Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics Indonesian Journal of Electrical Engineering and Computer Science Jurnal Bumigora Information Technology (BITe)
Alam, Sirojul
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

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

Found 5 Documents
Search

 1 
The performance of Naïve Bayes, support vector machine, and logistic regression on Indonesia immigration sentiment analysis Assiroj, Priati; Kurnia, Asep; Alam, Sirojul
Bulletin of Electrical Engineering and Informatics Vol 12, No 6: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v12i6.5688

Abstract

In recent years various attempts have been made to automatically mine opinions and sentiments from natural language in online networking messages, news, and product review businesses. Sentiment analysis is needed as an effort to improve service performance in the organization. In this paper, we have explored the polarization of positive and negative sentiments using Twitter user reviews. Sentiment analysis is carried out using the Naïve Bayes (NB), support vector machine (SVM), and logistic regression (LR) model then compares the results of these three models. The results of the experiment showed that the accuracy of LR was better than SVM and NB, namely 77%, 76%, and 70%.
How does natural language processing identify the issues? Assiroj, Priati; Alam, Sirojul; Spits Warnars, Harco Leslie Hendric
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 1: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i1.pp357-366

Abstract

Product innovation and service improvement have become essential or crucial for organisations, including public service organisations. The Indonesia Immigration Directorate released the m-passport application to enhance its quality of service. The m-passport application is considered good as it has been downloaded over a million times. Like immigration officers, this application seems to be at the forefront, reflecting an increasingly better service. However, there was still a need for significant improvement in the application. Improvements can be made to the application by considering user feedback or reviews. Reviews provided by users, approximately 12K, will serve as input for improving or enhancing the application. This was made possible as users interacti directly with the application. The most common issues are one-time password or OTP verification code with a probability value of 0.044, errors when logging in with a probability value of 0.283, and slow response applications with a probability value of 0.125.
Improving Large Language Model’s Ability to Find the Words Relationship Alam, Sirojul; Abdul Jabar, Jaka; Abdurrachman, Fauzi; Suharjo, Bambang; Rimbawa, H.A Danang
Jurnal Bumigora Information Technology (BITe) Vol 6 No 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v6i2.4127

Abstract

Background: It is still possible to enhance the capabilities of popular and widely used large language models (LLMs) such as Generative Pre-trained Transformer (GPT). Using the Retrieval-Augmented Generation (RAG) architecture is one method of achieving enhancement. This architectural approach incorporates outside data into the model to improve LLM capabilities. Objective: The aim of this research is to prove that the RAG can help LLMs respond with greater precision and rationale. Method: The method used in this work is utilizing Huggingface Application Programming Interface (API) for word embedding, store and find the relationship of the words. Result: The results show how well RAG performs, as the attractively rendered graph makes clear. The knowledge that has been obtained is logical and understandable, such as the word Logistic Regression that related to accuracy, F1 score, and defined as a simple and the best model compared to Naïve Bayes and Support Vector Machine (SVM) model. Conclusion: The conclusion is RAG helps LLMs to improve its capability well.
Improving Large Language Model’s Ability to Find the Words Relationship Alam, Sirojul; Abdul Jabar, Jaka; Abdurrachman, Fauzi; Suharjo, Bambang; Rimbawa, H.A Danang
Jurnal Bumigora Information Technology (BITe) Vol. 6 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v6i2.4127

Abstract

Background: It is still possible to enhance the capabilities of popular and widely used large language models (LLMs) such as Generative Pre-trained Transformer (GPT). Using the Retrieval-Augmented Generation (RAG) architecture is one method of achieving enhancement. This architectural approach incorporates outside data into the model to improve LLM capabilities. Objective: The aim of this research is to prove that the RAG can help LLMs respond with greater precision and rationale. Method: The method used in this work is utilizing Huggingface Application Programming Interface (API) for word embedding, store and find the relationship of the words. Result: The results show how well RAG performs, as the attractively rendered graph makes clear. The knowledge that has been obtained is logical and understandable, such as the word Logistic Regression that related to accuracy, F1 score, and defined as a simple and the best model compared to Naïve Bayes and Support Vector Machine (SVM) model. Conclusion: The conclusion is RAG helps LLMs to improve its capability well.
Invisible watermarking as an additional forensic feature of e-meterai Rimbawa, H.A Danang; Alam, Sirojul; Saputro, Joko W.; Mantoro, Teddy
Indonesian Journal of Electrical Engineering and Computer Science Vol 41, No 1: January 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v41.i1.pp344-356

Abstract

The e-meterai is an official digital product of the Indonesian government issued by the Directorate General of Taxation (DGT). Its usage has become increasingly widespread as conventional documentation transitions to digital formats, serving the same function as its printed counterpart. This product features a quick-response code embedded with unique Indonesian codes and offers overt, covert, and forensic features. This study aims to experiment with adding a forensic feature in the form of an invisible watermark. We employed two watermark embedding techniques, discrete Fourier transform (DFT) and scale-invariant feature transform (SIFT), to determine which is more suitable for this application. After embedding the watermark, we also simulate various attacks including gaussian noise, salt and pepper noise, averaging filter, rotation, translation, and speckle noise. For each attack, we calculated with normalized-cross correlation (NCC) values, obtaining 0.863 and 0.976 for the gaussian noise attack, 0.929 and 0.984 for the salt and pepper attack, 0.975 and 0.984 for the averaging filter attack, 0.173 and 0.097 for rotation attacks, 0.172 and 0.032 for translation attack, and 0.972 and 0.996 for speckle noise attack, using DFT and SIFT techniques, respectively.
Co-Authors Abdul Jabar, Jaka Abdurrachman, Fauzi Assiroj, Priati Kurnia, Asep Rimbawa, H.A Danang Saputro, Joko W. Suharjo, Bambang Teddy Mantoro Warnars, Harco Leslie Hendric Spits