cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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)
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Atma Luhur
ISSN : 23017988     EISSN : 25810588     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management
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 709 Documents
 67   68   69   70   71 
Music Playlist Personalization Using Clustering Analysis of Large-Scale Spotify Audio Features Qurothu Aini Ajizah
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2620

Abstract

Music streaming platforms provide access to extensive song collections; however, the abundance of available content often makes it difficult for users to create playlists that remain consistent with their musical preferences. This study proposes a content-based playlist personalization approach by grouping songs using clustering analysis of Spotify audio features, including danceability, energy, valence, tempo, loudness, and acousticness. K-Means clustering is applied to identify groups of songs with similar audio characteristics, and the number of clusters is determined through a multi-criteria evaluation to ensure a balance between compactness and separation. The results indicate that a two-cluster configuration provides the most stable and interpretable structure, supported by the highest Silhouette score (0.315). The identified clusters reveal distinct musical profiles, particularly along the energy and acousticness dimensions, which can be associated with different listening contexts. These findings suggest that clustering based on audio features can support the construction of more coherent playlists by grouping songs with consistent characteristics. This study contributes by providing a structured approach to cluster selection and demonstrating its relevance for playlist personalization, especially in scenarios where user interaction data is limited.
Security Risk Evaluation of ZombAI Claude: Prompt Injection as a Backdoor for Command and Control Exploitation Indra Bayu; Mahar Faiqurahman
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2634

Abstract

The rapid adoption of AI in industrial automation has introduced AI agents functioning as Command and Control (C2) systems capable of managing infrastructure autonomously. The integration of "Computer Use" into Claude Sonnet 4.5 introduces critical vulnerabilities exploitable through prompt-injection attacks. This study presents ZombAI, a direct black-box attack method targeting AI agents via six distinct strategies: Template Completion, In-Context Attack, Code Injection, Prompt Rewriting, Low-Resource Language exploitation, and Genetic Algorithm-based perturbation. Each strategy targets different layers of the model's safety filters without requiring internal model access or knowledge of training data. Experiments were conducted using Claude Sonnet 4.5 integrated into the Bytebot framework within a Docker sandbox environment to simulate real-world attack conditions. Results demonstrate a global attack success rate of 78%, with Low-Resource Language attacks achieving an absolute success rate of 100%, attributed to the absence of robust safety filtering for non-dominant languages within the Computer Use tool. These findings reveal that AI agents granted C2 authority harbor critical vulnerabilities transforming them into zombie executors capable of performing Remote Code Execution (RCE) without user awareness, underscoring the urgent need for language-inclusive security evaluation frameworks for autonomous AI systems.
Comparative Analysis of the Performance of Machine Learning and Deep Learning Methods in Detecting Hate Speech in Indonesia Priscilla Desinta Achelya; Ni Wayan Sumartini Saraswati; I Putu Agus Eka Darma Udayana
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2635

Abstract

The rapid expansion of social media usage in Indonesia has increased the spread of harmful online communication, including hate speech, which may contribute to social conflict and discrimination. As a result, automated hate speech identification has become an important research area in Indonesian natural language processing. Although many studies have applied machine learning and deep learning techniques for this task, comprehensive comparisons between conventional algorithms and transformer-based models in the Indonesian context remain limited. This study evaluates several machine learning algorithms, namely Naïve Bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF), alongside the transformer-based IndoBERT model for Indonesian hate speech classification. All models were trained and evaluated using the same dataset, identical preprocessing stages, and consistent evaluation metrics consisting of accuracy, precision, recall, and F1-score to ensure fair comparison. Experimental findings show that IndoBERT achieved the strongest overall performance, reaching an accuracy of 87.45% and an F1-score of 84.92%. Among the classical machine learning approaches, Logistic Regression produced the highest result with an accuracy of 84.49% and an F1-score of 84.32%. While several machine learning models obtained relatively competitive recall values, IndoBERT demonstrated more stable performance across evaluation metrics and showed stronger capability in understanding contextual language patterns commonly found in Indonesian social media content. Overall, the study highlights the advantages and trade-offs between conventional machine learning and transformer-based deep learning approaches in Indonesian hate speech detection, while also providing practical insights for developing automated content moderation systems.
O Optimization of Support Vector Machine Method Using Recursive Feature Elimination Feature Selection for Monkeypox Symptom Classification Yuniar Farida; Iftitakhun Ni'mah; Putroue Keumala Intan
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2636

Abstract

Regional outbreaks of monkeypox highlight the need for accurate and efficient symptom-based classification to support early detection. This study aims to improve the classification performance of monkeypox symptoms using a Support Vector Machine (SVM) optimized with Recursive Feature Elimination (RFE). The dataset consists of 1,000 cases, which were preprocessed via encoding and normalization, followed by feature selection using RFE and classification with SVMs using various kernel functions. Model performance was evaluated using accuracy, precision, sensitivity, and specificity. The results show that RFE successfully identified eight key features—Rectal Pain, Sore Throat, Penile Swelling, Oral Lesions, Swollen Tonsils, Single Lesions, HIV Infection, and Sexually Transmitted Infections—as the most influential variables. The optimized SVM, validated using a confusion matrix, achieved 77% accuracy, 84% precision, 66% sensitivity, and 88% specificity, representing a modest improvement over the baseline SVM (75%). The polynomial kernel demonstrated the best performance, indicating the presence of nonlinear relationships among symptoms. Although the improvement is relatively small, integrating RFE enhances feature relevance and model stability. These findings suggest that feature selection is an effective strategy for refining classification performance, while further validation and comparison with alternative methods are recommended to ensure robustness and generalizability.
Intrusion Detection For Network Security Using Information Gain Filters On Deep Neural Networks Ery Permana Yudha
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2641

Abstract

In recent years, technologies such as big data, cloud computing, and internet networks have grown significantly. Technological advancements are also accompanied by a growth in the number of users of internet-based services, such as cloud services, which grows annually. This growth in user numbers and technological advancements increase the opportunity for cyberattacks through networks, such as theft of user data or information. Therefore, an intrusion detection system is needed as a preventive measure against cyberattacks to protect information on the network. Intrusion detection prevents cyberattacks by using machine learning, which can work effectively in heavy network traffic. Designing an optimal intrusion detection system requires various approaches, such as feature selection and the selected machine learning model. In this study, feature selection was carried out using the filter method, wrapper method, and embedded method. The filter method uses Information Gain (IG) and the wrapper method uses Recursive Feature Elimination (RFE). Then, it was tested with deep learning-based machine learning models such as Deep Neural Network (DNN), Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), and with traditional machine learning models such as Random Forest (RF) and Logistic Regression (LR). In this research, we contribute by proposing a comprehensive comparative study that evaluates multiple feature selection method and machine learning models to identify the most effective combination for improving intrusion detection system performance. In this study, DNN was able to produce the highest average accuracy of 87.38%. This was followed by MLP, LSTM, and Random Forest with 87.28%, 86.48%, and 86.08%, respectively. Furthermore, the Logistic Regression model had the lowest accuracy value, at 72.34%. Furthermore, the best feature selection method, on average, was the wrapper method, providing a 0.14% improvement compared to the baseline.
Implementation of BPS RESTful API on Flutter-Based DALEM Mobile Application for Statistical Data Access Efficiency Aan Kia Asshifa; Bambang Agus Herlambang; Khoiriya Latifa; M Abdul Muhshi
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2646

Abstract

This study addresses the urgent issue of inefficient access to statistical data on the official BPS-Statistics Indonesia, Demak Regency website, particularly under conditions of increasing data volume and limited network stability. Users frequently experience slow response times and high data consumption due to complex web rendering and excessive network requests, which hinder timely access to critical information for decision-making. Therefore, this research aims to implement the RESTful API on the Flutter-based DALEM mobile application to improve the efficiency of access to BPS-Statistics Indonesia, Demak Regency statistical data. The method used is Research and Development (R&D) with the ADDIE model, accompanied by comparative experimental testing of the official BPS website system. Evaluation parameters include response time, number of requests, and data transfer efficiency. The test results showed that mobile applications have an average response time of 437-826 ms with 1-10 requests per scenario, while websites require 1,368-1,790 ms with 80-91 requests. Quantitatively, mobile applications showed an increase in access time efficiency of more than 50% and a reduction in the number of requests by up to 88%. These findings prove that the JSON-based RESTful API architecture combined with Asynchronous programming on Flutter is able to significantly optimize client-server communication in regional statistical data services.
Analysis of the Effect of Frequency Variation on SAR Test Results for Mobile Devices Naila Widhyadari; endah setyowati
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2648

Abstract

The rapid advancement of telecommunications technology led to an expansion of frequency spectrum usage, which raised significant concerns regarding human radiation safety. There was a lack of detailed data concerning how specific frequency fluctuations directly influenced the rate of electromagnetic energy absorption in human tissue. This study aims to provide a comprehensive analysis of Specific Absorption Rate (SAR) values across various frequency bands. A systematic evaluation was conducted to identify the correlation between frequency variation and energy absorption patterns. This research provides a critical contribution by establishing a clearer relationship between device operating frequencies and user safety compliance. The method involved a series of controlled tests across multiple frequency bands commonly utilized in cellular services. Electromagnetic simulations were performed to measure the energy distribution within body tissue models. The results indicated that frequency variation significantly influenced both the distribution and the peak absorption values. Higher frequencies tended to concentrate energy absorption within the surface layers of the body tissue rather than penetrating deeper structures. Furthermore, the data showed that as frequency increased, the absorption patterns became more localized. SAR values remained within international safety limits, yet showed distinct trends for each frequency interval tested. The findings confirmed that frequency was a primary determinant in electromagnetic interaction with biological systems. This study concluded that frequency variation must be a central consideration for establishing device compliance with safety standards. These results served as a foundational reference for optimizing transmission performance while maintaining safe radiation limits.
Digital Security Research Based on Blockchain and Zero Trust : A Bibliometric Analysis (2018–2025) Farrel Carasiola; Rakhmadi Irfansyah Putra
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2652

Abstract

Research integrating blockchain and Zero Trust for digital security is growing rapidly, yet the field remains fragmented and lacks a clear longitudinal mapping of its intellectual and thematic structure. This study applies a Scopus-based bibliometric analysis of 43 publications from 2018–2025 to examine publication growth, collaboration patterns, and knowledge structures using Biblioshiny (bibliometrix). The results show accelerated scientific growth (49.89% annual growth rate) and substantial impact (59.16 citations per document), with an international collaboration rate of 41.86%. Keyword and thematic analyses indicate that blockchain, cybersecurity, and authentication dominate the research landscape, positioning blockchain and cybersecurity as motor themes, while Zero Trust Security emerges as a developing niche theme. This study contributes a consolidated longitudinal map of research fronts, collaboration dynamics, and theme positioning, providing actionable insights for designing decentralized and adaptive security architectures and guiding future research directions in blockchain–Zero Trust digital security.
Real-Time, Machine Learning-Based Personalized Notifications in the Al-Qur’an Tahsin and Tahfiz Mentoring System Fendri Martadinata
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Mentoring for tahsin and tahfiz of the Qur’an is a crucial activity in enhancing the ability to read and memorize the Qur’an correctly and consistently. However, its implementation still faces various challenges, including irregular participant attendance, ineffective schedule coordination, and limitations in the communication system that hinder optimal fulfillment of individual needs. The notification systems currently in use tend to be generic, making them less effective in boosting participant engagement. Furthermore, previous research has generally not integrated machine learning-based predictive approaches with adaptive notification systems in the context of Qur’anic recitation and memorization mentoring, resulting in a gap in efforts to proactively increase participant participation. This study aims to develop an adaptive and personalized real-time notification system using the Random Forest algorithm and WhatsApp Gateway. Random Forest was chosen because it can handle highly complex data, reduce overfitting, and provide stable classification performance. The model is used to analyze attendance patterns, predict potential absences, and determine the appropriate timing and content of messages for each participant. The dataset consists of 5,664 mentoring activity records collected from a campus environment over a specific period. Each record represents a single attendance activity at one session, with a total of 16 sessions per participant. It includes attendance history, activity time, and participant engagement levels. The testing phase indicates that the model achieves an accuracy of 94.17%, with precision, recall, and F1-score of 91.67%, 97.17%, and 94.34%, respectively. These results correspond to a binary classification task (Present and Absent), where a probability threshold of ≥0.5 is applied for triggering notifications. This study offers novelty through the integration of a predictive model with a real-time WhatsApp-based notification system capable of enhancing communication personalization. Its contribution lies in improving the effectiveness of participant engagement through a data-driven adaptive notification approach.
Deep Learning-Based Artificial Neural Network For Predicting HIV/AIDS Risk Using Demographic Data in Medan City Windania Purba; Risda Putri Greccella; Dendy Prasetyo; M Arief; Nimrot Saritua Marbun; Mutiara Adelia Afrita Purba
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 3 (2026): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i3.2657

Abstract

Medan was one of the largest metropolitan areas in Indonesia, characterized by high population density and mobility, which increased the risk of the spread of infectious diseases, including HIV/AIDS. This disease remained a serious public health problem because it attacked the human immune system and increased vulnerability to opportunistic infections. The objective of this research was to develop a predictive model for HIV/AIDS risk using demographic data from Medan City. This study included the analysis of age, gender, year of onset, and transmission factors. The high number of HIV/AIDS cases and the need for a data-driven approach to support more effective prevention measures were the main challenges. Evaluating potential risks played a significant role in generating useful information for guiding decisions related to public health policies. This study used deep learning with an Artificial Neural Network (ANN) algorithm. The process included data preprocessing, min-max scaling for normalization, encoding, data splitting with a ratio of 80:20, and class weighting. The findings indicated that the model obtained an accuracy rate of 57% and an AUC score of 0.632. The results indicated that the majority of cases were found in men, with same-sex transmission playing a role, and individuals aged 25-49 faced the greatest risk. In conclusion, the ANN model showed potential for predicting HIV/AIDS risk, but its performance still needed improvement. Further development was required to achieve better results.

Page 70 of 71 | Total Record : 709

 67   68   69   70   71 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 02 (2026): MAY Vol. 15 No. 01 (2026): JANUARY Vol. 15 No. 3 (2026): JULY Vol. 14 No. 4 (2025): NOVEMBER Vol. 14 No. 3 (2025): JULY Vol. 14 No. 2 (2025): MEY Vol. 14 No. 1 (2025): JANUARY Vol. 13 No. 3 (2024): NOVEMBER Vol. 13 No. 2 (2024): JULY Vol 13, No 2 (2024): JULY Vol. 13 No. 1 (2024): MARET Vol 13, No 1 (2024): MARET Vol 12, No 3 (2023): NOVEMBER Vol. 12 No. 3 (2023): NOVEMBER Vol 12, No 2 (2023): JULI Vol. 12 No. 2 (2023): JULI Vol 12, No 1 (2023): MARET Vol 11, No 3 (2022): NOVEMBER Vol 11, No 2 (2022): JULI Vol 11, No 1 (2022): MARET Vol 10, No 3 (2021): NOVEMBER Vol 10, No 2 (2021): JULI Vol 10, No 1 (2021): MARCH Vol 9, No 3 (2020): NOVEMBER0 Vol 9, No 2 (2020): JULI0 Vol 9, No 1 (2020): MARET0 Vol 9, No 3 (2020): NOVEMBER Vol 9, No 2 (2020): JULI Vol 9, No 1 (2020): MARET Vol 8, No 2 (2019): SEPTEMBER0 Vol 8, No 2 (2019): SEPTEMBER Vol 8, No 1 (2019): MARET Vol 7, No 2 (2018): September Vol 7, No 1 (2018): Maret Vol 6, No 2 (2017): September Vol 6, No 1 (2017): Maret Vol 5, No 2 (2016): September Vol 5, No 1 (2016): Maret Vol 4, No 2 (2015): September Vol 4, No 1 (2015): Maret Vol 3, No 2 (2014): September Vol 3, No 1 (2014): Maret Vol 2, No 1 (2013): Maret 2013 Vol 2, No 2 (2013): September More Issue