cover
Contact Name
Mesran
Contact Email
jurnal.josh@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josh@gmail.com
Editorial Address
Sekretariat Forum Kerjasama Pendidikan Tinggi (FKPT) Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Artikel yang dimuat melalui proses Blind Review oleh Jurnal JOSH, dengan mempertimbangkan antara lain: terpenuhinya persyaratan baku publikasi jurnal, metodologi riset yang digunakan, dan signifikansi kontribusi hasil riset terhadap pengembangan keilmuan bidang teknologi dan informasi. Fokus Journal of Information System Research (JOSH)
Articles 77 Documents
Search results for , issue "Vol 6 No 2 (2025): Januari 2025" : 77 Documents clear
Identifikasi Citra Motif Kain Tenun Sumbawa (Kre Alang) Menggunakan Metode Convolutional Neural Network Arsitektur MobileNetV2 Dianda, Nandita; Rachman, A Sjamsjiar; Yadnya, Made Sutha
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6774

Abstract

Weaving is a cultural product that reflects the identity of the people who make it, with each region having its patterns, beauty, and distinctive features of its weaving motifs. However, identifying the origin of the region based on woven fabric motifs is often difficult to do due to the unique and diverse characteristics of the motifs. This paper aims to evaluate the performance of the MobileNetV2 architectural model in classifying the motif image of Sumbawa woven fabrics. This model was tested using a dataset of woven fabric images that included various motifs from Sumbawa. The results showed that the model managed to achieve the highest accuracy of 98.14% in the 20th and 25th epochs, with a training time of less than 1 hour. In the training data, the model obtained an accuracy of 99.71% with a loss of 12.99%, which indicates that the model can recognize images with a very high level of accuracy. However, in the validation data, the accuracy of the model was recorded at 92.71% with a loss of 41.98%, which shows that despite the decrease in accuracy, the model is still able to generalize well on data that has never been encountered before. In addition, the model showed excellent results in terms of precision (98.14%), recall (100%), and f1-score (99%). These findings confirm the effectiveness of the MobileNetV2 model in recognizing Sumbawa woven fabric motifs and provide a solid basis for the development of an automated system in supporting the preservation and promotion of regional weaving culture. This paper also shows the importance of model optimization to improve accuracy on validation data and reduce the gap between training data and unseen data. As a next step, the research can be directed to expand the dataset with more variations of motifs and regions to improve the model's ability to generalize to different types of woven fabric motifs.
Evaluating Deep Learning Models for HIV/AIDS Classification: A Comparative Study Using Clinical and Laboratory Data Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6783

Abstract

The accurate classification of HIV/AIDS status is critical for effective diagnosis, treatment planning, and disease management. This study evaluates the performance of four deep learning models: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) on a comprehensive clinical and laboratory dataset derived from the AIDS Clinical Trials Group Study 175. The dataset includes features such as demographic information, treatment history, and immune markers like CD4 and CD8 counts. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, followed by stratified 10-fold cross-validation to ensure robust evaluation. Each model's performance was assessed using metrics including accuracy, precision, recall, F1-score, and ROC-AUC. GRU emerged as the most effective model, achieving the highest accuracy (71.04%) and ROC-AUC (57.72%), demonstrating its robustness in handling sequential data. CNN and LSTM showed competitive performance, particularly in balancing precision and recall. However, all models faced challenges in recall, highlighting difficulties in identifying minority-class samples. The findings underscore the potential of GRU for HIV/AIDS classification while identifying limitations in current approaches to handling class imbalance. Future work will explore advanced architectures, such as attention mechanisms and hybrid models, to further improve sensitivity and robustness. This study contributes to the growing body of research on applying deep learning to healthcare, with implications for improving diagnostic accuracy and patient outcomes.
Performance Evaluation of Machine Learning Models for HIV/AIDS Classification Airlangga, Gregorius
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6790

Abstract

Accurate and early diagnosis of HIV/AIDS is critical for effective treatment and reducing disease transmission. This study evaluates the performance of several machine learning models, including Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naive Bayes, for classifying HIV/AIDS infection status. A dataset comprising 50,000 samples was used, and models were assessed based on accuracy, precision, recall, and F1 score using stratified ten-fold cross-validation to ensure robust evaluation. The results reveal significant trade-offs between sensitivity and specificity across the models. Gradient Boosting achieved the highest accuracy (70.85%) and precision (57.81%), making it suitable for confirmatory testing where minimizing false positives is critical. Conversely, Naive Bayes demonstrated the highest recall (57.99%) and F1 score (51.04%), emphasizing its effectiveness in early-stage diagnostics where sensitivity is paramount. SVM exhibited the highest precision (59.87%) but struggled with recall (11.28%), reflecting its conservative nature in classifying positive cases. These findings underscore the importance of selecting models tailored to specific diagnostic objectives. While Naive Bayes is ideal for comprehensive screening programs, Gradient Boosting and SVM are better suited for confirmatory testing. This research provides valuable insights into the strengths and limitations of machine learning models for medical diagnostics, paving the way for developing more robust, hybrid approaches to optimize sensitivity and specificity in HIV/AIDS classification.
Penerapan Geographic Information System (GIS) Menggunakan Metode GeoJSON untuk Visualisasi Data Geospasial Sebaran UMKM Batik Al'Amin, M; Naufal, Abdul Razak; Suseno, Akrim Teguh
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.5977

Abstract

Pekalongan City is one of the cities where batik grows. Until now, there are thousands of batiks MSMEs spread across many points in Pekalongan. To introduce batik MSMEs to the general public, a WebGIS-based platform is needed as an information center for Pekalongan batik. This research aims to build a website-based Geographic Information System (GIS) using GeoJSON as a platform for mapping the distribution of MSMEs of Batik and a digital batik literacy center in Pekalongan City. The GeoJSON method is used because it has the ability to read population data in only 14.7 seconds, loading geographic data via the GIS REST API usually takes 38.4 seconds, this makes it very suitable for use in web applications. Its simplicity, compatibility and platform independence have contributed to the geospatial community. GeoJSON is a natural fit with modern web technologies such as JavaScript, which makes it easy to use in web application development and integrates with web service APIs. The test scenario results obtained a total score of 85.8 and the System Usability Scale (SUS) test results obtained a total score of 83.5, which places it in the very good category. The SUS rating scale indicates that potential users find this application easy to use. The design of this application based on test results shows a better effect in terms of ease of use, apart from that, potential users generally give positive marks, so it can be concluded that the implementation of WebGIS using the GeoJSON method for visualizing the distribution of Batik MSMEs can be implemented very well.
Sentiment Analysis of Multilingual Customer Reviews in the Hospitality Sector Puspitarini, Titis
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6680

Abstract

This study investigates the role of sentiment analysis in improving service quality and guest satisfaction in the hospitality industry. Recognizing the increasing importance of customer feedback in shaping operational strategies, the research utilized a dataset of 1,141 original hotel reviews, comprising 1,113 positive and 28 negative sentiments. The methodology employed IndoBERT for sentiment classification, supported by a series of preprocessing steps, including text normalization, stopword removal, and text length filtering, to ensure data integrity. To address the significant class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied, resulting in a balanced dataset of 1,923 reviews, with 1,450 positive and 473 negative sentiments. The model demonstrated strong performance, achieving an Area Under the Curve (AUC) score of 94.7%, highlighting its capability to classify sentiments accurately. Findings reveal that positive sentiments often focus on room quality, staff friendliness, and breakfast service, while negative feedback highlights service delays and cleanliness issues. These insights enable data-driven recommendations for improving guest experiences and addressing critical concerns. The study demonstrates the potential of sentiment analysis as a strategic tool for enhancing service delivery, fostering guest loyalty, and maintaining competitiveness in the hospitality market.
Implementasi Model Sistem Dinamik Terhadap Analisis Tingkat Kemacetan Lalu Lintas Lubis, Irsyad Baihaqi; Syahputra, M.R; Syawaluddin, Syawaluddin; Sitorus, Syahriol
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6683

Abstract

Overcoming existing traffic congestion is something that many people hope for, especially people who are always trapped in these traffic problems. One of the methods used to reduce traffic congestion is the dynamic system approach. This method analyses and simulates the problem by determining the causal variables. The analysis was conducted using a causal loop diagram model which was then simulated with a stock flow diagram model using Ventana Simulation (Vensim) software. The results showed that there was a decrease in the average level of traffic congestion on Jalan Setia Budi with an initial condition of 1.06% to 0.71%. This 32% decrease has an impact on traffic conditions that are busy without any delays in travel time on Jalan Setia Budi.
Komparasi Metode Random Forest Dan Support Vector Machine (SVM) Untuk Pemodelan Klasifikasi Serangan DDos Lauwl, Christoper Michael; Husain, Husain; Nuzululnisa, Baiq Nadila; Wijaya, Hartono
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6684

Abstract

The Distributed Denial of Service (DDoS) attack is a type of cyberattack that aims to render a service, network, or website inaccessible to legitimate users. This attack not only disrupts services but also causes server crashes by repeatedly sending data packets, commonly referred to as spam. DDoS attacks can be identified as traffic anomalies. The National Cyber and Crypto Agency (BSSN) recorded 403,990,813 traffic anomalies with 347 cases specifically attributed to DDoS attacks. Based on this issue, a model capable of classifying DDoS attacks is necessary. This study employs the Random Forest and Support Vector Machine (SVM) methods through the steps of data collection, dataset loading, data preprocessing, classification modeling, and performance evaluation. In the final stage, the best method between Random Forest and Support Vector Machine is determined. The results indicate that Random Forest achieved an accuracy of 99.9%, whereas Support Vector Machine obtained an accuracy of 97.0%. Therefore, it can be concluded that Random Forest demonstrates better accuracy in classifying DDoS attacks.
Penerapan Program Dinamik dalam Menentukan Rute Optimal Perjalanan dari Pematangsiantar Menuju Samosir Simarmata, Linda Puspa Ayu; Sitanggang, Intan; Andini, Mira; Sirait, Barthy Ladi C.
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6688

Abstract

A tourist area with many roads often makes it difficult for someone to determine the optimal route, both in terms of distance or costs incurred from the place of origin to the destination. Moreover, in determining a decision support system to determine the route of a tourist trip is needed to determine the optimal route so that the costs incurred are minimum. To solve the problem in this article, we use the dynamic programming method where the method used is the forward method. With the aim of determining the fastest distance from Siantar to Samosir so that the minimum costs incurred. Dynamic Program (dynamic programming) is a method of solving problems by decomposing the solution into a set (stage), such that the solution to the problem can be viewed as a series of interrelated decisions. The solution used is dynamic programming with the data that has been obtained then processed and calculated so that the results obtained are optimal, It is known from the results of the calculation analysis, it can be concluded that the shortest route for tourist trips from Siantar to Samosir, namely from Siantar then to Sidamanik, then to Tomok, continuing to Simanindo, then to Pangururan until finally to Tele with a distance of about 116,2 km /h.
K-Means Clustering Untuk Mengukur Pengaruh Kompetensi Terhadap Kinerja Pegawai Syaqila, Saidatus; Fakhriza, M.
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6758

Abstract

Human resources play an important role in improving organizational performance, including in the North Sumatra Province Youth and Sports Agency (Dispora). This study aims to measure the effect of competence on employee performance using the K-Means Clustering algorithm, known as an unsupervised data clustering method. The dataset consists of 700 employee data with 15 attributes covering technical, managerial, and social competencies. Data were collected through direct surveys and processed using Python with a normalization process through the StandardScaler method to ensure data consistency. The elbow method was used to determine the optimal number of clusters, resulting in five clusters: best performance, very good, and average. The results of the analysis show that the clustering results group employees into five clusters, namely Cluster 0 with 145 employees who have high technical competence, Cluster 1 with 160 employees who excel in social and managerial competence, Cluster 2 with 125 employees who show average competence in all aspects, Cluster 3 with 135 employees who have moderate technical competence but excel in social competence, and Cluster 4 with 135 employees who have great potential for development. This research provides practical benefits in the form of identifying competency patterns for developing group-based training needs, as well as more objective strategic decision-making in human resource management. Thus, this research is expected to support improving employee performance through an effective data-based approach.
Analisis Sentimen Terkait Hilirisasi Industri Pada Opini Masyarakat X dengan Menggunakan Naive Bayes Pratama, Aditya Budi; Febriawan, Dimas
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): Januari 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6795

Abstract

This research examines public sentiment toward Indonesia's industrial downstreaming policy using data sourced from X. The study employs the Naive Bayes algorithm to categorize public opinions into three sentiment types: positive, negative, and neutral. Data collection was conducted via a crawling process utilizing the X API and tools like Tweepy, followed by preprocessing steps such as data cleansing, tokenization, case normalization, stopword removal, and either stemming or lemmatization. Subsequently, the data was manually annotated using a lexicon-based sentiment method to ensure accurate classification. The findings reveal that the Naive Bayes algorithm achieved an accuracy rate of 81.75% in sentiment classification, with the highest performance observed in identifying positive sentiments. This research offers valuable insights into public perspectives on the industrial downstreaming policy and suggests recommendations for policymakers to develop strategies that better resonate with public sentiment. Leveraging X as a data source allows for real-time analysis that adapts to shifts in public opinion.