Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal EMITTER International Journal of Engineering Technology Jurnal Rekayasa Elektro Sriwijaya
Lukman Nul Hakim
Politeknik Negeri Sriwijaya
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Model Prediksi Deep Learning dengan Pendekatan Feedforward Neural Network Lukman Nul Hakim; Tresna Dewi; Pola Risma; Yurni Oktarina
Jurnal Rekayasa Elektro Sriwijaya Vol. 6 No. 2 (2025): 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/jres.v6i2.158

Abstract

Penelitian ini bertujuan untuk menerapkan model deep learning, khususnya Feedforward Neural Network (FNN), dalam meramalkan nilai irradiance berdasarkan data waktu. Solar irradiance sangat penting dalam pengembangan sistem energi terbarukan seperti panel surya untuk meningkatkan efisiensi sistem tenaga surya dan mengoptimalkan perencanaan sumber daya energi. Penggunaan model ini diharapkan dapat memberikan prediksi yang lebih akurat dan handal, sehingga mendukung pengambilan keputusan dalam pengelolaan energi terbarukan secara berkelanjutan. Untuk meningkatkan akurasi prediksi, penelitian ini menerapkan teknik preprocessing data yang mencakup penghapusan nilai hilang dan normalisasi menggunakan MinMaxScaler guna meningkatkan stabilitas pelatihan model. Model FNN yang diusulkan terdiri dari beberapa lapisan tersembunyi dengan aktivasi non-linear untuk menangkap pola kompleks dalam data, serta lapisan output untuk menghasilkan prediksi akhir. Pelatihan model dilakukan menggunakan algoritma optimasi seperti Adam, dengan fungsi aktivasi ReLU untuk meningkatkan konvergensi. Evaluasi model dilakukan menggunakan metrik RMSE, MSE, MAE, dan R-squared (R²) sebagai indikator utama keakuratan model dalam peramalan irradiance. Hasil evaluasi menunjukkan bahwa model ini mampu memberikan prediksi yang akurat terhadap pola irradiance, dengan nilai RMSE dan MAE yang rendah serta R² mendekati satu, menandakan kinerja yang sangat baik dalam menangkap dinamika data.
Exploring YOLO-Based Deep Learning Approaches for Fish Detection in Intelligent Aquatic Monitoring Systems Tresna Dewi; Riyo Irawan; Agum Try Wardhana; Muhammad Amri Yahya; Lukman Nul Hakim; Dini Septiyani AR
EMITTER International Journal of Engineering Technology Vol 14 No 1 (2026)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v14i1.1007

Abstract

The Advancements in precision aquaculture demand robust visual monitoring systems capable of accurate, real-time fish detection in complex underwater environments characterized by turbidity, occlusion, and dynamic illumination. While YOLO (You Only Look Once) architectures have demonstrated high efficiency in object detection tasks, their comparative performance for underwater fish detection remains underexplored, particularly across recent variants such as YOLOv5, YOLOv8, and YOLOv11. This study presents a systematic evaluation of three state-of-the-art YOLO models using a curated GlowFish dataset consisting of 533 annotated images across three fluorescent species. Data were acquired under controlled but visually diverse conditions using multi-angle imaging and standardized illumination. A uniform training pipeline, consistent annotation using the COCO format, and identical hyperparameters were applied across models to ensure fair benchmarking. Key evaluation metrics include precision, recall, mAP@0.5, and mAP@0.5:0.95. Experimental results reveal that YOLOv5 achieved the highest precision (0.963) and mAP@0.5 (0.967), while YOLOv8 delivered superior recall (0.930) and more balanced detection across species classes. YOLOv11 demonstrated architectural potential but showed greater sensitivity to class imbalance and reduced confidence stability. Visual analysis and confusion matrices further confirmed model-specific trade-offs in classification reliability and localization precision. This work contributes critical empirical insights into the selection of YOLO architectures for intelligent aquaculture systems, offering practical guidance for real-time aquatic monitoring deployments. Future research will extend this framework to multi-species, multi-environment datasets, integrate spatiotemporal behavioral tracking, and investigate deployment on resource-constrained edge-AI platforms, advancing the field toward interpretable and autonomous aquatic monitoring solutions.
Co-Authors Agum Try Wardhana Dini Septiyani AR Muhammad Amri Yahya Pola Risma Riyo Irawan Tresna Dewi Yurni Oktarina