Article Per Year (5 Year)
p-Index From 2021 - 2026
1.006
P-Index
This Author published in this journals
All Journal JIKO (Jurnal Informatika dan Komputer) JOURNAL OF APPLIED INFORMATICS AND COMPUTING International Journal of Social Science, Educational, Economics, Agriculture Research, and Technology (IJSET) Brilliance: Research of Artificial Intelligence Buletin Sistem Informasi dan Teknologi Islam Jurnal Informatika
Ramadhan Renaldy
Universitas PGRI Semarang
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Mathematics Other

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Implementation of Image Data Security Using the AES-256 Algorithm in the Work Accident Recording System Dzulfiqar Alang Setiawan; Bambang Agus Herlambang; Ramadhan Renaldy
Jurnal Informatika Vol. 13 No. 1 (2026): April
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/informatika.v13i1.12372

Abstract

This study aims to implement an image data security mechanism in a web-based work accident recording system in an industrial environment by applying the Advanced Encryption Standard (AES) 256-bit cryptographic algorithm in Cipher Block Chaining (CBC) mode. The problem faced is the lack of an adequate protection mechanism for sensitive work accident photo files so that they have the potential to be accessed, copied, or modified by unauthorized parties. This study uses the Software-Oriented Prototyping method which allows system development to be carried out iteratively based on user needs and evaluation results at each development stage. The encryption process is carried out when the image file is uploaded into the system by generating a random Initialization Vector (IV) of 16 bytes, then the image data is encrypted using the AES-256-CBC algorithm and stored in ciphertext form with the file extension .enc. The decryption process is carried out when the file will be displayed again using the appropriate secret key and IV without storing the file in plaintext form on the server. The test results show that the encryption process has an average execution time of around 0.002–0.008 seconds, while the decryption process takes around 0.00004–0.001 seconds. In addition, the size of the encrypted file relatively follows the size of the original image file with an additional size of around 16–32 bytes due to the padding process and the use of initialization vectors. The results of the study indicate that the application of the AES-256-CBC algorithm is able to maintain the confidentiality and integrity of image data without having a significant impact on system performance. Thus, the developed system can improve the security of digital file storage and support a more structured, secure, and efficient management of work accident data.
IMPLEMENTATION OF THE MOVING AVERAGE ALGORITHM IN A WEB-BASED FOOD AND BEVERAGE RAW MATERIAL STOCK REQUIREMENT PREDICTION INFORMATION SYSTEM Ainia Hasna Salsabila; Bambang Agus Herlambang; Ramadhan Renaldy
International Journal of Social Science, Educational, Economics, Agriculture Research and Technology (IJSET) Vol. 5 No. 6 (2026): MAY
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.22149041

Abstract

Inventory is a critical component in business operations, particularly in the Food and Beverages (F&B) sector, which demands accurate management to mitigate the risks of stockouts and overstocking. However, many MSMEs still rely on conventional methods based on subjective assumptions, which are prone to errors and unable to accommodate demand fluctuations. This research aims to develop a web-based raw material stock forecasting information system integrated with the Single Moving Average (SMA) method to enhance inventory management efficiency. The system development follows a prototyping approach, encompassing data collection, quick design using UML, prototype construction using PHP Laravel and Python, evaluation, and system refinement. The dataset utilized consists of 12 periods of monthly financial reports from Benjiro Sushi, Lamper branch. Accuracy evaluation was conducted using MAPE, MSE, and RMSE metrics. The results indicate that the application of SMA without data pre-processing resulted in a high error rate (MAPE 77.25%). However, after implementing pre-processing techniques—including backward interpolation, outlier capping, and iterative smoothing—the accuracy improved significantly, with MAPE values ranging between 20.4% and 21.0%. The developed system provides automated and real-time stock predictions, facilitating more precise, efficient, and structured procurement decision-making. Thus, this system is considered effective in addressing inventory challenges within the F&B sector.
Implementation of Stacking Ensemble Learning on Decision Tree Regressor for Food Commodity Price Prediction in Indonesia Nukman Solikhudin; Mega Novita; Ramadhan Renaldy
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13092

Abstract

Fluctuations in staple food prices across Indonesian regions exhibit complex, non-linear patterns vulnerable to market shocks. This study aims to construct an accurate, stable food price prediction model utilizing a Stacking Ensemble Learning approach. A raw dataset of 27,722 records from the National Food Agency was cleaned by removing invalid data and zero values, yielding 27,270 well-indexed observations. To address severe scale disparity between commodities and heteroscedasticity effects, a natural logarithm transformation was applied to the target variable. Time-series features, specifically Lag 1 and Moving Average 3, were locally constructed based on commodity-province groups to capture temporal dependencies. The proposed Stacking Ensemble model integrates four multi-architecture base learners Ridge Regression, AdaBoost, Gradient Boosting, and Extra Tree with a Decision Tree Regressor acting as the meta-learner. Model evaluation was conducted using a temporal split method with an 80:20 ratio to strictly prevent data leakage. Experimental results demonstrate that the proposed Stacking Ensemble model achieves superior performance on nominal test data compared to baseline models, securing an R^2of 0.895, RMSE of 2,531, and MAE of 1,461. Furthermore, the model proved highly robust in balancing bias and variance, yielding the smallest R^2Gap of 0.035. Model transparency analysis reveals a powerful temporal inertia, where historical features dominate the decision weight by up to 87.55%. However, per-commodity performance analysis highlights a performance limitation on subsidized commodities (Minyak Kita) due to data distortion caused by non-market Price Ceiling regulations. This study provides critical implications for food authorities to formulate data-driven, responsive market interventions.  
Peningkatan Performa Prediksi Survival Pasien Gagal Jantung Menggunakan Stacking Ensemble Learning Faiza Rulla Salwa; Mega Novita; Ramadhan Renaldy
JURNAL INFORMATIKA DAN KOMPUTER Vol 9, No 3 (2025): Oktober 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v9i3.2126

Abstract

Prediksi kelangsungan hidup pasien gagal jantung merupakan aspek penting dalam mendukung pengambilan keputusan medis secara dini dan tepat. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi kelangsungan hidup pasien gagal jantung dengan menerapkan metode Stacking Ensemble Learning yang menggabungkan tiga base learners, yaitu Decision Tree, Naive Bayes, dan K-Nearest Neighbor, serta menggunakan Support Vector Machine sebagai meta-learner. Dataset yang digunakan adalah Heart Failure Clinical Records dari UCI Machine Learning Repository yang telah melalui proses pra-pemrosesan berupa standardisasi numerik dan pembagian data menggunakan stratified sampling dengan rasio 80:20. Eksperimen dilakukan menggunakan validasi silang (5-fold cross-validation) dan tuning hyperparameter pada meta-learner menggunakan GridSearchCV untuk menemukan kombinasi terbaik dari parameter C dan gamma. Hasil evaluasi menunjukkan bahwa model stacking mampu mencapai akurasi sebesar 98,7% dan F1-score 0,9791, mengungguli semua model tunggal. Keberhasilan ini menunjukkan bahwa strategi penggabungan beberapa model ringan mampu meningkatkan kinerja sistem prediktif secara signifikan, tanpa menambah kompleksitas yang berlebihan. Oleh karena itu, pendekatan ini sangat potensial untuk diterapkan pada sistem pendukung keputusan klinis berbasis data, khususnya dalam konteks prediksi penyakit kronis.
Klasterisasi Pola Perjalanan Wisatawan Nusantara Menggunakan DBSCAN Berbasis SIG Widya Aprilia; Setyoningsih Wibowo; Ramadhan Renaldy
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 3 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i3.3472

Abstract

Penelitian ini menganalisis dinamika spasial Wisatawan Nusantara (Wisnus) periode 2019 sampai 2024 dengan menerapkan algoritma Density-Based Spatial Clustering of Applications with Noise (DBSCAN) yang terintegrasi dengan Sistem Informasi Geografis (SIG). Penelitian membagi periode observasi menjadi tiga fase: pra-pandemi, masa pandemi COVID-19, dan fase pemulihan, yang masing-masing menunjukkan karakteristik distribusi spasial berbeda secara signifikan. Peneliti menggunakan data kunjungan Wisatawan Nusantara tingkat provinsi sebagai dasar analisis dan menambahkan atribut spasial berupa koordinat geografis. Peneliti mengekstrak fitur temporal dalam bentuk statistik deskriptif, seperti total kunjungan, rata-rata, standar deviasi, dan tren pertumbuhan. Peneliti menerapkan standardisasi z-score agar kontribusi setiap variabel seimbang. Peneliti mengoptimalkan parameter DBSCAN melalui grid search dan memperoleh kombinasi Eps 1,4 dan MinPts 2 dengan nilai Silhouette Score 0,430, Davies-Bouldin Index 1,889, dan Calinski-Harabasz Index 7,555. Hasil clustering memperlihatkan pergeseran signifikan pola distribusi spasial selama pandemi dan peningkatan konsentrasi kunjungan pada fase pemulihan. Integrasi DBSCAN dengan SIG menghasilkan visualisasi choropleth informatif yang mendukung pengambilan keputusan berbasis data dalam perencanaan destinasi wisata nasional yang adaptif.
Development of a Hybrid ConvNeXt-BiLSTM Model Based on Segment-Level Mel-Spectrograms for AI-Generated Song Detection Dimas Aditya Saputra; Nugroho Dwi Saputro; Ramadhan Renaldy
Brilliance: Research of Artificial Intelligence Vol. 6 No. 3 (2026): Brilliance: Research of Artificial Intelligence, Article Research August 2026
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v6i3.9372

Abstract

AI-generated music increasingly resembles human-produced songs, creating a need for reliable source detection in audio classification. This study aims to develop and evaluate a segment-level hybrid model that combines ConvNeXt with bidirectional long short-term memory (BiLSTM) to capture local spectral patterns and temporal relationships across a song. Each song is represented by 24 five-second segments. Every segment is converted into a 128 x 128 mel-spectrogram, processed by ConvNeXt to obtain 768 features, and arranged as a sequence for BiLSTM modeling. The base dataset contains 22,844 songs divided into 16,522 training, 877 validation, and 5,445 test songs. Under the same data split and training protocol, the proposed ConvNeXt-BiLSTM model achieved accuracy of 0.8408, balanced accuracy of 0.8450, sensitivity of 0.7002, and an F1-score of 0.8190. The ConvNeXt-only baseline achieved 0.8228, 0.8276, 0.6613, and 0.7934 for the same metrics. Fine-tuning used 3,200 additional balanced samples, while final evaluation used a separate balanced test set of 200 songs. With a calibrated threshold of 0.484, the fine-tuned model achieved an F1-score of 0.8556 and balanced accuracy of 0.8700, correctly identifying 97 non-AI songs and 77 AI-generated songs. These results show that temporal modeling across mel-spectrogram segments improves detection, although evaluation using additional music generators, codecs, recording qualities, and adaptive audio contexts remains necessary.
Co-Authors Ainia Hasna Salsabila Bambang Agus Herlambang, Bambang Dimas Aditya Saputra Dzulfiqar Alang Setiawan Faiza Rulla Salwa Mega Novita Nugroho Dwi Saputro Nukman Solikhudin Setyoningsih Wibowo Widya Aprilia