cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
ournal.jistr@gmail.com
Phone
+6281263151592
Journal Mail Official
journal.jistr@gmail.com
Editorial Address
Jl Mandala By Pass Pukat Banting IV No 41 Medan
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Information Systems and Technology Research
Published by Ali Institute of Research and Publication
ISSN : 28283864     EISSN : 28282973     DOI : https://doi.org/10.55537/jistr
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
JISTR is a periodical journal that aims to provide scientific literature, especially applied research studies in information systems (IS) / information technology (IT), and an overview of the development of theories, methods, and applied sciences related to these subjects Focus and Scope Artificial intelligence Autonomous reasoning Bio-inspired algorithms Bio-informatics Cloud computing Data science Data mining Data visualization Decision support systems Deep learning Evolutionary computation Fuzzy logic Human-Computer Interaction Hybrid intelligent systems, Adaptation and Learning Systems IoT and smart environments Knowledge mining Machine learning Neural networks Pattern recognition Soft computing Prediction systems Signal and image processing System modeling and optimization Time series prediction Web intelligence
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 89 Documents
 5   6   7   8   9 
Learning Rate and Epoch Analysis for Medicinal Plant Identification Using GLCM and BPNN Nurqolbiah, fatihani; Absharina, Eriene Dheanda; Utari, Aspirani; Febriady, Mukhlis; Saputra, Tommy
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1413

Abstract

Accurate identification of medicinal plants is essential for pharmacology and biodiversity conservation. However, traditional methods rely heavily on subjective visual inspection, which is prone to misclassification due to subtle differences in leaf textures. A primary challenge that remains unaddressed is the understanding of hyperparameter sensitivity within limited datasets, particularly when the subjects exhibit extremely high visual similarity. This study proposes an automated identification approach using Gray-Level Co-occurrence Matrix (GLCM) and Backpropagation Neural Network (BPNN) to classify three Indonesian medicinal species: white ginger, mango ginger, and yellow turmeric. The distinctive focus of this research lies in its attempt to differentiate these specific plants, which possess leaf texture characteristics so similar that they are often indistinguishable to the human eye. This approach involves a systematic analysis of learning rate and epoch parameters to optimize convergence for these nearly identical texture features. A dataset of 63 images was transformed into five GLCM statistical features to serve as the primary inputs for the BPNN. Experimental results demonstrate that classification performance is highly sensitive to parameter tuning. The system achieved its peak accuracy of 65.03% using a learning rate of 0.1 and 100 epochs. The findings reveal that smaller learning rates and limited training iterations facilitate more stable convergence when processing data with high feature similarity. While the accuracy indicates potential for further development, this study provides a significant contribution to creating objective identification methods for visually similar plants and offers empirical insights into optimal parameter selection for texture-based neural network architectures.
User Interface Design and UML-Based Modeling for an Internship Monitoring and Evaluation Information System Nurul Zafirah; Ikhsan Pratama; Samsudin
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1432

Abstract

Conventional internship monitoring workflows frequently suffered from critical inefficiencies, including data fragmentation, delayed reporting, and subjective performance evaluations. Furthermore, existing literature on system design often prioritized backend logical structures while neglecting frontend visual usability, resulting in functional but difficult-to-use applications. This study aimed to address these specific gaps by designing a comprehensive internship monitoring and evaluation system that explicitly integrated strict Unified Modeling Language architecture with high-fidelity user interface design at the conceptual level. The methodology utilized a qualitative descriptive approach, employing specific structural diagrams including use case, activity, and sequence diagrams to enforce role-based access control and user-centered design principles. The results demonstrated that the proposed blueprint successfully ensured data integrity and atomicity. Validated through black box testing, the conceptual models were confirmed to be translated into a functional design without logical errors, enabling real-time activity tracking and objective assessment. This study contributed to information system design research by bridging strict data security standards with minimalist usability heuristics, providing a matured visual and structural foundation. The findings offered a concrete basis for future implementation and empirical validation using user acceptance testing in operational environments.
A Web-Based Decision Support System for Inventory Procurement Optimisation Using Pareto Analysis Fajar , Ibnu; Rachmawati Yahya, Sitti; Bohani, Farah Aqilah; Yusof , Nor Nadiah
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1447

Abstract

Existing research and practical applications of multi-objective optimization in this domain continue to rely mainly on manual Pareto analysis. Typically, decision makers analyze trade-off curves or a collection of candidate solutions before making subjective configuration choices. This method is time-consuming, difficult to replicate, and subject to bias or inconsistency among evaluators. Furthermore, many publications stop at creating the Pareto front without giving a systematic mechanism for automated selection or assessing the effectiveness of the produced front in comparison to alternative tactics. Data for fast-moving product categories with high profit margins can be processed in a computerized application. These two parameters will provide the best recommendations according to the Pareto principle, which states that 80% of the best income comes from 20% of sources. Pareto Method optimization has proven to narrow the focus of work on the parts that have a significant effect (benefit) for the pharmacy. The manual process used before the research was conducted resulted in one item recommendation in 6 minutes and 20 seconds, while the computerized DSS could process a large amount of item data in just 3 minutes and 15 seconds, with an average gross profit for the top 10 recommended items of 32.1%. This study presents an automated Pareto optimization and selection methodology, which eliminates the need for manual inspection. The system not only creates candidates for Pareto-optimal solutions, but also ranks and selects them based on quantitative criteria. In addition, the framework includes comparative benchmarking, which allows for performance evaluation against baseline methodologies, heuristics, or existing decision procedures. This results in an objective, repeatable, data-driven decision pipeline.
An Intelligence-Oriented System Architecture for Integrated Pharmaceutical Data Analytics and Decision Support Ningsiah; Aminudin, Nur; Ariyanti, Septika; Abbasov, Ramil
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1461

Abstract

This study proposes and evaluates an intelligence-oriented hybrid information system architecture for pharmaceutical data analytics and decision support. Unlike conventional approaches that treat analytics as an external component, the proposed framework embeds analytical intelligence directly into the core system architecture through an integrated, multi-layer design. The study adopts an experimental and system development methodology using a large-scale public pharmaceutical dataset consisting of 240,591 records and 10 attributes. Supervised machine learning models are implemented to support data classification and intelligence generation, and system performance is evaluated using accuracy, precision, recall, and F1-score. The results demonstrate that the proposed hybrid system consistently outperforms baseline and non-integrated approaches, achieving higher predictive stability and analytical consistency. The main contribution of this study lies in its system-level integration model, which enables the transformation of raw pharmaceutical data into actionable decision-support intelligence. The findings confirm that embedding analytics within information system architecture significantly enhances both analytical performance and decision-making capability in pharmaceutical information systems.
Hybrid Intelligent Framework for Adaptive Decision-Making Systems dirayati, fadhilah; Anggun Sari, Resy; Fitria Purnomo, Rosyana; Jih-Fu Tu, Jih-Fu Tu
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1462

Abstract

This study proposes a Hybrid Intelligent Framework that integrates Neural Networks (NN), Fuzzy Logic Systems (FLS), and Evolutionary Computation (EC) to improve adaptive decision-making in dynamic, uncertain, and data-driven environments. The framework combines data-driven pattern learning using a multilayer perceptron, interpretable fuzzy reasoning through Mamdani inference and centroid defuzzification, and evolutionary optimization to tune network weights, membership parameters, and fuzzy rule structures. Two dataset categories were used to assess robustness: simulated decision scenarios and industrial datasets with dynamic operational variables. Data were normalized via min–max scaling and fuzzified using Gaussian membership functions before being processed by the NN–FLS pipeline. EC then minimized a weighted objective that balances prediction error and rule complexity, enabling accurate yet explainable decisions. Performance was evaluated using accuracy, MAE, RMSE, and F1-score, and compared against standalone NN and standalone FLS baselines. The hybrid model achieved the best results, reaching 92.3% accuracy and 0.93 F1-score while reducing MAE to 0.32 and RMSE to 0.48. These findings indicate that hybridizing learning, reasoning, and optimization yields faster adaptation and lower error rates than single-model approaches, supporting scalable deployment in real-world decision-support systems. Confusion-matrix inspection also showed fewer critical misclassifications under changing conditions, supporting suitability for online updates in practice.
Impact of Learning Independence and Practical Tool Utilization on Outcomes in Basic Automotive Engineering Siregar, Riski Elpari; Naibaho, Peter
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1463

Abstract

This study examines the effect of learning independence and the use of practical tools on students’ learning outcomes in the Basic Automotive Engineering subject. The research was conducted at SMK Negeri 4 Medan involving Grade X students of the Motorcycle Engineering Program. A quantitative approach with an ex post facto design was used to analyze the relationships among variables without experimental treatment. Data were collected through questionnaires to measure learning independence and practical tool usage, as well as tests to assess students’ learning outcomes. The data were analyzed using regression techniques to determine both partial and simultaneous effects. The results show that learning independence has a positive and significant influence on students’ learning outcomes. Likewise, the use of practical tools also positively affects students’ achievement. When analyzed together, learning independence and practical tool usage significantly contribute to improved learning outcomes in Basic Automotive Engineering. These findings highlight the important role of internal student factors and learning facilities in vocational education. Practically, the study suggests that teachers should encourage independent learning and maximize the use of practical tools during instruction, while theoretically it reinforces learning theories that emphasize learner autonomy and experiential learning as key determinants of academic success
Effect of Information System Quality on Administration via E-Office Applications: Evaluation of E-Office Performance at the KBB Manpower Office Ayu, Difta; Nurrohman, Aldy; Saelan, Athia; Supriana, Fadhlanrashif Ibrahim
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1475

Abstract

The implementation of digital administrative systems in public sector institutions is expected to enhance efficiency, transparency, and accountability; however, partial system adoption and varying levels of user acceptance often limit their effectiveness. This study evaluates the implementation of a web-based E-Office application in public sector administration by examining how system quality, information quality, and service quality influence administrative management and employee acceptance. This research employs a descriptive qualitative approach by integrating the Information System Success Model and the Technology Acceptance Model (TAM). Qualitative data were collected through in-depth interviews with selected employees, direct observation of administrative workflows, and documentation analysis related to E-Office utilization in a local government institution. The findings indicate that system quality, information quality, and service quality positively contribute to administrative management effectiveness by accelerating document processing, improving information accessibility, and strengthening administrative accountability. In addition, perceived usefulness and perceived ease of use significantly influence employee acceptance of the E-Office application. Nevertheless, several challenges remain, including an outdated user interface, limited document search functionality, and the coexistence of manual and digital administrative processes. The novelty of this study lies in its qualitative integration of information system quality dimensions and the Technology Acceptance Model within a local government administrative context, providing empirical insights into both technical system performance and user acceptance to support public sector digital transformation.
Extending the Technology Acceptance Model for Accounting Information Systems: A Comparative Analysis of Urban and Rural Users in Indonesia Ari, Mardi; Rodi, Muhamad
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1477

Abstract

The adoption of Accounting Information Systems (AIS) in Indonesia remains uneven between urban and rural areas, reflecting disparities in digital competence, social conditions, and infrastructural readiness. Addressing this gap, this study extends the Technology Acceptance Model (TAM) by incorporating digital literacy, trust, and social influence, while explicitly examining the moderating role of geographical context (urban versus rural). A quantitative survey method was employed, collecting data from 300 AIS users, comprising 150 respondents from urban areas and 150 from rural areas. The data were analyzed using partial least squares structural equation modeling (PLS-SEM) and multi-group analysis. The research model positions digital literacy, trust, and social influence as antecedent variables; perceived ease of use and perceived usefulness as mediators; behavioral intention as an intervening variable; and actual system usage as the outcome variable. The findings indicate that behavioral intention is a strong predictor of actual AIS usage in both urban and rural contexts. However, significant contextual differences emerge: digital literacy and trust positively influence perceived usefulness in urban areas, while these relationships are not significant in rural settings. This result highlights the moderating role of geographical context in shaping AIS acceptance patterns. This study contributes theoretically by extending TAM through a contextualized urban–rural perspective and empirically demonstrating the heterogeneous effects of key antecedents across geographical settings. From a policy perspective, the findings suggest that strategies to promote AIS adoption should be context-sensitive, with greater emphasis on digital capability development and trust-building mechanisms in rural areas.
Designing a Hybrid Machine Learning Model for Weather Forecasting in Batam City Christian, Yefta; Jupiter Agustio Liu Siaw Ping
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1504

Abstract

Accurate weather forecasting in tropical regions such as Batam City is challenging due to high climate variability and frequent data gaps caused by unstable atmospheric conditions. This study aims to develop a reliable daily average temperature forecasting system using a hybrid approach that combines the Seasonal Autoregressive Integrated Moving Average (SARIMA) model and the Long Short-Term Memory (LSTM) neural network. The main novelty of this research lies in the residual hybridization method, where SARIMA is used to capture linear seasonal patterns and LSTM is applied to model the non-linear residual components, as well as the use of a multi-source data integration strategy to fill missing data. Historical temperature data from BMKG and other publicly available meteorological sources were merged to produce a continuous dataset covering the period from 2015 to 2021. The study evaluated several model architectures, including standalone statistical models, standalone machine learning models, and hybrid models, to identify the most effective approach. The experimental results show that the SARIMA–LSTM hybrid model outperformed the other models, achieving a high prediction accuracy with an R² value of 0.92 and a Root Mean Square Error (RMSE) of 1.73°C. These findings demonstrate that integrating linear and non-linear models can significantly improve temperature forecasting performance and provide a practical solution for weather monitoring in tropical environments

Page 9 of 9 | Total Record : 89

 5   6   7   8   9 

Filter by Year

2022 2026


Reset
Filter By Issues
All Issue Vol. 5 No. 1 (2026): January 2026 Vol. 4 No. 3 (2025): September 2025 Vol. 4 No. 2 (2025): May 2025 Vol. 4 No. 1 (2025): January 2025 Vol. 3 No. 3 (2024): September 2024 Vol. 3 No. 2 (2024): May 2024 Vol. 3 No. 1 (2024): January 2024 Vol. 2 No. 3 (2023): September 2023 Vol. 2 No. 2 (2023): May 2023 Vol. 2 No. 1 (2023): January 2023 Vol. 1 No. 3 (2022): September 2022 Vol. 1 No. 2 (2022): May 2022 Vol. 1 No. 1 (2022): January 2022 More Issue