Article Per Year (5 Year)
p-Index From 2021 - 2026
3.147
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Jurnal INKOM Jurnal Edukasi dan Penelitian Informatika (JEPIN) Scientific Journal of Informatics Sistemasi: Jurnal Sistem Informasi Sinkron : Jurnal dan Penelitian Teknik Informatika International Journal of Artificial Intelligence Research Jurnal Informatika JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Pilar Nusa Mandiri Techno Nusa Mandiri : Journal of Computing and Information Technology Techne : Jurnal Ilmiah Elektroteknika Jurnal Pertanian Agros Jurnal Informatika Universitas Pamulang Indonesian Physical Review INTI Nusa Mandiri JATI EMAS (Jurnal Aplikasi Teknik dan Pengabdian Masyarakat) International Journal of Advances in Data and Information Systems Jurnal Pengabdian kepada Masyarakat Nusantara Insyst : Journal of Intelligent System and Computation Prosiding Konferensi Nasional Penelitian Matematika dan Pembelajarannya Seminar Nasional Riset dan Teknologi (SEMNAS RISTEK)
Agus Subekti
Balai Pengkajian Teknologi Pertanian Kalimantan Barat Jalan Budi Utomo No. 45, Siantan Hulu, Kotak Pos 6150, Pontianak 78061, Kalimantan Barat, Indonesia
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Mathematics Physics Public Health Social Sciences Other

Published : 30 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 30 Documents
Search

 1   2   3 
OPTIMIZING ELECTRON DIFFUSION, TEMPERATURE, AND PHOTOANODE THICKNESS FOR ENHANCED PHOTOVOLTAIC EFFICIENCY IN TiOâ‚‚/CuS DYE-SENSITIZED SOLAR CELLS (DSSCs) Muhammad, Nawafil; Supriyanto, Edy; Prasetya, Dwi Sabda Budi; Setyaningsih, Emy; Subekti, Agus
Indonesian Physical Review Vol. 8 No. 1 (2025)
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/ipr.v8i1.413

Abstract

This study addresses a critical gap in optimizing electron diffusion, operational temperature, and photoanode thickness to enhance the photovoltaic efficiency of TiO₂/CuS-doped dye-sensitized solar cells (DSSCs). While previous studies have investigated individual parameters affecting DSSC performance, limited research examines their combined effects on charge transport and recombination rates. Through computational modeling, we evaluated photoanode thicknesses from 1 µm to 100 µm and operational temperatures from 260 K to 350 K, analyzing their influence on electron mobility, recombination rates, and overall efficiency. Results show that the electron diffusion coefficient increases with temperature, reaching a maximum of 1.626 × 10⁻⁶ cm²/s at 350 K, thereby enhancing electron transport and reducing recombination losses. An optimal photoanode thickness of 3 µm was identified, yielding the highest efficiency of 17.28% across the temperature range. Efficiency declines at thicknesses exceeding 3 µm due to extended electron diffusion paths and higher recombination rates. These findings underscore the importance of balancing temperature and structural parameters to improve charge transport and minimize losses, particularly for DSSC applications in warm environments.
KERAGAAN ENAM VARIETAS UNGGUL BARU PADI KHUSUS PADA LAHAN SUB OPTIMAL DI KALIMANTAN BARAT Subekti, Agus; Umar, Abdullah
Agros Journal of Agriculture Science Vol 25, No 1 (2023): edisi JANUARI
Publisher : Fakultas Pertanian, Universitas Janabadra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37159/jpa.v25i1.2426

Abstract

Kebutuhan beras nasional terus mengalami peningkatan seiring dengan pertambahan jumlah penduduk. Selain berfungsi sebagai sumber utama karbohidrat, beras juga menjadi makanan dengan fungsi khusus terutama untuk kesehatan. Konsumsi beras yang memiliki Indeks Glikemik (IG) rendah sebagai makanan pokok dipercaya baik bagi penderita diabetes. Selain itu beras yang memiliki kandungan seng (Zn) dan antioksidan yang tinggi sangat berguna bagi penderita stunting dan gizi buruk. Beberapa varietas unggul baru (VUB) padi khusus hasil inovasi Badan Litbang Pertanian memiliki keunggulan dalam hal aroma, warna, atau kandungan nutrisi untuk mengatasi atau melengkapi kekurangan zat tertentu dalam tubuh. Dengan mempertimbangkan manfaat padi khusus bagi kesehatan, maka perlu dilakukan uji coba VUB padi khusus di Kalimantan Barat. Uji coba ini bertujuan untuk mengidentifikasi keragaan agronomi dan hasil VUB padi khusus pada lahan sub optimal. Metode penelitian menggunakan rancangan acak kelompok, dengan perlakuan berupa enam VUB padi khusus yaitu Arumba, Jeliteng, Baroma, Tarabas, Inpago 13 fortiz, dan Inpari IR Nutri Zinc, dengan lima ulangan. Uji coba Penelitian ini dilaksanakan di Desa Pal IX, Kecamatan Sungai Kakap, Kabupaten Kubu Raya, Kalimantan Barat, dengan jenis tanah Aluvial. Hasil uji coba  menunjukkan bahwa VUB padi khusus Inpari IR Nutri Zinc memiliki produktivitas 4,5 t/ha, produktivitas ini lebih tinggi dan berbeda nyata dibandingkan VUB padi khusus lainnya. VUB padi khusus Inpari IR Nutri Zinc cocok untuk dikembangkan pada lahan sub optimal pasang surut di Kalimantan Barat.
Texture Features of Aglaonema Leaves with Local Binary Pattern Code Nugroho, Agung Tjahjo; Nursulistyono, Yuda; Cahyono, Bowo Eko; Subekti, Agus
Sistemasi: Jurnal Sistem Informasi Vol 13, No 4 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i4.4180

Abstract

The Aglaonema type and quality is difficult to identify due to leaf pattern variety. For this reason, a technique is developed to classify Aglaonema types from leaf images. The Aglaonema is identified using the Local Binary Pattern (LBP) technique. The LBP recognizes objects in the form of pixel neighbor patterns in binary code, which is sensitive to the radius (R) and the number of neighbors (P) pixels. In this article we will study the appropriate radius and number of neighbors so that the LBP code becomes an accurate abject texture attribute. Experimentally, R is varied from 1 to 5 while P is varied from 4 to 24 pixels. Two types of Aglaonema with two varieties taken from each type were used to test the accuracy of the LBP code. The accuracy of the classification results is carried out with the help of K-Nearest Neighbors (KNN). The results show that the greater the number of neighbors in determining the LBP code, the more accurate the classification results. Neighbors with a total of 18 have a stable accuracy reaching a total of 79%. Increasing the number of neighbors does not significantly affect accuracy. The neighbor radius affects the batik type of Aglaonema, the wider the neighbor area, the accuracy increases up to 84%, but for the Lipstick type, the best accuracy is obtained when R=3. By choosing the right R and P, the types of Aglaonema batik and Lipstick can be differentiated well.
VISUAL HISTORICAL DATA-BASED TRAFFIC MOVEMENT AND DENSITY PATTERN EXTRACTION FOR ADAPTIVE PATTERN DETECTION BASE ON VEHICLE TYPE Angellia, Filda; Merlina, Nita; Subekti, Agus; Handayanto, Rahmadya Trias
International Journal of Artificial Intelligence Research Vol 9, No 1.1 (2025)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v9i1.1.1570

Abstract

Traffic congestion in urban areas has become a crucial issue, impacting time efficiency, energy consumption, and quality of life. One of the main causes of difficulties in traffic management is the lack of optimal predictive systems capable of detecting and adaptively responding to vehicle movement patterns. This study proposes a historical digital image-based approach to extract traffic movement patterns and density based on vehicle type and dimensions. The developed model utilizes historical traffic video footage from CCTV systems as a visual data source, which is then processed using the YOLOv5 algorithm to detect the number, size, and type of vehicles. After the detection process, vehicle information is converted into a sequential format that reflects vehicle movement in the temporal dimension. This data is then analyzed using a Long Short-Term Memory (LSTM) model to generate traffic density prediction patterns. This study also compares the performance of LSTM with other algorithms such as Random Forest and XGBoost in terms of prediction accuracy. Model evaluation is conducted using MSE and RMSE metrics to measure accuracy against actual data.The research results show that the integration of dimension-based vehicle detection with a visual historical data-driven prediction approach can improve the accuracy and flexibility of modeling future traffic conditions. This approach significantly contributes to the development of intelligent transportation systems that can adapt to dynamic environmental conditions and traffic patterns
Evaluasi Kinerja Model Machine Learning dalam Cross-Project Defect Prediction Menggunakan Library PyCaret Hidayat, Rian; Subekti, Agus
Techné : Jurnal Ilmiah Elektroteknika Vol. 24 No. 2 (2025)
Publisher : Fakultas Teknik Elektronika dan Komputer Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31358/techne.v24i2.603

Abstract

Cross Project Defect Prediction (CPDP) is used to overcome the limitation of training data on new projects. This study tests the performance of machine learning models (Random Forest, CatBoost, Logistic Regression, KNN, SVM) in a CPDP scenario with the AEEEM dataset, comparing results before and after hyperparameter adjustment. Models were tested using a one-to-many CPDP architecture, with evaluation metrics of Accuracy, AUC, Recall, Precision, and F1-Score. As a result, Random Forest excels in 9 out of 20 prediction combinations, followed by CatBoost which is best in 4 combinations after tuning. KNN and SVM won in 3 and 2 combinations respectively, while Logistic Regression only excelled in 2 combinations. Hyperparameter tuning improved the performance of all models except Logistic Regression, with SVM improving most significantly (6.39%), followed by KNN (3.94%), RF (5.14%), and CatBoost (1.4%). Project combinations such as LC ? EQ, ML ? EQ, and PDE ? EQ performed well, demonstrating the effectiveness of CPDP when projects are similar. In contrast, combinations such as EQ ? ML and ML ? LC performed poorly due to differences in data distribution. This study concludes that CPDP is effective for software defect prediction when local data is limited, and can be the basis for further research such as transfer learning or project selection based on semantic similarity.
Multi View Neural Network for Software Effort Estimation Prediction Setiawan, Boy; Subekti, Agus
Intelligent System and Computation Vol 7 No 2 (2025): INSYST: Journal of Intelligent System and Computation
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52985/insyst.v7i2.442

Abstract

Software Effort Estimation (SEE) is a critical challenge in software project management, dating back to the early years of software engineering. Accurate estimation of the effort required for software development is essential for project planning, resource allocation, and risk management. Incorrect effort estimates can result in poor resource distribution, cost overruns, missed deadlines, and even complete project failure. This issue is increasingly urgent today as software systems are deeply embedded in almost every product and service, amplifying the need for reliable and accurate predictions. Over the years, several methods for SEE have been proposed, ranging from algorithmic models to expert judgment. More recently, machine learning (ML) approaches such as Case-Based Reasoning (CBR), Support Vector Machines (SVM), Decision Trees (DT), and Neural Networks (NN) have gained attention for their ability to model complex, nonlinear relationships inherent in SEE tasks. In this study, we propose a novel approach based on multi-view learning with NN (MVNN), which leverages multiple views from existing datasets, thus improving performance and generalization, particularly when the available data is small and scarce. The effectiveness of the MVNN model is validated through empirical comparisons with existing SEE models, demonstrating its potential to enhance SEE accuracy and improve prediction reliability.
Performance analysis of OFDM-IM scheme under STO and CFO Suyoto, Suyoto; Subekti, Agus; Satyawan, Arief Suryadi; Mardiana, Vita Awalia; Armi, Nasrullah; Kurniawan, Dayat
International Journal of Electrical and Computer Engineering (IJECE) Vol 11, No 4: August 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v11i4.pp3293-3299

Abstract

In this letter, performance analysis of orthogonal frequency division multiplexing with index modulation (OFDM-IM) is presented in term of bit error rate (BERs). The analysis considers its performance under two impairments, symbol time offset (STO) and carrier frequency offset (CFO) in frequency-selective fading channel. As orthogonal multicarrier system, OFDM-IM is subject to both inter-symbol interference (ISI) and inter-carrier interference (ICI) in a frequency-selective fading channel. OFDM-IM is a new multicarrier communication system, where the active subcarriers indices are used to carry additional bits of information. In general, in the previous existing works, OFDM-IM are evaluated only for near-ideal communication scenarios by only incorporating the CFO factor. In this work, the OFDM-IM performance is investigated and compared with conventional OFDM in the presence of two impairments, STO and CFO. Simulation results show that OFDM-IM outperforms the conventional OFDM with the presence of STO and CFO, especially at high SNR areas.
Impact of carrier frequency offset and in-phase and quadrature imbalance on the performance of wireless precoded orthogonal frequency division multiplexing Suyoto, Suyoto; Subekti, Agus; Satyawan, Arief Suryadi; Armi, Nasrullah; Ali Wael, Chaeriah Bin; Nurkahfi, Galih Nugraha
International Journal of Electrical and Computer Engineering (IJECE) Vol 12, No 5: October 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v12i5.pp5153-5163

Abstract

Precoding in orthogonal frequency division multiplexing (OFDM) system proved to reduce the peak-to-average power ratio (PAPR), so that it improves BER. However, from the existing literature, the effect of carrier frequency offset (CFO), in-phase and quadrature (IQ) imbalance on precoded wireless OFDM systems has not been carried out. Therefore, this study evaluated the precoded OFDM (P-OFDM) system performance by considering the impact of CFO and IQ imbalance. P-OFDM performance evaluation is expressed in signal-to-interference noise ratio (SINR) and bit error rates (BER). The communication channels used are the additive white Gaussian noise (AWGN) channel and the frequency-selective Rayleigh fading (FSRF) channel, while the channel equalization process is considered perfect. The results of the analysis and simulation show that P-OFDM is greater affected by the presence of CFO and IQ imbalance than conventional OFDM system. In AWGN channel, P-OFDM experiences different SINR for each subcarrier. This is different from conventional OFDM system, where all SINRs are the same for all subcarriers. In the FSRF channel, both the POFDM system and the OFDM system experience different SINR for each subcarrier, where the SINRs fluctuation in the P-OFDM system is much larger than in the OFDM system.
A Comparative Methodological Study of Automated Machine Learning for Multiclass Stunting Prediction Using Anthropometric Data Joharini, Joharini; Subekti, Agus
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 2 (2026): Article Research April, 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i2.15886

Abstract

Stunting remains a major public health challenge among children under five years old and requires reliable early screening to support timely nutritional interventions, particularly in resource-limited healthcare settings. However, many existing stunting prediction studies rely on complex socio-economic variables and manually selected machine learning models, which limits reproducibility and practical deployment. This study proposes an automated machine learning (AutoML)–based framework for multiclass stunting prediction using routinely collected anthropometric data. The prediction task is formulated as a multiclass classification problem encompassing normal growth, stunted, severely stunted, and above-normal nutritional status. The proposed framework integrates standardized preprocessing, systematic model comparison, stratified 10-fold cross-validation, and controlled hyperparameter optimization, evaluated under SMOTE and non-SMOTE preprocessing scenarios. Experimental results demonstrate that reliable multiclass prediction can be achieved without socio-economic variables. Under SMOTE preprocessing, the optimized k-Nearest Neighbors model improves minority-class sensitivity, increasing accuracy from 0.9806 to 0.9820 with an MCC of 0.9688, while under non-SMOTE conditions, Random Forest achieves robust performance with an accuracy of 0.9985 and an MCC of 0.9975 without resampling. Confusion matrix, ROC, and learning curve analyses confirm strong discriminative capability and stable generalization for both models. Overall, the findings indicate that the proposed AutoML-based framework provides a practical, scalable, and reproducible solution for early multiclass stunting screening using anthropometric data alone.
Deep Learning Approach for Earthquake Detection and Classification using MobileNet V2 Transfer Learning Siregar, Giel Utami Putri; Subekti, Agus; Rozaq, Hasri Akbar Awal; Yildiz, Oktay
International Journal of Advances in Data and Information Systems Vol. 7 No. 1 (2026): April 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i1.1400

Abstract

Earthquake detection is a critical component of disaster management, as early identification of seismic events can help mitigate potential damage and support timely response efforts. This study evaluates the application of deep learning for binary earthquake detection using a lightweight Convolutional Neural Network (CNN) based on the MobileNetV2 architecture. The experiments were conducted using seismic waveform data from the Stanford Earthquake Dataset (STEAD), which were transformed into time–frequency representations through the Short-Time Fourier Transform (STFT). Spectrogram images derived from the seismic signals were used as input to the CNN models. Transfer learning was applied to MobileNetV2 to adapt the pretrained architecture to the earthquake detection task. The proposed approach achieved an accuracy of 99%, precision of 100%, recall of 97.96%, and an F1-score of 98.97% on the test dataset. In terms of model complexity, MobileNetV2 has 7,176,600 total parameters and 1,639,538 trainable parameters, indicating a favorable balance between performance and computational efficiency. For comparative evaluation, MobileNetV2 was benchmarked against several commonly used CNN architectures, including CNN Vanilla, MobileNetV1, VGG16, and ResNet, under the same experimental conditions. The results indicate that MobileNetV2 provides competitive detection performance while maintaining a significantly smaller model size. Although real-time deployment on mobile devices was not implemented in this study, the findings suggest that lightweight CNN architectures, such as MobileNetV2, hold promise for future earthquake detection systems operating in resource-constrained environments.
Co-Authors A.A. Ketut Agung Cahyawan W Abdullah Umar, Abdullah Aditya, Dedy Yusuf Agung Tjahjo Nugroho Akhmad Syukron Andra, Muhammad Bagus Ari Setiawan Arumjeni Mitayani Aryono Adhi, Aryono Bowo Eko Cahyono Chaeriah Bin Ali Wael, Chaeriah Bin Dayat Kurniawan Devi Wulandari Diantika, Sri Edy Supriyanto Emy Setyaningsih Eni Heni Hermaliani, Eni Heni Faisal, Anas Filda Angellia Haerul Fatah Heriyani, Novia Hidayat Teguh Wiyono Hiya Nalatissifa Indriyanti Indriyanti, Indriyanti Joharini, Joharini Kahar Muzakhar Khultsum, Umi Kusmayadi, Kusmayadi Kusumah, Maulana S. Lukman, Arif M. Rangga Ramadhan Saelan Mardiana, Vita Awalia Mareanus Lase Marta Dinata, Mochamad Mardi MUHAMMAD HARIS Muhammad, Nawafil Nasrullah Armi Nita Merlina, Nita Nufus, Fina Sifaul Nurkahfi, Galih Nugraha Nursulistyono, Yuda Nurul Priyantari Prasetya, Dwi Sabda Budi Purwoko Adhi Rahmadya Trias Handayanto Rian Hidayat Rozaq, Hasri Akbar Awal Satyawan, Arief Suryadi Setiawan, Boy Siregar, Giel Utami Putri Siti Helmyati Sugara, Bayu Supriyadi Supriyadi Suryanto, Wiwit Suyoto Suyoto Wahyudi Wahyudi Winarsa, Rudju YILDIZ, Oktay