cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jumanto
Contact Email
jumanto@mail.unnes.ac.id
Phone
+6281339762820
Journal Mail Official
joiser@shmpublisher.com
Editorial Address
Jl. Karanglo No 64 Gemah, Pedurungan, Kota Semarang, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Journal of Information System Exploration and Research
Published by shm publisher
ISSN : 29641160     EISSN : 29636361     DOI : https://doi.org/10.52465/joiser
Core Subject : Science, Engineering,
Computer Science & IT Decision Sciences, Operations Research & Management Engineering
Journal of Information System Exploration and Research (JOISER) (e-ISSN: 2963-6361, p-ISSN: 2964-1160) is a journal that publishes and disseminates scientific research papers on information systems to a wide audience, particularly within the information system society. Articles devoted to discussing any and all aspects of the most recent and noteworthy advancements in the fields of Decision Science, Computer Science, and Computer Science Applications will be considered for publication. Submit your paper now through Online submission ONLY. The JOISER publication period is carried out every six months, namely in January and July. But, authors can submit their work to JOISER at any time throughout the year, as the submission process is continuous. The JOISER has been indexed by Google Scholar, Crossref, Copernicus, and BASE. The Journal of Information Systems Exploration and Research aim publishes articles concerning the design and implementation information system, data models, process models, algorithms, and software for information systems. Subject areas include data management, data mining, machine learning, information retrieval coordinated with structured data, internet and cloud data management, business process management, web semantics, visual and audio information systems, scientific computing, and data science. We welcome system papers that focus on decision science and machine learning, computer science application, pplication domains, Internet of Things, which present innovative, high-performance, and scalable solutions to data management problems for those domains.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 4 Documents
 1 
Search results for , issue "Vol. 4 No. 1 (2026): January 2026" : 4 Documents clear
Ensemble Learning-based Potato Leaf Disease Classification Using DenseNet201 and MobileNetV2 Ahmad, Burhan; Alamsyah
Journal of Information System Exploration and Research Vol. 4 No. 1 (2026): January 2026
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i1.597

Abstract

Early and late blight are major threats to potato crops and can cause significant losses for farmers. Early disease classification is essential for quick and appropriate treatment. This study proposes an ensemble learning approach by combining DenseNet201 and MobileNetV2 architectures to classify potato leaf diseases from digital images. The dataset used consists of 2,152 potato leaf images and is processed through normalization, augmentation, and image resizing stages. The ensemble model was trained with optimized parameters and evaluated using accuracy, precision, recall, and F1-score. The test results showed an accuracy of 99.56%, with precision, recall, and F1- score values of 99.56% each. Demonstrated improved performance compared to single CNN models on the evaluated dataset, and offers an accurate and efficient solution for disease detection in the agricultural sector.
Ensemble Deep Learning: A State-Of-The-Art Comprehensive Review Samie, Mahmoud Abdel
Journal of Information System Exploration and Research Vol. 4 No. 1 (2026): January 2026
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i1.614

Abstract

Ensemble learning has been a cornerstone of machine learning, providing improved predictive performance and robustness by combining multiple models. However, in the era of deep learning, the landscape of ensemble techniques has rapidly evolved, influenced by advances in neural architectures, training models, and practical application requirements. This review provides a state-of-the-art survey of ensemble deep learning approaches, focusing on recent developments of ensemble methods. We introduce a classification of ensemble strategies based on model diversity, fusion mechanisms, and task alignment, and highlight emerging techniques such as attention-based ensemble fusion, neural architecture search-based ensembles, and large ensembles of language or vision models. The review also examines theoretical foundations, practical tradeoffs, and domain-specific adaptations in some fields. Compiling state-of-the-art benchmarks, we evaluate ensemble performance in terms of accuracy, efficiency, robustness, and interpretability. We also identify key challenges such as scalability, overfitting, and deployment limitations and present open research directions, including ensemble learning for continuous learning, federated learning, and learning from scratch. By connecting key insights with current trends, this review aims to guide researchers and practitioners in designing and implementing ensemble deep learning systems to address the next generation of AI challenges.
Analysis and Visualization of Purchasing Pattern in Retail Product Transaction using Apriori Algorithm Febriani SM, N. Nelis; Setyoningrum, Nuk Ghurroh; Lodana, Mae; Pertiwi, Dwika Ananda Agustina; Muslim, Much Aziz
Journal of Information System Exploration and Research Vol. 4 No. 1 (2026): January 2026
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i1.650

Abstract

The rapid growth of the retail industry generates large volumes of transaction data that can be analyzed to support data-driven business decision making. This study aims to analyze and visualize purchasing patterns in retail product transactions by applying data mining techniques using the Apriori algorithm and business intelligence visualization through Microsoft Power BI. The dataset consists of 1 million retail transactions collected from an open retail transaction repository. The research stages include data collection, transaction data preprocessing, implementation of the Apriori algorithm with a minimum support threshold of 0.002 and a minimum confidence of 0.5, and visualization of the analysis results through interactive dashboards using Power BI and a Python-based application developed with the Streamlit framework. The results indicate that the Apriori algorithm successfully identifies frequent product associations and generates 12 association rules that meet the criteria of strong association rules. Power BI visualizations provide comprehensive insights into transaction trends based on customer categories, store types, payment methods, seasons, and transaction regions. These findings are expected to assist retail companies in formulating marketing strategies, developing product recommendations, and optimizing inventory management in a more effective and data-driven manner. This study contributes by integrating large-scale association rule mining with interactive business intelligence visualization for retail decision support.
Optimization of Energy Consumption Prediction with Random Forest Regressor and XGBoost Feature Importance Syafei, Risma Moulidya; Nikmah, Tiara Lailatul; Anisa, Devi Nurul; Kharisma, Sidiq Noor
Journal of Information System Exploration and Research Vol. 4 No. 1 (2026): January 2026
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i1.653

Abstract

Energy consumption is increasing as industry and technology advance. However, it will have a bad impact if its use is not properly controlled. Therefore, predicting energy consumption is needed to prevent energy waste and to streamline its use across several influencing factors. Predictions are made using the Random Forest Regressor method. Where regression and Random Forest techniques can produce accurate results for continuous values such as total energy consumption. The feature importance method is also used to select the most influential features. Where of the 40 features in the energy consumption dataset in Southern California, only 24 features were selected based on the average threshold of the gain value. The results showed that the use of XGBoost feature importance lowered the Mean Absolute Error (MAE) value of the Random Forest Regressor, which was 16.56 to 16.55. This value is the difference between the actual data and the predicted data. This proves that the model successfully predicts with a small error value. The application of feature importance in energy consumption prediction using Random Forest Regressor is expected to be more efficient in energy consumption, especially in the sectors that most affect the increase in energy consumption.

Page 1 of 1 | Total Record : 4

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2026): January 2026 Vol. 3 No. 2 (2025): July 2025 Vol. 3 No. 1 (2025): January 2025 Vol. 2 No. 2 (2024): July 2024 Vol. 2 No. 1 (2024): January 2024 Vol. 1 No. 2 (2023): July 2023 Vol. 1 No. 1 (2023): January 2023