Article Per Year (5 Year)
p-Index From 2021 - 2026
3.935
P-Index
This Author published in this journals
All Journal Jurnal Teknoin SCIENCE TECH: Jurnal Ilmiah Ilmu Pengetahuan dan Teknologi VOLT : Jurnal Ilmiah Pendidikan Teknik Elektro JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Infomedia JURIKOM (Jurnal Riset Komputer) JURTEKSI Building of Informatics, Technology and Science JATI (Jurnal Mahasiswa Teknik Informatika) Information System Journal (INFOS) J-Intech (Journal of Information and Technology) Journal of Practical Computer Science (JPCS) EXPLORE Intechno Journal : Information Technology Journal Explore Jurnal Pengabdian Masyarakat Inovasi Indonesia Journal of Information Technology
Arifiyanto Hadinegoro, Arifiyanto
Universitas Amikom Yogyakarta, Yogyakarta
Agriculture, Biological Sciences & Forestry Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Library & Information Science Materials Science & Nanotechnology Mechanical Engineering Public Health Social Sciences

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Perancangan Sistem Informasi Buku Tamu Berbasis Web Pada Kantor Kementerian Hukum dan Hak Asasi Manusia Banda Aceh Icha Widya Pratiwi; Nazaruddin Ahmad; Arifiyanto Hadinegoro; Saifan Hafizh; Rana Sulthanah
J-INTECH ( Journal of Information and Technology) Vol 12 No 1 (2024): J-Intech : Journal of Information and Technology
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/j-intech.v12i1.1266

Abstract

In an agency, visits from other institutions and the general public frequently occur. To record these visits, an officer manages a guest book where visitors log their presence and state their purpose. However, the conventional method of using a guest book is susceptible to damage and leads to the accumulation of physical books. Additionally, summarizing visit data daily, weekly, monthly, or annually becomes challenging. Therefore, there is a need for digital modernization of visitor recording to align with the smart government concept implemented in government agencies. The proposed solution is to design a web-based guest book information system that will facilitate visitor data recording, visit monitoring, and visit summarization according to the needs of the leadership at the Regional Office of Law and Human Rights in Banda Aceh. To achieve optimal results, this study employs the Research and Development (R&D) method combined with the waterfall software development approach. The design process includes creating use case diagrams, conceptualizing database table relations, and utilizing the PHP programming language with the Bootstrap framework to ensure an easy-to-use interface. With this guest book information system, visitors will no longer need to fill out conventional guest books, and the Regional Office of Law and Human Rights in Banda Aceh will not require traditional guest book archiving. All visitor data, visit logs, and visit summaries will be stored in a system accessible to relevant parties as needed.
Implementation of SSL-Vision Transformer (ViT) for Multi-Lung Disease Classification on X-Ray Images Baasith, Rafi Haqul; Sasongko, Theopilus Bayu; Hadinegoro, Arifiyanto; Saputro, Uyock Anggoro
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11844

Abstract

Chest X-ray imaging is one of the most widely used modalities for lung disease screening; however, manual interpretation remains challenging due to overlapping pathological patterns and the frequent presence of multiple coexisting abnormalities. In recent years, Vision Transformer (ViT) models have demonstrated strong potential for medical image analysis by capturing global contextual relationships. Nevertheless, their performance is highly dependent on large-scale labeled datasets, which are costly and difficult to obtain in clinical settings. To address this limitation, this study proposes a Self-Supervised Learning Vision Transformer (SSL-ViT) framework for multi-label lung disease classification using the CheXpert-v1.0-small dataset. The proposed approach leverages self-supervised pretraining to learn robust and transferable visual representations from unlabeled chest X-ray images prior to supervised fine-tuning. A total of twelve clinically relevant thoracic disease labels are retained, while non-disease labels are excluded to enhance interpretability and reduce confounding effects. Experimental results demonstrate that SSL-ViT achieves a high recall of 0.73 and a peak AUC of 0.75 on the test set, indicating strong sensitivity in detecting pathological cases. Compared to the baseline ViT model, SSL-ViT exhibits a recall-oriented performance profile that is particularly suitable for screening applications, where minimizing false negatives is critical. Furthermore, Grad-CAM visualizations confirm that the model focuses on anatomically meaningful lung regions, supporting its clinical relevance. These findings suggest that SSL-enhanced Vision Transformers provide a robust and effective solution for multi-label chest X-ray screening tasks.
Robust Deep Learning Approach for Automatic Age and Gender Recognition Based on Voice M. Nasyid Yunitian Rizal; Theopilus Bayu Sasongko; Arifiyanto Hadinegoro; Kumara Ari Yuana; Wahid Miftahul Ashari
Intechno Journal : Information Technology Journal Vol. 8 No. 1 (2026): July
Publisher : Universitas AMIKOM Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/intechnojournal.2026v8i1.2827

Abstract

Voice-based age and gender recognition plays an important role in biometric authentication, personalized human–computer interaction, and digital forensic applications. However, existing single deep learning architectures often struggle to simultaneously capture local acoustic patterns, temporal dependencies, and long-range contextual information from speech signals. This study proposes a hybrid CNN–BiLSTM–Transformer framework to improve the accuracy and robustness of multi-class age and gender classification. The proposed approach employs Mel-spectrogram representations generated from the Mozilla Common Voice dataset, followed by audio standardization and feature extraction. A Convolutional Neural Network (CNN) enhanced with Squeeze-and-Excitation blocks extracts discriminative spectral features, a Bidirectional Long Short-Term Memory (Bi-LSTM) network models bidirectional temporal dependencies, and a Transformer Encoder captures global contextual relationships through a multi-head self-attention mechanism. The model was evaluated on 40,392 speech samples across 12 age–gender categories. Experimental results achieved an overall classification accuracy of 91%, outperforming standalone CNN and Bi-LSTM models, which obtained accuracies of 84% and 74%, respectively. In addition, the proposed model demonstrated balanced performance with macro-average precision, recall, and F1-scores of 0.91, 0.92, and 0.91. The novelty of this research lies in the integration of complementary spatial, temporal, and global attention mechanisms within a unified architecture for large-scale multi-class voice-based demographic classification, providing an effective and scalable solution for intelligent biometric and speech analysis systems.
DETEKSI PENYAKIT KULIT DENGAN MENGGUNAKAN MODEL PRETRAINED DAN HYBRID KNOWLEDGE DISTILLATION Theopilus Bayu Sasongko; Arifiyanto Hadinegoro; Eli Pujastuti; I Made Artha Agastya; Nazaruddin Ahmad
Information System Journal Vol. 8 No. 02 (2025): Information System Journal (INFOS)
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/infosjournal.2025v8i02.2585

Abstract

Knowledge Distillation (KD) merupakan paradigma efektif untuk mentransfer pengetahuan dari model teacher berkapasitas tinggi ke model student yang ringan melalui kombinasi soft label dan hard label. Meskipun KD Hinton mampu menangkap kesamaan antar kelas, pendekatan ini masih terbatas dalam mentransfer representasi fitur mendalam yang krusial pada tugas pencitraan medis, seperti klasifikasi lesi kulit, di mana fitur halus sering hilang jika hanya mengandalkan keluaran akhir model. Untuk mengatasi keterbatasan tersebut, penelitian ini mengembangkan tiga varian KD, yaitu KD Hinton dengan supervisi hard label, KD dengan penyelarasan fitur, dan Hybrid KD yang mengombinasikan keduanya. Pendekatan ini memungkinkan student meniru distribusi semantik dan representasi fitur internal teacher sekaligus mempertahankan informasi diskriminatif dari ground truth. Eksperimen pada berbagai pasangan teacher–student menunjukkan adanya trade-off antara akurasi dan biaya komputasi. Hasilnya, metode Hybrid KD memberikan peningkatan kinerja tertinggi, mencapai akurasi Top-1 sebesar 82,07% pada MobileNetV2 tanpa menambah kompleksitas model, sehingga efektif untuk aplikasi pencitraan medis real-time berbasis sumber daya terbatas.
Co-Authors Adi Saputro, Johan Agung Pambudi Anggit Dwi Hartanto Arif Akbarul Huda Arya Yudistira Ashari, Wahid Miftahul Baasith, Rafi Haqul Dhiaulhaq, Muhammad Faishal Ali Drajat Indah Mawarni Eli Pujastuti Fajarudin, Rohmad Faris Fathahillah Herman Fikri, Muhammad Ainul Hafizh, Saifan Hasif Priyambudi Hendrawan, Mohammad Yan Fikri Huda, Amirudin Khorul I Made Artha Agastya Icha Widya Pratiwi Ikramillah, Syauqi Khairan AR Kumara Ari Yuana Kusuma Wardana, Raka M. Nasyid Yunitian Rizal Muhamad Syah Reza Muhamad Sysah Reza Nazaruddin Ahmad Nazaruddin Ahmad Ningrum, Fauzia Anis Sekar NUR AINI Nuri Cahyono Pratiwi, Icha Widya Rahim, Abd. Mizwar A. Rana Sulthanah Rizaldilhi, Dicky Andhika Saifan Hafizh Saputro, Uyock Anggoro Sasongko, Theopilus Bayu Siti Fatonah Subektiningsih Subektiningsih Sulthanah, Rana Teguh Wibowo Uyock Anggoro Saputro Yuana, Kumara Ari