Detection Transformers (DETR) method is used to build a vehicle logo detection system that focuses on small-scale logo. The testing process was conducted using the VL-10 dataset, which was specifically designed for vehicle logo detection evaluation. The results show that the DETR model can detect vehicle logos very well, even for small-scale logos. The model achieved an AP50 value of 0.952, which indicates a high level of accuracy and reliability in detecting the vehicle logo in the dataset used.
Zebra Cross Violation Detection with YOLOv9: A Novel Approach for Traffic Regulation in Indonesia Kamil, Muhammad Najmi; Gamma Kosala
Jurnal Pendidikan Informatika (EDUMATIC) Vol 9 No 1 (2025): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v9i1.29244

Abstract

Technological advancements in zebra cross-violation detection are necessary to address traffic rule violations in Indonesia, especially zebra cross violations. The You Only Look Once (YOLO) algorithm has been effective for detecting objects in various situations. The objective of this research is to focus on detecting zebra cross violations using YOLOv9, the improved accuracy and efficiency from earlier versions of YOLO. Consisting of two models to detect violations of the zebra crossing. The first model, a segmentation model called YOLO, is used for zebra cross localization, while the second model, a pretrained YOLO, detects the vehicles. The results of these two models are used for calculations in considering violations by drivers. Two datasets were used in this research. One of the datasets has 1100 images of zebra crosses, while the other comprises 100 surveillance videos from CCTV in Yogyakarta, Indonesia, for testing. The findings from this study indicate that the approach enables effective and efficient detection and classification of zebra crossing violations with an accuracy of 93%. This research demonstrates the approach's enhanced ability to handle real-world scenarios with diverse camera angles and varying traffic conditions. Additionally, it underscores the potential for practical applications in automated traffic monitoring and enforcement.
Deteksi Objek Makhluk Hidup dalam Filum Arthropoda Menggunakan YOLOv3 Safarin, Arva Adwitya; Rachmawati, Ema; Kosala, Gamma
eProceedings of Engineering Vol. 10 No. 2 (2023): April 2023
Publisher : eProceedings of Engineering

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

Abstract

Abstrak-Makhluk hidup yang berasal dari filum Arthropoda merupakan makhluk hidup yang memiliki beragam karakteristik. Karakteristik tersebut bisa dibedakan dengan melihat ordo dari makhluk hidup tersebut. Beberapa jenis makhluk hidup yang ada dalam filum Arthropoda merupakan makhluk sosial. Oleh karena itu, mereka sering ditemukan berada di lokasi yang sama dan berkerumun. Selain itu, sebagian besar spesies yang ada dalam filum Arthropoda memiliki ukuran tubuh yang kecil. Pada tugas akhir ini, metode yang diajukan adalah YOLOv3. YOLOv3 merupakan metode deteksi objek yang memiliki beberapa pembaruan yang memungkinkan metode tersebut lebih mudah mendeteksi objek yang berkerumun dan memiliki ukuran yang kecil. Untuk mengembangkan sistem pendeteksi makhluk hidup dalam filum Arthropoda menggunakan YOLOv3, terdapat 12.082 data citra yang terbagi dalam 7 (tujuh) kelas untuk melatih model tersebut. Hasil terbaik yang didapatkan saat pengujian memakai 1.544 data uji adalah nilai mAP sebesar 57,6% pada IOU 0,5.Kata kunci - deep learning, deteksi objek, You Only Look Once (YOLO), deteksi makhluk hidup
Klasifikasi Buah-Buahan dengan Metode ResNet-RS Fruit Classification With ResNet-RS Wirasakananda, Dewa Made Aditya; Rachmawati, Ema; Kosala, Gamma
eProceedings of Engineering Vol. 10 No. 3 (2023): Juni 2023
Publisher : eProceedings of Engineering

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

Abstract

Abstrak-Buah-buahan merupakan salah satu makanan yang dikonsumsi oleh masyarakat di dunia. Dengan adanya berbagai jenis buah-buahan yang tersedia di dunia, buah-buah tersebut mempunyai karakteristik bentuk dan warna yang berbeda-beda. Oleh karena itu perlunya dilakukan klasifikasi sebagai cara untuk mengidentifikasi buah-buahan secara cepat, dengan menerapkan teknik computer vision yang menggunakan metode ResNet-RS. Metode ini digunakan karena ResNet-RS merupakan metode yang mempunyai peningkatan terhadap ResNet yang diperkenalkan pada 2015. Untuk klasifikasi buah-buahan dengan menggunakan metode ResNet-RS mendapatkan hasil yaitu 97.29% akurasi, 97.29% F1-Score, 97.28% recall, dan 97.31% precision. Terdapat selisih 4.07% dalam akurasi terhadap model ResNet dengan dataset yang sama.Kata kunci-buah-buahan, ResNet-RS , klasifikasi
Deteksi Kanker Kulit Melanoma Menggunakan Derivative of Gaussian dan Convolutional Neural Network Rahman, Rahadian Yusuf Abdul; Sthevanie, Febryanti; Kosala, Gamma
LOGIC: Jurnal Penelitian Informatika Vol. 2 No. 1 (2024): Mei 2024
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/logic.v2i1.7529

Abstract

Melanoma merupakan jenis kanker kulit paling mematikan di seluruh dunia. Namun, kanker kulit merupakan salah satu kanker yang mudah untuk disembuhkan karena terletak di bagian luar tubuh dan apabila dapat dideteksi sejak dini maka penyakit ini dapat ditangani lebih efektif. Ada beberapa metode klasifikasi yang digunakan untuk deteksi dini kanker kulit seperti SVM, KNN dan CNN. Dalam hal ini, jurnal ini menunjukkan metode untuk mendeteksi kanker kulit melanoma menggunakan derivative of gaussian(DOG) dan convolutional neural network(CNN). Akan dilakukan 5 skenario pengujian untuk mengetahui bagaimana performa dari apa yang diusulkan, salah satu dari skenario tersebut menggunakan gaussian filter.
Co-Authors Abdul Khaliq Al Bari Agus Harjoko Al’Fattah, Bimayudha Bedy Purnama Deny Haryadi Ema Rachmawati Ema Rachmawati Ema Rachmawati Febryanti Sthevanie Gibran, Hilal Ilham Imaduddin, Ilham Kamil, Muhammad Najmi Ketut Sudyatmika Putra Kurniawan Nur Ramadhani Latifah Noor, Latifah Mahmud Dwi Sulistiyo Muhammad Mukhlis Nugraha, Muhammad Mukhlis Muhammad Rayhan Subhi Naufal Harsa Pratama Purnama , Bedy Rahman, Rahadian Yusuf Abdul Rifki Wijaya Safarin, Arva Adwitya Setyawan, Hendy Sri Hartati Tito Waluyo Ubaidillah, Rifky Fahrizal Ulfah Fitriyani, Ulfah Wirasakananda, Dewa Made Aditya