IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Systematic Review of High Interaction Honeypots for Microsoft SQL Server
Full text linkThis systematic review aims to dive into high interaction honeypots for Microsoft SQL Server. Topics covered include various honeypot environments (bare-metal, virtual machine, container) and monitoring methods (network-based, VMM-based, honeypot-based) to understand how to effectively monitor encrypted communications. The main focus is to compare different data monitoring techniques for high-interaction honeypots, especially considering the challenges posed by encrypted protocols such as TDS used by Microsoft SQL Server. This research identifies limitations in current research and proposes the use of encrypted MITM proxies as a potential solution. Ultimately, this research highlights the need for further research in this area due to the limited existing literature on high interaction honeypots for Microsoft SQL Server
Recognition of Toraja Carving Motifs Using Texture Features with GLCM
Full text linkIndonesia comprises a diverse array of ethnic groups and cultures. Each ethnic group has unique carving motifs rich in philosophical meaning. Toraja motifs are among the most distinctive in the world. These motifs are often found in traditional houses, textiles, and architectural ornaments. However, people's understanding of the symbolic value of these carvings remains limited, thereby risking cultural erosion. This study aims to recognize Toraja carving motifs using digital image processing, specifically through the extraction of Gray Level Co-occurrence Matrix (GLCM) texture features, which include contrast, correlation, energy, and homogeneity at 0° orientation. The Toraja carving dataset was processed through preprocessing, feature extraction, and thresholding-based classification stages. This study contributes to the combination of GLCM and thresholding that can improve accuracy while providing a computationally efficient solution for traditional motif pattern recognition. Experimental results show that thresholds of 0.002 and 0.004 produce recognition accuracies of 100% and 82%, respectively
Support Vector Machine for Accurate Classification of Diabetes Risk Levels
Full text linkThis research explores the application of Support Vector Machines (SVM) for accurately classifying diabetes risk levels based on a publicly available dataset containing 768 instances and 9 attributes, including glucose levels, BMI, blood pressure, and insulin levels. The model's systematic development process involved data preprocessing, feature selection, and hyperparameter optimization to ensure robust performance. Results indicate an overall accuracy of 76%, with high precision and recall for the non-diabetic risk class, but relatively lower performance for the diabetic risk class, highlighting the challenges posed by class imbalance and overlapping data features. To address these issues, future research should incorporate advanced resampling techniques, refined feature engineering, and alternative machine learning models like Random Forest or XGBoost. This research underscores the potential of SVM as a valuable tool for early diabetes detection, offering healthcare professionals a reliable means to identify at-risk individuals and personalize intervention strategies. By bridging theoretical advancements and practical applications, the research contributes to enhancing predictive analytics in medical diagnostics, paving the way for improved patient outcomes and efficient public health managemen
Breast Cancer Classification Based on Mammogram Images Using CNN Method with NASNet Mobile Model
Full text linkIn Indonesia, the type of cancer that contributes to the highest death rate is breast cancer, so there is a great need for early examination, clinical examination, and screening, which includes mammography. Mammography is currently the most effective method for detecting early-stage breast cancer. This study aims to classify breast cancer cells based on mammogram images. The method used in this research is CNN (Convolutional Neural Network) with the NASNet Mobile model for classifying three classes: normal, benign, and malignant. The CNN method can learn various input attributes powerfully so that CNN can obtain more detailed data characteristics and has better detection capabilities. This research obtained the most optimal model based on the percentage of accuracy, sensitivity, and specificity values of 99.67%, 98.78%, and 99.35%, respectively. This research can be used to help radiologists as considerations in making breast cancer diagnosis decisions
Sentiment Analysis Mobile JKN Reviews Using SMOTE Based LSTM
Full text linkThe JKN Mobile application plays an important role in providing easy and fast access to health services for JKN-KIS users. However, user reviews indicate dissatisfaction with several aspects of the application, such as login issues and OTP codes, which can affect the overall user experience. Another challenge faced is class imbalance in the review dataset, which can affect the performance of sentiment analysis. This study uses Long Short-Term Memory (LSTM) combined with Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Review data was collected from Google Play Store and Kaggle, then preprocessed including lemmatization, tokenization, and padding. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results showed that LSTM with SMOTE achieved 88% accuracy, 90% precision, 88% recall, and 89% F1-score. SMOTE successfully improved performance in the minority class although there was a slight decrease in accuracy compared to the model without SMOTE. Word cloud visualization reveals positive sentiments regarding the ease of use of the application, while negative sentiments indicate areas that need improvement. This study emphasizes the importance of handling imbalanced datasets to produce more accurate sentiment analysis
Enhancing Neural Collaborative Filtering with Metadata for Book Recommender System
Full text linkBook recommender systems often face the challenges of information overload and item cold start due to the dynamics of the evolving book market. This paper proposes Feature Enhanced Neural Collaborative Filtering (FENCF), which is a novel method that combines the interaction between users and items with genre metadata information to address the item cold start problem and improve the accuracy of rating predictions. The uniqueness of FENCF lies in the preprocessing of metadata genres, which is different from typical book recommendation research. Experiments with the Amazon book dataset show the contribution of FENCF, which outperforms NCF by reducing RMSE by 4.04% and MAE by 2.73%. In addition, FENCF is also better able to cope with item cold start, with lower MAE across all testing data scenarios. The advantages of FENCF in improving rating accuracy and overcoming item cold start on complex data are very relevant to the actual condition of book sales in e-commerce, which is dynamic. In real-world applications, FENCF can accurately recommend old and new books according to each user's preference. This not only encourages users to stay with the e-commerce platform in the long run but also has the potential to increase the conversion rate of sales
SMOTE-SVM for Handling Imbalanced Data in Obesity Classification
Full text link Obesity is a significant health issue associated with various chronic diseases, making its early classification critical for effective interventions. This study investigates the performance of Support Vector Machine (SVM) models with Radial Basis Function (RBF) and Linear kernels on imbalanced obesity datasets. To address data imbalance, Synthetic Minority Over-sampling Technique (SMOTE) and Random Undersampling (RUS) were applied. The results reveal that balancing techniques significantly enhance classification performance, with the Linear model achieving the highest accuracy of 96.54% when balanced using SMOTE. However, limitations include reduced recall for minority classes and potential overfitting risks. These findings underscore the importance of balancing techniques in health data classification and offer insights for further optimizing model performance. The study highlights the need for advanced data balancing strategies to improve predictive accuracy and equity across all classes
Multi-Domain Sentiment Analysis on Ibu Kota Nusantara (IKN) Tweets Using CNN-LSTM
Full text linkThe construction of Ibu Kota Nusantara (IKN) is a national project aimed at relocating Indonesia’s capital from Jakarta to East Kalimantan. This project has sparked various public opinions, which are widely expressed through social media platforms such as Twitter. Sentiment analysis of these opinions is crucial for understanding public perception of the IKN project. However, previous sentiment analysis studies have often overlooked domain variations in the analyzed data, such as economy, environment, and politics, each of which has distinct linguistic characteristics. This study aims to develop a multi-domain sentiment analysis model by comparing three main methods: CNN-LSTM, CNN, and LSTM. The multi-domain model is designed to address the differences in characteristics across domains and enhance the model’s ability to capture more complex sentiment patterns. The results indicate that multi-domain models outperform single-domain models, as they improve classification performance by leveraging information from multiple domains. CNN-LSTM proved to be the best model, achieving the most balanced Accuracy and F1-Score across various scenarios. The use of Keyword Embedding also significantly enhances model performance, particularly benefiting LSTM, which initially had the lowest performance
DESICION SUPPORT SYSTEM OF LAND SUITABILITY FOR CORN SEED VARIETIES
Full text linkDecision making in selecting suitable agricultural land is a key factor for the success of corn cultivation. The selection of agricultural land is still largely based on the experience of farmers, which lacks a strong analytical foundation, this can lead to a decrease in production as the evidenced in 2023, the dry corn kernel production decline by 12,5% compared to the previous year. This research develops a Decision Support System (DSS) to analyze land suitability for corn varieties by using the Analytical Hierarchy Process (AHP) method to calculate the priority weights of each evaluation criterion, and the Profile Matching (PM) method to rank agricultural. The research uses data from 22 sub-districts in Blitar Regency as alternatives and 5 types of corn varieties as ideal profiles. The ranking results of this research indicate that the best agricultural land for varieties V1, V2, V3, and V4 is in Sanankulon Sub-district, while for variety V5, it is in Doko Sub-district. The validity test results showed a “Strong” coefficient, and the reliability test yielded a Cronbach's alpha of 0.8019, indicating a "Good" level of consistency
Machine Learning Approaches for Predicting Seasonal Stock Trends
Full text linkThe financial market is vital for economic growth yet it often experiences volatility, particularly in Indonesia’s transportation sector where stock prices are strongly affected by seasonal fluctuations. Conventional forecasting methods often neglect these recurring patterns, lowering predictive accuracy. This study assesses the capability of Machine Learning algorithms to capture seasonality in stock price prediction, using PT Garuda Indonesia (Persero) Tbk (GIAA.JK)’s monthly data from August 2019 to May 2025, retrieved from Yahoo Finance. Four models–Linear Regression, Extreme Gradient Boosting (XGBoost), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM)–were trained and tested, with performance evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Hyperparameter tuning was applied to XGBoost, LSTM, and GRU, while statistical validation employed the Kruskal-Wallis test. Results showed that the tuned GRU outperformed other models, achieving MAE of 5.90, RMSE of 7.33, and MAPE of 9.67%, demonstrating ‘excellent’ accuracy in modelling both short-term and seasonal dynamics. These findings highlight the superiority of GRU in modelling both short-term fluctuations and long-term seasonal dependencies in stock prices. The results contribute practical insights for investors and emphasize the importance of integrating seasonality in predictive models for volatile sector