cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fajril Akbar
Contact Email
ijab@fti.unand.ac.id
Phone
+627517770
Journal Mail Official
teknosi@fti.unand.ac.id
Editorial Address
Jurusan Sistem Informasi, Fakultas Teknologi Informasi Universitas Andalas Kampus Limau Manis, Padang 25163, Sumatera Barat
Location
Kota padang,
Sumatera barat
INDONESIA
Jurnas Nasional Teknologi dan Sistem Informasi
Published by Universitas Andalas
ISSN : 24768812     EISSN : 24603465     DOI : https://dx.doi.org/10.25077/TEKNOSI
Core Subject : Science,
Computer Science & IT Decision Sciences, Operations Research & Management
Jurnal ini menerbitkan artikel penelitian (research article), artikel telaah/studi literatur (review article/literature review), laporan kasus (case report) dan artikel konsep atau kebijakan (concept/policy article), di semua bidang : Geographical Information System, Enterpise Application, Bussiness Intelligence, Data Warehouse, Network Computer Security, Data Mining, Computer Architecture Design, Mobile Computing, Computing Theory, Embedded system, Decision Support System
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 424 Documents
 39   40   41   42   43 
Systematic Literature Review: Optimasi Model Klasifikasi pada Imbalanced Data Menggunakan SMOTE, Hyperparameter Tuning, dan Ensemble Learning Muhammad Alfin Ghozali; Agus Bahtiar
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 2 (2026): Agustus 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i2.2026.350-362

Abstract

Imbalanced Data merupakan salah satu permasalahan utama dalam pengembangan model klasifikasi karena menyebabkan model cenderung mempelajari kelas mayoritas sehingga kemampuan mendeteksi kelas minoritas menjadi menurun. Berbagai pendekatan, seperti Synthetic Minority Oversampling Technique (SMOTE), Hyperparameter Tuning, dan Ensemble Learning, telah dikembangkan untuk meningkatkan performa model pada kondisi tersebut. Penelitian ini bertujuan menganalisis karakteristik penelitian, mengkaji penerapan SMOTE, Hyperparameter Tuning, dan Ensemble Learning, serta mengidentifikasi Research Gap dalam optimasi model klasifikasi pada Imbalanced Data. Penelitian menggunakan metode Systematic Literature Review (SLR) dengan mengacu pada pedoman PRISMA 2020. Proses kajian meliputi penyusunan Research Question, pencarian literatur pada basis data Scopus, seleksi artikel berdasarkan kriteria inklusi dan eksklusi, Quality Assessment, ekstraksi data, serta sintesis hasil. Sebanyak 14 artikel yang memenuhi kriteria ditetapkan sebagai Primary Studies. Hasil sintesis menunjukkan bahwa SMOTE merupakan teknik yang paling banyak digunakan untuk menangani Imbalanced Data, sedangkan Hyperparameter Tuning berperan dalam memperoleh konfigurasi model yang optimal melalui pendekatan seperti Optuna dan Bayesian Optimization. Selain itu, Ensemble Learning, khususnya Stacking dan Soft Voting, banyak diintegrasikan dengan teknik optimasi lainnya untuk meningkatkan akurasi, stabilitas, dan kemampuan generalisasi model. Penelitian ini menyimpulkan bahwa integrasi SMOTE, Hyperparameter Tuning, dan Ensemble Learning menjadi pendekatan yang dominan dalam optimasi model klasifikasi pada Imbalanced Data. Penelitian juga mengidentifikasi peluang pengembangan pada aspek interpretabilitas model, efisiensi komputasi, serta pengembangan kerangka optimasi yang lebih terintegrasi.
Development of a Real-time Solar Panel Power Prediction Model Using the Long Short-term Memory Christio Revano Mege; Ferizandi Qauzar Gani; Amrina Mustaqim; Listra Yehezkiel Ginting; Hesti Wahyu Handani; Jodes Parasian Simatupang; Friska Hasugian
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 2 (2026): Agustus 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i2.2026.363-368

Abstract

Indonesia’s remote islands face significant challenges in electricity access due to the high cost and logistical difficulties of extending the national grid, leading many communities to rely on expensive and polluting diesel generators. Solar-based microgrids offer a sustainable alternative, yet the intermittent nature of solar energy, driven by fluctuating weather conditions, poses major obstacles to a reliable power supply and efficient system sizing. This study addresses these issues by developing a real-time solar panel power prediction model using Long Short-Term Memory (LSTM) networks. A 50 Wp solar panel system equipped with an INA260 current sensor, a voltage sensor, a DHT-22 temperature sensor, and an ESP32 microcontroller was constructed to collect real-time voltage, current, and temperature data at 10-second intervals. The collected data underwent preprocessing, feature engineering, and transformation into supervised learning sequences for training. Three temporal resolutions of the LSTM model were systematically evaluated: 3-minute, 2-minute, and 1-minute, all with 30 output timesteps. Performance was assessed using rolling-window predictions on the held-out test set with metrics including RMSE, MAPE, and R². Results demonstrated that finer temporal resolution significantly improves forecasting accuracy. The 1-minute variation achieved the best performance with the lowest RMSE and highest R², effectively capturing both diurnal patterns and short-term fluctuations in solar power output. The developed LSTM model enables accurate short-term predictions (30–90 minutes ahead), supporting proactive energy management, including optimized battery charging, load scheduling, and reduced grid dependency. Future work will incorporate additional meteorological variables and seasonal data to improve model robustness further. Three temporal variations of the LSTM model were systematically evaluated: 3-minute, 2-minute, and 1-minute resolutions, all with 30 output timesteps. Performance was assessed using rolling-window predictions on the held-out test set with metrics including RMSE, MAPE, and R². Results demonstrated that finer temporal resolution significantly improves forecasting accuracy. The 1-minute variation achieved the best performance with the lowest RMSE and highest R², effectively capturing both diurnal patterns and short-term fluctuations in solar power output. The developed LSTM model enables accurate short-term predictions (30–90 minutes ahead), supporting proactive energy management such as optimized battery charging, load scheduling, and reduced grid dependency. Future work will incorporate additional meteorological variables and seasonal data to further improve model robustness.
Implementasi Transfer Learning Menggunakan DenseNet121 untuk Deteksi Presentation Attack pada Citra Wajah Septian Nuno Zildjian; Dian Nurdiana; Fonda Leviany
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 2 (2026): Agustus 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i2.2026.266-275

Abstract

Remote examinations have become a cornerstone of distance education in Indonesia, particularly in large-scale institutions such as Universitas Terbuka and Massive Open Online Course (MOOC) platforms. However, the reliability of face verification in commercial online proctoring systems continues to be challenged by presentation attacks (face spoofing). Using simple and inexpensive media such as printed photographs, images displayed on another device, masks, or mannequins, impersonators can deceive the initial face verification process without requiring advanced technical skills. Once authenticated, they are able to complete the entire examination without being detected. Given the large number of participants in distance education examinations, manual verification of every examinee is impractical. Therefore, an automated, fast, lightweight, and reliable detection solution is needed to efficiently screen webcam captures at scale within university server infrastructures. This study addresses this challenge by developing a presentation attack detection model based on transfer learning using the DenseNet121 architecture. The model was trained on a multiclass facial image dataset consisting of 1,403 images across six categories: fake_mannequin, fake_mask, fake_printed, fake_screen, fake_unknown, and realperson. Partial fine-tuning was applied to the final convolutional layers (denseblock4 and norm5), while the training process employed the AdamW optimizer, the ReduceLROnPlateau learning rate scheduler, and early stopping to enhance performance and prevent overfitting. Experimental results achieved an accuracy of 87.68%, a weighted precision of 88.79%, a weighted recall of 87.68%, and a weighted F1-score of 87.62%, demonstrating stable and consistent performance across all attack categories. The best-performing model was subsequently deployed in a Streamlit-based application to provide an interactive and user-friendly demonstration for non-technical users. These findings demonstrate that the proposed DenseNet121 transfer learning approach is accurate, lightweight, and computationally efficient, making it a promising additional security layer for online examination proctoring systems in large-scale distance education environments amid the growing threat of face spoofing attacks.
Pemetaan Kualitas Udara Menggunakan Integrasi K-Means dan Random Forest Berbasis Data Sentinel-5P Muhammad Ridwan; Fenty Kurnia Oktorina; Hanifah Khairiah; Fajril Akbar
Jurnal Nasional Teknologi dan Sistem Informasi Vol 12 No 2 (2026): Agustus 2026
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v12i2.2026.222-230

Abstract

Kualitas udara merupakan salah satu indikator penting dalam pengelolaan lingkungan, namun ketersediaan data hasil pengukuran lapangan masih terbatas pada banyak wilayah, termasuk Kabupaten Kampar. Penelitian ini bertujuan menganalisis sebaran spasial polutan atmosfer, memetakan kualitas udara menggunakan integrasi metode K-Means dan Random Forest, serta mengidentifikasi kontribusi masing-masing parameter polutan terhadap pembentukan kelas kualitas udara. Penelitian memanfaatkan data Sentinel-5P Level-3 periode Januari–Desember 2025 yang diolah melalui Google Earth Engine (GEE). Lima parameter atmosfer yang digunakan meliputi nitrogen dioksida (NO2), karbon monoksida (CO), sulfur dioksida (SO2), ozon (O3), dan Aerosol Index (AI). Metode K-Means digunakan untuk membentuk pseudo-label melalui proses clustering, kemudian hasilnya digunakan sebagai data pelatihan pada algoritma Random Forest untuk menghasilkan peta kualitas udara. Hasil penelitian menunjukkan bahwa kualitas udara di Kabupaten Kampar terbagi ke dalam tiga kelas, yaitu kelas rendah sebesar 45 persen, kelas sedang 44 persen, dan kelas tinggi 11 persen. Wilayah dengan kualitas udara tinggi terkonsentrasi di bagian selatan Kabupaten Kampar, terutama Kecamatan Kampar Kiri Hulu dan sekitarnya. Analisis feature importance menunjukkan bahwa CO dan Aerosol Index merupakan parameter yang memberikan kontribusi terbesar terhadap pembentukan kelas kualitas udara, diikuti oleh O3, NO2, dan SO2. Selain itu, distribusi spasial kelas kualitas udara tinggi menunjukkan kesesuaian dengan beberapa lokasi kejadian kebakaran hutan dan lahan pada tahun 2025. Penelitian ini menunjukkan bahwa integrasi K-Means dan Random Forest berbasis data Sentinel-5P berpotensi menjadi alternatif pemetaan kualitas udara pada wilayah yang memiliki keterbatasan stasiun.

Page 43 of 43 | Total Record : 424

 39   40   41   42   43 

Filter by Year

2015 2026


Reset
Filter By Issues
All Issue Vol 12 No 2 (2026): Agustus 2026 Vol 12 No 1 (2026): April 2026 Vol 11 No 3 (2025): Desember 2025 Vol 11 No 2 (2025): Agustus 2025 Vol 11 No 1 (2025): April 2025 Vol 10 No 3 (2024): Desember 2024 Vol 10, No 2 (2024): Agustus 2024 Vol 10 No 2 (2024): Agustus 2024 Vol 10, No 1 (2024): April 2024 Vol 10 No 1 (2024): April 2024 Vol 9 No 3 (2023): Desember 2023 Vol 9, No 3 (2023): Desember 2023 Vol 9, No 2 (2023): Agustus 2023 Vol 9 No 2 (2023): Agustus 2023 Vol 9 No 1 (2023): April 2023 Vol 9, No 1 (2023): April 2023 Vol 8 No 3 (2022): Desember 2022 Vol 8, No 3 (2022): Desember 2022 Vol 8 No 2 (2022): Agustus 2022 Vol 8, No 2 (2022): Agustus 2022 Vol 8, No 1 (2022): April 2022 Vol 8 No 1 (2022): April 2022 Vol 7 No 3 (2021): Desember 2021 Vol 7, No 3 (2021): Desember 2021 Vol 7 No 2 (2021): Agustus 2021 Vol 7, No 2 (2021): Agustus 2021 Vol 7, No 1 (2021): April 2021 Vol 6, No 3 (2020): Desember 2020 Vol 6, No 2 (2020): Agustus 2020 Vol 6, No 1 (2020): April 2020 Vol 5, No 3 (2019): Desember 2019 Vol 5, No 2 (2019): Agustus 2019 Vol 5, No 1 (2019): April 2019 Vol 5 No 1 (2019): April 2019 Vol 4, No 3 (2018): Desember 2018 Vol 4, No 2 (2018): Agustus 2018 Vol 4, No 1 (2018): April 2018 Vol 3, No 3 (2017): Desember 2017 Vol 3, No 2 (2017): Agustus 2017 Vol 3, No 1 (2017): April 2017 Vol 2, No 3 (2016): Desember 2016 Vol 2, No 2 (2016): Agustus 2016 Vol 2, No 1 (2016): April 2016 Vol 1, No 1 (2015): Oktober 2015 More Issue