Article Per Year (5 Year)
p-Index From 2021 - 2026
3.815
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) JURNAL PENDIDIKAN KEPERAWATAN INDONESIA Indonesia Symposium on Computing Indonesian Journal on Computing (Indo-JC) IJoICT (International Journal on Information and Communication Technology) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Indonesian Journal of Artificial Intelligence and Data Mining Technomedia Journal Journal of Electronics, Electromedical Engineering, and Medical Informatics Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Teknik Informatika (JUTIF) Charity : Jurnal Pengabdian Masyarakat Indonesian Community Journal Jurnal Locus Penelitian dan Pengabdian eProceedings of Engineering Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS BATIK: Jurnal Pengembangan dan Pengabdian Masyarakat Multikultural LOGIC: Jurnal Penelitian Informatika Journal of The Physical Society of Indonesia IJoICT (International Journal on Information and Communication Technology) Journal of Soft Computing Exploration
Bedy Purnama
Telkom University
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mathematics Nursing Physics Public Health Social Sciences Other

Published : 40 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 40 Documents
Search

 1   2   3   4 
Pose Classification in Archery Sports Based on YoloV8 Using SVM and Random Forest Methods Yuridikta Adha Muslim; Bedy Purnama; Bayu Erfianto
IJoICT (International Journal on Information and Communication Technology) Vol. 11 No. 1 (2025): Vol. 11 No. 1 Jun 2025
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v11i1.8996

Abstract

This research creates a YOLOv8-based pose classification system that can analyze and classify the movements of archery athletes. The system is combined with SVM and RF methods, and utilizes YoloV8 pose detection and machine learning techniques to provide more accurate classification. Video data collection, system design and implementation, and analysis of implementation results are some of the stages passed during system development. The process includes joint feature extraction using YOLOv8 and classification for Recurve and Barebow categories using SVM and RF. The test results show the difference in performance between the two classification methods. For the Recurve category, SVM had 90% accuracy for testing, while RF had 87% accuracy for testing. For the Barebow category, SVM had 76% accuracy for testing, while RF had 75% accuracy for testing. In terms of generalization, the two methods differed, with SVM showing better stability between testing and training performance. The results show that SVM is superior when testing when compared to RF which makes an anomaly with previous studies
Usability Of “DFU Application” For Diabetic Foot Ulcer Prevention Purnama, Bedy; Lindayani, Linlin; Mutiar, Astri; Erfianto, Bayu; Darmawati, Irma
Jurnal Pendidikan Keperawatan Indonesia Vol 11, No 1 (2025): Volume 11, Nomor 1, Juni 2025
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jpki.v11i1.81809

Abstract

Introduction: The development of smart detection software may help reduce the number of decubitus ulcer infections by enabling early identification and management. Ensuring the usability and effectiveness of such technology is essential before widespread adoption. Objective: This study aimed to explore prospective users’ perceptions of the mobile app for detecting diabetic foot ulcer (DFU) infection, focusing on its usefulness, ease of use, and overall user satisfaction. Methods: The usability of the DFU app was assessed by experienced users. The evaluation included perceived usefulness, ease of use, and overall satisfaction. Standardized tools such as the System Usability Scale (SUS) and a specific app rating scale were used to collect user feedback. Results: The DFU app received usability ratings ranging from 0.50 to 0.88. The lowest rating was for performance quality (Mean = 0.50, SD = 0.12), while the highest was for integrity (Mean = 0.88, SD = 0.07). The overall usability score, as measured by SUS, was considered acceptable (Mean = 78.4, SD = 6.83). Most users reported no significant issues with using the app, except for difficulty understanding the language used in the interface, which was rated as a serious usability issue with a severity score of 3. Conclusions: Users perceived the DFU app as useful and efficient, particularly in detecting the risk of infection. Despite a noted language comprehension issue, the app demonstrated good overall usability and has the potential to support early intervention for decubitus ulcer prevention.
Development of Health Kiosk Prototype for Blood Pressure and Fat Mass Measurement Umiatin, Umiatin; Putri, Pinkan Amanda; Purwalaksana, Ahmad Zatnika; Al Farizy, Firnas; Nurdin, Muhammad; Purnama, Bedy; Ifa, Rista Putri Nur; Abidin, Muhammad
Journal of the Physical Society of Indonesia Vol. 1 No. 2 (2025): October 2025
Publisher : The Physical Society of Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35895/jpsi.1.2.76-86.2025

Abstract

Health development in Indonesia faces a double burden of disease, namely infectious and non-communicable diseases (NCDs), with cardiovascular diseases (CVDs) accounting for nearly half of NCD-related deaths. Major CVD risk factors are hypertension and obesity, which can be controlled through routine monitoring of blood pressure and body mass index (BMI). This study aims to develop a health kiosk prototype integrating a sphygmomanometer and BMI–fat analyzer. The research consists of three stages: characterization of sensors for blood pressure and body fat measurement, comparison of proximity sensors, and prototype testing. The MPX5050GP pressure sensor achieved an R² of 1 with a sensitivity of 0.012 volts. Proximity sensor characterization showed R² values of 0.9996 (HC-SR04) and 0.9997 (JSN-SR04T), with sensitivities of 0.9943 cm and 0.9831 cm, respectively. The load cell reached an R² of 1 with a sensitivity of 1.0056 kg, while the AD5933 impedance showed R² = 1 and a sensitivity of 0.9999 Ω. Prototype trials with ten samples indicated that blood pressure, BMI, and fat mass measurements were feasible but not yet optimal, with errors in height measurement and limitations in the blood pressure algorithm. Despite these challenges, the successful integration of the sphygmomanometer and BMI–fat analyzer was achieved.
Implementation of EfficientNet-B0-Based Convolutional Neural Network Architecture for Classification of Digital Images of Traditional Spices Muhamad Rafi Raihan Akbar; Bedy Purnama
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 2 (2026): July 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

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

Abstract

Traditional Indonesian spice identification has historically depended on human expertise, a process prone to subjective error and limited scalability. This study evaluates the use of an EfficientNet-B0-based Convolutional Neural Network, incorporating transfer learning and fine-tuning, to automatically classify digital images representing 31 categories of traditional Indonesian spices. The Indonesian Spices Dataset, containing 6,510 images from Kaggle, was divided into 80% training, 10% validation, and 10% testing sets. Data augmentation techniques, such as random horizontal flipping and rotation, were implemented to enhance model generalization and reduce overfitting. The model was trained for over 20 epochs using the AdamW optimizer with cosine learning rate scheduling. Results indicate that the proposed model achieved a test accuracy of 97%, with macro average precision, recall, and F1-score also at 97%. The minimal difference between training and validation accuracy demonstrates robust generalization to unseen data. The model is computationally efficient and suitable for deployment on edge devices, supporting applications in agribusiness for automated spice identification, quality control, and education
Yoga Pose Classification Using Body Landmark-Based Pose Estimation with Mediapipe and Machine Learning Approach Audrey Nasywaa Harimaydina; Bedy Purnama
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 2 (2026): July 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

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

Abstract

Practicing yoga independently without professional supervision can lead to incorrect postures, increasing the risk of injury and reducing exercise effectiveness. Although various studies have utilized pose estimation and machine learning techniques for yoga pose classification, most focus on a single feature representation. This study proposes a static image-based yoga pose classification system using MediaPipe to extract 33 body landmarks, which are transformed into geometric features consisting of landmark coordinates, joint angles, and inter-body point distances. The novelty of this study lies in the systematic evaluation of these features, both individually and in combination, within a Random Forest classification framework. The dataset consists of 1,531 images representing five yoga pose classes: Downward Dog, Goddess, Plank, Tree, and Warrior II. The Random Forest model was optimized using hyperparameter tuning and cross-validation. Experimental results show that combining landmark, angle, and distance features achieved the best performance, with an accuracy of 95.02% and an F1-score of 0.9501. The model also demonstrated stable performance during cross-validation, with accuracy ranging from 0.9436 to 0.9608. The results show that combining multiple geometric feature representations improves yoga pose classification performance while maintaining computational efficiency, supporting safer and more effective self-guided yoga practice
Early Fusion of CNN Features for Multimodal Biometric Authentication from ECG and Fingerprint Using MLP, LSTM, GCN, and GAT Priyatama, Muhammad Abdhi; Nugrahadi, Dodon Turianto; Budiman, Irwan; Farmadi, Andi; Faisal, Mohammad Reza; Purnama, Bedy; Adi, Puput Dani Prasetyo; Ngo, Luu Duc
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 6 (2025): JUTIF Volume 6, Number 6, Desember 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.6.5299

Abstract

Traditional authentication methods such as PINs and passwords remain vulnerable to theft and hacking, demanding more secure alternatives. Biometric approaches address these weaknesses, yet unimodal systems like fingerprints or facial recognition are still prone to spoofing and environmental disturbances. This study aims to enhance biometric reliability through a multimodal framework integrating electrocardiogram (ECG) signals and fingerprint images. Fingerprint features were extracted using three deep convolutional networks—VGG16, ResNet50, and DenseNet121—while ECG signals were segmented around the first R-peak to produce feature vectors of varying dimensions. Both modalities were fused at the feature level using early fusion and classified with four deep learning algorithms: Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Graph Convolutional Network (GCN), and Graph Attention Network (GAT). Experimental results demonstrated that the combination of VGG16 + LSTM and ResNet50 + LSTM achieved the highest identification accuracy of 98.75 %, while DenseNet121 + MLP yielded comparable performance. MLP and LSTM consistently outperformed GCN and GAT, confirming the suitability of sequential and feed-forward models for fused feature embeddings. By employing R-peak-based ECG segmentation and CNN-driven fingerprint features, the proposed system significantly improves classification stability and robustness. This multimodal biometric design strengthens protection against spoofing and impersonation, providing a scalable and secure authentication solution for high-security applications such as digital payments, healthcare, and IoT devices.
PEMANFAATAN KECERDASAN BUATAN (AI) UNTUK MENINGKATKAN EFEKTIVITAS PENGAJARAN DI SMK YPPS SUMEDANG Mahmud Imrona; Bedy Purnama; Rian Febrian Umbara; Dwi Fitrizal Salim
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 3 No. 6 (2025): Desember
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59407/jpki2.v3i6.3184

Abstract

Pengabdian ini bertujuan meningkatkan efektivitas pengajaran guru SMK YPPS Sumedang melalui pemanfaatan kecerdasan buatan (AI) sebagai pendukung penyusunan RPP, pengembangan materi ajar, serta evaluasi pembelajaran yang lebih efisien dan adaptif. Metode pengabdian yang digunakan meliputi observasi kebutuhan, pelaksanaan pelatihan berbasis praktik (workshop), demonstrasi penggunaan berbagai aplikasi AI, simulasi penyusunan perangkat ajar berbasis AI, serta pendampingan intensif dalam pengembangan artefak pembelajaran. Hasil pengabdian menunjukkan bahwa peserta memiliki tingkat penerimaan yang sangat baik, dengan seluruh guru menyatakan setuju hingga sangat setuju bahwa program sesuai kebutuhan, tujuan, serta waktu pelaksanaan. Guru mampu mengintegrasikan AI untuk pembuatan soal, perancangan outline pembelajaran, dan analisis hasil belajar, serta menunjukkan peningkatan literasi digital dan kesiapan etis dalam penggunaan AI. Simpulan dari kegiatan ini adalah bahwa pelatihan AI berhasil meningkatkan kompetensi teknopedagogik guru, memperkuat efektivitas pengajaran vokasional, dan mendukung implementasi pembelajaran berbasis teknologi secara berkelanjutan di SMK YPPS Sumedang.
PELATIHAN PEMANFAATAN KECERDASAN BUATAN UNTUK MERANCANG MODUL AJAR, AKTIVITAS PEMBELAJARAN, DAN ASESMEN PEMBELAJARAN DENGAN PENDEKATAN DEEP LEARNING BAGI GURU- GURU SMPN 6 KARAWANG BARAT Rian Febrian Umbara; Mahmud Imrona; Bedy Purnama
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 4 No. 1 (2026): Februari
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59407/jpki2.v4i1.3446

Abstract

Pemanfaatan kecerdasan buatan (Artificial Intelligence/AI) dalam pendidikan menjadi strategi penting untuk mendukung peningkatan kualitas perencanaan dan pelaksanaan pembelajaran. Teknologi AI memungkinkan guru merancang modul ajar yang lebih sistematis, mengembangkan aktivitas pembelajaran yang adaptif, serta menyusun asesmen berbasis kompetensi secara lebih efisien. Sejalan dengan penerapan Kurikulum Merdeka dan pendekatan deep learning, guru perlu dipersiapkan agar mampu menerapkan pembelajaran bermakna (meaningful learning), reflektif (mindful learning), dan menyenangkan (joyful learning) secara terintegrasi. Program Pengabdian kepada Masyarakat ini bertujuan meningkatkan kompetensi guru-guru SMPN 6 Karawang Barat dalam memanfaatkan AI sebagai alat bantu dan mitra diskusi dalam perancangan modul ajar, aktivitas pembelajaran, dan asesmen berbasis pendekatan deep learning. Kegiatan dilaksanakan melalui metode workshop, praktik langsung, dan pendampingan, dengan melibatkan 28 guru sebagai peserta. Hasil evaluasi menunjukkan tingkat penerimaan dan kepuasan peserta yang sangat tinggi terhadap kesesuaian program dengan tujuan, kebutuhan sasaran, serta kualitas pelaksanaan kegiatan. Pelatihan ini terbukti meningkatkan literasi digital guru dan kepercayaan diri dalam mengintegrasikan AI ke dalam perencanaan pembelajaran. Luaran kegiatan meliputi peningkatan kompetensi teknopedagogik guru, tersusunnya modul ajar berbantuan AI yang relevan dengan Kurikulum Merdeka, serta publikasi hasil kegiatan dalam bentuk artikel jurnal pengabdian kepada masyarakat, media massa institusi, dan video dokumentasi kegiatan. Program ini diharapkan dapat berkontribusi pada penguatan transformasi digital pendidikan dan pengembangan pembelajaran yang lebih adaptif dan berkelanjutan di lingkungan sekolah
Lightweight thermogram classification for diabetic foot screening: A handcrafted-feature and RFE-SVM pipeline for low-resource settings Bedy Purnama; Bayu Erfianto; Linlin Lindayani
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.81

Abstract

Diabetic foot problems continue to be a significant cause of morbidity among people with diabetes, requiring accurate and scalable methods for early identification. Infrared thermography is a non-invasive technique for detecting asymmetry in plantar temperature, which is associated with the risk of inflammation. However, the use of infrared thermography is limited by the small size of labeled datasets in the biomedical domain, posing issues for the generalizability of models and the reliability of validation. In this work we aim at studying the effectiveness of a carefully verified handcrafted-feature based model for diabetic foot thermogram categorization with limited data. The suggested pipeline combines multi-descriptor feature representation, Recursive Feature Elimination (RFE) and margin-based classification by means of Support Vector Machines in a nested cross-validation setting, together with bootstrap stability analysis. Experiments on a publicly accessible plantar thermogram dataset (N = 167) show strong performance with holdout AUC of 0.942 and nested cross-validation AUC of 0.959 ± 0.045. Calibration findings show a low Brier score of 0.065 with balanced sensitivity (0.88) and specificity (0.889). Further study shows that discriminative performance stems from distributed gradient–texture interactions, not sparse feature subsets. The results show that a careful validation and a systematic design of the representation can overcome the limitations of data and allow the development of reliable thermographic screening systems.
Pengembangan Sistem Deteksi Jatuh Ringan Berbasis Pose Estimation Pada Video CCTV Untuk Edge Device Imam Yabunaiya Ramadhani; Bedy Purnama; Mulyantini, Agustien; Satrio, Cahyo Tri
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol. 12 No. 2 (2026): Volume 12 No 2
Publisher : Program Studi Informatika

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

Abstract

Deteksi jatuh merupakan komponen penting dalam sistem pemantauan kesehatan, khususnya bagi lansia dan individu berisiko tinggi. Sebagian besar metode berbasis deep learning membutuhkan sumber daya komputasi yang besar sehingga kurang sesuai untuk perangkat edge. Penelitian ini mengusulkan sistem deteksi jatuh berbasis video yang menggabungkan human pose estimation dan klasifikasi lightweight dalam pipeline terintegrasi yang mencakup preprocessing video, pose estimation, temporal smoothing, ekstraksi fitur kinematik, temporal pooling, dan klasifikasi. Eksperimen dilakukan menggunakan gabungan UR Fall Detection, Le2i, dan Multicam Dataset sebanyak 472 video, dan diuji pada Raspberry Pi 5. Hasil menunjukkan bahwa kombinasi OpenPose Body25 dan Random Forest memperoleh accuracy tertinggi sebesar 89,58% dan F1-score sebesar 92,96%, sedangkan BlazePose Lite dan TinyML memberikan keseimbangan terbaik antara performa klasifikasi dan efisiensi komputasi dengan accuracy sebesar 85,42% dan F1-score sebesar 91,36%.
Co-Authors Abidin, Muhammad Ade Romadhony Adhan Mulya Rahmawan Adhyaksa, Resky Adi, Puput Dani Prasetyo Afandi, Rusdi Agung Toto Wibowo Agustien Mulyantini Ahmad Zatnika Purwalaksana, Ahmad Zatnika Al Farizy, Firnas Al’Fattah, Bimayudha Andi Farmadi Andre Sitompul Angga Rusdinar Aprianti Putri Sujana Audrey Nasywaa Harimaydina Bambang Pudjoatmodjo Bambang Pudjotatmodjo Bayu Erfianto Bramantya Purbaya Danu Hary Prakoso Darmawati, Irma Ditari Salsabila E. Dodi Wisaksono Sudiharto Dodon Turianto Nugrahadi Dwi Fitrizal Salim Edward Ferdian Ema Rachmawati Ema Rachmawati Ema Rachmawati Entik Insanudin Farid Hidayat Fat'hah Noor Prawira Fat’hah Noor Prawira Fat’hah Noor Prawira Fauzi, Roki Fazmah Arif Yulianto Febryanti Sthevanie Ferdian, Edward Furqoon, Naufal Sayyid Gamma Kosala Gibran, Hilal Gryaningrum Widi Pangestuti Hafidz Al Djohari Ifa, Rista Putri Nur Imam Yabunaiya Ramadhani Imamul Akhyar Irwan Budiman Ismail Ismail Koredianto Usman Labib, Fahdi Lindayani, Linlin Linlin Lindayani Mahmud Dwi Sulistiyo Mahmud Imrona Marliani Harahap Muhamad Rafi Raihan Akbar Muhammad Arzaki Muhammad Jendro Yuwono Muhammad Jendro Yuwono Muhammad Nurdin Muhammad Reza Faisal, Muhammad Reza Muhammad Shafhi Kasyfillah Mutiar, Astri Ngo, Luu Duc Pangestu, Arya Priyatama, Muhammad Abdhi Pudjoadmojo, Bambang Purbaya, Bramantya Putra, Bima Andika Putri, Pinkan Amanda Putu Harry Gunawan Rahmawan, Adhan Mulya Reza Dwi Ansari Rian Febrian Umbara Rikman Aherliwan Rudawan Rimba Whidiana Ciptasari Risnandar, Risnandar Rivan Ardyanto Sutoyo Satrio, Cahyo Tri Selly Meliana Setyorini Setyorini Sonia Dian Maniswari Tito Prihambodo Tjokorda Agung Budi Wirayuda Umiatin, Umiatin Wirawan, Ilo Raditio Yuridikta Adha Muslim