Article Per Year (5 Year)
p-Index From 2020 - 2025
4.129
P-Index
This Author published in this journals
All Journal Lontar Komputer: Jurnal Ilmiah Teknologi Informasi Techno.Com: Jurnal Teknologi Informasi Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik Prosiding Semnastek English Review: Journal of English Education EMITTER International Journal of Engineering Technology Fountain of Informatics Journal JRSI (Jurnal Rekayasa Sistem dan Industri) JURNAL MEDIA INFORMATIKA BUDIDARMA IKRA-ITH Informatika : Jurnal Komputer dan Informatika DIKLUS: Jurnal Pendidikan Luar Sekolah Jurnal Teknoinfo KOMPUTIKA - Jurnal Sistem Komputer Infoman's: Jurnal Ilmu-Ilmu Manajeman dan Informatika Applied Technology and Computing Science Journal Jurnal Mantik Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) PELS (Procedia of Engineering and Life Science) SAINTEK Journal of Information System and Application Development
Oddy Virgantara Putra
Universitas Darussalam Gontor
Arts Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Social Sciences

Published : 32 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 32 Documents
Search

 1   2   3   4 
KLASIFIKASI POSE MANUSIA BERBASIS POINT CLOUD MENGGUNAKAN DEEP LEARNING Siddiq, Muhammad; Muriyatmoko, Dihin; Putra, Oddy Virgantara
Prosiding Semnastek PROSIDING SEMNASTEK 2024
Publisher : Universitas Muhammadiyah Jakarta

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

Abstract

Dengan menggunakan teknologi untuk mengklasifikasikan pose manusia, pemantauan pekerjaan yang berisiko cedera dapat dilakukan dengan lebih aman, sejalan dengan prinsip mempertahankan keamanan dan privasi yang merupakan bagian dari prinsip-prinsip syariah dalam menjaga jiwa. Namun, dalam pengambilan sampel data tubuh manusia, terdapat risiko pengambilan data aurat yang melanggar prinsip privasi. Melalui penggunaan data point cloud dari LiDAR, bagian tubuh yang menjadi aurat dapat tersamarkan dan menjaga privasi. Meskipun demikian, pose manusia yang dihasilkan belum terlihat dengan jelas. Oleh karena itu, tujuan dari penelitian yang dilakukan ini adalah untuk membuat model klasifikasi pose manusia berbasis voxel point cloud dengan menggunakan deep learning agar dapat mengetahui pose manusia. Dalam penelitian ini, model klasifikasi pose manusia berbasis voxel point cloud dengan menggunakan pendekatan deep learning Conv3D telah berhasil dikembangkan dengan akurasi sebesar 95.76%.Kata kunci: Human pose classification; LiDAR; Point cloud data; Deep learning
Improving 3D Human Pose Orientation Recognition Through Weight-Voxel Features And 3D CNNs Riansyah, Moch. Iskandar; Putra, Oddy Virgantara; Rahmanti, Farah Zakiyah; Priyadi, Ardyono; Wulandari, Diah Puspito; Sardjono, Tri Arief; Yuniarno, Eko Mulyanto; Hery Purnomo, Mauridhi
EMITTER International Journal of Engineering Technology Vol 13 No 1 (2025)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v13i1.847

Abstract

Preprocessing is a widely used process in deep learning applications, and it has been applied in both 2D and 3D computer vision applications. In this research, we propose a preprocessing technique involving weighting to enhance classification performance, incorporated with a 3D CNN architecture. Unlike regular voxel preprocessing, which uses a zero-one (binary) approach, adding weighting incorporates stronger structural information into the voxels. This method is tested with 3D data represented in the form of voxels, followed by weighting preprocessing before entering the core 3D CNN architecture. We evaluate our approach using both public datasets, such as the KITTI dataset, and self-collected 3D human orientation data with four classes. Subsequently, we tested it with five 3D CNN architectures, including VGG16, ResNet50, ResNet50v2, DenseNet121, and VoxNet. Based on experiments conducted with this data, preprocessing with the 3D VGG16 architecture, among the five architectures tested, demonstrates an improvement in accuracy and a reduction in errors in 3D human orientation classification compared to using no preprocessing or other preprocessing methods on the 3D voxel data. The results show that the accuracy and loss in 3D object classification exhibit superior performance compared to specific preprocessing methods, such as binary processing within each voxel.
Co-Authors Achmad, Dellyan Adi Darmanto Agung Toto Wibowo Ahmad Saroji Ardyono Priyadi azis isrofi Aziz Musthafa Dahlan, Muhammad Alwi Diah Puspito Wulandari Dihin Muriatmoko Dihin Muriyatmoko Eko Mulyanto Yuniarno Ema Rachmawaty Faisal Reza Pradana Faisal Reza Pradhana Faishal Reza Pradhana Farah Zakiyah Rahmanti Febri Vicky Allen Harris Abdillah Faqih Havidz Muhammad Iqbal Hesti Rokhaniyah, Hesti Imam Fauzi Annur Imron Rosyadi Jordan Istiqlal Qalbi Adiba Jumhurul Umami Jumhurul Umami, Jumhurul Kukuh Prasetyo Wibowo Kurniawan, Widya Lukman Effendi Lukman Effendi, Lukman Mauridhi Hery Purnomo Moch. Iskandar Riansyah Moch. Nasheh Annafii Muhamad Rido Muhamad Taufiq Riza Muhammad Alwi Muhammad Arsyad Maulana Muhammad Fakhruzzaini Muhammad Firdaus Muhammad Nur Muhammad Rizal Muttaqin1 Muhammad Siddiq, Muhammad Muhammad Zaim Mustaqim Niken Sylvia Puspitasari Pradana, Kelvin Raja Syam Abbas Shagir Reyhan Nafis Ibrahim Shoffin Nahwa Utama Taufiqurrahman Tri Arief Sardjono Triana Harmini Trisnaningrum, Niken Wijaya, Akhmad Trisna Yoke Suryadarma Zsaffa Aulia Putri Prasetyo