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 32 Documents
 1   2   3   4 
Comparative evaluation of deep learning models for dried corn price prediction in east java Antika Zahrotul Kamalia; Choiriyatun Nisa Latansa; Zaenur Rozikin; Hemdani Rahendra Herlianto; Shiza Hassan
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.48

Abstract

Forecasting dry shelled corn prices was important for supporting decision-making by farmers, traders, feed industries, and local governments. This study comparatively evaluated several deep learning models, namely Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network 1D (CNN1D), Temporal Convolutional Network (TCN), and Transformer, for predicting dry shelled corn prices in East Java. Classical benchmark models, namely naïve, drift, and simple exponential smoothing (SES), were also incorporated into the experimental design. Using daily price data from 2020 to 2024, a 30-day lookback window, and multivariate features derived from price movements, calendar variables, and rolling statistics, model performance was assessed using MAE, RMSE, MAPE, sMAPE, and . The results showed that the naïve baseline achieved the best overall performance on the 2024 test set, while TCN was the strongest among the evaluated deep learning models. TCN obtained RMSE of 176.95 and of 0.6895, whereas the naïve baseline achieved RMSE of 20.06 and of 0.9960. Overall, all deep learning models were outperformed by the naïve persistence benchmark, indicating that greater model complexity did not automatically improve forecasting accuracy on this highly persistent price series.
Enhancing sarcasm detection via multimodal learning: A BiLSTM-attention approach with text and emojis integration Nasa Zata Dina; Moch. Nafkhan Alzamzami
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.49

Abstract

The detection of sarcasm is a difficult task in Natural Language Processing (NLP) because to the presence of implicit meaning and contextual ambiguity. This is particularly problematic in social media, where emojis are used frequently to indicate tone and intent. The study proposes a multimodal deep learning strategy that combines both textual and emoji features, by utilizing a BiLSTM with attention mechanisms. The goal of this method is to improve the performance of sarcasm detection. The model makes advantage of bidirectional contextual learning and preferentially focuses on informative tokens and emojis in order to do more effective work of capturing complex expressions. According to the findings of the experiments, the Text+Emoji model that was proposed achieves an F1-score of 96.44%, an accuracy of 97.08%, and an area under the curve (AUC) of 99.23%, which is a significant improvement over the unimodal baselines. Future research will focus on enhancing the proposed model by investigating transformer-based architectures to achieve deeper and more contextualized representation learning.
Development and usability evaluation of an adaptive cognitive training game based on raven’s coloured progressive matrices Ashafidz Fauzan Dianta; Fony Revindasari; Muhammad Raoul Archibald
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.34

Abstract

This study proposes an intelligent adaptive cognitive training system based on a soft computing approach to enhance non-verbal reasoning skills in children with mild intellectual disabilities (MID). The system integrates Raven’s Coloured Progressive Matrices (RCPM) into a mobile puzzle-based learning environment called Cognitia. Unlike conventional educational games with static difficulty levels, the proposed system employs a fuzzy inference system (FIS) to dynamically adjust task difficulty based on user performance metrics, including normalized completion time, error frequency, and level of assistance. A Mamdani-type fuzzy model with defined membership functions and rule-based reasoning is utilized to handle uncertainty and variability in user behavior, enabling personalized and human-like decision-making in difficulty adaptation. The system was developed using the Game Development Life Cycle (GDLC) framework and implemented on the Android platform. Experimental evaluation was conducted through usability testing and real-world deployment involving 12 students with MID in a special education setting. The results indicate that the proposed adaptive mechanism successfully maintains an optimal challenge level, achieving a task completion rate of 92% and a user acceptance score of 84.38%. Furthermore, qualitative feedback from teachers confirms that the system is accessible, engaging, and pedagogically relevant. This study contributes to the field of soft computing by demonstrating the practical implementation of a fuzzy-based adaptive difficulty model in an educational game context. The findings highlight the effectiveness of integrating lightweight computational intelligence into cognitive training systems to support inclusive and personalized learning environments.
Enhancing YOLO performance with attention module for plastic and non-plastic waste detection on water surfaces Adri Priadana; Aris Wahyu Murdiyanto; Muhammad Ichwandar Akrianto; Heru Cahyono
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.46

Abstract

The rapid accumulation of plastic waste in aquatic environments poses serious threats to ecosystems, water management systems, and human health. This growing concern creates an urgent need for efficient and accurate detection methods. To address this challenge, this work proposes an approach to enhance YOLO performance by integrating attention modules for plastic and non-plastic waste detection on water surfaces. A comprehensive evaluation is conducted on the Plastic on Water dataset, considering detection accuracy, computational complexity, and inference speed. The results identify YOLO11n as the most effective baseline, achieving a mean Average Precision (mAP) of 96.3% with 2,590,230 parameters, 6.4 GFLOPs, and an inference speed of 18.58 FPS. To further improve performance, several attention modules are integrated into the YOLO11n architecture. Among them, the Convolutional Block Attention Module (CBAM) yields the best performance, achieving an mAP of 96.7% with 2,598,520 parameters and 6.5 GFLOPs, while maintaining real-time performance at 18.26 FPS. The results demonstrate improved detection capability, particularly for small and less prominent objects, with negligible additional computational cost. These findings highlight the effectiveness of attention mechanisms, especially CBAM, in enhancing lightweight object detection models for real-time aquatic waste monitoring.
Lightweight discrete q-learning for self-tuning PID on ESP32: Robustness evaluation and cross-volume adaptation in egg incubators Tino Feri Efendi; Zainal Arifin
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.8

Abstract

Temperature stability is the most crucial factor in the success of the egg incubation process. The use of conventional Proportional–Integral–Derivative (PID) control with static Ziegler–Nichols tuning often fails to adapt to external disturbances and thermal dynamics, leading to temperature overshoot that can be fatal to embryo survival. This study proposes the implementation of an adaptive PID controller using a Discrete Q-Learning method based on Edge-AI on an ESP32 microcontroller. Experimental results under standard conditions show that the Q-Learning method successfully reduces overshoot by up to 81.8%, limiting the temperature spike to only 0.2°C above the target of 38.0°C, and accelerating the stabilization time by 76.9% with a reduction in IAE of 52.5%. In the dynamic disturbance rejection test, the adaptive system validated the algorithm's robustness against dynamic disturbances. Furthermore, cross-environment adaptation evaluation by reducing the incubator volume by 50% demonstrates the agent’s autonomous adaptation capability, eliminating overshoot entirely (0.000°C) without parameter recalibration and reducing IAE by 55.1% compared to static PID. This study concludes that the implementation of Q-Learning on low-cost hardware produces a robust, precise, and autonomously adaptive thermal control system for agricultural technology applications.
Comparative evaluation of random forest, GRU, and transformer models for soil moisture prediction using reanalysis and meteorological time series data Defilia Fatikasari; Miftahul Walid; Muhsi; Moh. Aminollah Hamzah
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.54

Abstract

Soil moisture is an important indicator influenced by climate change and water resource availability, with significant impacts across various sectors, particularly agriculture. Limited continuous observational data necessitate historical data-driven approaches for accurate soil moisture prediction. This study aims to comparatively evaluate the performance of Random Forest, Gated Recurrent Unit (GRU), and Transformer models in soil moisture prediction using time series data based on a combination of NASA POWER reanalysis and BMKG meteorological data for the period 2020–2025. The methodology involves data acquisition, preparation, preprocessing (train–test split, min-max normalization, and windowing), model training, and performance evaluation based on MAE, RMSE, and R². The results show that the Random Forest model with a window size of 21 days achieves the best performance, yielding an MAE of 0.0396, an RMSE of 0.0534, and an R² of 0.8585. The Random Forest model produces predictions closest to the actual values and demonstrates better stability in capturing time series patterns, outperforming the GRU and Transformer models in soil moisture prediction using integrated global and local time series data
Web-based sentiment analysis of environmental issues on social media X: A comparison of svm and random forest Subandi; Agus Setiyo Budi Nugroho; Muhammad Hidayat
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.55

Abstract

This study aims to compare the performance of Support Vector Machine (SVM) and Random Forest (RF) in classifying public sentiment toward environmental issues on social media X (formerly Twitter) and to develop a web-based system for sentiment monitoring and visualization. A total of 47,245 tweets from 2021–2025 were collected using 24 environmental keywords. The data were processed through text cleaning, tokenization, stopword removal, and stemming. Sentiment labeling was performed automatically using a lexicon-based approach with the InSet dictionary, resulting in positive, negative, and neutral classes. After filtering, 13,063 tweets were used for model training. Classification employed TF-IDF features and 5-fold cross-validation. The results indicate that SVM outperformed RF with an accuracy of 83%, compared to 81%. Both models performed well in identifying sentiment polarity, although challenges remain in classifying neutral sentiment. The novelty of this study lies in integrating lexicon-based labeling with machine learning and implementing it in a web-based system for automated analysis and visualization. Practically, this system supports stakeholders in monitoring public opinion and enables data-driven decision-making in environmental policy and management.
An intelligent academic recommendation system for learning support in higher education Dwiny Meidelfi; Dikky Chandra; Fanni Sukma; Ulya Ilhami Arsyah; Sri Yusnita
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.28

Abstract

Higher education institutions increasingly rely on data-driven approaches to improve student learning outcomes. However, many academic advisory systems still provide general recommendations without considering individual learning patterns and academic performance. This study proposes an intelligent academic recommendation system that utilizes machine learning techniques to support personalized learning in higher education. The proposed system analyzes student academic data including grade point average, attendance, assignment scores, and study habits to predict academic performance. The proposed approach was evaluated using a dataset consisting of 1000 simulated student records representing academic performance indicators in higher education. Based on prediction results, the system generates personalized learning recommendations to assist students in improving their academic outcomes. Several machine learning algorithms, including Decision Tree, Random Forest, and Support Vector Machine, were evaluated to determine the most suitable predictive model. Experimental results show that the Random Forest algorithm achieved the highest prediction accuracy compared with other models. The developed system provides proactive learning recommendations that can assist both students and academic advisors in making better academic decisions.
YOLO26 for automated batik pattern classification: Preserving cultural heritage through advanced computer vision Moch. Sjamsul Hidajat; Dibyo Adi Wibowo; Zudha Pratama
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.60

Abstract

Batik is an important cultural heritage of Indonesia, characterized by diverse motifs reflecting regional identity, philosophy, and historical background. Manual identification requires expert knowledge and is time-consuming, making automated classification a valuable research challenge. This study proposes an automated batik motif classification system using YOLO26, a modern deep learning architecture optimized for end-to-end inference without Non-Maximum Suppression. The removal of post-processing stages enables a simpler and more efficient classification pipeline, suitable for lightweight and scalable deployment. A dataset of 20 batik motif classes, including Batik Bali, Batik Parang, Batik Mega Mendung, and Batik Kawung sourced from Kaggle, was constructed and preprocessed using standardized image resizing and normalization techniques. Data augmentation strategies such as geometric and photometric transformations improved model robustness. The system was trained using GPU acceleration to ensure efficient experimentation and reproducibility. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results show the proposed system achieved 86.44% overall classification accuracy with balanced macro and weighted F1-scores, indicating consistent performance across all batik categories. Results demonstrate that YOLO26 effectively captures fine-grained texture details and high-level motif structures, enabling discrimination between visually similar patterns. This approach contributes to automated batik recognition systems and supports digital preservation, cultural education, and practical applications in batik authentication and classification.
Optimizing YOLOv8 architecture using particle swarm optimization for high-precision binary quality classification in industrial welding seams Waluyo Nugroho; Heru Suprapto; Muhammad Hidayat
Journal of Soft Computing Exploration Vol. 7 No. 2 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i2.84

Abstract

The structural integrity of heavy machinery fundamentally depends on precise welding quality. However, traditional manual inspections remain inconsistent, labor-intensive, and susceptible to human error. While You Only Look Once v8 (YOLOv8) architectures have become the standard for real-time object detection, their performance in accurately classifying micro defects like porosity or cracks is frequently hindered by suboptimal default hyperparameters. To overcome this limitation, this study proposes PSO YOLOv8, an intelligent framework integrating the Particle Swarm Optimization (PSO) algorithm to automatically tune YOLOv8 critical hyperparameters, specifically learning rate, batch size, and weight decay. The framework was evaluated using a specialized dataset of 2,600 high resolution welding seam images, strictly categorized into Normal and Defective classes. Utilizing validation Mean Average Precision (mAP) as the fitness function, PSO was configured to maximize accuracy over 50 iterations. Experimental results demonstrate a substantial performance enhancement. The PSO optimized model achieved an mAP@50 of 94.2%, a significant improvement over the 83.7% baseline. Furthermore, the optimized configuration attained a 96.5% Precision rate, effectively reducing false-positive detections by 38.4%. These findings validate that fusing metaheuristic algorithms with deep learning provides a robust, high precision tool for automated quality assurance in smart manufacturing.

Page 3 of 4 | Total Record : 32

 1   2   3   4 

Filter by Year

2026 2026


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