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 795 Documents
 76   77   78   79   80 
A Multi-Criteria Decision-Making Approach Using MOORA for Evaluating Job Search Platforms Rogayah, Rogayah; Kusumawijaya, Ike Putri; Ningrum, Witta Listiya
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9117

Abstract

With the development of technology today, it can make it easier for many people to carry out various activities. For example, in searching for work using various job search websites. A job search website is one of the sites where there is an online platform opportunity that allows users to search for and apply for jobs that suit their qualifications and interests. This job search website also has the main aim of helping fresh graduates who have no experience in the field of work. However, this job search website has both positive and negative impacts. Therefore, applicants must first seek detailed information before applying for work. And you also have to look for a truly official platform to avoid fraud. The problems above can make applicants face difficulties in determining which is the best platform to meet their needs. So, to resolve the problems that occur in selecting a job search website, criteria data is really needed, including ease of use, ease of application, detailed information, speed of access, security, and number of site uses. So, a decision support system (DSS) is very necessary as a problem solving tool in selection of the best job search websites. In this research, the author applies the MOORA method to search for final results accurately and is assisted by using the ROC weighting method. Therefore, the one that gets the highest ranking in selecting the best job search website is an alternative. with value.
Decision Support System for Selecting Outstanding Students University using the Method Multi Attribute Utility Theory (MAUT) Sallaby, Achmad Fikri
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9118

Abstract

The Selection of Outstanding Students describes the activities that have been carried out by the Higher Education since 2004. These activities include sorting and distributing awards to students who have achieved great achievements, both curricular and extracurricular achievements. Therefore, in each academy it is necessary to identify students who are able to do both and be given awards as outstanding students, namely by conducting mawapres selection at the high academic level. In the higher academies there is a program where students want to be selected and are also entitled to become outstanding students and are also given awards each year. In the process of achieving students at Budi Darma University, Medan, it is still being tried manually. This allows errors in the evaluation and processing of student data information. For this reason, it is necessary to make a decision support system that can help determine achievements and can take into account all the criteria. the predicate of outstanding students are cases that require an assessment process. So that in solving something that is needed a multi-process decision support system. The trick used in this research is the MAUT procedure. Determine the determination of students to overcome problems that require part of the evaluation process. So that the solution requires a multi-process decision support system. The procedure used in this research is the MAUT method. The MAUT method is to obtain a decision support information system for companies with a large level of data accuracy, so that by using this procedure it is expected to determine student achievement and process information more effectively. With this MAUT method creates the most preference as the best alternative results in the initial ranking which lies in the alternative with the highest preference level of 0.5419 on behalf of Khamsah Anugrah.
Implementasi Arsitektur CNN untuk Klasifikasi dan Identifikasi Penyakit Daun Tanaman Padi Hidayat, Helmy Purnomo; Imaduddin, Helmi
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9192

Abstract

Leaf diseases in rice plants are a serious threat that can reduce productivity and crop quality, thus directly impacting national food security. Farmers still face various obstacles in identifying diseases conventionally, especially in the early stages of infection which can potentially cause delays in treatment. This study aims to develop a Deep Learning-based rice leaf disease classification system by building a Convolutional Neural Network (CNN) architecture independently (from scratch). The dataset used includes 18,445 rice leaf images categorized into ten disease classes, with an allocation of 70% training data, 15% validation data, and 15% test data. All images were resized to 224×224 pixels before being input into the model. Data augmentation was applied to prevent overfitting by rotation (20°), horizontal and vertical shifts (15%), shear (15%), zoom (15%), horizontal flip, and brightness variations (0.8-1.2). The CNN model was designed using five convolution blocks with cascaded filter configurations (32, 64, 128, 256, 512) using a 3×3 kernel and equipped with Batch Normalization, MaxPooling2D, and Dropout. The model was compiled using the Adam optimizer with a learning rate of 0.0001, a categorical cross-entropy loss function, and ReLU and Softmax activation functions. The training process used a batch size of 8 equipped with EarlyStopping and ReduceLROnPlateau callbacks. The experimental results showed that training with 75 epochs produced optimal performance with an accuracy of 97.91%, a precision of 0.9792, a recall of 0.9791, and an F1-score of 0.9790 on the test data. Evaluation per class showed that the Bacterial Leaf Blight and Tungro classes achieved perfect accuracy (100%), while Leaf Blast had the lowest accuracy (93.8%) due to its visual similarity to Brown Spot. The best model was implemented into a web system called Pariku using the Flask framework, which provides automatic diagnosis features, prediction confidence levels, and Integrated Pest Management (IPM)-based treatment recommendations.
Implementasi Metode Random Forest Untuk Memprediksi Jumlah Penjualan Gorden Berdasarkan Data Historis Wijanarko, Amiladito Adhyatma; Imaduddin, Helmi
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9194

Abstract

The rapid development of information technology has encouraged companies, including Tova Gorden, a small business engaged in curtain sales, to adopt technology to improve operational efficiency and competitiveness. Tova Gorden often faces obstacles in fulfilling orders, especially when demand suddenly increases, which is exacerbated by limited stock, raw material difficulties (such as smokers), fabric pre-order systems, and time-consuming production processes. Determining stock that is still based on employee estimates often leads to inefficiencies in the form of shortages or excesses of goods. This condition highlights the urgent need for an accurate prediction system to optimize inventory management. This study aims to implement and test the performance of the Random Forest algorithm, which is an ensemble learning method, to predict the number of curtain sales based on historical sales data. The collected data includes historical information related to curtain sales, including sales weeks, curtain motifs, and sales volumes. Unlike previous studies that generally use Linear Regression and focus on products with stable sales patterns, this study applies Random Forest to address more fluctuating curtain demand patterns. This research method includes several stages, namely Data Collection, Exploratory Data Analysis (EDA), Data Preprocessing, Data Splitting (70% training, 15% validation, 15% testing), Modeling with Random Forest, Evaluation, and Deployment. The evaluation results show that the model has excellent performance, with a coefficient of determination (R²) value of 97.83% on training data, 93.72% on validation data, and 96.64% on test data. Furthermore, the model is integrated into a web-based system using the Flask framework. This system is equipped with data upload features, prediction processes and curtain category grouping, and presentation of model evaluation results.
Digital Transformation of Smart Parking: A Design Science Research Study Sampetoding, Eliyah Acantha Manapa; Fudhayl, Andi Ahmad Fa’il; Sianipar, Kelvin Leonardo; Ta’dung, Mario Valerian Rante
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8590

Abstract

This research discusses the design and development of a digital transformation concept for a parking system in the context of smart city development in Makassar, Indonesia. This research was conducted in response to the problems of illegal parking and low accountability for parking revenues, which impact regional income and the quality of parking services. This research resulted in an information system in the form of an artifact model, developed using a Design Science Research (DSR) approach, including the stages of design, model building, demonstration, and conceptual evaluation of the artifact. The resulting model has not been implemented as an operational mobile application, but rather compiled as a conceptual and technical design that is validated through presentations and discussions with relevant stakeholders and potential users (the public) as part of the demonstration phase within the DSR framework. The research methods include needs analysis, system design, technology selection, system architecture design, and conceptual evaluation based on the Hevner Design Science Research methodology. The proposed system model uses the Model/View/ViewModel (MVVM) architecture and is designed to integrate with supporting services, including Firebase, the Google Maps API, and the Midtrans Payment Gateway. This artifact model serves as a basis and initial recommendation for the Makassar City Government in developing a tangible, operational digital parking application that can be implemented and tested in subsequent research or policy phases. The research results indicate that the proposed digital parking system model has the potential to increase transparency and accountability in parking management and support sustainable smart city planning, particularly in Makassar.
Perbandingan Algoritma K-Nearest Neighbor dan Naive Bayes Untuk Klasifikasi Status Penjualan Furniture dengan Data Historis Sucahyo, Bangkit Dwi; Riskiono, Sampurna Dadi
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8675

Abstract

This study aims to evaluate the performance of two machine learning classification methods, K-Nearest Neighbor (KNN) and Naive Bayes, in predicting the sales status of furniture products at CV. Surya Gemilang. The data used comes from previous sales records and includes details such as product category, product name, price, sales amount, revenue, and sales status, which are labeled "Best Selling" and "Not Selling". This study follows several steps, including data collection, data cleaning and organization, labeling, model training, and performance assessment using accuracy, precision, recall, and F1-score. The research process includes data preprocessing, handling missing values, encoding categorical features, normalizing numeric features, separating training and testing data, model training, and performance evaluation using accuracy, precision, recall, and F1-score. The results show that the KNN algorithm achieves 97% accuracy, 100% precision, 95% recall, and 0.97 F1-score. Meanwhile, the Naïve Bayes algorithm achieved 85% accuracy, 92% precision, 81% recall, and an F1-score of 0.86. These findings indicate that KNN is better able to recognize complex patterns in sales data than Naïve Bayes. The contribution of this research is to provide a machine learning-based classification model that can be used to support production planning and marketing strategies by predicting furniture product sales levels. The results show that KNN achieved 97% accuracy, while Naïve Bayes only achieved 85%. This indicates that KNN is better at identifying complex relationships between features in sales data, while Naïve Bayes is less effective because it assumes all variables are independent. In summary, KNN is more effective in classifying furniture product sales status and can be the basis for making informed business decisions based on data. This research makes a significant contribution to the application of machine learning in small and medium-sized enterprises, helping to improve sales forecasting and develop more effective marketing strategies.
Pengembangan Sistem Informasi Monitoring Checklist Maintenance untuk Efisiensi Pemeliharaan Pada Divisi General Affair Priyadi, Angga; Fernando, Daniel; Irawan, Debi; Saelan, Athia
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8723

Abstract

The General Affair (GA) Division at a telecommunications company faces problems in the maintenance checklist process, which is still carried out manually using paper and simple worksheets. This process often result in data duplication, inaccurate documentation, and delays in reporting. This research aims to develop a web-based maintenance checklist monitoring information system to support the digitalization and improve the efficiency of the facility maintenance process in the GA Division. The system development was carried out using the waterfall method through the steps of needs analysis, system design, implementation, and testing. The system was developed using the CodeIgniter 4 framework, Metronic UI interface, and MySQL as the database. Testing was conducted using the Black Box Testing method on 12 functional testing scenarios covering the main functions of the system for the roles of GA Admin and GA Officer, and all main functions of the system showed a 100% success rate according to specifications. In addition, a limited User Acceptance Test (UAT) was conducted involving GA Admin as expert judgment and GA Officers, showing that the system is easy to use, helps speed up the monitoring and reporting process, and improves the accuracy of checklist data. The research results are in the form of a web-based system that is capable of integrating the activities of various field officer roles, providing centralized data access, increasing maintenance efficiency, and supporting real-time monitoring and maintenance reporting.
Deteksi Intrusi Jaringan Berbasis Machine Learning Menggunakan Model Boosting dengan Session-Level Feature Representation Sanwasih, Mochamad; Septian, Fajar; Septiana, Ristasari Dwi
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8775

Abstract

The increasing complexity of network security threats demands intrusion detection systems that are both contextual and adaptive. Conventional signature-based Intrusion Detection Systems (IDS) suffer from limitations in detecting emerging and previously unseen attack patterns, making machine learning–based approaches a more flexible alternative. However, fragmented packet-level feature representations still limit the ability of models to capture network behavior comprehensively. This study aims to evaluate the performance of boosting models, namely XGBoost and LightGBM, using the publicly available Cybersecurity Intrusion Detection Dataset from Kaggle, which represents network activity at the session level. The proposed approach develops a session-level feature representation based on aggregated and ratio-based features to capture network behavior characteristics more comprehensively. Experimental results demonstrate that the implementation of session-level feature representation yields consistent improvements across multiple evaluation metrics. Accuracy increased from 0.8779 to 0.8847, while the F1-score improved from 0.8452 to 0.8525 for XGBoost and from 0.8455 to 0.8523 for LightGBM. Furthermore, ROC-AUC increased from 0.8789 to 0.8844 for XGBoost and from 0.8793 to 0.8859 for LightGBM. Although the improvement in accuracy is relatively moderate, the gains in F1-score and ROC-AUC indicate enhanced discriminative capability and a better balance between precision and recall. The main contribution of this study lies in the integration of session-level feature engineering with boosting models within a systematic evaluation framework, emphasizing the critical role of behavioral feature representation in improving intrusion detection performance.
Perancangan Sistem Informasi Penjualan Seragam Sekolah Dasar Berbasis Mobile dengan Menggunakan Metode Prototype Alda, Muhamad; Hidayat, Riyan; Surbakti, Gita Syahfitri Wulandari; Azmi Pohan, Wulan; Tarigan, Tasya Ika Saylani
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9001

Abstract

Advances in information and communication technology have driven digital transformation across various sectors, including education and business, making the use of technology crucial for data processing and sales. Information systems are capable of integrating people, data, processes, and technology to improve efficiency and support decision-making. In the context of education, the use of technology for sales and data processing is important for increasing effectiveness and service quality. However, in the education sector, the sale of elementary school goods is still largely done manually, which can lead to problems such as data inconsistencies, delayed reports, and decreased efficiency. Therefore, an information system is needed that can manage sales transactions and data in an integrated and automated manner. Various previous studies have shown that implementing a digital sales information system can improve data processing effectiveness, minimize recording errors, and support managerial decision-making. As the use of mobile devices increases, the development of mobile-based information systems becomes a relevant solution because it offers ease of access, flexibility of use, and improved customer service quality. In addition, the prototyping method has proven effective in system development because it directly involves users, resulting in a system that is more aligned with user needs. Based on these problems and previous research findings, this study aims to design a Mobile-Based Elementary School Uniform Sales Information System using the prototyping method. This method allows for direct user involvement in the design process, thus creating a system design that is more aligned with user needs. The research results include a system design that encompasses process modeling using the Unified Modeling Language (UML) and the design of the mobile application's user interface. This system design is expected to serve as a reference in the development of an integrated mobile-based school information system and improve efficiency in data processing and sales.
Rancang Bangun Aplikasi Pembelajaran Berbasis Web dan Android dengan Presensi Digital dan Sistem Poin Menggunakan Metode Waterfall Juzairi, Wardah; Suhendar, Agus
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9006

Abstract

The implementation of learning at SMAN 1 Kalibawang requires an efficient academic administration system to replace manual processes that potentially cause data inaccuracies and suboptimal management. This study designs and develops a web-based learning application for teachers and a Flutter-based mobile application for students using the Waterfall system development method. The system is equipped with features such as real-time digital attendance, material distribution, assignment and quiz submission, as well as a motivation mechanism through the integration of a Points System. The system design is modeled using UML (Use Case and Activity diagrams), supported by system Flowcharts. Functional testing using Black Box Testing on 10 scenarios showed a success rate of 100%. The implementation of this system is expected to streamline school administrative procedures while increasing student participation and self-motivation in the learning process.

Page 78 of 80 | Total Record : 795

 76   77   78   79   80 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue 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