Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electrical Engineering and Informatics (IJEEI) PROtek : Jurnal Ilmiah Teknik Elektro JIKO (Jurnal Informatika dan Komputer)
Muhamad Dwisnanto Putro
Sam Ratulangi University
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
An Efficient Fall Detector Using Improvement of the YOLOv12n Via ONA-Net Florensce Sumarauw; Febriyanti Ludja; Robby Moody Lintong; Alwin Melkie Sambul; Muhamad Dwisnanto Putro
PROtek : Jurnal Ilmiah Teknik Elektro Vol 13 No 2 (2026): Protek : Jurnal Ilmiah Teknik Elektro
Publisher : Program Studi Teknik Elektro Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/protk.v13i2.11653

Abstract

Meningkatnya permintaan akan sistem deteksi jatuh yang andal dalam pemantauan perawatan pasien sekaligus membantu lingkungan kehidupan mendorong pengembangan model visi komputer yang mampu mengidentifikasi kejadian jatuh secara akurat dalam kondisi dunia nyata. Sistem ini harus mendeteksi perubahan postur tubuh manusia di berbagai posisi sambil mempertahankan ketahanan terhadap latar belakang yang kompleks, yang seringkali mengurangi akurasi deteksi. Selain itu, penerapan di dunia nyata membutuhkan model yang beroperasi secara efisien pada perangkat berbiaya rendah dan memproses aliran video langsung secara real-time. Studi ini menganalisis efektivitas peningkatan versi nano dari arsitektur YOLOv12 untuk deteksi jatuh dengan mengintegrasikan mekanisme ONA-Net. Modul yang diusulkan memungkinkan jaringan untuk fokus pada beberapa respons penting yang terkait dengan postur tubuh manusia, memungkinkan model untuk menangkap isyarat spasial yang terkait dengan kejadian jatuh dengan lebih baik. Desain yang ringan mengurangi beban komputasi sambil mempertahankan ekstraksi fitur yang efektif untuk deteksi yang akurat. Temuan eksperimental menunjukkan YOLOv12-ONA-Net sebagai model yang diperkenalkan memperoleh kinerja deteksi yang kuat, dengan memperoleh 92,3% mAP@50 dan 59,7% mAP@50:95. Meskipun arsitekturnya ringan, model ini tetap mempertahankan efisiensi praktis dengan mencapai kecepatan inferensi 13,13 frame per detik (FPS). Hasil ini menunjukkan bahwa penggabungan ONA-Net ke dalam jaringan YOLOv12n meningkatkan kemampuan deteksi jatuh sekaligus mempertahankan penggunaan komputasi yang sesuai untuk penggunaan pemantauan waktu nyata pada perangkat dengan kapasitas komputasi terbatas.
Lightweight Enhancement Module for Efficient Sea Turtle Species Detection under Illumination Variation Yuliana Mose; Alex Copernikus Andaria; Hebron Prasetya; Muhamad Dwisnanto Putro
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 14, No 2: June 2026
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v14i2.7399

Abstract

Sea turtle monitoring is crucial for maintaining ecosystem balance, although traditional methods are costly and inefficient. Object detection provides a foundation for autonomous monitoring by localizing sea turtles in their natural habitat. At the same time, recent deep learning models can operate in real-time. On the other hand, underwater detection remains challenging due to extreme illumination, underwater blur, and underwater distortions, which obscure key features from the background. To address these issues, this work proposes a new sea turtle detector, based on a modified YOLOv12-nano model that incorporates a lightweight enhancement module to improve robustness under diverse illumination. The network introduced Efficient Spatial Convolution (ESC) at the end of the backbone to improve the representation of high-level features. It involves Dual Spatial Convolution (DSC) to improve backbone feature extraction with a large kernel size while preserving efficiency. The Lite module is designed to enrich feature diversity and selectively enhance the quality of high-level features. These modifications significantly enhance detection performance under diverse underwater lighting conditions. The proposed network achieves higher precision than the original YOLOv12-nano while maintaining efficiency, making it well-suited for deployment on low-cost devices.
YOLOv12n-RL-MSCAM: Enhancing Lightweight Trash Detection with Reinforced Local Multi-Scale Channel Attention Module Robby Moody Lintong; Florensce Sumarauw; Febriyanti Ludja; Sary Diane Ekawati Paturusi; Muhamad Dwisnanto Putro
JURNAL INFORMATIKA DAN KOMPUTER Vol 10, No 2 (2026): Juni 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v10i2.2700

Abstract

The growing demand for efficient environmental monitoring has led to the development of computer vision based trash detection models for real world urban deployment. These systems must recognize diverse waste types under challenging conditions, such as variations in appearance, scale, and complex backgrounds, which can significantly reduce detection accuracy. Moreover practical applications require lightweight models capable of maintaining real-time performance on CPU devices. This study enhances the YOLOv12n architecture for trash detection by integrating a Reinforced Local Multi-Scale Channel Attention Module (RL-MSCAM). The proposed module improves feature representation by highlighting informative channels and reducing irrelevant background noise, leading to better extraction of discriminative spatial features of waste objects. The lightweight design ensures these improvements are achieved without significant computational overhead, making the model suitable for real-time applications. Experimental results show that the proposed model achieves strong detection performance, with 60.6 % mAP@50 and 50.9% mAP@50:95. Despite its lightweight design, the model maintains practical efficiency, reaching an inference speed of 16.12 frames per second (FPS). These findings indicate that integrating RL-MSCAM into the YOLOv12n framework improves trash detection performance while preserving computational efficiency, making it suitable for real-time deployment on CPU devices.
Co-Authors Alex Copernikus Andaria Alwin Melkie Sambul Febriyanti Ludja Febriyanti Ludja Florensce Sumarauw Florensce Sumarauw Hebron Prasetya Robby Moody Lintong Sary Diane Ekawati Paturusi Yuliana Mose