cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ramdan Satra
Contact Email
Ramdan Satra
Phone
-
Journal Mail Official
ramdan@umi.ac.id
Editorial Address
-
Location
Kota makassar,
Sulawesi selatan
INDONESIA
ILKOM Jurnal Ilmiah
Published by Universitas Muslim Indonesia
ISSN : 20871716     EISSN : 25487779     DOI : -
Core Subject : Science,
Computer Science & IT
ILKOM Jurnal Ilmiah is an Indonesian scientific journal published by the Department of Information Technology, Faculty of Computer Science, Universitas Muslim Indonesia. ILKOM Jurnal Ilmiah covers all aspects of the latest outstanding research and developments in the field of Computer science, including Artificial intelligence, Computer architecture and engineering, Computer performance analysis, Computer graphics and visualization, Computer security and cryptography, Computational science, Computer networks, Concurrent, parallel and distributed systems, Databases, Human-computer interaction, Embedded system, and Software engineering.
Arjuna Subject : -
Articles 617 Documents
 58   59   60   61   62 
Evaluation of Multi-Class Classification Performance Lung Cancer Through K-NN and SVM Approach Saputra Troy, Muh. Indra Endriartono; Jabir, Sitti Rahmah; Anraeni, Siska
ILKOM Jurnal Ilmiah Vol 17, No 1 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i1.2464.27-33

Abstract

Lung cancer is one of the deadliest diseases in the world with a mortality rate of 25% of all cancer-related deaths in 2021. Lung cancer is a lung disease caused by genetic changes in respiratory epithelial cells, resulting in uncontrolled cell proliferation. In an effort to improve diagnosis and treatment, this study proposes an approach for multiclass performance evaluation using K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms based on 2024 data. in this study KNN is implemented conventionally while SVM applies 2 kernel processes, namely Linear and Polynominal. The data used is 1000 rows and uses 24 variables with a ratio of 70% training data and 30% testing data, the data in this study includes important information such as medical history, diagnostic test results, and clinical characteristics of patients. this study aims to determine which algorithm has the best performance by looking at the final results based on accuracy in identifying lung cancer data. Based on the research and discussion of SVM and KNN performance evaluation, the SVM algorithm produces an accuracy of 98.28%, surpassing the accuracy of the KNN algorithm of 97.25%. Therefore, the results show that the SVM algorithm is superior to the KNN algorithm. The KNN and SVM methods were implemented for multi-class classification of lung cancer, allowing identification of various subtypes of lung cancer with optimal accuracy.
Detection of Persistent vs. Non-Persistent Drugs in Pharmacy Using Decision Tree Classification Based on Gini, Entropy, and Log Loss Criteria Mardewi, Mardewi; Aziz, Firman; Usman, Syahrul; Fuadi Syam, Rahmat
ILKOM Jurnal Ilmiah Vol 17, No 2 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i2.2585.186-195

Abstract

This study evaluates the performance of Decision Tree methods in classification, utilizing three different criteria: Entropy, Gini, and Log Loss. The objective is to determine which criterion is most effective in achieving high classification accuracy using prescription data from the UCI repository, comprising 3,424 prescription records with 67 variables. The analysis results show that the Entropy criterion delivers the best performance with an accuracy of 79.1%, followed by the Gini criterion at 78%, and the Log Loss criterion at 77.9%. These findings indicate that the Entropy criterion is superior in reducing uncertainty and capturing the underlying data structure, while both Gini and Log Loss criteria also provide competitive, though slightly lower, results. The main contribution of this research is a comparative evaluation of decision tree criteria using real-world prescription data to support accurate classification of medication adherence, which can be beneficial for developing intelligent pharmacy systems. This research offers valuable insights into the effectiveness of various criteria within the Decision Tree method and can aid in selecting the most appropriate criterion for future classification applications.
A Hybrid BERT–RAG Model for Developing Knowledge-Validated Conversational Systems Anggreani, Desi; Ismawati, Ismawati; Auliyah, A. Inayah; Lukman, Lukman; Rahman, Aedah Abd; Nurmisba, Nurmisba; Akbar, Muh Ilham
ILKOM Jurnal Ilmiah Vol 18, No 1 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i1.3126.30-42

Abstract

The transition of freshmen into the university environment requires adaptive and responsive information support. This study develops a chatbot system based on a hybrid BERT–RAG architecture integrated with the FAISS Index to provide automated consultation services for new students. The novelty of this research lies in the implementation of a faculty-based hierarchical knowledge structure and an adaptive multi-domain context mechanism—an approach not previously found in studies involving BERT–RAG for university onboarding services. This design enables the chatbot to deliver more relevant, personalized, and faculty-specific responses. The dataset was derived from three primary sources of information: the Faculty of Economics and Business (FEB), the Faculty of Teacher Training and Education (FKIP), and the Faculty of Engineering (FT), which were structured into a validated knowledge base in documents.json format. System evaluation was conducted across ten interaction scenarios using performance metrics including BERT Similarity, BLEU Score, ROUGE-1, ROUGE-2, and ROUGE-L. The system achieved excellent results, with average scores of 0.905 (BERT Similarity), 0.844 (BLEU), 0.876 (ROUGE-1), 0.820 (ROUGE-2), and 0.871 (ROUGE-L) and standard deviations below 0.1 across all metrics. Strong metric correlations (0.85–0.99) further indicate consistency between semantic understanding and generated text quality. Furthermore, the system effectively minimizes hallucination through validated knowledge integration and faculty-based reranking strategies. Overall, this research provides a significant contribution to the development of institutionally contextual educational chatbots capable of delivering accurate, natural, and responsive communication to support new student orientation in higher education
An Enhanced Mean Value Theorem with Bisection Technique to Elevate User Focus Metrics in Talent Finder Applications Arifin, M Zainal; Wibawa, Aji Prasetya; Safii, Moh; Noertjahyana, Agustinus; Che Pee, Ahmad Naim
ILKOM Jurnal Ilmiah Vol 17, No 2 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i2.2822.140-149

Abstract

Contemporary digital workplaces face pervasive distractions (e.g., notifications, multitasking), yet talent-assessment systems rarely quantify their impact on attention. To address this gap, we integrate the classical Mean Value Theorem (MVT) with an adaptive bisection algorithm to model user-focus dynamics in talent-matching applications. MVT’s limit-based formulation captures continuous attentional shifts, while the iterative bisection method focus metrics by capturing dynamic attentional shifts through the mean toward optimal focus equilibrium, ensuring temporal continuity and rapid convergence. A controlled experiment involving Universitas Negeri Malang undergraduate students tested the Enhanced Mean Value Theorem–Bisection (EMVT-B) method in four simulated workplace scenarios. Participants selected Focus-oriented options over alternative strengths (Communication, Input, Relator, Adaptability) in approximately 65% of decisions, highlighting moderate yet improvable attentional commitment. Sensitivity analysis indicated that increasing the mean-shift threshold by 0.05 could raise Focus-oriented selections to 72%, emphasizing the method's practical impact. These findings establish EMVT-B as both a diagnostic and prescriptive tool, quantifying attentional stability while providing personalized strategies to enhance user focus. Future research should examine longitudinal applications and broader talent portfolios.
Explainable Boosting Machine for Transparent Risk Assessment in BAZNAS Microfinance Desa Wicaksono, Harjunadi; Riyanto, Agus; Darmawan, Risanto; Hidayat, M. Fahmi; Khumaidi, Ali
ILKOM Jurnal Ilmiah Vol 17, No 3 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i3.3214.312-322

Abstract

Microfinance institutions face substantial challenges in managing financing risk, particularly in assessing the creditworthiness of mustahik when available data are limited. BAZNAS Microfinance Desa (BMD) requires a predictive risk system that is both accurate and transparent to ensure program sustainability while adhering to sharia principles. This study develops an Explainable Boosting Machine (EBM) model using historical data from 736 mustahik across three BMD locations (2019-2024). The methodology integrates comprehensive feature engineering, including the DTI Ratio, Savings Ratio, Financial Stress Indicator, and Dependency Ratio. Model performance was evaluated using ROC-AUC, precision-recall metrics, and confusion matrix analysis, while interpretability was examined through SHAP values and partial dependence plots. The EBM model achieved strong predictive performance, recording an ROC-AUC of 0.853, an accuracy of 80%, a precision of 82%, and a recall of 77%. Global interpretability analysis identified Remaining Balance (18.2%), Business Type (12.5%), and Household Income (11.3%) as the most influential predictors. Feature-engineered variables contributed 42% to the model’s predictive strength, confirming the added value of domain-knowledge-driven feature engineering. Critical risk thresholds were identified at Remaining Balance below IDR 200,000 and DTI Ratio above 0.8. The EBM framework effectively balances predictive accuracy with full interpretability, making it suitable for deployment in microfinance decision-support systems. The model provides actionable insights for risk-based pricing and early warning mechanisms while maintaining the transparency essential in microfinance financing.
Optimization-Based Geospatial Clustering Using Fuzzy Geographically Weighted Clustering and Flower Pollination Algorithm for Stunting Risk Mapping Ngatimin, Ngatimin; Istiawan, Deden; Ustyannie, Windyaning; Riansyah, Rahmat; Sholicah, Ameliatus
ILKOM Jurnal Ilmiah Vol 18, No 1 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i1.3130.151-164

Abstract

Stunting remains a major public health challenge in Indonesia, characterized by significant regional disparities and complex multidimensional determinants. Effective intervention strategies therefore require analytical approaches that are capable of capturing spatial heterogeneity and identifying region-specific vulnerability patterns. This study applies Fuzzy Geographically Weighted Clustering (FGWC) optimized using the Flower Pollination Algorithm (FPA) to map district-level stunting vulnerability and identify priority intervention areas. The analysis covers 514 districts using 21 multidimensional indicators representing health, nutrition, housing conditions, food security, social protection, and demographic characteristics derived from the Central Statistics Agency. The integration of FGWC with FPA enhances clustering performance by incorporating spatial dependence and metaheuristic optimization, enabling the algorithm to produce more stable and geographically sensitive clusters. Cluster validity indices confirm that a four-cluster solution provides the most optimal segmentation of stunting vulnerability. The results reveal distinct regional structures, socioeconomic-driven vulnerability associated with limited asset ownership, high dependence on social assistance and large household size, multidimensional deprivation concentrated primarily in eastern Indonesia, and nutrition-related vulnerability linked to breastfeeding duration and food security. These findings demonstrate that stunting patterns in Indonesia are spatially heterogeneous and influenced by diverse structural factors. The proposed FGWC–FPA framework offers a robust geospatial optimization approach that can support more precise, evidence-based, and region-specific strategies for accelerating stunting reduction.
Tackling Attendance Analysis: Unraveling Employee Patterns using K-means Clustering for Workforce Optimization Nur Khusna, Arfiani; Efendi, Wisdah; Hidayati, Nur Arina
ILKOM Jurnal Ilmiah Vol 17, No 1 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i1.2309.54-63

Abstract

This study aims to apply the K-Means Clustering method using employee attendance data. The background of this research problem is to improve the understanding and management of employee attendance by identifying similar attendance patterns in different groups. Employee attendance impacts their morale, sense of responsibility, discipline, cooperation with supervisors or colleagues, and their level of productivity. The K-means Clustering method divides employees into groups based on their attendance patterns, to create groups with similar attendance characteristics. This research has important benefits in decision-making related to human resource management, scheduling, and employee performance evaluation. The results of the study were measured using the Silhouette Coefficient, with a value of 0.3140272065284342, which shows a moderate level of accuracy in separating groups based on attendance patterns. Furthermore, the study also achieved a 100% truth value, signifying the success of consistent and accurate grouping. The main contribution of this research is the use of the K-Means Clustering method as an effective tool in analyzing the attendance of employees and providing valuable insights into managing employee attendance by understanding existing attendance patterns.
A Hybrid Movie Recommendation System to Address Data Sparsity Using Genre-Based K-Means and Neural Collaborative Filtering Darwis, Herdianti; Syahrir, Firdaus Abrazawaiz; Hayati, Lilis Nur
ILKOM Jurnal Ilmiah Vol 17, No 2 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i2.2868.203-212

Abstract

Recommendation systems play a crucial role in helping users navigate the overwhelming volume of information on digital platforms. However, conventional Collaborative Filtering (CF) methods often suffer from data sparsity, leading to reduced prediction accuracy and limited recommendation diversity. To address this challenge, this study proposes a hybrid recommendation model that integrates K-Means clustering based on genre, release year, and rating statistics into the Neural Collaborative Filtering (NCF) framework. Unlike previous works that rely on a single dimension like genre or demographics for clustering, our model uniquely combines multiple content-based features. Furthermore, we explicitly integrate the cluster labels as additional embedding features within the NCF framework, enabling more nuanced and context-aware representation learning. Using the MovieLens Latest-Small dataset, our hybrid model significantly outperforms the baseline NCF across all metrics, achieving a Mean Absolute Error (MAE) of 0.6097, a Root Mean Square Error (RMSE) of 0.7946, and improvements in Precision@10 (0.6065) and Recall@10 (0.7063). These findings highlight the effectiveness of our novel, content-aware clustering approach in deep learning recommenders, resulting in more accurate, diverse, and contextually relevant movie suggestions.
Enhancing Crack Detection on Levees with Synthetic Data Augmentation via ACGAN and Attention-Boosted Faster R-CNN Saludin, Saludin; Priyadi, Wiwit; Artiani, Gita Puspa; Darmawan, Risanto; Khumaidi, Ali
ILKOM Jurnal Ilmiah Vol 18, No 1 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i1.3206.58-68

Abstract

This study introduces an innovative approach for detecting cracks on levee surfaces by integrating an Auxiliary Classifier Generative Adversarial Network (ACGAN) for data augmentation with a Faster R-CNN model enhanced by an attention mechanism. The ACGAN-based augmentation aims to generate synthetic images that enrich data variability in the original dataset. The attention-optimized Faster R-CNN is designed to improve detection precision, particularly for small objects and fine cracks that are difficult to distinguish from the background. Experimental results demonstrate that the incorporation of ACGAN improves detection performance, increasing both the mean Average Precision (mAP) and Average Recall (AR). The model achieved an mAP of approximately 0.56 at IoU = 0.50 and 0.34 at IoU = 0.75, while the AR (maxDets = 100) reached 0.55, indicating a strong capability in identifying most crack instances. When trained on the combined dataset of original and synthetic images, the Faster R-CNN model reached a precision of 0.92 for the severe crack class, while performance for minor cracks remained lower (precision 0.78). Adjusting the confidence threshold to 0.65 improved detection reliability by reducing noise and retaining high-confidence predictions. Improved performance in detecting severe cracks supports timely maintenance and repair decisions. This study demonstrates the effectiveness of GAN-based data augmentation and attention-enhanced object detection for automated structural health monitoring (SHM) of levee infrastructure
Performance Comparison of Ensemble Learning Models for Brain Tumor Detection on Augmented MRI Datasets Titaley, Gilberth Valentino; Rismayanti, Nurul; Handayani, Anik Nur; Ardiansah, Jevri Tri
ILKOM Jurnal Ilmiah Vol 17, No 2 (2025)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v17i2.2523.86-97

Abstract

Brain tumors are highly fatal diseases, making early detection a critical factor in improving patient survival rates. Magnetic Resonance Imaging (MRI) has become a primary tool in brain tumor diagnosis; however, manual analysis processes are often time-consuming and prone to subjective errors. This study employs a machine learning-based classification model to detect four categories of brain tumors—glioma, meningioma, pituitary, and healthy—with high accuracy. The methods include image segmentation using the U-Net model, which excels in medical image analysis due to its encoder-decoder architecture with skip connections, allowing efficient integration of spatial and contextual information. Features are extracted using HuMoments, known for their invariance to rotation, translation, and scale, ensuring robust spatial pattern representation. Data normalization is conducted using Robust Scaling and L2 Normalization to address outliers and harmonize feature scales, enhancing model performance. The MRI dataset, originally comprising 7,023 images, was augmented to 8,000 images using techniques such as rotation, flipping, and contrast adjustments to improve class balance and minimize overfitting. Three ensemble algorithms—Random Forest, XGBoost, and Stacking—were employed to train the models, with performance evaluation based on accuracy, ROC-AUC, F1-score, and confusion matrix. The results demonstrate that Random Forest achieved the best performance with an accuracy of 72% and an ROC-AUC of 0.91. This study illustrates the potential of machine learning approaches for automated brain tumor diagnosis, with further improvement possible through model optimization and the use of more diverse datasets.

Page 61 of 62 | Total Record : 617

 58   59   60   61   62 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol 18, No 1 (2026) Vol 17, No 3 (2025) Vol 17, No 2 (2025) Vol 17, No 1 (2025) Vol 16, No 3 (2024) Vol 16, No 2 (2024) Vol 16, No 1 (2024) Vol 15, No 3 (2023) Vol 15, No 2 (2023) Vol 15, No 1 (2023) Vol 14, No 3 (2022) Vol 14, No 2 (2022) Vol 14, No 1 (2022) Vol 13, No 3 (2021) Vol 13, No 2 (2021) Vol 13, No 1 (2021) Vol 12, No 3 (2020) Vol 12, No 2 (2020) Vol 12, No 1 (2020) Vol 11, No 3 (2019) Vol 11, No 2 (2019) Vol 11, No 1 (2019) Vol 11, No 1 (2019) Vol 10, No 3 (2018) Vol 10, No 3 (2018) Vol 10, No 2 (2018) Vol 10, No 2 (2018) Vol 10, No 1 (2018) Vol 10, No 1 (2018) Vol 9, No 3 (2017) Vol 9, No 3 (2017) Vol 9, No 2 (2017) Vol 9, No 2 (2017) Vol 9, No 1 (2017) Vol 9, No 1 (2017) Vol 8, No 3 (2016) Vol 8, No 3 (2016) Vol 8, No 2 (2016) Vol 8, No 2 (2016) Vol 8, No 1 (2016) Vol 8, No 1 (2016) More Issue