cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yeni Kustiyahningsih
Contact Email
ykustiyahningsih@trunojoyo.ac.id
Phone
+6282139239387
Journal Mail Official
kursor@trunojoyo.ac.id
Editorial Address
Informatics Department, Engineering Faculty University of Trunojoyo Madura Jl. Raya Telang - Kamal, Bangkalan 69162, Indonesia Tel: 031-3012391, Fax: 031-3012391
Location
Kab. bangkalan,
Jawa timur
INDONESIA
Jurnal Ilmiah Kursor
Published by Universitas Trunojoyo Madura
ISSN : 02160544     EISSN : 23016914     DOI : https://doi.org/10.21107/kursor
Core Subject : Science,
Computer Science & IT Decision Sciences, Operations Research & Management
Jurnal Ilmiah Kursor is published in January 2005 and has been accreditated by the Directorate General of Higher Education in 2010, 2014, 2019, and until now. Jurnal Ilmiah Kursor seeks to publish original scholarly articles related (but are not limited) to: Computer Science. Computational Intelligence. Information Science. Knowledge Management. Software Engineering. Publisher: Informatics Department, Engineering Faculty, University of Trunojoyo Madura
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 157 Documents
 12   13   14   15   16 
Comparison of Feature Extraction in Support Vector Machine (SVM) Based Sentiment Analysis System Rozi, Imam Fahrur; Maulidia, Irma; Hani’ah, Mamluatul; Arianto, Rakhmat; Yunianto, Dika Rizky; Ananta, Ahmadi Yuli
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.417

Abstract

Sentiment analysis plays a crucial role in natural language processing by identifying and categorizing opinions or emotions conveyed in textual data. It is widely applied across diverse fields such as product review analysis, social media monitoring, and market research. To enhance the accuracy and reliability of sentiment classification, various methods and feature extraction techniques have been explored. This study investigates the use of Support Vector Machine (SVM) for sentiment analysis, comparing three feature extraction techniques: Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words (BoW), and Word2Vec. Our findings indicate that SVM performs effectively with all three feature extraction methods, with TF-IDF yielding the highest accuracy at 0.79. Although the BoW method showed competitive results, it slightly trailed TF-IDF in k-fold validation. Word2Vec, however, exhibited the lowest performance, achieving a maximum accuracy of 0.69. A comparative analysis of accuracy, precision, recall, and F1-score highlight the superiority of TF-IDF in delivering consistent and accurate results. Further statistical analysis using ANOVA revealed no significant differences between the models across any of the evaluation metrics. Additionally, the evaluation was conducted under several scenarios, including tests on balanced and imbalanced datasets, varying dataset sizes, and different CCC parameter values for SVM. These scenarios provided deeper insights into the factors influencing the system's performance, reinforcing that TF-IDF combined with SVM remains the most effective approach in this study.
Generative adversarial networks (GANS) for generating face images Indra, Dolly; Hidayat, Muh Wahyu; Umar, Fitriyani
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.422

Abstract

The advancement of artificial intelligence technology, particularly deep learning, presents significant potential in facial image processing. Generative Adversarial Networks (GANs), a type of deep learning model, have demonstrated remarkable capabilities in generating high-quality synthetic images through a competitive training process between a generator, which creates new data, and a discriminator, which evaluates its authenticity. However, the use of public facial datasets such as CelebA and FFHQ faces limitations in representing global demographic diversity and raises privacy concerns. This study aims to generate realistic synthetic facial datasets using the StyleGAN2-ADA architecture, a specialized variant of GAN, with two training approaches: training from scratch on two types of datasets (private and public), each containing 480 images. The public dataset used is FFHQ (Flickr-Faces-HQ), known for its broader facial variation and high-quality images. Evaluation is conducted using the Frechet Inception Distance (FID), a metric that assesses image quality by comparing the feature distributions of real and generated images. Results indicate that training from scratch with the public dataset (FFHQ) using a batch size of 16 and a learning rate of 0.0025 achieves an FID score of 85.67 and performance of 86.46% at Tick 100, whereas the private dataset, under the same conditions, results in an FID score of 98.59 with a performance of 18.54%.. The training from scratch approach with the public dataset proves more effective in generating high-quality synthetic facial images compared to the private dataset. In conclusion, this approach supports the optimal generation of realistic synthetic facial data.
Comparative analysis of random forest and deep learning approaches for automated acute lymphoblastic leukemia detection using morphologicaland textural features Swastika, Windra; Prilianti, Kestrilia Rega; Irawan, Paulus Lucky Tirma; Setiawan, Hendry
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.427

Abstract

Acute Lymphoblastic Leukemia (ALL) is a type of blood cancer that requires early and accurate detection for effective treatment. Current diagnostic approaches face significant challenges including time-consuming manual examination, inter-observervariability, and difficulty in balancing sensitivity with specificity. This study aims to develop and compare two automated ALL detection methodologies to overcome these limitations. We propose: (1) a Random Forest classifier using carefully engineered morphological and textural features, and (2) a Convolutional Neural Network (CNN)architecture for automated feature learning from microscopic blood cell images. Using 10,661 images from the ALL Challenge dataset, we evaluated both approaches on training (70%), validation (15%), and test (15%) sets. Feature importance analysis revealed cell area (10.71%), energy (10.67%), and skewness (10.50%) as the mostsignificant discriminative features. The Random Forest achieved 85% accuracy withnotable sensitivity for ALL detection (93%), while the deep learning approachdemonstrated superior performance with 87% accuracy and better false positive control(27.50% vs. 35.76%). Our comparative analysis shows that while both methodsdemonstrate clinical viability for automated ALL screening, the deep learning approachoffers advantages in reducing false positives while maintaining high detectionsensitivity. This research contributes to the advancement of computer-aideddiagnostic tools that can support pathologists in early ALL detection,potentially reducingdiagnostic time and improving consistency.
Hyperparameter optimization of XGBoost using artificial bee colony for predicting medical complications in hemodialysis patients Laksana Aryananda, Rangga; Trimono; Syaifullah J, Wahyu; Wan Awang, Wan Suryani
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.459

Abstract

Chronic Kidney Disease (CKD) is a serious global health issue, ranking as the 12th leading cause of death in 2019, with a 31.7% increase since 2010. Many CKD patients require hemodialysis, which poses risks of complications such as hypertension, hypotension, and gastrointestinal disorders, increasing mortality. This study predicts hemodialysis complications using XGBoost optimized with the Artificial Bee Colony (ABC) algorithm. The dataset includes numerical and categorical variables such as blood pressure, hemoglobin levels, gender, and complication history. To improve class distribution, the Synthetic Minority Over-sampling Technique is applied. Five test scenarios with different ABC parameter configurations were conducted to optimize XGBoost hyperparameters. Results indicate that balancing the dataset with SMOTE enhances model accuracy. Among the tested scenarios, Test 3, with ABC parameters n_bees set to 30, max_iter set to 30, and limit set to 10, achieved the highest accuracy, increasing from 89% (unbalanced) to 94% (balanced). Although training time increased, the improved performance highlights the potential of the XGBoost-ABC framework for early complication detection. This approach can enhance patient care, reduce mortality risks, and support clinical decision-making for hemodialysis patients.
PCA-counseled k-means and k-medoids with dimension reduction for improved in determining optimal aid clustering Jauhari, Achmad; Suzanti, Ika Oktavia; Anamisa, Devie Rosa; Admojo, Fadhila Tangguh
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.460

Abstract

Assuring effective allocation requires targeted distribution of aid, which makes aid clustering a crucial component. For the purpose of using data-driven segmentation based on important characteristics to determine effective help targeting, accuracy in clustering is essential. The study explores the combination of Principal ComponentAnalysis (PCA), k-means, and k-medoids to enhance aid clusters, with the goal ofincreasing aid distribution accuracy and efficiency. The information gathered consists of 1600 records with 13 attributes. In order to standardized the data having two processes in it, preprocessing is first applied. When used with PCA, it makes measuring variance easier and preserves 80% of the variation by choosing five components. Thenumber of clusters may be determined with the use of PCA, k-medoids, and the k-means approach. Greater PCA-k-means silhouette coefficients, which indicate betterclustering ability, are highlighted by comparative analysis. This analysis shows thatPCA-k-means is an effective technique for creating accurate and unique clusters withina data set's structure.The clustering results using the PCA-k-means algorithm have produced the greatest accuracy in the silhouette score of 0.49 and the DBI score is 0.84.
A Multi-label book genre classification: Comparison of machine learning techniques and problem transformation methods Subroto, Eka Mira Novita; Faisal, Muhammad
Jurnal Ilmiah Kursor Vol. 13 No. 2 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i2.389

Abstract

Books play an essential role in life as a source of knowledge and information. The increasing number of books published makes classification more complex, especially in a multi-label context where a book may belong to more than one genre. Furthermore, automatic classification of book genres is required due to the transition of books to e-book and audiobook formats. This research analyzes the application of machine learning techniques using Support Vector Machine (SVM), Logistic Regression (LR), and Multinomial Naive Bayes (MNB) for multi-label book genre classification by comparing their performance through stemming and unstemming process in text preprocessing with TF-IDF and K-Fold cross-validation (k = 10). In addition, two problem transformation methods, Binary Relevance (BR) and Label Powerset (LP), are evaluated. The results show that SVM combined with stemming outperforms other models across all metrics of accuracy, precision, recall, and F1-score. SVM is effective in handling complex and imbalanced data distributions, resulting in more accurate and consistent predictions. The stemming process positively contributes by reducing word variation and allowing the model to focus on word meanings. Among problem transformation methods, LP yields better results because it can capture relationships between labels more effectively than BR.
Comparative study of unsupervised anomaly detection methods on imbalanced time series data Hanifa, Riza Aulia; Thobirin, Aris; Surono, Sugiyarto
Jurnal Ilmiah Kursor Vol. 13 No. 2 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i2.431

Abstract

Anomaly detection in time series data is essential, especially when dealing with imbalanced datasets such as air quality records. This study addresses the challenge of identifying point anomalies rare and extreme pollution levels within a highly imbalanced dataset. Failing to detect such anomalies may lead to delayed environmental interventions and poor public health responses. To solve this, we propose a comparative analysis of three unsupervised learning methods: K-means clustering, Isolation Forest (IForest), and Autoencoder (AE), including its LSTM variant. These algorithms are applied to monthly air quality data collected in 2023 from 2,110 cities across Asia. The models are evaluated using Area Under the Curve (AUC), Precision, Recall, and F1-score to assess their effectiveness in detecting anomalies. Results indicate that the Autoencoder and Autoencoder LSTM outperform the others with an AUC of 98.23%, followed by K-means (97.78%) and IForest (96.01%). The Autoencoder’s reconstruction capability makes it highly effective for capturing complex temporal patterns. K-means and IForest also show strong results, offering efficient and interpretable solutions for structured data. This research highlights the potential of unsupervised anomaly detection techniques for environmental monitoring and provides practical insights into handling imbalanced time series data.

Page 16 of 16 | Total Record : 157

 12   13   14   15   16 

Filter by Year

2011 2025


Reset
Filter By Issues
All Issue Vol. 13 No. 2 (2025) Vol. 13 No. 1 (2025) Vol. 12 No. 4 (2024) Vol. 12 No. 3 (2024) Vol. 12 No. 2 (2023) Vol 12 No 1 (2023) Vol 11 No 4 (2022) Vol 11 No 3 (2022) Vol 11 No 2 (2021) Vol 11 No 1 (2021) Vol 10 No 4 (2020) Vol 10 No 3 (2020) Vol 10 No 2 (2019) Vol 10 No 1 (2019) Vol 9 No 4 (2018) Vol 9 No 3 (2018) Vol 9 No 2 (2017) Vol 9 No 1 (2017) Vol 8 No 4 (2016) Vol 8 No 3 (2016) Vol 8 No 2 (2015) Vol 8 No 1 (2015) Vol 7 No 4 (2014) Vol 7 No 3 (2014) Vol 7 No 2 (2013) Vol 7 No 1 (2013) Vol 6 No 4 (2012) Vol 6 No 3 (2012) Vol 6 No 2 (2011) Vol 6 No 1 (2011) More Issue