Article Per Year (5 Year)
p-Index From 2021 - 2026
5.581
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Jurnal Teliska Bulletin of Electrical Engineering and Informatics Sinergi Annual Research Seminar Proceeding of the Electrical Engineering Computer Science and Informatics VOLT : Jurnal Ilmiah Pendidikan Teknik Elektro Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Journal of Applied Smart Electrical Network and System (JASENS) Jurnal Rekayasa Elektro Sriwijaya International Journal of Research in Vocational Studies (IJRVOCAS) Aptekmas : Jurnal Pengabdian Kepada Masyarakat Sriwijaya Electrical and Computer Engineering (Selco) Journal
Yurni Oktarina
Politeknik Negeri Sriwijaya
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 45 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 45 Documents
Search

 1   2   3   4   5 
Model Deep Learning Hybrid CNN-AE untuk Klasifikasi Presisi Warna Buah Melon Oktarina, Yurni; Dewi, Tresna; Septiyani AR, Dini
Journal of Applied Smart Electrical Network and Systems Vol. 6 No. 2 (2025): Vol. 6 No. 02 (2025): Vol 06, No. 02 Desember 2025
Publisher : Indonesian Society of Applied Science (ISAS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/d3hydf28

Abstract

Melon fruit color classification is a critical step in assessing fruit ripeness and quality. This study proposes a hybrid deep learning model that integrates Convolutional Neural Network (CNN) and Attention Enhancement (AE) for accurate classification of melon fruit color. The model leverages CNN’s strength in visual feature extraction while enhancing focus on crucial image regions through the attention mechanism. A diverse image dataset of melon fruits was collected under various lighting conditions and angles. Pre-processing steps, including data augmentation, normalization, and image scaling, were applied to improve model generalization. The CNN-Attention hybrid architecture incorporates an attention module into the CNN layers to emphasize significant features. Comparative experiments between the standard CNN and the hybrid model demonstrate that the latter achieves superior classification accuracy, with an average improvement of 5%. Moreover, the hybrid model exhibits better robustness against image noise and lighting variations. These results indicate that incorporating Attention Enhancement can yield a more adaptive and reliable model for melon fruit color classification. The proposed approach is expected to support the development of automated systems for fruit sorting in agriculture and distribution, enhancing speed, accuracy, and efficiency for farmers, traders, and consumers.
IMPLEMENTASI ALGORITMA POLYNOMIAL REGRESSION UNTUK PREDIKSI PERTUMBUHAN TANAMAN PAKCOY PADA SISTEM HIDROPONIK Yurni Oktarina; Rendi Dwi Yanto; Tresna Dewi
JURNAL TELISKA Vol 19 No I (2026): TELISKA Maret 2026
Publisher : Teknik Elektro Polsri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/teliska.v19iI.11816

Abstract

This study aims to apply the polynomial regression algorithm to model and predict the growth of pakcoy plants in a hydroponic system. The observed growth parameters include plant height, plant width, and number of leaves, with plant age used as the independent variable. Data were collected over two planting periods, with weekly observations conducted from the seedling stage until harvest. In addition to morphological parameters, Total Dissolved Solids (TDS) and water temperature were recorded as supporting parameters to ensure stable cultivation conditions throughout the study. The non-linear relationship between growth parameters and plant age was represented using a second-order polynomial regression model. The modeling results indicate a good level of fit, with coefficients of determination (R²) of 0.989 for plant height, 0.946 for plant width, and 0.970 for number of leaves, respectively. The relatively low Root Mean Square Error (RMSE) values for each parameter indicate that the model is capable of providing predictions with low estimation error. These findings demonstrate that second-order polynomial regression is a simple and effective approach for modeling the growth dynamics of pakcoy plants in hydroponic systems with limited data availability
PREDIKSI PEMANENAN ENERGI PADA ARRAY PIEZOELEKTRIK KONFIGURASI SERI-PARALEL BERBASIS RANDOM FOREST REGRESSION Fairuz Attalah; Yurni Oktarina; Pola Risma; Assyifa Mourlina Faraquinsha; Hendra Marta Yudha
JURNAL TELISKA Vol 19 No I (2026): TELISKA Maret 2026
Publisher : Teknik Elektro Polsri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/teliska.v19iI.11829

Abstract

This study analyses the electrical characteristics and predicts the power output of a piezoelectric smart carpet system through a comparative analysis of series and parallel circuit configurations using the Random Forest Regression (RFR) algorithm. The system was designed using 16 piezoelectric ceramic elements per block integrated into a 100 cm carpet structure. Experimental data were collected from five subjects with body masses ranging from 54–98 kg through walking and running activities, yielding 100 observational samples. Results show the series configuration produced an average power output of 1649.3 mW, outperforming the parallel configuration by 104.8%, which yielded only 805.1 mW, with peak voltage reaching 80 V during running. The RFR model optimized using GridSearchCV with 5-fold cross-validation achieved a coefficient of determination (R²) of 88.25%, a Mean Absolute Error (MAE) of 145.06 mW, and a Root Mean Squared Error (RMSE) of 179.15 mW. Feature importance analysis revealed that circuit configuration (47.59%) and step frequency (47.18%) are the dominant predictive factors, while body mass contributed only 5.22% due to mechanical saturation in the carpet structure. This study confirms that RFR is effective as a predictive model for optimizing biomechanical energy harvesting systems in public infrastructure.
Multistage Fertile Egg Prediction via Texture Using Convolutional Neural Network Bimo, Muhammad; Dewi, Tresna; Maulidda, Renny; Oktarina, Yurni; Risma, Pola; Yudha, Hendra Marta
Jurnal Rekayasa Elektro Sriwijaya Vol. 7 No. 2 (2026): Jurnal Rekayasa Elektro Sriwijaya
Publisher : Jurusan Teknik Elektro Fakultas Teknik Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/q58ezz91

Abstract

Accurate early detection of egg fertilisation status is necessary for effective incubation management in chicken production in order to avoid energy waste and decreased hatchery productivity brought on by infertile or non-viable eggs. Due to their comparable perceptual traits, conventional candling inspection relied on manual observation, which introduced subjectivity and made it challenging to distinguish between fertilised and blighted eggs early on. This study suggested an automated multistage fertilisation prediction method based on candling image analysis, utilising a convolutional neural network framework to get around this restriction. Rather than using traditional binary classification, the suggested system allowed for progressive monitoring of embryonic growth. On incubation days 1, 7, 14, and 21, candling photos were taken from native chicken eggs and classified into three groups: fertilised, infertile, and blighted. To enhance feature extraction efficiency under constrained dataset conditions, a transfer learning technique utilising the MobileNetV2 architecture was implemented. To guarantee consistent learning performance, image preprocessing, augmentation, model training, and validation were carried out. Precision, recall, F1-score, and classification accuracy were used as assessment measures. According to experimental findings, the suggested model produced consistent classification results for both fertilised and infertile eggs, with validation accuracy ranging from 90 to 95% throughout the incubation period. The results of multistage prediction showed consistent decision-making throughout the observation of embryo development. However, during intermediate incubation stages, visual uncertainty with fertilised eggs led to decreased performance in recognising blighted eggs. All things considered, the suggested method showed great promise as a nondestructive intelligent system for early fertilisation prediction. To increase the accuracy of blighted egg classification, more dataset expansion and model improvement were still required.
Benchmarking YOLOv8 and vision transformers for intelligent fish monitoring in aquaponics and controlled aquarium environments Tresna Dewi; Yurni Oktarina; Sri Rezki Artini; Gita Ayu Julianka; Jhoni Satria
SINERGI Vol. 30 No. 2 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.2.022

Abstract

Sustainable aquaculture requires reliable and accurate fish monitoring systems capable of operating across heterogeneous environmental conditions. Conventional monitoring approaches are labor-intensive and prone to human error, while recent advances in deep learning have enabled vision-based automation for aquatic environments. Convolutional object detectors such as YOLO and emerging Vision Transformer (ViT) models have demonstrated promising performance; however, most existing studies remain limited to single-environment evaluations and rarely address energy-constrained, real-world deployment. To bridge this gap, this study presents a systematic benchmark of YOLOv8 and ViT across two complementary settings: a controlled aquarium environment and a solar-powered, off-grid aquaponics system. The proposed framework integrates 1080p CCTV video acquisition, dataset annotation and augmentation, and standardized training and evaluation using COCO metrics. Experimental results show that ViT consistently outperforms YOLOv8 in detection accuracy and prediction stability across both environments. ViT achieves 99.73% accuracy in the controlled aquarium and ≥99.6% accuracy performance (99.68–99.73%) in aquaponics, while YOLOv8 records 87.90% accuracy in the aquarium and 93.92–97.92% across aquaponics fish classes, exhibiting higher sensitivity to background clutter. Statistical validation using McNemar’s test (p < 0.001) confirms that these differences are statistically significant. Beyond accuracy, the results reveal a trade-off between robustness and computational efficiency. ViT provides superior resilience under occlusion and glare, whereas YOLOv8 offers faster inference suitable for real-time operation on resource-limited edge devices. End-to-end deployment on a solar-powered NVIDIA Jetson Xavier NX demonstrates the feasibility of continuous, off-grid aquaculture monitoring and provides practical guidance for context-aware model selection in intelligent aquaculture systems.
Co-Authors Ahmad Fudholi Alkausar, Muhammad Fajri Amperawan Amperawan Anggraini, Citra Assyifa Mourlina Faraquinsha Auliya, Annisa Azhar, M. Sayid Bambang, Muhammad Refo Bhakti Yudho Suprapto Bimo, Muhammad Citra Anggraini Dadi Setiadi Daniesar, Muhammad Nouval Destri Zumar Sastiani Dewi, Tresna Dewi, Tresna Dewi Dicky Astra Yudha Edo Triyandi Evelina Ginting Fairuz Attalah Gita Ayu Julianka Hendra Marta Yudha Husni, Nyayu Latifah Jhoni Satria Juwita, Aulia Ratna Liwijaya, Angga Lukman Nul Hakim M. Nawawi Mardiyati, Elsa Nurul Mayastri Devana Muhammad Dede Yusuf Muhammad Nawawi Muhammad Ridho Kenawas Muhammad Taufik Roseno Mulya, Zarqa Muslikhin Nawawi, M. Neta Larasati Noer, Mohammad Nawawi Nur Aina Okta Ferrisa Pola Risma Pratama, Yudha Wira Putri Repina Kesuma Rahman, Raihan Aldiaz Rapli Wijaya RD Kusumanto RD Kusumanto Rendi Dwi Yanto Renny Maulidda, Renny Rinaldi Rinaldi Riyo Irawan Ronald Sukwadi Rusdianasari Rusdianasari Sakuraba, Takahiro Sastiani, Destri Zumar SELAMET MUSLIMIN Septiyani AR, Dini Siproni Umar Siti Afiyah Qatrunnada Solly Aryza Sri Rezki Artini Sri Rezki Artini Tresna Dewi Tresna Dewi Tresna Dewi Tulak, Windy Gafrila Wahju, Marsellinus Bachtiar Windy Gafrila Tulak Yolanda Eka Pratiwi Yudha Wira Pratama Yudi Wijanarko, Yudi Zainuddin Nawawi Zarqa Mulya