cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kab. indragiri hilir,
Riau
INDONESIA
Sistemasi: Jurnal Sistem Informasi
Published by Universitas Islam Indragiri
ISSN : 23028149     EISSN : 25409719     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
Sistemasi adalah nama terbitan jurnal ilmiah dalam bidang ilmu sains komputer program studi Sistem Informasi Universitas Islam Indragiri, Tembilahan Riau. Jurnal Sistemasi Terbit 3x setahun yaitu bulan Januari, Mei dan September,Focus dan Scope Umum dari Sistemasi yaitu Bidang Sistem Informasi, Teknologi Informasi,Computer Science,Rekayasa Perangkat Lunak,Teknik Informatika
Arjuna Subject : -
Articles 40 Documents
 1   2   3   4 
Search results for , issue "Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi" : 40 Documents clear
Comparative Analysis of T5 Model Performance for Indonesian Abstractive Text Summarization Bagus Dwi Satya, Mohammad Wahyu; Luthfiarta, Ardytha; Althoff, Mohammad Noval
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.4884

Abstract

The rapid growth of digital content has created significant challenges in information processing, particularly in languages like Indonesian, where automatic summarization remains complex. This study evaluates the performance of different T5 (Text-to-Text Transfer Transformer) model variants in generating abstractive summaries for Indonesian texts. The research aims to identify the most effective model variant for Indonesian language summarization by comparing T5-Base, FLAN-T5 Base, and mT5-Base models. Using the INDOSUM dataset containing 19,000 Indonesian news article-summary pairs, we implemented a 5-Fold Cross-Validation approach and applied ROUGE metrics for evaluation. Results show that T5-Base achieves the highest ROUGE-1, ROUGE-2, and ROUGE-L scores of 73.52%, 64.50%, and 69.55%, respectively, followed by FLAN-T5, while mT5-Base performs the worst. However, qualitative analysis reveals various summarization errors: T5-Base exhibits redundancy and inconsistent formatting, FLAN-T5 suffers from truncation issues, and mT5 often generates factually incorrect summaries due to misinterpretation of context. Additionally, we assessed computational performance through training time, inference speed, and resource consumption. The results indicate that mT5-Base has the shortest training time and fastest inference speed but at the cost of lower summarization accuracy. Conversely, T5-Base, while achieving the highest accuracy, requires significantly longer training time and greater computational resources. These findings highlight the trade-offs between accuracy, error tendencies, and computational efficiency, providing valuable insights for developing more effective Indonesian language summarization systems and emphasizing the importance of model selection for specific language tasks.
Literature Review: A Comparative Study of Waste Classification using Deep Learning Algorithms Ikhlas, Ariza; Hendrik, Billy
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5163

Abstract

Waste type classification remains a daily challenge in modern waste management. Proper waste classification contributes significantly to environmental protection and enhances the efficiency of the recycling process. Unfortunately, manual waste classification is rarely performed by individuals, resulting in mixed waste that is difficult to separate into recyclable and non-recyclable categories. This leads to increased waste accumulation, which becomes harder to process over time. Therefore, automating this procedure using computer vision is of critical importance. This study adopts a Systematic Literature Review (SLR) methodology to analyze existing research conducted by previous scholars. The main objectives are to identify the most appropriate algorithms for waste type classification, determine the most suitable model architectures, and examine the correlation between dataset size, number of classes, and classification accuracy. The results of the literature review show that the Convolutional Neural Network (CNN) algorithm is widely used and considered highly effective for computer vision tasks. Among the best-performing models are: A standard CNN architecture achieving 100% accuracy with 150 data points and 3 classes, CNN with ResNet50 model achieving 99.41% accuracy on 2,527 data points and 6 classes, A combination of ResNet, k-Nearest Neighbors (kNN), and Neighborhood Component Analysis (NCA) achieving 99.35% accuracy on 13,089 data points and 1,672 classes, CNN with CapSA ECOC + ANN model reaching 99.01% accuracy on 1,515 data points and 12 classes. These findings indicate that numerous prior studies have successfully developed high-accuracy models for waste classification, which can serve as a solid foundation for building computer vision systems to automate the waste sorting process.
Conversion Prediction in Google Search Ads Keyword Selection Using the K-Nearest Neighbor and C4.5 Algorithms Harahap, Muhammad Sya'ban; Muhammad, Alva Hendi
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5174

Abstract

This study was conducted to analyze and compare the effectiveness of two algorithms—K-Nearest Neighbor (K-NN) and C4.5—in predicting keyword conversion on the Google Ads platform. With the rapid growth of digital marketing, selecting the right keywords has become crucial for improving conversion rates. The research utilized a dataset of 673 entries with 12 relevant attributes, collected from historical ads and the Google Ads Keyword Planner. A comparative experimental approach was employed, with the data split into training (80%) and testing (20%) sets. The analysis revealed that the C4.5 algorithm achieved higher accuracy (85.41%) compared to K-NN (74.86%). Evaluation was based on metrics such as accuracy, precision, recall, and F1-score, which indicated that C4.5 was more effective in predicting conversions using the given dataset. These findings offer valuable insights for advertisers aiming to optimize their ad campaigns by selecting more effective keywords. However, the study also acknowledges limitations and recommends further research using larger and more diverse datasets to enhance model accuracy.
Evaluation of Artificial Neural Network Model for Predicting Nitrogen Oxides (NOₓ) Concentration Arsyada, Muhammad Farrih Mahabbataka; Tyasnurita, Raras
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.4371

Abstract

Nitrogen Oxides (NOₓ) are air pollutants that require serious attention due to their potential negative impacts on human health, the environment, and the economy. This research is crucial to provide accurate predictive models of NOₓ concentration, which can serve as a foundation for decision-making and effective air pollution mitigation measures. The objective of this study is to evaluate several artificial neural network (ANN) models to determine the most effective model for accurately predicting NOₓ concentrations. One of the methods used for predicting air pollution data, such as NOₓ, is artificial neural networks (ANN). In this study, four ANN models were constructed and evaluated: Feed Forward Neural Network (FNN), Time Lagged Neural Network (TLNN), Seasonal Artificial Neural Network (SANN), and Long Short-Term Memory (LSTM). The models predict NOₓ concentration using data from the air quality dataset provided by the UCI Machine Learning Repository. Testing results indicate that the LSTM model performs best, achieving the lowest error value, characterized by 24 input nodes, three hidden nodes, one output node, and 300 training epochs. The RMSE values for LSTM, FNN, TLNN, and SANN are 57.3, 62.8, 64, and 89, respectively.
Development of Joomla based Website for Mapping and Location Information of Waste Disposal Sites in Palembang Wibagso, Stefanus Setyo; Adi, Steven
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.4965

Abstract

Waste is a problem that occurs in many areas. Palembang City is no exception, which will contribute 1,180 tons of waste per day in 2023. One solution that can be offered to reduce the amount of waste scattered around is the existence of a website that provides map information and the location of Temporary Waste Disposal Sites (TPS). This website facilitates the retrieval of information regarding local waste disposal sites, enabling individuals to locate them swiftly and effortlessly, thus promoting the proper disposal of waste at designated areas. For website development, researchers will use CMS Joomla and the Phoca Maps extension. The design stages adopt RAD methodology consisting of requirement planning, user design, construction, and cutover. In the functionality assessment, accurate results were achieved for Map Search and locations categorized by Specific Area Categories and TPS Names. The results obtained from this research are that the website provides information on maps and TPS locations. Joomla CMS, along with the Phoca Maps extension, offers benefits in terms of convenience, affordability, and ease of managing maps and location markers. Additionally, this study presents an alternative perspective on the use of Joomla CMS, which is typically associated with text or image content usage.
Sentiment Analysis of Public Satisfaction with the 'INFO BMKG' Application using Naive Bayes, SVM, and KNN Aditiya, Natasya; Setiaji, Pratomo; Supriyono, Supriyono
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5223

Abstract

This study aims to analyze public sentiment regarding the Info BMKG application on the Google Play Store. With the increasing number of users of information-based applications, understanding how users perceive and evaluate such applications has become essential. This research employs three classification algorithms—Naive Bayes, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)—to categorize user reviews into positive, neutral, or negative sentiments. The dataset was obtained through web scraping from the Google Play Store, consisting of usernames, dates, star ratings, and user comments. Data preprocessing was conducted to clean and prepare the data for analysis. Additionally, a web-based data mining application was developed to facilitate data processing and result visualization. The study aims to present the distribution of sentiment (positive, neutral, and negative) toward the Info BMKG app and help developers understand the factors that influence user satisfaction. Moreover, it contributes to the field of sentiment analysis and information technology, particularly in disaster-related information applications. Based on model evaluation, the Naive Bayes algorithm demonstrated the best performance with an accuracy of 79.84%, precision of 60%, recall of 58%, and the fastest runtime at 0.19 seconds. KNN achieved an accuracy of 74.35% with the lowest recall at 44%, while SVM had an accuracy of 72.26% but required the longest runtime at 611 seconds. AUC validation further confirmed the superiority of Naive Bayes, with the highest scores across all sentiment categories. Thus, Naive Bayes is shown to be the most optimal for sentiment analysis in this study, whereas KNN and SVM showed certain limitations, particularly in efficiency and classification accuracy.
Comparative Analysis of Oversampling and SMOTEENN Techniques in Machine Learning Algorithms for Breast Cancer Prediction Yulian, Tri; Susanto, Erliyan Redy
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5146

Abstract

Breast cancer is the leading cause of cancer-related death among women, with one of the major challenges in developing predictive models being the class imbalance in medical datasets. This imbalance hinders the detection of minority classes (patients with cancer), which is critical for early diagnosis. This study aims to analyze the performance of Support Vector Machine (SVM) and Random Forest algorithms in predicting breast cancer using oversampling and SMOTEENN preprocessing techniques. The dataset used is the SEER Breast Cancer Dataset, which was balanced using both techniques. Model performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results showed that SVM with oversampling achieved the highest accuracy of 98.97%, followed by SVM with SMOTEENN at 97.20%. Random Forest with oversampling reached an accuracy of 96.63%, while with SMOTEENN it achieved 95.90%. SVM proved more effective in identifying both classes with minimal error, particularly when combined with oversampling. These findings highlight that selecting the appropriate model and data preprocessing technique—such as oversampling or SMOTEENN—can significantly enhance predictive accuracy. This research contributes to the development of more accurate and reliable breast cancer prediction systems, supporting early diagnosis and clinical decision-making in medical applications.
Data Analysis using Business Intelligence and Tableau for Visualizing Indonesia's Poverty Line Senduk, Fabianus Kevin; Waluyo, Retno; Isnaini, Khairunnisak Nur
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.4993

Abstract

Poverty is the condition of being unable to meet an adequate standard of living. The poverty line serves as a key indicator for measuring poverty, particularly in developing countries. In Indonesia, poverty line data provided by the Central Statistics Agency (Badan Pusat Statistik – BPS) is typically presented in static tables, lacking in-depth analysis or annual trend insights needed to understand poverty dynamics across 578 regions. This study aims to analyze poverty line data in Indonesia using a Business Intelligence (BI) approach and visualize it through Tableau Public. BI was chosen for its capability to process complex data into more accessible and actionable information for decision-making. The output of this study is an interactive visualization dashboard that illustrates the distribution patterns and trends of the poverty line in Indonesia over the period 2022–2024. The dashboard offers in-depth insights into regional poverty shifts, including the identification of high-poverty areas and analysis of poverty line growth rates. It also serves as a strategic data-driven decision support tool. This research can be further developed by exploring the underlying factors driving poverty line fluctuations, applying the method to other dimensions such as income inequality, and leveraging alternative data visualization tools for a more comprehensive analysis.
Optimizing Feature Selection in Sentiment Analysis of Bank Saqu: A Comparative Study of SVM and Random Forest using Information Gain and Chi-Square Subandono, Anelta Tirta Putri; Ariatmanto, Dhani
Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.5106

Abstract

The selection of an optimal feature selection method is a crucial factor in improving the accuracy and efficiency of text classification models. Irrelevant features can degrade model performance, increase computational complexity, and lead to overfitting. Although various feature selection techniques have been employed in sentiment analysis, systematic studies comparing the effectiveness of Information Gain and Chi-Square in enhancing classification performance remain limited. This study aims to evaluate and optimize the impact of different feature selection methods on the performance of Support Vector Machine (SVM) and Random Forest (RF) in sentiment analysis. Experiments were conducted using eight testing schemes, including models without feature selection, with Information Gain, Chi-Square, and a combination of both. The results showed that SVM with Chi-Square achieved the highest accuracy at 93%, while Random Forest with Chi-Square achieved the best performance at 91%. These findings indicate that Chi-Square is more effective than Information Gain in improving accuracy, and that SVM outperforms Random Forest in text classification tasks. In conclusion, selecting the appropriate feature selection method significantly contributes to enhancing the accuracy of text classification models. This research can serve as a reference for optimizing feature selection techniques in the development of more accurate and efficient machine learning-based systems.
Information Retrieval Method for the Qur’an based on FastText and Latent Semantic Indexing ramadhan, aziz; Utomo, Fandy Setyo
SISTEMASI Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i3.4446

Abstract

Retrieving contextually relevant verses from the Al-Qur'an translation dataset presents significant challenges due to the linguistic richness and semantic variation of the text. This study aims to enhance the accuracy and relevance of information retrieval in the Al-Qur'an translation dataset by combining Latent Semantic Indexing (LSI) and FastText word embeddings. The proposed method involves several steps: text preprocessing (lowercasing, punctuation removal, stopword elimination, and stemming), tokenization and vocabulary creation, Bag-of-Words (BoW) representation, creation of LSI models, conversion of FastText vectors, and combining LSI and FastText vectors. A similarity index is then created from the combined vectors to process user queries and rank documents based on cosine similarity. Testing on the dataset, consisting of 6236 translated verses from 114 surahs, showed promising results. The combined approach effectively captures both broader semantic structures and detailed word meanings, providing more accurate and contextually relevant search results. Key findings include high similarity scores, with 90% of retrieved verses being highly relevant to the user query, an accuracy improvement to 85%, and enhanced handling of synonyms and morphological variations at 88%. Further development is recommended, including parameter optimization, advanced preprocessing techniques, real-time search optimization, integration of contextual embeddings, and multilingual support to improve search performance and accuracy.

Page 3 of 4 | Total Record : 40

 1   2   3   4 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 14, No 6 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 5 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 4 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 3 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 2 (2025): Sistemasi: Jurnal Sistem Informasi Vol 14, No 1 (2025): Sistemasi: Jurnal Sistem Informasi Vol 13, No 6 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 5 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 4 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 3 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 2 (2024): Sistemasi: Jurnal Sistem Informasi Vol 13, No 1 (2024): Sistemasi: Jurnal Sistem Informasi Vol 12, No 3 (2023): Sistemasi: Jurnal Sistem Informasi Vol 12, No 2 (2023): Sistemasi: Jurnal Sistem Informasi Vol 12, No 1 (2023): Sistemasi: Jurnal Sistem Informasi Vol 11, No 3 (2022): Sistemasi: Jurnal Sistem Informasi Vol 11, No 2 (2022): Sistemasi: Jurnal Sistem Informasi Vol 11, No 1 (2022): Sistemasi: Jurnal Sistem Informasi Vol 10, No 3 (2021): Sistemasi: Jurnal Sistem Informasi Vol 10, No 2 (2021): Sistemasi: Jurnal Sistem Informasi Vol 10, No 1 (2021): Sistemasi: Jurnal Sistem Informasi Vol 9, No 3 (2020): Sistemasi: Jurnal Sistem Informasi Vol 9, No 2 (2020): Sistemasi: Jurnal Sistem Informasi Vol 9, No 1 (2020): Sistemasi: Jurnal Sistem Informasi Vol 8, No 3 (2019): Sistemasi: Jurnal Sistem Informasi Vol 8, No 2 (2019): Sistemasi: Jurnal Sistem Informasi Vol 8, No 1 (2019): Sistemasi Vol 8, No 1 (2019): Sistemasi: Jurnal Sistem Informasi Vol 7, No 3 (2018): Sistemasi: Jurnal Sistem Informasi Vol 7, No 2 (2018): Sistemasi: Jurnal Sistem Informasi Vol 7, No 2 (2018): SISTEMASI Vol 7, No 1 (2018): Sistemasi: Jurnal Sistem Informasi Vol 6, No 3 (2017): Sistemasi: Jurnal Sistem Informasi Vol 6, No 2 (2017): Sistemasi: Jurnal Sistem Informasi Vol 6, No 1 (2017): Sistemasi: Jurnal Sistem Informasi Vol 5, No 3 (2016): Sistemasi: Jurnal Sistem Informasi Vol 5, No 2 (2016): Sistemasi: Jurnal Sistem Informasi Vol 5, No 2 (2016): sistemasi Vol 5, No 1 (2016): Sistemasi: Jurnal Sistem Informasi Vol 4, No 3 (2015): Sistemasi: Jurnal Sistem Informasi Vol 4, No 2 (2015): Sistemasi: Jurnal Sistem Informasi Vol 4, No 1 (2015): Sistemasi: Jurnal Sistem Informasi Vol 3, No 4 (2014): SISTEMASI: Jurnal Sistem Informasi Vol 3, No 3 (2014): Sistemasi: Jurnal Sistem Informasi Vol 3, No 2 (2014): Sistemasi: Jurnal Sistem Informasi Vol 3, No 1 (2014): Sistemasi: Jurnal Sistem Informasi Vol 2, No 4 (2013): Sistemasi: Jurnal Sistem Informasi Vol 2, No 3 (2013): Sistemasi: Jurnal Sistem Informasi Vol 2, No 2 (2013): Sistemasi:Jurnal Sistem Informasi Vol 2, No 1 (2013): Sistemasi: Jurnal Sistem Informasi More Issue