cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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)
Published by Forum Kerjasama Pendidikan TInggi
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Computer Science & IT Decision Sciences, Operations Research & Management
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)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 870 Documents
 80   81   82   83   84 
Analisis Perbandingan Algortima Support Vector Machine, Random Forest dan Naive Bayes Untuk Prediksi Penyakit Kanker Paru-Paru Rendy Alfa Rizky; Ahmad Fauzi; Dwi Sulistya Kusumaningrum; Hilda Yulia Novita
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9611

Abstract

The lungs are one of the vital organs responsible for the processes of respiration and blood circulation, with smoking habits being the primary factor contributing to the development of lung cancer. In Indonesia, the prevalence of this disease continues to increase, placing it eighth in the Southeast Asian region. Globally, lung cancer accounts for approximately 11.6% of all cancer cases and 18% of total cancer-related deaths.This study aims to analyze and compare the performance of Support Vector Machine (SVM), Random Forest, and Naïve Bayes algorithms in predicting lung cancer, as well as to determine the best-performing algorithm based on accuracy, precision, and recall metrics. The study utilizes the Lung Cancer Prediction dataset obtained from Kaggle, consisting of 309 instances and 16 attributes. The approach involves the implementation of three machine learning algorithms, namely Support Vector Machine (SVM), Random Forest, and Naïve Bayes. The research process includes data collection, preprocessing, data transformation, feature selection, model development, and evaluation using a confusion matrix. The experimental results show that both SVM and Naïve Bayes achieve the same accuracy of 91.07%, while Random Forest obtains an accuracy of 89.28%. In terms of evaluation metrics, SVM demonstrates more consistent performance with a precision of 95% and recall of 93%, whereas Naïve Bayes shows a higher recall of 95% with a precision of 93%. On the other hand, Random Forest exhibits limitations in identifying non-cancer cases. Based on the overall results, SVM is considered the most optimal method as it provides a better balance of performance. This study indicates that machine learning has significant potential as a supporting tool for early detection of lung cancer in a more accurate and efficient manner.
Comparison of Nazief–Adriani and Porter Stemmer in Determining Javanese Root Words Anggi Ayu Maharani; Fadhli Almu’iini Ahda
Journal of Information System Research (JOSH) Vol 7 No 4 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i4.9019

Abstract

Stemming is an important step in text processing to convert inflected words into their root word. In Javanese, the stemming process is more challenging due to its complex morphological characteristics, including prefixes, infixes, suffixes, and combinations of affixes that are often accompanied by phonological changes. This study aims to compare the performance of the Nazief–Adriani and Porter Stemmer algorithms in Javanese stemming by including infix processing as part of the stemming stage. The dataset used consists of 603 Javanese affixed words covering various types of affixes. The evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics, as well as an analysis of over-stemming and under-stemming errors. The results show that the Nazief–Adriani algorithm performs better with an accuracy of 90.05%, compared to the Porter Stemmer, which achieved 76.12%. This advantage is influenced by the validation of the dictionary at each stage of affix cutting, so that the stemming results are more controlled. The application of infix processing has also been proven to contribute to improving the accuracy of stemming results. This study is expected to be a reference in the development of natural language processing systems for Javanese and encourage further research related to the refinement of morphological rules.
Model-Driven Incremental Modernization of a Django–MySQL Monolithic English Test into Go–PostgreSQL-ReactJS Microservices Iqbal Fadhil; Umi Laili Yuhana; Sarwosri Sarwosri
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9128

Abstract

The need for efficient and scalable web-based learning systems is increasing as English proficiency becomes a key employability factor worldwide. The existing English qualification try-out platform, built as a Django–MySQL monolith, showed inadequate performance under concurrent real-exam workloads. This study addresses these limitations by migrating the platform to a Go–PostgreSQL–ReactJS microservices architecture using the Model-Driven Incremental Modernization (MDIM) methodology. The migration starts with reverse engineering to extract structural and behavioral models, represented as UML component and sequence diagrams that capture dependencies and execution flows. These models guide service boundary identification, transformation planning, and stepwise service extraction and validation. Therefore, authentication, user management, and examination workflows are incrementally decomposed into independently deployable services while preserving functional correctness. The new system is deployed as native processes on Ubuntu Server 22.04 and evaluated with k6 for API load testing, JMeter for end-to-end scenarios, and Python scripts for resource and database performance monitoring. Experimental results show that the microservices system reaches 127.57 requests per second with 156.97 ms average latency and 342.68 ms P95 latency, while the monolith on Ubuntu handles 33.40 requests per second and the monolith on cPanel 28.69 requests per second with much higher latency and CPU utilization. These findings demonstrate that the MDIM-guided microservices migration improves scalability, responsiveness, and resource efficiency and provides a reusable, model-based reference for modernizing similar educational assessment platforms.
Peningkatan Keamanan Kunci Vigenère Menggunakan Steganografi Least Significant Bit (LSB) pada Sistem IoT Smart Door QR Code Kasliono Kasliono; Syamsul Bahri; Dwi Marisa Midyanti; Muhammad Dito Asrofa; Riski Arasyid
Journal of Information System Research (JOSH) Vol 7 No 4 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i4.9205

Abstract

In an increasingly connected digital era, the Internet of Things (IoT) enables seamless real-time data exchange across devices but also introduces critical challenges in data security. Although symmetric cryptography is widely adopted for its computational efficiency, key distribution and protection remain major vulnerabilities. This study aims to enhance IoT network security by integrating the Vigenère Cipher with Least Significant Bit (LSB) steganography. The LSB method is employed to conceal cryptographic keys within digital media, reducing the risk of unauthorized key interception. The proposed system is evaluated across three communication channels: the server, the user web interface, and ESP32/ESP32-CAM devices. Sniffing attack tests confirm that all transmitted data appears only as ciphertext, indicating successful protection of plaintext and secure key exchange. Performance measurements also demonstrate that the combined methods operate efficiently. On the server, encryption and encode require an average of 0.14 ms, while decode and decryption on the user web interface require 0.13 ms. On the ESP32-CAM, encryption and encode average 2.22 ms, with decode and decryption on the server requiring 0.10 ms. For the ESP32, server-side encryption and encode take 0.10 ms, while device-side decode and decryption take 1.46 ms. Overall, the integration of Vigenère Cipher and LSB steganography effectively improves data security in IoT communication without significantly impacting system performance.
Penerapan Deep Neural Investigation Network (DNIN) Dengan Feature Selection Untuk Prediksi Bencana Banjir Fachrul Ilmawan; Yuhandri Yuhandri; Sumijan Sumijan
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9321

Abstract

Floods are natural disasters caused by high rainfall intensity and poor absorption capacity in an area. The impact of floods results in material and human casualties, necessitating a flood disaster mitigation process. Based on this, the purpose of this study is to predict flood disasters with the Deep Learning (DL) concept using the Deep Neural Investigation Network (DNIN) method, which is a CNN–BiLSTM hybrid. The research method used includes Deep Neural Investigation Network (DNIN) combined with feature selection to predict floods. Feature selection is carried out using the SelectKBest method with the ANOVA F-test (f_classif) evaluation function to select features that have the most significant influence on the target flood variable. The DNIN method extracts features from input data and processes the sequence of these features to capture two-way temporal dependencies before being used for prediction. This research dataset consists of 3000 rows of data sourced from Kaggle (https://www.kaggle.com/datasets/yusufginanjar7/banjir-jabodetabek) with fields name_2, name_3, avg_rainfall, max_rainfall, avg_temperature, elevation, landcover_class, ndvi, slope, soil_moisture, year, month banjir, lat long. The results of this study have proven the application of the Deep Neural Investigation Network (DNIN) method with feature selection is able to predict floods. The results show that the application of the DNIN method with feature selection is able to predict flood disasters with an accuracy level of 93%. Based on the results of this study, the application of the Deep Neural Investigation Network (DNIN) method with feature selection is able to provide a significant contribution in predicting flood disasters accurately and can be used as a decision support system in flood disaster risk mitigation and reduction efforts
Optimalisasi Strategi Pembelajaran Siswa Melalui Identifikasi Gaya Belajar Menggunakan Klasterisasi K-Means dan Klasifikasi K Nearest Neighbor Ilsa Hidayat; Musli Yanto; Rini Sovia
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9322

Abstract

Accuracy in adjusting teaching strategies to student learning characteristics is important because it can determine the effectiveness of the learning process. One of the key factors in improving the quality of learning is the suitability between teachers' teaching strategies and students' learning styles. The mismatch between the two aspects can reduce the effectiveness of the learning process and have an impact on low learning outcomes. Based on this, this study aims to optimize students' learning strategies through the application of the K-Means clustering model and the K-Nearest Neighbor classification. The performance of the K-Means Algorithm is able to classify learning styles and determine the labeling of learning styles, K-Nearest Neighbor is used to classify data that has been labeled by the K-Means algorithm. This research dataset amounted to 200 student data sourced from SMP Negeri 1 Panyabungan from the results of 20 questions answered by students. The results showed that the combination of the K-Means and K-Nearest Neighbor algorithms produced good performance with an accuracy value of 0.92, precision of 0.92, recall of 0.92, and F1-score of 0.91. The contribution of this research is expected to enrich the literature related to the application of the K-Means and K-Nearest Neighbor models in optimizing learning strategies, as well as assisting teachers at SMP Negeri 1 Panyabungan in designing and implementing learning strategies that are more effective and in accordance with the needs of students.
Simulasi dan Analisis Strategi Hybrid Teaming Menggunakan Algoritma Naive Bayes dalam Deteksi Serangan Distributed Denial of Service (DDoS) Aprilian Gevindo; Yuhandri Yuhandri; Billy Hendrik
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9323

Abstract

Cyber attacks, particularly Distributed Denial of Service (DDoS), have become a serious threat to the availability of servers and other network infrastructure. These attacks can paralyze services on large-scale networks by flooding the target system with extremely high traffic. Based on this, the objective of this research is to simulate and analyze a Hybrid Teaming strategy using the Naïve Bayes algorithm. This strategy simulates structured collaboration between the Red Team (attackers), Blue Team (defenders), and Purple Team (evaluators) to test resilience while comprehensively strengthening the security posture. The Naïve Bayes algorithm is one of the best algorithms in Machine Learning and excels at performing data classification processes. The performance of the Naïve Bayes algorithm combined with the Hybrid Teaming strategy is developed into an intelligent detection system. This system is trained using 10,000 data points from a public dataset and 1,688 data points from the network logs of the Tapan Regional General Hospital (RSUD). Based on the data analysis results, the model training outcomes fall into the perfect category, with accuracy, precision, recall, and F1-score achieving a result of 100%. The model was then implemented on a server and a MikroTik router within a simulation environment that replicates the Tapan RSUD network. The test results on these two components show that the system successfully detected various Flooding attack patterns with a detection accuracy of 100%. The system is capable of responding automatically by blocking the attacker's IP (Internet Protocol) address at both layers, as well as sending real-time notifications via WhatsApp and Email. The contribution of this research results in a comprehensive and effective cybersecurity defense framework.
Analisis Kepuasan Masyarakat terhadap Layanan KUA Menggunakan Algoritma K-Means dan C4.5 Nabilah Putri Permana; Agung Ramadhanu; Gunadi Widi Nurcahyo
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9324

Abstract

The Office of Religious Affairs (KUA) is an institution under the Ministry of Religious Affairs that provides religious services to the community, including marriage administration. Improving the quality of public services requires data-driven evaluation to measure the level of public satisfaction with the services provided. This study aims to analyze the level of community satisfaction with the services of the Office of Religious Affairs in Tebing Tinggi District using a combination of the K-Means Clustering and C4.5 algorithms. The research data were obtained from questionnaires distributed to community members who used KUA services. The K-Means algorithm was applied to group community satisfaction data based on the similarity of attribute values, while the C4.5 algorithm was used to build a classification model that generates decision rules to predict the level of community satisfaction. The results show that the proposed methods are able to group satisfaction levels in a structured manner and produce a classification model with high accuracy in analyzing public service satisfaction. The findings of this study are expected to support KUA in evaluating and improving service quality, as well as provide a reference for the application of data mining techniques in analyzing community satisfaction in public service sectors.
Komparatif Metode Convolutional Neural Network, GoogleNet & Transfer Learning pada Klasifikasi Sampah Ariza Ikhlas; Yuhandri Yuhandri; Agung Ramadhanu
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9326

Abstract

The waste problem is a very complex global issue, especially in Indonesia. The volume of waste that continues to increase every year is a major challenge for the environment, health, and the economy. so it is necessary to conduct research related to smart waste management, namely, a concept of utilizing artificial intelligence in waste management by adopting image management techniques. Based on this, this study aims to compare the modeling of Covolutional Neural Network (CNN), GoogleNet, and Transfer Learning. The methods used in this study, CNN, GoogleNet, and Transfer Learning by utilizing data augmentation, activation functions, and transfer learning, are able to overcome the problem of limited data and reduce or avoid overfitting problems in modeling. The datasets used in this study are sourced from datasets built by the researcher himself and Kaggle datasets with a total of 300 samples consisting of 6 classes: Cardboard, Glass, Plastic, Metal, Paper, and Other/Trash. The results present that the transfer learning method is superior to other methods with accuracy, precision, recall, and f1-score, 100%. The contribution of this research is to enrich the literature in the field of machine learning and computer vision, develop more efficient models for limited datasets, and become a reference for future researchers who want to develop similar systems.
Identifikasi Faktor Dominan Kegagalan Akademik pada Data Tidak Seimbang Menggunaan Ensemble Learning dan Hybrid SMOTE-ENN Rizky Nurhasanah; Solikhun Solikhun
Journal of Information System Research (JOSH) Vol 7 No 3 (2026): April 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i3.9448

Abstract

Academic failure and student dropout remain significant challenges in higher education because they affect educational quality and institutional performance. One of the major challenges in developing an effective dropout prediction model is class imbalance, which causes classification algorithms to be biased toward the majority class and reduces their ability to identify minority-class instances. This study aims to identify the dominant factors influencing academic failure by integrating the Hybrid Synthetic Minority Oversampling Technique–Edited Nearest Neighbour (SMOTE-ENN) with Ensemble Learning algorithms, including Decision Tree, Random Forest, XGBoost, and Voting Ensemble. Hybrid SMOTE-ENN was selected because it combines minority-class oversampling with noise and overlapping data removal, resulting in a more balanced training dataset and improving classification performance. The experiment was conducted using the Predict Students' Dropout and Academic Success dataset containing 4,424 student records. The research procedure consisted of data preprocessing, train–test splitting, Hybrid SMOTE-ENN resampling, model training, performance evaluation using accuracy, precision, recall, and F1-score, followed by feature importance analysis. Experimental results demonstrate that XGBoost with Hybrid SMOTE-ENN achieved the best performance, obtaining an accuracy of 87.12%, precision of 87.20%, recall of 87.12%, and F1-score of 87.15%. More importantly, the proposed model achieved a dropout-class recall of 80.99%, indicating its effectiveness in identifying students at risk of academic failure. Feature importance analysis revealed that Curricular Units 2nd Semester (Approved), Curricular Units 1st Semester (Approved), and Curricular Units 2nd Semester (Grade) are the three most influential factors affecting student dropout risk. These findings contribute to the development of an early warning system based on machine learning to support academic decision-making for imbalanced educational datasets.

Page 82 of 87 | Total Record : 870

 80   81   82   83   84 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol 7 No 4 (2026): July 2026 Vol 7 No 3 (2026): April 2026 Vol 7 No 2 (2026): January 2026 Vol 7 No 1 (2025): October 2025 Vol 6 No 4 (2025): July 2025 Vol 6 No 3 (2025): April 2025 Vol 6 No 2 (2025): January 2025 Vol 6 No 1 (2024): Oktober 2024 Vol 5 No 4 (2024): Juli 2024 Vol 5 No 3 (2024): April 2024 Vol 5 No 2 (2024): Januari 2024 Vol 5 No 1 (2023): Oktober 2023 Vol 4 No 4 (2023): Juli 2023 Vol 4 No 3 (2023): April 2023 Vol 4 No 2 (2023): January 2023 Vol 4 No 1 (2022): October 2022 Vol 3 No 4 (2022): Juli 2022 Vol 3 No 3 (2022): April 2022 Vol 3 No 2 (2022): Januari 2022 Vol 3 No 1 (2021): Oktober 2021 Vol 2 No 4 (2021): Juli 2021 Vol 2 No 3 (2021): April 2021 Vol 2 No 2 (2021): Januari 2021 Vol 2 No 1 (2020): Oktober 2020 Vol 1 No 4 (2020): JULI 2020 Vol 1 No 3 (2020): April 2020 Vol 1 No 2 (2020): Januari 2020 Vol 1 No 1 (2019): Oktober 2019 More Issue