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
shmpublisher@gmail.com
Editorial Address
Jl. Karanglo Raya No. 64, Pedurungan, Semarang, 50191, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Journal of Soft Computing Exploration
Published by shm publisher
ISSN : 27467686     EISSN : 27460991     DOI : https://doi.org/10.52465/joscex
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering
The journal focuses on publishing high-quality, original research and review articles in the field of Soft Computing, Informatics and Computer Science, emphasizing the development, application, and rigorous evaluation of Advanced Computational Methods, Artificial Intelligence (AI), Machine Learning (ML), and Data Science to address complex real-world challenges. The scope of the journal includes, but is not limited to, innovative research in the following areas: 1. Artificial Intelligence and Machine Learning Novel Algorithms and Architectures: Development and comparison of ML/DL models for classification and prediction (including Logistic Regression, Ridge Classifier, SVM, k-NN, and Random Forest). Ensemble Learning: Evaluation and optimization of ensemble methods Balanced Random Forest, SMOTE-RF, SMOTEBoost, and RUSBoost for robust prediction. Data Challenges and Preprocessing: Techniques for mitigating issues like class imbalance (using methods like SMOTE and GAN) and feature extraction/dimension reduction techniques (including Principal Component Analysis (PCA) and Local Binary Pattern (LBP)). 2. Deep Learning and Computer Vision Convolutional Neural Networks (CNNs): Research on CNN architectures (VGG16, ResNet50, DenseNet121, EfficientNet, and MobileNetV2) and the impact of optimization functions (Adam, SGD, NAdam) on model performance. Hybrid and Concatenated Architectures: Proposing and evaluating hybrid models (MobileNetV2 combined with LBP) or concatenated architectures (MobileNetV2 and DenseNet201) to improve classification and feature representation. Image Analysis Tasks: Advanced techniques for image classification (specifically Diabetic Retinopathy), image similarity detection (using Siamese Networks and Test-Time Augmentation), and multi-object segmentation (using FCN with Squeeze-and-Excitation and Attention Mechanisms for palm oil images). 3. Data Science and Advanced Analytics Pattern Detection and Data Mining: Performance evaluation of data mining algorithms, including Biclustering (Cheng & Church and Spectral Biclustering), specifically under challenging structural conditions like collinearity and overlap. Time Series Analysis and Forecasting: Application of advanced decomposition and clustering methods (Ensemble Empirical Mode Decomposition (EEMD) and Time Series Clustering with DTW/ARIMA) for accurate economic or temporal prediction. 4. Applied Informatics (Domain-Specific Applications) Health and Medical Informatics: Classification models for disease diagnosis (including Heart Attack Disease and Diabetic Retinopathy). Agricultural Informatics: Automated detection and classification of plant diseases from leaf/crop images (including Mango Leaf Disease and Chili Plant Disease) and Palm Oil Segmentation. Business and Economic Informatics: Predictive modeling for crucial business metrics (Customer Churn Prediction in Telecommunications) and economic forecasting (Rice Price Forecasting).
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 56 Documents
 2   3   4   5   6 
An interpretable hybrid ensemble model for early academic risk detection with shap-based explainability Rita Wahyuni Arifin; Sumardiono; Shalahuddin; Yeffry Handoko Putra; Khoem Sambath
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.50

Abstract

Student dropout remains a major challenge in educational institutions, affecting both academic achievement and institutional performance. Early identification of at-risk students is essential to support timely intervention and improve retention rates. This study proposes an interpretable hybrid ensemble model for early academic risk detection by integrating stacking ensemble learning, Bayesian optimization, and SHAP-based interpretability. The study used a public dataset from Kaggle containing 10,000 student records with demographic, behavioral, and academic performance attributes. Exploratory analysis indicated that at-risk students generally had lower GPA and attendance rates, while higher stress levels were associated with increased dropout risk. Due to the moderately imbalanced class distribution in the dataset, SMOTE was applied only to the training data after train–test splitting to improve minority class representation while avoiding data leakage during evaluation. Experimental results demonstrate that the proposed hybrid model outperformed individual baseline classifiers and standard stacking ensemble methods, achieving an accuracy of 0.93 ± 0.01, precision of 0.92 ± 0.01, recall of 0.91 ± 0.01, and F1-score of 0.91 ± 0.01 under stratified 5-fold cross-validation. The integration of Bayesian Optimization improved model stability and classification consistency, while SHAP-based analysis identified GPA, CGPA, attendance rate, study hours, and stress index as the most influential contributors to prediction outcomes.
Information security awareness among students in eastern indonesia: A HAIS-Q based assessment and intervention priority mapping Muhammad Fadlan; Syarifah Syarifah; Denis Prayogi; Suprianto Suprianto
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.52

Abstract

The increasing use of digital technology among university students is not always accompanied by adequate levels of information security awareness, especially in Eastern Indonesia, which has its own characteristics and challenges regarding facilities and digital literacy. This study aims to assess students’ information security awareness using an adapted HAIS-Q and to provide a soft computing-oriented interpretation for mapping intervention priorities. A quantitative survey was conducted involving students from Universitas Amal Ilmiah Yapis Wamena. The instrument measured three awareness dimensions, namely knowledge, attitude, and behaviour, across five focus areas. The results show that students’ information security awareness is generally in the good category, with attitude obtaining the highest score of 81.44, followed by knowledge at 80.10, and behaviour at 75.04. At the focus area level, mobile device security achieved the highest mean score, while email security obtained the lowest. The distribution of awareness levels shows that 60% of respondents were in the good category, 33% in the average category, and 7% in the poor category. From a soft computing perspective, these results can be interpreted as input indicators for mapping intervention priorities, particularly by identifying behaviour-related weaknesses, vulnerable awareness groups, and specific security domains requiring improvement.
A comparative benchmark of vision transformer architectures for chili leaf disease classification Acihmah Sidauruk; Danang Wijayanto; I Made Artha Agastya; Jumanto Unjung; Mulia Sulistiyono
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.62

Abstract

Chili plant disease detection represents a critical component for enhancing agricultural productivity. Although Convolutional Neural Networks (CNN) have demonstrated promising results, they encounter limitations in capturing global contextual relationships within images. However, existing Vision Transformer studies on plant disease commonly assess only a single architecture, leaving the relative performance of different Vision Transformer families on chili disease data largely unexamined. This research aims to conduct a comparative benchmark analysis of five Vision Transformer-based architectures ViT, Swin Transformer, MaxViT, DINOv2, and EVA-02 to identify the most optimal model for chili plant disease classification. The methodology begins with data preprocessing and augmentation on a chili leaf dataset comprising five classes: healthy, leaf curl, leaf spot, whitefly, and yellowish. Each model is then fine-tuned under consistent training configurations with early stopping to prevent overfitting, and evaluated using accuracy, precision, recall, F1-score, and AUC. The results indicate that DINOv2 achieves superior performance with 96% accuracy, 96% precision, 96% recall, 96% F1-score, and 99% AUC, along with the highest training efficiency through convergence at epoch 12, outperforming ViT (92%), Swin (88%), MaxViT (88%), EVA-02 (86%), and previous CNN-based approaches. These findings confirm the superior potential of Vision Transformers, particularly self-supervised models, as a promising alternative for agricultural disease detection applications. The main contribution of this study is the first unified, head-to-head benchmark of five distinct Vision Transformer families for chili leaf disease classification, providing practical guidance on model selection in terms of both accuracy and training efficiency.
Indonesian sign language (BISINDO) gesture detection using Yolov11-Pose Achmad Dany Alfansyah; Ardian Yusuf Wicaksono; Pima Hani Safitri
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.69

Abstract

Sign language serves as the primary means of communication for deaf individuals, yet existing recognition systems for Bahasa Isyarat Indonesia (BISINDO) have not fully exploited keypoint-based pose estimation, particularly for dynamic alphabetic gestures. This study developed a BISINDO gesture detection system using the YOLOv11m-Pose algorithm integrated with MediaPipe hand landmark extraction, Letterbox image preprocessing, and a multi-phase class representation strategy that divided dynamic letters into two movement-phase classes. The main novelty of this study lies in the integration of YOLOv11-Pose with MediaPipe hand keypoint extraction and a multi-phase representation strategy for dynamic letters, which has not been previously applied to BISINDO alphabet detection. A dataset of 1.450 images across 29 classes was collected, augmented to 8.700 samples, and split into training, validation, and test sets. Evaluation on 870 test images yielded an overall accuracy of 99,43%, a macro precision of 99,44%, macro recall of 99,43%, and a mAP50 of 99,11%. All six dynamic letter classes achieved perfect prediction scores, confirming the effectiveness of the multi-phase representation approach. These results demonstrated that the proposed system was capable of reliable BISINDO alphabet detection and provided a solid foundation for further development toward full support for sign language communication.
An integrated email security gateway and dual-layer frequency-domain watermarking framework for business transaction receipt authentication against generative AI manipulation Bonifacius Vicky Indriyono; Rabei Raad Ali
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.77

Abstract

Business document forgery and email phishing have been significantly amplified by generative artificial intelligence, yet existing security frameworks address communication-channel protection and document authentication as separate concerns, leaving organizations vulnerable to coordinated multi-vector attacks. This research aims to design, implement, and evaluate a unified "Dual-Shield" framework that bridges this gap through an integrated, lightweight solution for real-time business operations. The proposed system combines a four-stage email security gateway—covering sender verification, URL analysis via VirusTotal API, and attachment sanitization—with a dual-layer digital watermarking engine applied to transaction receipt images. The watermarking component pairs a robust Discrete Wavelet Transform–Singular Value Decomposition layer for authorship attribution with a semi-fragile Quantization Index Modulation–Discrete Cosine Transform layer for monetary integrity verification, assessed via imperceptibility, robustness, and tamper-detection metrics on synthetic and real-world datasets. Results show the robust watermark achieved peak signal-to-noise ratio values of 43.38–43.48 dB with SSIM above 0.98. All generative AI manipulations were detected with bit error rates of 0.375–0.472, and targeted ten-percent numerical fraud was identified by the semi-fragile layer. The gateway correctly classified all test scenarios, confirming that malicious URL detection overrides trusted sender status to prevent whitelist exploitation.
A CoCoSo-based decision support framework for electric vehicle evaluation using deep learning-derived policy sentiment evidence Nur Tulus Ujianto; Gunawan Gunawan; Diajeng Tyas Purwa Hapsari; Gunawan Raharjo; Didiek Trisatya
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.80

Abstract

Electric vehicle adoption is shaped not only by technical and economic attributes but also by public perception of government incentive policies. Existing electric vehicle evaluation models commonly prioritize conventional criteria, while policy-related public sentiment is often treated only as descriptive context. This study proposes a hybrid decision support framework that integrates IndoBERT-based sentiment analysis with the Combined Compromise Solution (CoCoSo) method for electric vehicle evaluation in Indonesia. Public comments on electric vehicle incentives were classified into positive, neutral, and negative sentiment to construct a Policy Sentiment Evidence Index (PSEI). The index was incorporated into the CoCoSo decision matrix together with price, driving range, battery capacity, and charging time. The sentiment classifier achieved an accuracy of 0.6447 and a macro-F1 score of 0.5228, indicating moderate class-balanced performance under imbalanced sentiment distribution. The rescaled PSEI value of 0.3746 indicates relatively unfavorable public sentiment toward electric vehicle incentives. The CoCoSo results ranked Tesla Model 3 first, followed by Hyundai Ioniq 5, Nissan Leaf, and Wuling Air EV. Sensitivity analysis confirmed stable rankings across policy sentiment weighting scenarios, suggesting that sentiment evidence can enrich multi-criteria electric vehicle evaluation without destabilizing the decision outcome.
Lightweight thermogram classification for diabetic foot screening: A handcrafted-feature and RFE-SVM pipeline for low-resource settings Bedy Purnama; Bayu Erfianto; Linlin Lindayani
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.81

Abstract

Diabetic foot problems continue to be a significant cause of morbidity among people with diabetes, requiring accurate and scalable methods for early identification. Infrared thermography is a non-invasive technique for detecting asymmetry in plantar temperature, which is associated with the risk of inflammation. However, the use of infrared thermography is limited by the small size of labeled datasets in the biomedical domain, posing issues for the generalizability of models and the reliability of validation. In this work we aim at studying the effectiveness of a carefully verified handcrafted-feature based model for diabetic foot thermogram categorization with limited data. The suggested pipeline combines multi-descriptor feature representation, Recursive Feature Elimination (RFE) and margin-based classification by means of Support Vector Machines in a nested cross-validation setting, together with bootstrap stability analysis. Experiments on a publicly accessible plantar thermogram dataset (N = 167) show strong performance with holdout AUC of 0.942 and nested cross-validation AUC of 0.959 ± 0.045. Calibration findings show a low Brier score of 0.065 with balanced sensitivity (0.88) and specificity (0.889). Further study shows that discriminative performance stems from distributed gradient–texture interactions, not sparse feature subsets. The results show that a careful validation and a systematic design of the representation can overcome the limitations of data and allow the development of reliable thermographic screening systems.
Comparative analysis of ARIMA, RNN, LSTM, and GRU for multi-sector Indonesian stock price forecasting Asep Muhidin; Agung Nugroho; Muhtajudin Danny
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.91

Abstract

Forecasting stock prices remains a challenging task because financial time series are highly volatile, nonlinear, and often differ across sectors. In the Indonesian market, previous studies have mainly focused on single stocks or limited model comparisons, leaving cross-sector evidence relatively scarce. This study compared the forecasting performance of Autoregressive Integrated Moving Average (ARIMA) and three deep learning models, namely Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), using historical daily closing price data from 12 Indonesian listed companies across four sectors: banking, energy, consumer goods, and telecommunications. The data cover the period from 2010 to 2025 and comprise more than 47,000 observations. The historical datasets were preprocessed and divided into training and testing sets using an 80:20 holdout strategy. For the deep learning models, normalized closing prices were transformed into supervised sequences using a 30-day sliding window, and forecasting performance was evaluated under a rolling forecasting framework. Forecasting accuracy was measured using RMSE, MAE, and MAPE. The ARIMA baseline produced an average RMSE of 158.74 and an average MAPE of 3.30%. Among the deep learning models, RNN achieved the best overall performance, with the lowest mean RMSE (117.01) and mean MAPE (2.72%). In contrast, GRU obtained seven stock-level wins and the lowest median MAPE (1.97%), indicating greater consistency across individual stocks. LSTM showed weaker overall performance, with a mean RMSE of 146.96 and a mean MAPE of 3.83%. The Friedman test indicated significant differences among the compared models (χ² = 9.50, p = 0.0087). Pairwise Wilcoxon analysis showed a significant difference between LSTM and GRU (p = 0.0015), while no significant differences were found for RNN–LSTM and RNN–GRU. These findings suggest that simpler recurrent architectures remain highly effective for stock forecasting, and that model selection should consider both sector characteristics and evaluation criteria.
Predicting international tourist arrivals in north sumatra using machine learning and google trends keyword selection Angga Putra Juledi; Fajar Maulana; Yofhanda Septi Eirlangga; Yomei Hendra; Qiuyun Cao
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.107

Abstract

This study examined the prediction of monthly international tourist arrivals in North Sumatra by combining historical visitation data with Google Trends keyword selection in a machine learning framework. Monthly data from January 2010 to December 2025 were analyzed. The proposed approach constructed temporal features from past arrivals and search-interest features from tourism-related keywords grouped into destination, travel-intent, and attraction-specific segments. A seasonal naive model was used as the baseline, while Random Forest and Gradient Boosting were applied as the main prediction models. The results showed that the historical-only Random Forest model achieved the best performance among the main forecasting scenarios and clearly outperformed the seasonal baseline. The inclusion of all Google Trends keywords did not improve prediction accuracy consistently. However, the destination segment provided more useful predictive information than the other keyword groups. Further keyword selection revealed that Bukit Lawang was the most robust single keyword, while a compact subset consisting of Danau Toba, Medan, Sumatra Utara, and Bukit Lawang produced the best test performance. These findings indicated that Google Trends improved forecasting accuracy only when relevant keywords were selected carefully.
Particle swarm optimization-based support vector regression for unemployment rate prediction using panel data Muhtajuddin Danny; Asep Muhidin
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.113

Abstract

Predicting the Open Unemployment Rate (OUR) is important for supporting data-driven employment policies, particularly in regions with complex economic and social conditions. This study aims to develop a predictive model for OUR using panel data from districts/cities in West Java Province during the 2018–2025 period by applying Support Vector Regression (SVR) optimized with Particle Swarm Optimization (PSO). The dataset includes economic, social, and demographic variables, namely labor force participation rate, average years of schooling, population, minimum wage, Human Development Index, GRDP per capita, poverty rate, and population density. The proposed approach combines SVR as a nonlinear regression technique with PSO for hyperparameter optimization to improve prediction accuracy. The experimental results show that the model achieved a Mean Squared Error (MSE) of 1.4888 and a coefficient of determination (R²) of 0.4343, indicating moderate predictive performance. In addition, the optimization process demonstrated a stable reduction in RMSE values during iterations, confirming the effectiveness of PSO in enhancing the SVR model. The findings suggest that the SVR–PSO model is capable of capturing general unemployment patterns in panel data and can support adaptive, data-driven employment policy analysis.

Page 5 of 6 | Total Record : 56

 2   3   4   5   6 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 3 (2026): September 2026 Vol. 7 No. 2 (2026): June 2026 Vol. 7 No. 1 (2026): March 2026