Article Per Year (5 Year)
p-Index From 2021 - 2026
0.983
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal Pendidikan dan Teknologi Indonesia Jurnal Algoritma Journal of Digital Market and Digital Currency
Berlilana
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Pengembangan dan Evaluasi Protokol VHE-PIR Berbasis Multi-Server untuk Pengambilan Informasi yang Privat dan Skalabel Widodo, Slamet; Setyo Utomo, Fandy; Berlilana
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 9 (2025): JPTI - September 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.1026

Abstract

Penelitian ini bertujuan untuk mengembangkan protokol Private Information Retrieval (PIR) berbasis multi-server yang mengintegrasikan enkripsi homomorfik terverifikasi (Verifiable Homomorphic Encryption - VHE) untuk meningkatkan privasi, efisiensi, dan keandalan dalam pengambilan informasi dari basis data. Protokol ini dirancang untuk mengatasi keterbatasan arsitektur server tunggal, seperti risiko kegagalan sistem, beban kerja yang tinggi, dan keterbatasan skalabilitas. Metode penelitian melibatkan distribusi basis data ke beberapa server, penggunaan public key dan private key untuk enkripsi dan verifikasi hasil, serta penerapan modul akselerasi untuk mendukung pemrosesan paralel. Simulasi dilakukan pada lingkungan terdistribusi untuk mengevaluasi waktu respons, penggunaan memori, serta kemampuan failover dalam kondisi server bermasalah. Hasil penelitian menunjukkan bahwa pada skenario normal, arsitektur multi-server secara konsisten memiliki waktu respons lebih rendah dibandingkan arsitektur server tunggal, baik untuk protokol non-VHE maupun VHE-PIR. Misalnya, pada 200 pengguna, waktu respons multi-server VHE adalah 3,6070 detik dibandingkan dengan 4,2433 detik pada single server. Selain itu, dalam kondisi server bermasalah, arsitektur multi-server tetap mampu melayani permintaan dengan mendistribusikan beban ke server lain, sementara server tunggal mengalami kegagalan total. Protokol VHE-PIR menunjukkan privasi yang lebih tinggi dengan memastikan elemen yang diakses tidak dapat diketahui oleh server, meskipun memerlukan sumber daya memori dan waktu respons sedikit lebih besar dibandingkan protokol non-VHE. Implikasi dari penelitian ini mencakup kontribusi akademik dalam desain protokol PIR tahan gangguan dan kontribusi praktis terhadap sistem informasi modern yang membutuhkan skala besar, kecepatan akses, serta jaminan kerahasiaan. Penelitian ini relevan untuk implementasi nyata, dan membuka ruang eksplorasi lebih lanjut dalam penerapan teknologi PIR di lingkungan cloud publik dan sistem basis data terdistribusi.
Time Series Analysis of Bitcoin Prices Using ARIMA and LSTM for Trend Prediction Berlilana; Wahid, Arif Mu’amar
Journal of Digital Market and Digital Currency Vol. 1 No. 1 (2024): Regular Issue June 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v1i1.1

Abstract

This study investigates the efficacy of ARIMA and LSTM models in predicting Bitcoin prices, emphasizing the importance of accurate price prediction for trading, risk management, and investment strategies in the volatile cryptocurrency market. The objectives are to analyze Bitcoin prices to identify underlying patterns and trends, compare the predictive performance of ARIMA and LSTM models, and provide insights into their practical applications for Bitcoin price prediction. A comprehensive dataset of Bitcoin prices from January 1, 2011, to December 31, 2023, sourced from CoinMarketCap, was used. Data preprocessing included handling missing values, removing duplicates, achieving stationarity through differencing, and normalizing data using MinMaxScaler. The ARIMA model's best-fitting parameters were identified using ACF and PACF plots, and it was trained with the statsmodels library. The LSTM model involved data preparation through windowing and train-test splitting, constructing a neural network with LSTM layers, and training using TensorFlow/Keras. Evaluation metrics included Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), with comparisons based on accuracy and computational efficiency. The ARIMA model demonstrated impressive performance with an MAE of 2.308392356829177e-215 and an RMSE of 0.0, indicating a near-perfect fit to the training data. The LSTM model achieved an MAE of 0.00021804577826689423 and an RMSE of 0.00021916977109865863, showing robust performance in handling nonlinear and long-term dependencies. The ARIMA model excelled in computational efficiency with a training time of 2.548070192337036 seconds and a prediction time of 0.0009970664978027344 seconds, while the LSTM model required 378.69622468948364 seconds for training and 0.6859967708587646 seconds for prediction. The results highlight ARIMA's effectiveness in capturing linear trends and its suitability for short-term trading strategies, while LSTM is better for long-term investment strategies due to its ability to model complex patterns. Despite potential overfitting in ARIMA and high computational demands for LSTM, the study suggests exploring hybrid models, incorporating additional data sources, and developing advanced techniques to enhance predictive accuracy in future research.
Penerapan Algoritma K-Nearest Neighbor untuk Analisis Sentimen Ulasan Produk Elektronik pada Platform E-Commerce Octavia, Noer Fotin; Berlilana
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.3083

Abstract

The study aims to evaluate user sentiment toward Samsung products on the Tokopedia e-commerce platform using the K-Nearest Neighbor (KNN) algorithm. E-commerce plays a crucial role in modern trade, where consumer reviews provide insights into their level of satisfaction. The KNN method is applied to classify reviews into positive, negative, and neutral sentiment categories based on the collected review data. The research procedure includes collecting 2,200 Samsung product reviews from Tokopedia, followed by preprocessing steps such as tokenization, normalization, stopword removal, stemming, and data cleaning. The data is then weighted using TF-IDF before being classified with KNN. The results show that the KNN model achieved the highest accuracy of 91.35 percent at K=3, while K=5 yielded 90.38 percent and K=7 reached 90.14 percent. The model performed exceptionally well in detecting positive sentiment, with 100 percent precision and recall and an F1-score of 96 percent, although its performance was less optimal for negative and neutral sentiments. Overall, KNN proved effective in analyzing sentiment in Tokopedia product reviews, demonstrating higher accuracy than other methods used in previous studies and showing the capability to capture local patterns within a single-brand dataset. Nevertheless, further methodological improvements and enhanced data processing are needed to achieve more precise and balanced performance across all sentiment categories.
Pengembangan Sistem E-Learning Inklusif Cerdas untuk Tuna Netra dengan Integrasi Teknologi Voice Command dan Text-To-Speech Fandy Setyo, Utomo; Saputro, Rujianto Eko; Baihaqi, Wiga Maulana; Sarmini; Berlilana; Aptana, Naufal Yogi
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 2: April 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.132

Abstract

Aksesibilitas menjadi tantangan utama dalam e-learning bagi penyandang tunanetra karena keterbatasan visual dalam memahami konten digital. Penelitian ini bertujuan mengembangkan sistem e-learning inklusif dengan fitur voice command dan text-to-speech untuk mendukung interaksi non-visual. Pengembangan sistem dilakukan menggunakan metode Agile Scrum dalam beberapa siklus sprint, yang mencakup tahapan product backlog, sprint planning, daily scrum, sprint review, dan sprint retrospective. Sistem dirancang dalam arsitektur tiga lapisan, dengan React.js pada sisi klien dan Node.js pada sisi server, serta mengintegrasikan layanan API Gemini untuk pemrosesan suara dan teks ke audio. Validasi sistem dilakukan secara internal melalui dokumentasi sprint review dan skenario pengujian teknis. Hasil dokumentasi sprint menunjukkan bahwa fitur ini berfungsi sesuai dengan skenario pengujian internal dan berpotensi meningkatkan aksesibilitas. Meskipun belum dievaluasi langsung oleh pengguna tunanetra, hasil pengembangan awal ini memberikan fondasi penting untuk pengujian lebih lanjut dan pengembangan sistem e-learning yang lebih inklusif.   Absctract Accessibility is a major challenge in e-learning for visually impaired individuals due to visual limitations in understanding digital content. This study aims to develop an inclusive e-learning system with voice command and text-to-speech features to support non-visual interaction. The system was developed using the Agile Scrum method in several sprint cycles, which included the product backlog, sprint planning, daily scrum, sprint review, and sprint retrospective stages. The system is designed with a three-layer architecture, using React.js on the client side and Node.js on the server side, and integrates the Gemini API service for voice and text-to-audio processing. System validation was conducted internally through sprint review documentation and technical testing scenarios. The sprint documentation results indicate that this feature functions according to internal testing scenarios and has the potential to improve accessibility. Although it has not yet been directly evaluated by visually impaired users, these initial development results provide an important foundation for further testing and the development of a more inclusive e-learning system.
Two-Stage Framework Using IndoBERT for Sentiment Analysis of Tokopedia Reviews under Extreme Class Imbalance Ades Tikaningsih; Imam Tahyudin; Berlilana
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16187

Abstract

The rapid growth of the Indonesian e-commerce industry has generated a large volume of customer reviews for sentiment analysis, but the data distribution often suffers from extreme class imbalance. The review dataset exhibits a 97.6% dominance of the positive class, causing the single-stage transformer model to produce high accuracy that does not fully represent classification capability. The baseline model achieves a macro-averaged F1-score of 0.599, with a neutral-class recall of 26.3%. Approaches based on loss function adjustment, such as class-balanced loss, focal loss, weighted cross-entropy, and decision-threshold adjustment, are unable to fundamentally address this issue, yielding only limited performance improvements. This study proposes a two-stage classification approach that decomposes the multi-class classification task into two sequential binary classification stages using a BERT-based Indonesian-language transformer model (IndoBERT). The first stage separates the positive class from the non-positive class, while the second stage distinguishes between the neutral and negative classes in a more balanced decision space. The proposed approach achieves a macro-averaged F1-score of 0.761, representing a 16.2% improvement over the baseline and outperforming all loss-function-based methods. These findings suggest that, under conditions of extreme class imbalance, simplifying the decision space through gradual task decomposition is more effective than intervention at the loss-function level. Furthermore, error propagation analysis and qualitative evaluations demonstrate that this approach improves sensitivity to minority classes, although challenges remain in cases involving ambiguous expressions.
Co-Authors Ades Tikaningsih Aptana, Naufal Yogi Baihaqi, Wiga Maulana Fandy Setyo Utomo Fandy Setyo, Utomo Imam Tahyudin Octavia, Noer Fotin Rujianto Eko Saputro Sarmini Slamet Widodo Wahid, Arif Mu’amar