cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dede Kurniadi
Contact Email
dede.kurniadi@itg.ac.id
Phone
+6287880007464
Journal Mail Official
jistics@aptika.org
Editorial Address
Green Garden Residence C-87, Kabupaten Garut, Provinsi Jawa Barat, Indonesia, 44151
Location
Kab. garut,
Jawa barat
INDONESIA
Journal of Intelligent Systems Technology and Informatics
Published by Aliansi Peneliti Informatika
ISSN : -     EISSN : 3109757X     DOI : https://doi.org/10.64878/jistics
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Engineering
The Journal of Intelligent Systems Technology and Informatics (JISTICS) is an international peer-reviewed open-access journal that publishes high-quality research in the fields of Artificial Intelligence, Intelligent Systems, Information Technology, Computer Science, and Informatics. JISTICS aims to foster global scientific exchange by providing a platform for researchers, practitioners, and academics to disseminate original findings, critical reviews, and innovative applications. The journal is published three times a year (March, July, November) and may also publish special issues on emerging topics.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 15 Documents
 1   2 
Indonesian Sign Language Alphabet Image Classification using Vision Transformer Agustiansyah, Yoga; Kurniadi, Dede
Journal of Intelligent Systems Technology and Informatics Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i1.5

Abstract

Effective communication is fundamental for social interaction, yet individuals with hearing impairments often face significant barriers. Indonesian Sign Language (BISINDO) is a vital communication tool for the deaf community in Indonesia. However, limited public understanding of BISINDO creates communication barriers, which necessitate an accurate automatic recognition system. This research aims to investigate the efficacy of the Vision Transformer (ViT) model, a state-of-the-art deep learning architecture, for classifying static BISINDO alphabet images, exploring its potential to overcome the limitations of previous approaches through robust feature extraction. The methodology involved utilizing a dataset of 26 BISINDO alphabet classes, which underwent comprehensive preprocessing, including class balancing via augmentation and image normalization. The Google/vit-base-patch16-224-in21k ViT model was adapted with a custom classification head and trained using a two-phase strategy: initial feature extraction with a frozen backbone, followed by full network fine-tuning. The fine-tuned Vision Transformer model demonstrated exceptional performance on the unseen test set, achieving an accuracy of 99.77% (95% CI: 99.55%–99.99%), precision of 99.77%, recall of 99.72%, and a weighted F1-score of 0.9977, significantly surpassing many previously reported methods. The findings compellingly confirm that the ViT model is a highly effective and robust solution for BISINDO alphabet image classification, underscoring the potential of advanced Transformer-based architectures in developing accurate assistive communication technologies to benefit the Indonesian deaf and hard-of-hearing community.
Comparison of CNN Models Using EfficientNetB0, MobileNetV2, and ResNet50 for Traffic Density with Transfer Learning Fauzi, Dhika Restu; Haqdu D, Gezant Ashabil
Journal of Intelligent Systems Technology and Informatics Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i1.6

Abstract

Traffic congestion in urban areas poses a significant and widespread challenge, stemming from the essential role of modern transportation in daily human activities. To address this issue, artificial intelligence (AI), particularly through applying convolutional neural networks (CNN), offers a promising solution for developing automated, accurate, and efficient traffic density classification systems. However, the performance of such systems is critically dependent on the selection of optimal model architecture. This study comprehensively analyzes three leading pre-trained CNN models: EfficientNetB0, MobileNetV2, and ResNet50. Utilizing a transfer learning approach, the models were trained over 20 epochs to classify traffic density into five categories: Empty, Low, Medium, High, and Traffic Jam. The research methodology was based on the public Traffic Density Singapore dataset. To enhance model robustness and address class imbalances, the initial dataset of 4,038 images was expanded to 6,850 images through data augmentation techniques. All images were subsequently resized to a uniform size of 224x224 pixels. The evaluation results conclusively demonstrate that the ResNet50 architecture delivered superior performance, achieving a validation accuracy of approximately 85%. Furthermore, ResNet50 consistently yielded higher precision, recall, and f1-score values across most classes. For comparison, EfficientNetB0 and MobileNetV2 achieved 81% and 79% validation accuracies, respectively. This study concludes that ResNet50 is the optimal architecture for this classification task, and these findings establish a foundation for developing real-world, intelligent traffic monitoring systems.
Image Classification Using MobileNet Based on CNN Architecture for Grape Leaf Disease Detection Nur Sahid, Ahmad; Cahyadi, Deden Ruli
Journal of Intelligent Systems Technology and Informatics Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i1.7

Abstract

Grape cultivation, while economically important, is often challenged by various leaf diseases that can significantly impact yield and quality, underscoring the need for rapid and accurate detection methods. Traditional diagnostic approaches can be time-consuming and require expert knowledge, whereas advanced image classification techniques offer a promising avenue for automated disease identification. This research aimed to develop and rigorously evaluate a Convolutional Neural Network (CNN) model, specifically leveraging the MobileNetV2 architecture, for the precise classification of four common grape leaf diseases: healthy, Black Rot, Esca (also known as Black Measles), and Leaf Blight. The methodology encompassed dataset acquisition and pre-processing, data augmentation to increase training data diversity, and applying transfer learning using pre-trained MobileNetV2 weights, followed by a fine-tuning stage to adapt the model to the specific task. A comprehensive evaluation on 1,805 previously unseen test images demonstrated the model's exceptional performance, achieving an overall accuracy of 99.89%. Ultimately, the proposed approach significantly outperforms previous methods, demonstrating the feasibility of applying lightweight CNN architectures to real-world detection scenarios. The main contribution of this research is showing that high computational efficiency can be achieved without sacrificing accuracy, paving the way for implementation in digital detection systems with limited resources, particularly for mobile devices or edge systems.
Brain Tumor Classification using Convolutional Neural Network with ResNet Architecture Fadilah, Azki; Azkia, Azka
Journal of Intelligent Systems Technology and Informatics Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i1.8

Abstract

Brain tumors are dangerous, sometimes fatal illnesses that require prompt, accurate diagnosis to enhance patient outcomes. Given the intricacy and diversity of tumor characteristics, manual interpretation of brain MRI data is frequently laborious and prone to human error. This research aims to create an automated system for classifying brain tumors by integrating the Convolutional Neural Network (CNN) algorithm with the ResNet architecture. The suggested approach makes use of 7,023 MRI pictures that have been divided into four categories: non-tumor, pituitary tumor, meningioma, and glioma. Image normalization, grayscale conversion, scaling, and data augmentation methods, including rotation and flipping, were among the preprocessing processes used to enhance model performance. The ResNet design was chosen because it effectively trains deeper networks by utilizing residual connections to prevent vanishing gradient problems. Metrics such as F1-score, accuracy, precision, and recall were used to train and assess the system. According to the testing data, the model performed consistently across all classes and attained an outstanding accuracy of 94.14%. These results validate the promise of deep learning methods, especially CNNs with ResNet enhancements, for classification tasks involving medical images. The system created in this work is a promising tool for assisting clinical decision-making, cutting down on diagnostic time, and improving the accuracy of brain tumor identification and classification.
Fruit Image Classification Using CNN With EfficientNet Architecture for Visual Education Nashrulloh, Muhammad Hallaj; Subarkah, Adie
Journal of Intelligent Systems Technology and Informatics Vol 1 No 2 (2025): JISTICS Vol. 1 No. 2 July 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i2.9

Abstract

Advancements in artificial intelligence and computer vision have significantly influenced education, particularly by enhancing visual-based learning for young learners. One promising application is fruit image classification, which helps students recognize and differentiate fruits through visual cues. Traditional methods often struggle with varied backgrounds and lighting conditions, making deep learning models more suitable. This study aims to develop an efficient fruit classification system using the EfficientNetB0 architecture within a convolutional neural network (CNN) framework. This study evaluates the model's effectiveness as a visual learning tool in educational contexts while ensuring computational efficiency. The dataset, sourced from Kaggle, consists of eight fruit categories: apples, bananas, kiwis, lemons, passion fruits, peaches, pineapples, and raspberries. It was split into training and validation sets with an 80:20 ratio using stratified random sampling to ensure balanced class representation during evaluation. Preprocessing steps included resizing images to 224×224 pixels, normalization with EfficientNet preprocessing, and data augmentation techniques to improve generalization. A custom classification head was added, and the EfficientNetB0 base was frozen. Training employed the Adam optimizer, categorical cross-entropy loss, early stopping, and class weighting across 30 epochs. The model achieved a validation accuracy of 99%, with near-perfect precision, recall, and F1-score across all classes. The confusion matrix showed minimal misclassification, indicating strong generalization even among visually similar fruits. In conclusion, the EfficientNetB0-based model demonstrates high accuracy, balance, and computational efficiency. It is ideal for integrating interactive visual learning tools to enhance concept recognition in educational settings, particularly among early learners.
Sentiment Analysis of Indonesian-Language Plantix Application Reviews for Plant Disease Diagnosis Using Naive Bayes Methods Rahmaliyadi, Virzza; Maridjan, Maula Muhammad
Journal of Intelligent Systems Technology and Informatics Vol 1 No 2 (2025): JISTICS Vol. 1 No. 2 July 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i2.12

Abstract

The Plantix app is one of the digital solutions widely utilized by farmers to diagnose plant diseases through image recognition technology and support from the user community. The large amount of Indonesian-language customer feedback on Google's application can be a valuable source of information for assessing the effectiveness and user satisfaction of this application. This study uses naive Bayes algorithms to classify sentiments based on the Plantix application's customer feedback. The dataset was obtained by implementing web scraping techniques with the Google Play scraper library, resulting in more than 354 reviews. Data preprocessing stages include case folding, text cleaning, tokenization, stemming using the Sastrawi library, and text transformation into numerical form using the Term Frequency-Inverse Document Frequency (TF-IDF) method. Sentiment labels are determined based on user star ratings, which are divided into three categories: positive, neutral, and negative. The Multinomial Naive Bayes algorithm performs the classification process and is assessed through the K-fold Cross Validation technique (K=10). The assessment results show that the model achieves the highest accuracy of 75.10% and F1-score of 72.35% with the shuffle sampling method, which falls into the category of fairly good classification. This study demonstrates that naive Bayes methodology is effectively used in sentiment analysis of text-based agricultural application reviews in Bahasa Indonesia.
Detection of Pneumonia Disease on Chest X-ray Images Using Convolutional Neural Network Salsabila, Rosa; Lea Saumi
Journal of Intelligent Systems Technology and Informatics Vol 1 No 3 (2025): JISTICS Vol. 1 No. 3 November 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i3.18

Abstract

Pneumonia is a critical lung infection and a leading cause of morbidity and mortality worldwide. Early and accurate diagnosis is essential to ensure effective treatment and improved patient outcomes. Chest X-ray imaging, as a widely accessible diagnostic tool, presents challenges in manual interpretation due to overlapping anatomical structures and inter-observer variability. To address this, this study investigates the application of Convolutional Neural Networks (CNN) for automated pneumonia detection from chest X-ray images. The dataset used in this research consists of 5,863 labeled grayscale pictures obtained from the Kaggle repository, comprising 4,273 pneumonia and 1,583 normal cases. Preprocessing steps included image resizing, normalization, and class balancing through augmentation. The CNN model was trained using the augmented dataset and evaluated using various performance metrics. The proposed model achieved an overall accuracy of 79% on the test set, with a precision of 0.84, a recall of 0.79, and an F1-score of 0.78. The class-wise analysis revealed strong performance in detecting normal cases (F1-score = 0.82) but lower recall in pneumonia cases (Recall = 0.60), indicating a need for further improvement. In conclusion, CNN-based approaches demonstrate promising potential for aiding pneumonia diagnosis in clinical settings. However, additional work is necessary to enhance model reliability, particularly in detecting complex patterns of pneumonia. Future research may explore ensemble models and attention mechanisms to improve classification performance.
Customer Comment Clustering for Kahf Face Wash at Kahf Official Shop Using K-Means Method Arbiansyah, Gilang; Haq, Faizal
Journal of Intelligent Systems Technology and Informatics Vol 1 No 3 (2025): JISTICS Vol. 1 No. 3 November 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i3.23

Abstract

The advancement of information technology has encouraged people to shop more confidently, including for men's skincare products. Although data indicate that men's interest in skincare remains relatively low, sales of Kahf Face Wash show high figures. In this context, consumer reviews on e-commerce platforms serve as a valuable source of information for understanding customer satisfaction and experience. This study aims to group consumer comments on Kahf Face Wash products from the Kahf Official Shop using the K-Means clustering method. A total of 4,966 consumer comments were collected automatically through web crawling techniques. These comments then underwent several text processing stages, including case folding, cleaning, tokenization, normalization, removal of stop words, and stemming. After the cleaning process, 2,431 comments remained for analysis. The textual data was transformed into numerical representations using the TF-IDF method, and the optimal number of clusters was determined using the Elbow method, which indicated the optimal value at k = 3. The clustering results categorized the comments into three groups: purchase experience (1,506 comments), product effectiveness (474 comments), and delivery and service (451 comments). Visualization was conducted using PCA and bar charts to better illustrate the distribution and proportion of comments in each cluster. Evaluation of the clustering results using inertia and the Davies–Bouldin Index revealed that the model effectively grouped the comments with a reasonably high quality. This study makes a significant contribution by helping companies analyze customer behavior through an unsupervised learning approach. This method enables companies to efficiently extract structured insights from unstructured reviews, which can be utilized to enhance service quality, marketing strategies, and future product development.
Classification of Thyroid Disease Risk Using the XGBoost Method Amelia, Melina; Fitriyani, Dila
Journal of Intelligent Systems Technology and Informatics Vol 1 No 3 (2025): JISTICS Vol. 1 No. 3 November 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i3.26

Abstract

Thyroid disease is one of the essential health threats and requires early detection to enable more effective medical intervention. This study aims to develop a classification model using the XGBoost algorithm to categorize patient clinical data from the Kaggle platform into three levels of thyroid cancer risk: low, moderate, and high. The data processing process follows the stages of the SEMMA (Sample, Explore, Modify, Model, Assess) methodology, with main techniques such as label coding, stratified 5-fold cross-validation, and hyperparameter tuning being applied. Performance evaluation was conducted using accuracy metrics, including F1-score and AUC-ROC. The results show that the model exhibits excellent performance in detecting low-risk cases (AUC = 1.00), but it still faces challenges in classifying moderate and high-risk categories. After adjusting the hyperparameters, the validation accuracy increased to 96.24%, although the final accuracy on the test data remained at 69.85%. These findings suggest that XGBoost is a promising approach for the early assessment of thyroid disease risk, particularly in detecting low-risk cases. However, further model development is needed to enhance generalizability across risk levels and support informed clinical decision-making.
Gender Identification from Facial Images Using Custom Convolutional Neural Network Architecture Amiludin, Ikbal; Putra, Andika Eka Sastya
Journal of Intelligent Systems Technology and Informatics Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v1i1.27

Abstract

Gender classification from facial images has become increasingly important in biometric applications. This study introduces a deep learning approach utilizing a custom convolutional neural network (CNN) model trained on 8,908 labeled facial images obtained from Kaggle, comprising 4,169 female and 4,739 male samples. Each image underwent preprocessing, including grayscale conversion, face alignment, cropping, resizing to 100×100 pixels, and pixel normalization. The CNN architecture consists of three convolutional layers with ReLU activation, max-pooling layers, a flatten layer, and two dense layers, ending with a sigmoid activation function for binary classification. The model was implemented using TensorFlow and trained for 70 epochs on Google Colab with GPU acceleration. Evaluation metrics include classification accuracy, confusion matrix, and area under the curve (AUC) from the ROC curve. The proposed system achieved 90.79% accuracy and 0.97 AUC, indicating robust performance. However, the confusion matrix revealed slightly higher precision for male predictions, suggesting the need for class balance refinement. The method demonstrates strong potential for integration into real-world facial analysis systems, such as identity verification, access control, and intelligent surveillance platforms.

Page 1 of 2 | Total Record : 15

 1   2 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 1 No 3 (2025): JISTICS Vol. 1 No. 3 November 2025 Vol 1 No 2 (2025): JISTICS Vol. 1 No. 2 July 2025 Vol 1 No 1 (2025): JISTICS Vol. 1 No. 1 March 2025