cover
Contact Name
Fransiskus Panca Juniawan
Contact Email
Fransiskus Panca Juniawan
Phone
-
Journal Mail Official
fransiskus.pj@atmaluhur.ac.id
Editorial Address
-
Location
Kota pangkal pinang,
Kepulauan bangka belitung
INDONESIA
Jurnal Sisfokom (Sistem Informasi dan Komputer)
ISSN : 23017988     EISSN : 25810588     DOI : -
Jurnal Sisfokom merupakan singkatan dari Jurnal Sistem Informasi dan Komputer. Jurnal ini merupakan kolaborasi antara sivitas akademika STMIK Atma Luhur dengan perguruan tinggi maupun universitas di Indonesia. Jurnal ini berisi artikel ilmiah dari peneliti, akademisi, serta para pemerhati TI. Jurnal Sisfokom diterbitkan 2 kali dalam setahun yaitu pada bulan Maret dan September. Jurnal ini menyajikan makalah dalam bidang ilmu sistem informasi dan komputer.
Arjuna Subject : -
Articles 603 Documents
Comparative Analysis of Random Forest and Support Vector Machine for Sundanese Dialect Classification Using Speech Recognition Features Anshor, Abdull Halim; Wiyatno, Tri Ngudi
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2347

Abstract

This study investigates the classification of West and South Sundanese dialects using Random Forest (RF) and Support Vector Machine (SVM). Using a dataset of 100 recordings with features extracted via Mel Frequency Cepstral Coefficient (MFCC), models were evaluated by accuracy, precision, recall, and F1-score. Results show RF achieved an accuracy of 93.33%, outperforming SVM's 73.33%. The analysis demonstrates that RF is more reliable in distinguishing dialectal features. This research contributes to regional speech recognition, supporting language preservation and improved dialectal analysis.
The Effect of SMOTE and Optuna Hyperparameter Optimization on TabNet Performance for Heart Disease Classification Wijayanto, Danang; Marco, Robert; Sidauruk, Acihmah; Sulistiyono, Mulia
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2348

Abstract

Heart disease is a medical condition affecting the cardiovascular system, disrupting blood circulation and reducing cardiac function efficiency, which can lead to severe health complications. Early diagnosis of heart disease has become increasingly crucial as delayed detection can significantly impact patient outcomes and survival rates. While numerous studies have explored various approaches for heart disease classification, challenges related to data imbalance and improper parameter settings remain persistent issues that affect model performance. This research evaluated the effectiveness of combining TabNet with SMOTE and optuna hyperparameter optimization for heart disease classification. We conducted four experimental scenarios using a heart disease dataset with 303 instances: baseline TabNet, baseline TabNet with SMOTE, TabNet with Optuna, and TabNet with both SMOTE and Optuna. Results demonstrated that applying SMOTE alone to TabNet decreased model performance (accuracy from 85.24% to 77.04%, AUC from 0.89 to 0.83). However, when combining SMOTE with Optuna hyperparameter optimization, we achieved optimal performance with 90.16% accuracy, 93.33% precision, 87.50% recall, 90.32% F1-score, and 0.93 AUC. This represented a significant improvement over other configurations and several previous classification approaches. The integration of SMOTE with Optuna optimization  provided an effective framework for heart disease classification that outperformed traditional methods particularly in discriminative capability as evidenced by the superior AUC score.
Trend Analysis and Prediction of Violence Against Women and Children Cases in Jakarta Based on the Victim’s Education Level Using ARIMA and SARIMA Method Kurniawan, Zaqi; Tiaharyadini, Rizka; Wibowo, Arief; Rusdah
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2349

Abstract

Violence against women and children remains a critical social issue in Jakarta, Indonesia, where densely populated urban areas often correlate with increased risks of domestic abuse. The urgency of addressing this problem lies in its direct impact on public health, education, and community well-being. This study uses time series prediction models to examine and anticipate trends in the number of reported incidents of violence against women and children in Jakarta. Using publicly accessible data from Jakarta Open Data and the National Commission for the Protection of Women and Children, we applied the ARIMA and SARIMA  Models. Key variables included in the dataset are the data period, education level, and total number of victims Using three performance indicators—MAE (Mean Absolute Error), MAPE (Mean Absolute Percentage Error), and RMSE (Root Mean Square Error)—to assess model accuracy the ARIMA model performed better than the SARIMA model. SARIMA recorded an RMSE of 80.26, an MAE of 66.21, and an undefined MAPE because of zero values in the real data, while ARIMA specifically obtained an RMSE of 32.22, an MAE of 32.09, and a MAPE of 5.19%. These results suggest that the non-seasonal ARIMA model is more suitable for this dataset. The study contributes to policy planning and early intervention strategies by offering a data-driven approach to predicting trends in violence within urban contexts.
Application of SMOTE-ENN Method in Data Balancing for Classification of Diabetes Health Indicators with C4.5 Algorithm Bakti Putra Pamungkas; Muhammad Jauhar Vikri; Ita Aristia Sa'ida
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2350

Abstract

Data imbalance in health datasets often leads to decreased performance of classification models, especially in detecting minority classes such as diabetics. This study evaluates the effect of the SMOTE-ENN method on improving the performance of the C4.5 algorithm in the classification of diabetes health indicators. The dataset used is the 2021 Diabetes Binary Health Indicators BRFSS from Kaggle, which consists of 236,378 respondent data with unbalanced class distribution: 85.80% non-diabetic and 14.20% diabetic. The SMOTE method was used to add synthetic data to the minority classes, while ENN was applied to remove data considered noise. After balancing, the C4.5 algorithm was used for classification. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results showed that the application of SMOTE-ENN improved accuracy from 79.49% to 80.33% and precision from 29% to 30%. Although the recall value did not increase, this method proved to be able to improve the overall stability of the prediction, especially in terms of the accuracy of the classification of the positive class. The novelty of this research lies in the specific application of the SMOTE-ENN method on large-scale health datasets with the C4.5 algorithm, which has not been widely explored before. Therefore, further exploration of other balancing techniques and algorithms is needed to obtain more optimal classification results on unbalanced data.
Implementation of Elementary School Student Attendance Information System Based on Android using AppSheet Reni Haerani; Devi, Putri Ayu Permata; Hendriyati, Penny; Ansor, Ahmad Sofan
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2351

Abstract

This study aims to implement an Android-based elementary school student attendance information system using the AppSheet platform. This system is designed to replace the manual attendance method that is still widely used, making it easier for teachers to record student attendance and provide real-time attendance reports. AppSheet was chosen because of its ability to create Android-based applications without the need for complex programming skills. This system has key features such as attendance recording, cloud data storage, and integrated report access. The study results show that implementing this attendance information system can increase the efficiency of the attendance recording process by 89% compared to the manual method. In addition, attendance reports can be accessed by the school quickly and accurately. This system also received positive responses from teachers and administrative staff because of its ease of use. This system also improves the efficiency of attendance data management and makes the communication process between schools and parents more effective. Thus, the Android-based attendance information system using AppSheet provides a practical solution relevant to current technological developments, supporting digital transformation for managing student attendance data in elementary schools.
Optimizing Gated Recurrent Unit (GRU) for Gold Price Prediction: Hyperparameter Tuning and Model Evaluation on Historical XAU/USD Data Faqih, Abdul; Vikri, Muhammad Jauhar; Sa’ida, Ita Aristia
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2352

Abstract

This study investigates the use of a Gated Recurrent Unit (GRU) model with a four-layer architecture for daily gold price closing prediction, motivated by the model's ability to effectively capture temporal dependencies in time series data. Gold price forecasting is highly challenging due to its volatility and external factors, making it an important area of research for investors and financial analysts. By systematically optimizing hyperparameters through 72 combinations of epochs, batch size, GRU layer units, and dropout rates, the study identifies the optimal configuration (100 epochs, batch size of 16, 256 units, dropout rate 0.1) based on MSE performance on validation data. The best model achieved MAE of 25.76, MSE of 954.97, and RMSE of 30.90, after inverse transformation on test data. These results highlight the potential of the GRU model in accurately forecasting gold prices, with implications for financial decision-making . However, the prediction error suggests that further improvements could be made by incorporating external factors or exploring advanced model architectures.
Skincare Recommendation System Based on Facial Skin Type with Real-Time Weather Integration Gabrielle Sheila Sylvagno; Rochadiani, Theresia Herlina
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2355

Abstract

Skin conditions can be significantly affected by unpredictable weather changes, creating the need for a solution that can provide personalized skincare product recommendations. This study presents the development of an AI-based skincare recommendation system that integrates skin type classification using Convolutional Neural Networks (CNN) with real-time weather data via the OpenWeatherMap API. The system consists of three main components: a ResNet50-based Skin Analyzer, a Weather Analyzer using the Decision Tree algorithm, and a Product Recommendation module. The image dataset is sourced from two Kaggle datasets: "Dry, Oily, and Normal Skin Types" and "Acne Dataset." The total dataset consists of 2,885 images, divided into four classes: Acne (549 images), Dry (652 images), Normal (884 images), and Oily (800 images). The dataset exhibits diversity in skin types, allowing for a more valid evaluation of the CNN model. The training and testing process involved splitting the data into training and testing sets, with augmentation applied to the training data to enhance the feature diversity across classes. Evaluation results show an average validation accuracy of 90.94% ± 0.60% with consistent performance. This system aids users in identifying their skin type and suggests appropriate skincare products based on current weather conditions. It is expected to contribute to the advancement of AI-driven personalization in the skincare industry.
Implementation Of Triple Exponential Smoothing Method To Predict Palm Oil Production Of PT.Lonsum Web-Based syafhira ananda galasca; Harahap, Aninda Muliani
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2358

Abstract

This research aims to develop a web-based palm oil (CPO) production forecasting system by applying the Triple Exponential Smoothing (TES) method to the production data of PT Lonsum Turangi. The data used includes 60 monthly data from 2020 to 2024. The first 36 data were used for model training, while the remaining 24 data were used for validation. Research instruments included semi-structured interviews and participatory observations to understand the operational patterns and needs of the system in the field. Triple Exponential Smoothing method was chosen for its ability to handle level, trend and seasonal components simultaneously, making it superior to other time series forecasting methods that require large volumes of data. The system was developed using the Rapid Application Development (RAD) method, PHP programming language, and MySQL database. The test results show a good level of prediction accuracy with a Mean Absolute Percentage Error (MAPE) value of 17.34% at an alpha value of 0.1. This system not only improves prediction accuracy, but also provides practical benefits in production planning, meeting market demand, and reducing potential losses due to production imbalances. The novelty of this research lies in the integration of the TES method into a web-based decision support system specific to the CPO industry.
Modeling Political Discourse in Indonesia’s 2024 Election Using Unsupervised Machine Learning Malikhatul Ibriza; Maya Rini Handayani; Wenty Dwi Yuniarti; Khothibul Umam
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2359

Abstract

The 2024 General Election in Indonesia has generated a large volume of diverse and unstructured digital political discourse, necessitating a machine learning-based analytical approach for efficient, objective, and scalable data processing. This study aims to map political discourse from 14,813 text data collected from the open-source "Indonesian Election 2024" dataset on the Hugging Face platform, encompassing social media posts (e.g., Twitter) and online news content from January to March 2024. This research integrates three core methods: Principal Component Analysis (PCA) for dimensionality reduction, K-Means for clustering, and Latent Dirichlet Allocation (LDA) for topic extraction. This combination represents an original approach in Indonesian political discourse studies, leveraging unsupervised learning techniques to enhance topic mapping efficiency compared to single-method approaches in prior research. The analysis identified three primary clusters electoral technical issues, candidate figures, and official agendas yielding a Silhouette Score of 0.51 (a clustering quality metric) and a top topic coherence score of 0.51. Validation was conducted both quantitatively and qualitatively by content experts. This approach not only demonstrates strong analytical capability in uncovering thematic patterns but also offers practical applications for institutions such as the General Elections Commission (KPU), Election Supervisory Body (Bawaslu), and the media in monitoring strategic issues and detecting potential disinformation in the lead-up to the election.
Selection of Recipients of Excellent Scholarship Educational Assistance using Simple Addictive Weighting Method Rudi Hidayat; Ryan Prasetya; Gandung Triyono
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 2 (2025): MEY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i2.2360

Abstract

The selection of educational assistance recipients is an important process that determines the effectiveness of aid distribution. However, inconsistencies in assessment criteria and less systematic data management often become obstacles in determining the right recipient candidates. This problem results in subjectivity and lack of transparency in the selection process. This study proposes a solution in the form of implementing the Simple Additive Weighting (SAW) method as a multi-criteria-based decision support system. This method is used to process data on prospective recipients with criteria including economic conditions, number of family dependents, written test results, and interviews. The approach used is quantitative descriptive with stages of data collection, criteria weighting, SAW score calculation, and evaluation of results. The results of the study show that the SAW method is able to provide objective and consistent rankings of prospective recipients. Evaluation of real data on scholarship recipients shows an accuracy level of 84.62%, indicating the effectiveness of this method in the selection process. These results indicate that the SAW method can be an effective solution to increase transparency, consistency, and fairness in the educational assistance selection process.