cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Much Aziz Muslim
Contact Email
a212muslim@mail.unnes.ac.id
Phone
+628164243462
Journal Mail Official
adminjoiser@shmpublisher.com
Editorial Address
SHM Publisher No. 64, Karanglo st, Pedurungan Distr, Semarang, Central Java, Indonesia 50191.
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.xxxx
Core Subject :
Journal of Information System Exploration and Research is a journal that publishes and disseminates scientific research papers on information systems to a wide audience particularly within the information system society
Arjuna Subject : -
Articles 37 Documents
 1   2   3   4 
Pneumonia Classification from Chest X-Rays Using CLAHE and Xception-Based Transfer Learning Adi Fajar Saputra; Nurul Huda
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.112

Abstract

Pneumonia classification from chest X-ray (CXR) images remains challenging because radiographic appearance varies in contrast, intensity, anatomical structure, and disease manifestation, while class imbalance may affect automated classification. This study proposes a transfer learning framework based on the Xception architecture for binary pneumonia classification from CXR images. The proposed framework integrates systematic image preprocessing, including image resizing, Contrast Limited Adaptive Histogram Equalization (CLAHE), Xception-specific normalization, training-only data augmentation, and class weighting. The dataset consisted of 5,856 CXR images and was stratified into 70% training, 20% validation, and 10% testing subsets. Xception was trained using a two-phase strategy, comprising 20 epochs with the backbone frozen and 30 epochs of fine-tuning with the last 30 layers selected while Batch Normalization layers remained frozen. Evaluation on 586 testing images achieved 95.56% accuracy, 98.79% Pneumonia precision, 95.09% recall, 96.90% F1-score, and 0.9929 ROC-AUC. These results indicate that the integrated preprocessing and Xception-based transfer learning framework provides strong and reproducible classification performance on the evaluated public dataset.
Unsupervised Anomaly Detection for Water Pump Fault Identification Under Extreme Class Imbalance Mochamad Rizal Fauzan; Ghayrie Habsy Alghifary; Muhamad Husen
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.114

Abstract

Water pump fault detection in industrial systems is challenged by extreme class imbalance, where anomalous states account for less than 7% of operational data and labeled fault examples are scarce. This paper presents a comparative evaluation of three unsupervised anomaly detection approaches Isolation Forest (IF), Long Short-Term Memory Autoencoder (LSTM-AE), and One-Dimensional Convolutional Neural Network Autoencoder (1D-CNN-AE) applied to a real-world multivariate water pump sensor dataset comprising 220,320 one-minute observations across 51 sensors. All models are trained exclusively on normal operational data, eliminating dependence on fault labels. A sliding-window preprocessing pipeline (W = 30 timesteps) with a scaler fitted only on normal training data ensures no temporal data leakage. Anomaly thresholds are derived statistically (mean + 3σ) from reconstruction errors on the normal test partition. Using a chronological 60/40 train-test split and threshold-free metrics, Isolation Forest achieves AUROC = 0.9973 and Recall = 0.9850, while LSTM-AE yields F1 = 0.9218 and Precision = 0.8892. The results reveal a fundamental sensitivity-selectivity trade-off across unsupervised paradigms and provide actionable guidance for deploying anomaly detection in water infrastructure monitoring systems.
Interpretable Airline Passenger Satisfaction Prediction Using Recursive Feature Elimination, Bayesian-Optimized Random Forest, and SHAP Arrijalu Ringga Fahreza; Anggyi Trisnawan Putra
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.119

Abstract

Airline passenger satisfaction prediction can assist service-quality planning, but accurate classification alone does not explain model decisions. This study evaluates four Random Forest (RF) configurations with and without Recursive Feature Elimination (RFE) and Bayesian Optimization, complemented by SHapley Additive exPlanations (SHAP). A publicly used airline satisfaction dataset comprising 129,880 records and 25 original columns was examined. Following removal of two identifiers and the target, 22 candidate predictors remained. Stratified training–testing division (80:20) and training-only preprocessing were used to prevent data leakage. The four models achieved respective test accuracies of 94.67% (RF), 94.60% (RF+RFE), 96.25% (RF + Bayesian Optimization), and 95.82% (RF+RFE+Bayesian Optimization). The integrated model retained 15 predictors and achieved 96.64% precision, 93.65% recall, 95.12% F1-score, and 0.9927 ROC-AUC. Sensitivity analysis over 10–20 predictors identified a higher cross-validation accuracy at 18 features (96.30%) than at 15 (95.73%); 15 features were retained as a compact, predefined subset, not an accuracy-optimal solution. Positive-class SHAP explanations identified Type of Travel, Inflight WiFi Service, Online Boarding, Class, and Customer Type as leading contributors in a 300-observation test sample. The findings support an interpretable feature-reduction and predictive-performance trade-off without claiming that the integrated model maximizes accuracy or establishes causal service effects.
Efficient Pneumonia Detection with MobileNetV2 Through a Staged Optimization Pipeline and Grad-CAM Interpretability Evaluation Faray Juan Tody; Majid Rahardi
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.127

Abstract

Pneumonia remains a major cause of morbidity and mortality, and chest X-ray screening in resource-constrained settings could benefit from lightweight deep learning models. This study provides an integrated evaluation of established techniques, adaptive histogram standardization (AHS), automatic mixed-precision (AMP) training, and FP16 post-training quantization, applied to a MobileNetV2-based pneumonia classifier, using a four-scenario ablation design with repeated hold-out validation across three seeds. The selected model of each scenario reached 91.03–91.42% test accuracy, and peak validation accuracy across seeds did not differ significantly between scenarios (p > 0.05, n = 3, which does not prove equivalence). AMP reduced training VRAM by 47.9%; FP16 quantization reduced model size by 49.6% and increased single-image throughput by 29.9% (1.30× speedup) over its FP32 counterpart, with a test confusion matrix identical to that of the autocast-evaluated FP32 model. False negatives decreased from 14 to 8 (42.9%) in the selected models. In three high-confidence true-positive cases, Grad-CAM maps remained qualitatively similar in location across all stages. In this dataset and configuration, staged optimization improved efficiency without measurable loss of accuracy; external validation and tests on physical edge devices are needed before deployment claims.
Web-Based Inventory Management System Using Economic Order Quantity for Optimal Stock Ordering at A Vape Store Kristalenta; Dian Widiyanto Chandra
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.137

Abstract

Inventory management is essential to sustaining business operations and meeting customer demand. BigBoss Vape Store still manages its inventory manually, which leads to stock discrepancies, delayed replenishment, and difficulty in determining optimal order quantities; sales transactions and order management are likewise not integrated, reducing operational efficiency. This study designs and develops a web-based inventory management system that applies the Economic Order Quantity (EOQ) method to determine the optimal order quantity. The system was developed using the Prototype method and implemented with the CodeIgniter 4 framework, the PHP programming language, a MySQL database, and Unified Modeling Language (UML) for system modeling, and was evaluated using Black Box Testing. The results show that the system manages product, vendor, and vendor-product data, purchase and sales transactions, the shopping cart and checkout process, transfer-proof uploads, and administrator order management. The EOQ implementation determines the economic order quantity, order frequency, and Reorder Point (ROP), and recommends vendors based on purchase price. Testing confirms that all system functions operate as required, indicating that the system can improve inventory management efficiency, support procurement decision-making, and enhance service quality at the Vape Store.
Development and Evaluation of an SAW-Based Tourism Service Recommendation Model for Island Tourism Destinations Jefri Rahmadian; Hari Setiyani; Santi Setiyaningsih; Fayyaza Faryal Anakidanda
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.138

Abstract

Island tourism destinations often involve services managed by independent local providers, making it challenging for tourists to identify suitable alternatives. This study developed and evaluated a web-based tourism service recommendation model using Simple Additive Weighting (SAW) for Pramuka Island, Indonesia. The model considers three criteria: category similarity, price similarity, and user rating. Weights were derived through the Analytic Hierarchy Process (AHP) based on pairwise comparisons by 21 tourists, yielding 0.43, 0.37, and 0.20, respectively, with an acceptable Consistency Ratio of 7.72%. SAW calculated preference scores and ranked service alternatives. Computational verification confirmed that application rankings matched manual spreadsheet calculations. Recommendation relevance was evaluated using Precision@6 across four service categories, achieving an average of 54.17%, with 100% precision for Homestay and Diving, 16.67% for Tour Package, and 0% for Rental due to limited same-category alternatives. Usability testing with 32 tourists yielded an average System Usability Scale (SUS) score of 83.3. These findings demonstrate the model's feasibility and computational consistency in the Pramuka Island context. However, recommendation relevance depends heavily on category-level service availability, requiring broader validation using larger and more balanced datasets.
Comparative Evaluation of Resampling Techniques and Machine Learning Classifiers for Credit Risk Prediction in Imbalanced Peer-to-Peer Lending Data Dwika Ananda Agustina Pertiwi; Sidiq Noor Kharisma; Rini Muzayanah; Apri Dwi Lestari; Sumarsono Sumarsono; Much Aziz Muslim; Andi Saputra
Journal of Information System Exploration and Research Vol. 4 No. 4: October 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i4.142

Abstract

Class imbalance in peer-to-peer (P2P) lending data can bias machine learning predictions toward the majority class, limiting the identification of loans that are not fully repaid. This study evaluates three resampling techniques: Synthetic Minority Over-sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), and Conditional Tabular Generative Adversarial Networks (CTGAN), combined with four classifiers: Logistic Regression, Ridge Classifier, XGBoost, and LightGBM. The Lending Club dataset was divided into training and testing sets, with resampling applied only to the training data. Models were evaluated on the original, unresampled test set. Without resampling, LightGBM achieved an F1-score of 33.37%. LightGBM with ADASYN obtained the highest Recall (96.95%), while LightGBM with CTGAN achieved the highest F1-score (83.28%) and Accuracy (84.54%). These results demonstrate that resampling effectiveness depends on the classifier and evaluation metric. Statistical significance testing and synthetic data quality assessment were also conducted to examine result reliability. Overall, CTGAN combined with LightGBM provided the most balanced performance among the tested combinations, whereas ADASYN with LightGBM was more suitable for prioritizing minority-class detection. Further research should validate these findings using additional datasets.

Page 4 of 4 | Total Record : 37

 1   2   3   4 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 4: October 2026 Vol. 4 No. 3: July 2026 Vol. 4 No. 2: April 2026