Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering JURNAL SISTEM INFORMASI BISNIS JUTI: Jurnal Ilmiah Teknologi Informasi Journal of Information Systems Engineering and Business Intelligence Jurnal Teknologi dan Sistem Komputer bit-Tech
Agus Subhan Akbar, Agus Subhan
Mahasiswa Magister Sistem Informasi Universitas Diponegoro
Computer Science & IT Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Library & Information Science

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

Found 6 Documents
Search

 1 
Analisis Sentimen Berbasis Ontologi di Level Kalimat untuk Mengukur Persepsi Produk Akbar, Agus Subhan; Sediyono, Eko; Nurhayati, Oky Dwi
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 5, No 2 (2015): Volume 5 Nomor 2 Tahun 2015
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1207.424 KB) | DOI: 10.21456/vol5iss2pp84-97

Abstract

The purpose of this research is to do sentiment analysis on tweets data retrieved using ontology framework and using naïve bayes classifier algorithm for classification process. This study is based on the habits of twitter users who frequently writes opinion, expression, or sentiment on a specific product, especially smartphones. These tweets can be used as a basis for sentiment analysis on a particular product. The method used in this study include the use of ontology framework for tweets retrieval that match the domain of the discussion and the use of naïve bayes classification algorithm for data classification. Classification process carried past the 3 pieces of layer classification to fine tune the final result of classification. Three layers of classification used include buzz/promo classification (classifying tweets into buzz and not-buzz tweets), subjectivity classification (classifying not-buzz tweets into subjective and objective tweets), and sentiment classification (classifying subjective tweets into positive, negative, or neutral tweets). The resulted software can classify tweets with high accuracy. This software was trained and tested with the composition of 25:75, 50:50, 75:25 from sample data and tested 10 times for each composition. Average accuracy of the system reached 84.16%, 86.15%, and 87.54% for each composition. The result showed that by employing this system, product marketing stakeholders can determine the level of user sentiment expressed in the form of tweets. The method used in this study could be developed to improve the accuracy of classification systems.  
Erratum: Optimasi nilai k dan parameter lag algoritme k-nearest neighbor pada prediksi tingkat hunian hotel Akbar, Agus Subhan; Kusumodestoni, R. Hadapiningradja
Jurnal Teknologi dan Sistem Komputer Volume 9, Issue 1, Year 2021 (January 2021)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2021.14007

Abstract

This correct the article "Optimasi nilai k dan parameter lag algoritme k-nearest neighbor pada prediksi tingkat hunian hotel (Optimization of k value and lag parameter of k-nearest neighbor algorithm on the prediction of hotel occupancy rates)" in vol. 8, no. 3, pp. 246-254, Jul. 2020; https://doi.org/10.14710/jtsiskom.2020.13648In the original published article, the placement of Figure 8 and Figure 9 less appropriate, which causes the manuscript hard to read. In addition, Table 2 through Table 6 need to be repositioned. These placing errors have been corrected online.The publisher apologizes for these errors. 
Nonlinear regression analysis to predict mandibular landmarks on panoramic radiographs Nafiiyah, Nur; Hanifah, Ayu Ismi; Susanto, Edy; Astuti, Eha Renwi; Fatichah, Chastine; Putra, Ramadhan Hardani; Akbar, Agus Subhan
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i2.pp2098-2108

Abstract

An automatic system for determining mandibular landmark points on panoramic radiography can reduce errors due to differences in expert professionalism and save time. Previous research has shown that the linear regression method is ineffective at predicting condyle and gonion landmark points in panoramic radiography. So, this research proposes an analysis of nonlinear regression methods (support vector machine (SVM) kernel=‘polynomial’, polynomial regression, ensemble regression) for predicting condyle and gonion landmark points. There are four predicted landmark points, namely the right condyle, left condyle, right gonion, and left gonion. The nonlinear regression methods used are SVM, polynomial regression, and ensemble regression. The Dental and Oral Hospital, within the Faculty of Dentistry at Universitas Airlangga, provides the research data. The research encompasses 119 patients between the ages of 19 and 70, dividing 103 into training and 16 into testing. The research results show that the SVM method is only good at predicting the right condyle point with a mean radial error (MRE) of 4,724 pixels. Meanwhile, to predict the left condyle, right gonion, and left gonion points, it is better to use the polynomial regression method and ensemble regression with an order of success detection rate (SDR) of 37.5%, 18.75%, and 12.5%, respectively.
Metode Multi-Criteria Iterative Forward Search Untuk Penjadwalan Ujian dan Pengawas Ujian Akbar, Agus Subhan; Zyen, Akhmad Khanif
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 17, No. 1, Januari 2019
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v17i1.a775

Abstract

Setting Examination schedules to support learning evaluation is crucial. The ideal scheduling for this exam must be able to allocate all related components in the implementation of the test within a predetermined time span. The components of the implementation of an examination in a university include the departments in the faculty, a number of courses and participants, the room used, the time of execution, and the lecturer serving as supervisor. The arrangement of each component of the implementation of the exam needs to be carried out appropriately so there is no collision of the schedule between the participants, the schedule, the room used, and the supervisor in charge. The purpose of this study is to produce an ideal exam scheduling and examination supervisor. The study was conducted by applying the Multi-Criteria Iterative Forward Search from the Academic Information System (SIAKAD) data at the Faculty of Science and Technology, Unisnu Jepara. This research has resulted in a system that is able to create an examination schedule and supervisory schedule that accommodates all factors without conflict, well tested, and applied.
Business Optimization Through Implementation of Cost of Production Pricing System Using Bill of Material Method Ananta, Yoga Sofian; Sabilla, Alzena Dona; Akbar, Agus Subhan
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2750

Abstract

The furniture industry often struggles with setting accurate selling prices due to the lack of structured and precise cost calculation systems. Many furniture entrepreneurs still rely on traditional methods that base prices on market trends, without accounting for underlying production costs. This often leads to prices that are too low, eroding profit margins, or too high, making it difficult to stay competitive. This study introduces a novel Cost of Goods Manufactured (COGM) calculation system, integrated with the Bill of Materials (BOM) method, to advance current pricing systems in the furniture industry. By incorporating key cost elements such as raw materials, labor, and the impact of waste and rework, the system enhances the accuracy of COGM calculations. Additionally, it offers greater transparency by providing a detailed breakdown of each cost component, allowing entrepreneurs to better understand their production expenses. The implementation of this system led to a 15% improvement in pricing accuracy, significantly reducing pricing errors and optimizing production costs. Furthermore, businesses reported a 20% increase in competitiveness due to more informed pricing strategies. This research demonstrates that integrating COGM with BOM not only improves production efficiency but also strengthens pricing strategies, contributing to long-term profitability. It highlights the role of cost transparency in driving sustainable growth, particularly for small and medium-sized furniture enterprises.
Academic Guidebook Chatbot: Performance Comparison of Fine-Tuned Mistral 7B and LlaMA-2 7B Rachman, Davied Indra; Akbar, Agus Subhan; Sabilla, Alzena Dona
Journal of Information Systems Engineering and Business Intelligence Vol. 11 No. 3 (2025): October
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.11.3.383-392

Abstract

Background: Chatbot is recently ranked as the main technological solution due to the high demand for fast and efficient information retrieval. Therefore, this study was carried out to develop a local document-based chatbot that can answer questions related to the contents of PDF documents using open-source AI models such as Mistral 7B and LLaMA-2 7B. Although these models were effective at processing natural language, a major challenge was observed in the tendency to generate hallucinated answers, characterized by having inaccuracies and being out of context. Objective: This study aims to reduce hallucinatory responses from chatbot models by making their responses more precise and accurate through fine-tuning. The performance of fine-tuned models (Mistral 7B and LLaMA-2 7B) was also compared. Methods: Fine-tuning of the two models was performed using domain-specific datasets taken from Academic Guidebook. This process was conducted to improve models ability to understand and answer questions relevant to Academic Guidebook context. Performance was evaluated using METEOR Score to measure literal agreement and BERTScore to assess meaning agreement. In addition, response time was measured to assess efficiency, while chatbot system was developed using Streamlit and LangChain for real-time interaction. Results: Fine-tuned Mistral 7B model achieved the highest METEOR value of 0.40 and F1 of 0.78 based on BERTScore results. Regarding efficiency, fine-tuned Mistral 7B showed a faster response time than LLaMA-2. Meanwhile, the non-fine-tuned Mistral 7B and LLaMA-2 7B showed a longer response time than fine-tuned Mistral 7B and LLaMA-2 7B. Conclusion: The results showed that the enhancements significantly improved the performance of large language models in specific tasks, reduced hallucinations, and enhanced response quality Keywords: Chatbot, Large Language Model, Mistral 7B, LLaMA-2 7B, METEOR Score
Co-Authors Akhmad Khanif Zyen, Akhmad Khanif Ananta, Yoga Sofian Ayu Ismi Hanifah Chastine Fatichah edy susanto Eha Renwi Astuti Eko Sediyono Nafiiyah, Nur Oky Dwi Nurhayati Putra, Ramadhan Hardani R Hadapiningradja Kusumodestoni Rachman, Davied Indra Sabilla, Alzena Dona