Article Per Year (5 Year)
p-Index From 2021 - 2026
2.133
P-Index
This Author published in this journals
All Journal Telematika Jurnal Informatika dan Teknik Elektro Terapan Jurnal Informatika Upgris JITK (Jurnal Ilmu Pengetahuan dan Komputer) JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Community Engagement and Emergence Journal (CEEJ) JOURNAL OF INFORMATION SYSTEM MANAGEMENT (JOISM) Jurnal Algoritma Journal Of Computer Science And Technology Jurnal Medika: Medika
Bagus Adhi Kusuma
Universitas Amikom Purwokerto
Humanities Computer Science & IT Dentistry Economics, Econometrics & Finance Education Environmental Science Health Professions Medicine & Pharmacology Nursing Public Health

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Klasifikasi Kultivar Jambu Semarang Menggunakan MobileNetV2 dengan Pendekatan Transfer Learning Ndaru Febrian Pujo Leksono; Bagus Adhi Kusuma; Andi Dwi Riyanto
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3437

Abstract

Manual identification of Semarang guava cultivars is prone to subjectivity. This study proposes a MobileNetV2 model based on transfer learning to classify 12 cultivars. As an initial study, the main limitation of this research is the very small dataset size, consisting of 192 images with a balanced distribution of 16 images per class. The data were acquired under varied in-the-wild conditions, including differences in background, lighting, and shooting angles. The dataset was divided using a 70 percent training and 30 percent validation ratio. The testing results showed that the validation accuracy reached 94 percent, with an average F1-score of 0.94. However, analysis using the confusion matrix and per-class evaluation showed that the model still experienced difficulties in fine-grained misclassification among visually similar fruits. Considering the small dataset size and the absence of testing using an independent test set or cross-validation, the model’s performance should only be regarded as an initial indication with limited generalizability. In addition, the fine-tuning stage was found to be less significant. As a recommendation, future research should increase the data volume, apply cross-validation testing, and explore architectures with attention mechanisms.
Pendampingan e-Smart Early Warning untuk Peringatan Dini Banjir di Wisata Desa Karangsalam Lor Nandang Hermanto; Pungkas Subarkah; Dini Riandini; Refida Septiana Putri; Salma Ngarifatul Khofiyah; Bagus Adhi Kusuma; Primandani Arsi
Jurnal Medika: Medika Vol. 4 No. 4 (2025)
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/0yyt8272

Abstract

The Juneng Mijil Community Self-Help Group (KSM) in Karangsalam Lor Village, Baturraden District, Banyumas Regency is a village tourism manager, one of which is Juneng Waterfall. The problem with the partners is that there is no technology used for early flood warning at the Juneng Waterfall and Twin Waterfall tourist sites, as well as low community literacy regarding early flood management. This activity aims to optimize the use of Android-based information technology and the Internet of Things (IoT) applied at Juneng Waterfall and Kembar Waterfall, through KSM Juneng Mijil in Karangsalam Lor Village. The implementation methods in this community service include the Pre-Implementation Stage, Implementation Stage, and Evaluation Stage. The results of the activity showed high enthusiasm among participants, as well as an increase in understanding and knowledge regarding the benefits, usage, and maintenance of the Internet of Things (IoT) and Android. This activity is important in the utilization of technology, particularly in optimal and safe flood warning systems for the community.
Hybrid CNN for Sleep Stage Classification Based on EEG Maria Angelina Cahyani Candrakasih; Bagus Adhi Kusuma; Pungkas Subarkah
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12999

Abstract

Sleep stage classification is essential for diagnosing sleep disorders such as insomnia and sleep apnea. However, manual scoring of polysomnography (PSG) is time consuming and subjective. Automatic systems based on single channel EEG are promising for home based monitoring, but they face challenges due to class imbalance and inter subject variability. This study proposes a hybrid model that combines 15 handcrafted features (statistical and spectral) with 128 dimensional features extracted by a one dimensional Convolutional Neural Network (1D CNN), followed by a stacking ensemble (Random Forest and Support Vector Machine as base learners, Logistic Regression as meta learner). Using 40 subjects from the Sleep EDF Expanded dataset, a strict subject independent split (80% train / 20% test) was applied to avoid data leakage. The dataset contained 107,258 epochs with extreme imbalance (Wake 67.6%, N1 2.95%). After SMOTE oversampling on the training set, the model achieved an accuracy of 67.5%, macro F1 score of 31.4%, and Cohen’s Kappa of 0.34. An ablation study showed that CNN features alone (72.2% accuracy) outperformed handcrafted features (70.4%) and hybrid features (67.5%). The confusion matrix revealed that minority stages (especially N1, N3, REM) were poorly recognized. These results highlight that cross subject generalization remains a major challenge in EEG based sleep staging, and proper subject independent validation is critical to avoid overoptimistic claims.
DESIGN OF A PORTABLE DIGITAL SCOLIOMETER BASED ON A MICROCONTROLLER FOR EARLY DETECTION OF SCOLIOSIS Firman Nur Hidayat; Bagus Adhi Kusuma
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 3 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i3.10018

Abstract

Scoliosis is a spinal disorder that is often not detected early, potentially causing postural disorders and more serious complications. Early detection through the measurement of Angle of Trunk Rotation (ATR) using conventional scoliometers still has limitations in terms of portability and reading subjectivity. This study aims to design and build a portable microcontroller-based digital scoliometer capable of measuring ATR values in real-time. The developed system uses an MPU6050 sensor to read body tilt angle, processed with the Kalman Filter method to improve data stability, and an ESP32 microcontroller for data processing and transmission to a web-based system via WiFi protocol. Testing was performed experimentally covering component functionality tests, ATR angle reading tests, and data transmission tests. The test results show that the device can measure ATR values stably at various tilt positions, display data in real-time on an LCD, and successfully transmit 8 out of 10 measurement data to the web server without delay. 2 transmissions experienced 4-second and 10-second delay caused by network instability. Overall, the developed digital scoliometer is proven to function as a practical, portable, and digitally-based scoliosis early detection tool.
Co-Authors Abdul Jahir Agam Purusha Putra Ahmad Bahar Andi Dwi Riyanto Ari Priono Hesti Arief Kurnia Ramadhani Azizan Nurhakim Dini Riandini Dwi Krisbiantoro Fandy Setyo Utomo Firman Nur Hidayat Hendra Marcos Jamie Mayliana Alyza Kuat Indartono Maria Angelina Cahyani Candrakasih Mohd Sanusi Azmi Nandang Hermanto Ndaru Febrian Pujo Leksono Prayoga Pribadi Primandani Arsi Pungkas Subarkah Purwadi Purwadi Refida Septiana Putri Riyanto Riyanto Salma Ngarifatul Khofiyah Sarmini - Sarmini Sitaresmi Wahyu Handani Wiga Maulana Baihaqi Yuli Purwati