cover
Contact Name
Agus Harjoko
Contact Email
ijccs.mipa@ugm.ac.id
Phone
+62274 555133
Journal Mail Official
ijccs.mipa@ugm.ac.id
Editorial Address
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
ISSN : 19781520     EISSN : 24607258     DOI : https://doi.org/10.22146/ijccs
Indonesian Journal of Computing and Cybernetics Systems (IJCCS), a two times annually provides a forum for the full range of scholarly study . IJCCS focuses on advanced computational intelligence, including the synergetic integration of neural networks, fuzzy logic and eveolutionary computation, so that more intelligent system can be built to industrial applications. The topics include but not limited to : fuzzy logic, neural network, genetic algorithm and evolutionary computation, hybrid systems, adaptation and learning systems, distributed intelligence systems, network systems, human interface, biologically inspired evolutionary system, artificial life and industrial applications. The paper published in this journal implies that the work described has not been, and will not be published elsewhere, except in abstract, as part of a lecture, review or academic thesis.
Articles 10 Documents
Search results for , issue "Vol 20, No 1 (2026): January" : 10 Documents clear
IndoBERT Optimization for Sentiment Analysis on DeepSeek App Reviews Sunan, Muh.; Resiloy, Unique Desyrre A.; Endriani, Desy; Suhaeni, Cici; Sartono, Bagus; Dito, Gerry Alfa
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.107507

Abstract

In the digital era, sentiment analysis is important to evaluate public opinion, especially in the context of Play Store apps with Indonesian-language reviews. This research aims to improve the performance of the IndoBERT model in sentiment analysis of DeepSeek app reviews by using data augmentation and hyperparameter tuning techniques. Data augmentation is done through the back-translation technique, while the hyperparameters tested include the number of epochs, learning rate, and batch size. Experimental results show that the combination of data augmentation with epoch 10, learning rate 2e-5, and batch size 16 produces the highest accuracy of 93.95% and F1-score of 0.94, with better stability than the model without augmentation. The model without augmentation showed fluctuations in performance, indicating overfitting in some configurations. These findings confirm the importance of applying augmentation techniques and hyperparameter tuning in improving the accuracy and stability of sentiment analysis models, and contribute to the development of NLP models for Indonesian and other resource-constrained languages.
Improved Wavelet-GLCM for Robust Batik Motif Classification Pradana, Gregorius Adi; Harjoko, Agus
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.108011

Abstract

Batik is a traditional Indonesian fabric made by applying wax on the fabric, then processed with a certain technique. The diversity of batik motifs often makes it difficult for people to recognize them. Therefore, a batik motif classification system is needed, one of the methods of which is based on digital image processing. However, in this method, variations in rotation and scale in the image often cause feature values to change, thus decreasing accuracy. To overcome this, this study proposes a robust Improved Wavelet-GLCM (IWGLCM) feature extraction method for classifying batik motif images that account for rotation and scale variations. This method combines the Gray Level Co-occurrence Matrix (GLCM) and statistical values from the results of the Discrete Wavelet Transform (DWT). These combined features are then classified using Support Vector Machine (SVM). In the test scenario with variations in rotation and scale at the same time, this method managed to achieve optimal performance with an accuracy of 95.00%, a precision of 95.08%, a recall of 95.00%, and an f1-score of 95.00%.
Classification of Infected Salmon Using CNN Deep Features and Optuna-Optimized SVM Pradita, Agus Hendra; Ayu, Putu Desiana Wulaning; Hostiadi, Dandy Pramana
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.108820

Abstract

Fish diseases are a major challenge in the aquaculture industry, impacting productivity and the economy, particularly in salmon farming. This study aims to develop an image classification system for infected salmon using Convolution Neural Network (CNN) deep features approach and Support Vector Machine (SVM) classifier optimized with Optuna. The dataset consists of 1,208 images that were balanced through augmentation before being divided into 70% training data and 30% test data. Features were extracted from the middle layer of three pretrained CNN architectures: EfficientNetB1 (block6d_add), ResNet50 (conv4_block6_out), and VGG16 (block4_pool), then selected using the Least Absolute Shrinkage and Selection Operator (LASSO) method to address high-dimensionality issues. An SVM classification model was trained using stratified 5-fold cross-validation, both with default parameters and hyperparameter optimization results from Optuna. The results show that the model with features from EfficientNetB1 tuned by Optuna achieved the highest accuracy of 99.34%, a significant improvement over the default model 98.23%. Meanwhile, ResNet50 and VGG16 achieved optimal accuracies of 98.23% and 98.89%, respectively, after tuning. This study contributes to the development of an adaptive and accurate early detection system for infected fish.
Rainfall Intensity Prediction Using LSTM and Random Forest Hybrid Model Pambudi, Ari; Aryani, Diah; Sunarto, Ronald Nur
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.109189

Abstract

Predicting rainfall accurately is essential for managing water resources and preventing hydrometeorological disasters. The unpredictability of daily rainfall patterns necessitates accurate and effective prediction methods. This study proposes a residual hybrid approach to forecast rainfall using historical rainfall data alone. To record temporal information, a Long Short-Term Memory (LSTM) model is used. patterns in the time series data and generate initial predictions. The residual, defined as the difference between actual values and LSTM predictions, is then used as the intend to use a Random Forest (RF) model for training, which learns the non-linear patterns not effectively captured by the LSTM. Although the dataset includes various meteorological variables such as temperature and humidity, this study uses only rainfall as the main input. The data is split into training and testing sets with an 80:20 ratio. Model performance is evaluated using MAE, MSE, and RMSE, with RMSE as the primary evaluation metric. Experimental results show that the LSTM-RF hybrid model consistently delivers greater accuracy of predictions in comparison to single-model approaches, demonstrating strong potential in improving the reliability of rainfall forecasting based solely on historical data.
Sentiment Classification of MyTelkomsel Reviews Using SVM and Logistic Regression Adinata, Rijal Bagus; Supriyono, Supriyono; Fithri, Diana Laily
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.110409

Abstract

The development of digital technology has encouraged increased user participation in expressing opinions through review platforms, such as the Google Play Store. MyTelkomsel's application, a digital service from Indonesia's leading telecommunications provider, has received various responses, from appreciation to complaints related to app performance and customer service. This study aims to evaluate sentiment in user reviews using Support Vector Machine (SVM) and Logistic Regression algorithms. Data was collected from the Google Play Store and underwent a series of pre-processing stages, including data cleaning, case folding, normalization, tokenization, stopword removal, and stemming. The feature extraction process uses the TF-IDF approach, while model performance evaluation is based on accuracy, precision, recall, F1-score, and Area Under Curve (AUC) metrics. The results showed that the performance of both models was relatively balanced, but SVM exhibited an advantage in recall for positive sentiment (82%), accuracy (93.36%), and AUC (0.9680). Logistic Regression excels in precision (99%) in the positive class. WordCloud visualization illustrates consistency of dominant words in each sentiment class, reflecting the model's ability to identify patterns in user opinion. These findings are expected to contribute to the improvement of digital services based on user input.
Leaf Disease Detection Model in Gayo Coffee Plantations Using Deep Learning Hidayat, Rahmad
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.110529

Abstract

Coffee is one of the most important tropical plantation commodities, significantly supporting the economy of the Gayo Highlands. Attacks of various diseases can significantly reduce the productivity and quality of Gayo coffee. This study developed a leaf disease detection model in coffee plants using the Convolutional Neural Network (CNN) method. The model developed in this study used two datasets. The first dataset, the Gayo Coffee Leaf Disease (PDKG), comprises 900 images of healthy and diseased leaves collected from Gayo coffee plantations. The acquired images in the PDKG dataset were then preprocessed to improve their image quality. The results of model training and testing on the PDKG dataset showed an accuracy of 0.91. On the public Coffee Leaf Diseases (CLD) dataset, the model achieved an accuracy of 0.95, representing a 7.1% increase compared to previous studies. The resulting model can help local coffee farmers in the Gayo Highlands detect leaf diseases early and manage plant health more efficiently and accurately. 
Developing an NLP-Powered Chatbot Application for MSME Legal Literacy Hidayatulloh, Syarif; Utami, Lilyani Asri; Rachmi, Hilda
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.111460

Abstract

Micro, Small, and Medium Enterprises (MSMEs) play a vital role in the national economy but often face legal challenges due to limited literacy regarding regulations and lack of access to information. This study aims to develop a legal literacy chatbot application for MSMEs based on Natural Language Processing (NLP) using the Rapid Application Development (RAD) method. The development process was carried out iteratively by involving users to ensure the system meets their needs. System evaluation included Black Box testing, usability testing using the System Usability Scale, relevance testing, and performance testing. The Black Box results showed that all functions ran 100% successfully. Usability testing involving 24 respondents obtained an average SUS score of 71.98, which exceeded the standard threshold of 68, indicating that the application is acceptable and easy to use. Relevance testing showed a high level of answer suitability, while performance testing with GTmetrix produced a Performance score of 87%, Structure score of 92%, a fully loaded time of 2.1 seconds, and a total page size of 0.98 MB. These findings highlight that the chatbot application can provide legal information quickly, accurately, and practically, as well as has the potential to improve the legal literacy of MSME actors.
Virtual Reality-Based Counseling Innovation for Depression Therapy in the Patient Healing Process Jiwa Permana, Agus Aan Aan Jiwa
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.111768

Abstract

Depression is a mental disorder that significantly affects patients’ quality of life and psychological well-being, necessitating innovative therapeutic approaches. This study focuses on the development of Virtual Reality (VR)-based Counseling Innovation, as VR technology offers immersive and interactive experiences that enhance patient engagement and support the healing process. The research employs the Rapid Application Development (RAD) method, which includes requirement identification, prototype design, system construction, and implementation. The VR therapy model incorporates a calming night environment with natural sounds and a daytime environment accompanied by instrumental music to facilitate relaxation and emotional recovery. Testing was conducted with 12 respondents to evaluate system usability and user interface/user experience (UI/UX), yielding a System Usability Scale (SUS) score of 82.08, indicating high acceptance. The results demonstrate that the VR counseling model provides an enjoyable and effective experience that supports patients’ emotional healing. These findings suggest that VR-based counseling can serve as an innovative alternative for depression therapy, offering a personalized, interactive, and adaptive approach. Furthermore, the study provides a foundation for integrating digital technologies into modern psychotherapy practices, highlighting the potential of VR to enhance therapeutic engagement and promote mental health recovery in a controlled, immersive environment.
Interpretable Rule-Based Clinical Decision Support for Early Screening Of Heart Disease using C4.5 Decision Trees Andriyani, Widyastuti; Wiyanti, Dian Tri; Nugroho, Daniel C.A.
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.112701

Abstract

This study develops an interpretable rule-based clinical decision support system for early screening of heart disease presence by integrating the C4.5 decision tree algorithm with a rule-based reasoning mechanism. The proposed approach is intended to assist clinicians in obtaining rapid, transparent preliminary indications from clinical data, particularly in settings that require lightweight and auditable solutions. The dataset was obtained from the UCI Heart Disease Repository and comprises 299 patient records, evaluated using a 70% training and 30% testing split in RapidMiner. Experimental results show that the C4.5 model achieves an accuracy of 86.52% and produces clinically interpretable IF–THEN rules, enabling traceable reasoning and decision auditing. Although C4.5 is a classical learning algorithm, it remains relevant for clinical decision support due to its auditability, low computational cost, and ease of deployment in resource-constrained environments. The developed system is expected to support early screening/triage and data-driven clinical decision-making, contributing to the advancement of medical decision support systems (MDSS).
Hybrid Manhattan Distance-Certainty Factor for Early Cardiovascular Diagnosis in a Hospital Tomatala, Michel
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.114611

Abstract

Cardiovascular disease drives high mortality and operational strain in public hospitals, underscoring the need for tools that standardize rapid early decisions. We evaluated a hybrid expert system that integrates Manhattan Distance (MD) for case-based similarity with a Certainty Factor (CF) framework for rule-based evidence aggregation. Using a locally curated knowledge base (110 cases, 69 symptoms, 13 conditions) and a 26-case hold-out against specialist references, the system retrieves nearest cases via MD on symptom vectors and then computes per-diagnosis confidence with CF. The system achieved 23/26 exact matches (accuracy 88.46%), with confidence values spanning 71.90–99.99% higher when nearest-case patterns and rules converged and moderated in ambiguous presentations (e.g., suspected aneurysm). Outputs were interpretable and suitable for 15–30-minute consultations, supporting consistent triage where specialist capacity is limited. These findings suggest a practical pathway to improve timeliness and reduce variability. Future work should pursue multi-site validation, knowledge-based expansion for atypical phenotypes, and governance for safe, equitable deployment.

Page 1 of 1 | Total Record : 10