Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
From Serial to Parallel: Enhancing Needleman-Wunsch Performance through GPU-Based Computing
No full textThe increasing demand for faster bioinformatics analysis calls for more efficient approaches for sequence alignment. In this study, we demonstrate that a GPU-based implementation of the Needleman-Wunsch algorithm can achieve up to 14.8× speedup compared to its traditional CPU-based serial counterpart, without compromising alignment accuracy. By leveraging the parallel processing capabilities and shared memory of an NVIDIA GeForce RTX 3060 Laptop GPU, we significantly accelerated global sequence alignment tasks. Using clinically relevant genes such as NRAS, BRCA1, BRCA2, and Saccharomyces cerevisiae from NCBI ensures realistic alignment challenges and biological significance. Performance evaluation across a wide range of sequence lengths demonstrates the scalability and efficiency of the parallel approach. More importantly, this study provides a unique contribution by showing that a commodity GPU, such as the NVIDIA GeForce RTX 3060 Laptop, can serve as a practical alternative when high-performance computing clusters are unavailable or prohibitively expensive, thereby offering an accessible and cost-effective pathway to high-throughput bioinformatics workflows
The Impact of Squeeze-and-Excitation Blocks on CNN Models and Transfer Learning for Pneumonia Classification Using Chest X-ray Images
No full textPneumonia is one of the leading causes of death due to respiratory tract infections, especially in children and the elderly. Early detection using chest X-ray images is crucial to accelerate diagnosis and treatment, but manual interpretation is often subjective and error-prone. This study evaluates the effect of Squeeze-and-Excitation (SE) Block integration on the performance of a custom Convolutional Neural Network (CNN) model and three popular transfer learning architectures: MobileNetV2, VGG16, and InceptionV3 in X-ray image-based pneumonia classification. A dataset of 5,856 images, taken from Chest X-ray Images (Pneumonia) on Kaggle, was processed through preprocessing, undersampling, and augmentation. Each model was tested in two configurations: without and with SE Block. Evaluation was performed using accuracy, precision, recall, F1-score, and test loss metrics. The results show that SE Block integration improves the performance of most models. The accuracy of the custom CNN increased from 95.17% to 95.88%, MobileNetV2 from 97.18% to 97.59%, and VGG16 from 96.88% to 97.69%. InceptionV3 also saw an accuracy increase from 94.06% to 94.16%, although accompanied by an increase in test loss. SE Block proved effective in strengthening the model's emphasis on important features through an inter-channel recalibration mechanism, especially on efficient architectures like MobileNetV2 and complex models like VGG16. These findings support the development of a more accurate, efficient, and adaptive deep learning-based pneumonia diagnosis system, especially for implementation in healthcare facilities with limited resources.
 
A Data-Driven Comparison of Linear Mixed Model and Mixed Effects Regression Tree Approaches for Dairy Productivity Analysis
No full textDairy productivity studies often involve hierarchical and longitudinal data structures that violate the assumptions of linear regression. This study compares two modeling approaches, Linear Mixed Model (LMM) and Mixed Effects Regression Tree (MERT), in predicting dairy productivity based on the 2024 National Dairy Productivity Survey data. Predictive performance was evaluated using MSEP, RMSEP, MAD, and MAPE, with MERT consistently outperforming LMM in accuracy and robustness. Permutational Multivariate Analysis of Variance (PERMANOVA) test results reinforced this finding, yielding a pseudo-F value of 224.7 and a p-value of 0.001, indicating statistically significant differences in model performance. Key predictors of MERT model included farm altitude, the previous week’s milk production, and the amounts of concentrate feed given, which are part of significant predictor variables in LMM. This finding underscores MERT’s superiority in modeling complex agricultural datasets while providing interpretable insights through data-driven segmentation. The study advocates policy focus in sustainable milk production as well as the availability of high quality of feed and altitude-based dairy farms location to improve milk productivity. Should these focuses implemented by the industry, combined with the MBG Program, Indonesia would be progressing better towards achievement of SDGs Goal 2 and 3
Correlation Analysis of ISO 25010 Modularity, CK Metrics, and Architecture Smells
No full textOpen-source software projects face increasing challenges in maintaining design quality as they evolve, often resulting in technical debt accumulation and reduced maintainability. This study explores the relationship between software modularity, measured using ISO/IEC 25010 quality attributes, Chidamber and Kemerer (CK) object-oriented metrics, and architectural smells (AS) in Java-based open-source software. Six Java-based open-source projects were strategically selected based on varying complexity levels (ranging from 6-994 classes) and different application domains to ensure comprehensive analysis coverage using DesigniteJava to extract AS, CK metrics, and modularity indicators. Correlation analyses showed that architectural smells such as Cyclic Dependency, Ambiguous Interface, and God Component are strongly correlated with CK metrics like Weighted Methods per Class, Depth of Inheritance Tree, and Number of Children. These CK metrics also exhibited strong positive correlations with Cyclomatic Complexity, indicating that structurally complex components also tend to have more complex control logic. Dense Structure was found to negatively correlate with Coupling of Components Conformance, suggesting its effect on modularity compliance. On the other hand, smells like Feature Concentration and Scattered Functionality showed weak or inconsistent correlations with these metrics. The findings highlight the importance of addressing specific architectural smells to improve modularity and software quality
Interdisciplinary Analysis of Machine Learning Applications: Focus on Intent Classification
No full textGiven the rapid growth of machine learning publications on platforms such as arXiv, there is a need for systematic approaches to understand their objectives and contributions. This study aimed to analyze scientific intentions across domains, identify research trends, and evaluate the impact of external contextual enrichment on automatic intent classification. We perform a cross-domain comparison of research objectives, methodological designs, and application scenarios in machine learning publications, focusing on computer science and biology. We propose IntentBERT-Wiki, an enhanced BERT model enriched with contextual knowledge from Wikipedia, designed for intent classification in scientific documents. Our dataset comprises annotated sentences extracted from arXiv articles, categorized according to established rhetorical role taxonomies. The model’s performance is evaluated using standard classification metrics and compared to a baseline BERT model. Experimental results show that IntentBERT-Wiki achieves F1-scores of 95.9% in computer science and 87.4% in biology, with corresponding accuracies of 96.5% and 91.4%, outperforming the baseline. These findings demonstrate that Wikipedia-based contextual enrichment can significantly improve intent classification accuracy, enhance the organization of academic discourse, and facilitate cross-domain knowledge transfers. This study contributes to the understanding of how machine learning research is framed across disciplines and provides a scalable framework for scientific content analysis
Enhancing Premier League Match Outcome Prediction Using Support Vector Machine with Ensemble Techniques: A Comparative Study on Bagging and Boosting
No full textPredicting football match outcomes is a significant challenge in sports analytics, requiring models that are both accurate and resilient. This study evaluates the effectiveness of ensemble techniques, specifically Bagging and Boosting, in enhancing the performance of Support Vector Machine (SVM) models for predicting match outcomes in the English Premier League. The dataset comprises detailed match statistics from 1,520 matches across multiple seasons, including features such as team performance, player statistics, and match outcomes. Four models were examined: baseline SVM, SVM with Bagging, SVM with Boosting, and a combined SVM + Bagging + Boosting approach. Evaluation metrics include accuracy, recall, precision, F1 score, and ROC-AUC, providing a comprehensive assessment of each model's performance. Experimental results indicate that ensemble methods substantially improve model accuracy and stability, with the SVM + Bagging + Boosting combination achieving perfect scores in accuracy, recall, precision, and F1 score, alongside an ROC-AUC value of 0.88. However, this model's slightly reduced ROC-AUC compared to others and its high computational cost highlight potential risks of overfitting and the need for significant resources. These findings underscore the practical potential of combining Bagging and Boosting with SVM for robust and accurate predictions. Limitations include the dataset's focus on a single league and the high resource requirements for ensemble methods. Future research could expand this approach to other sports and leagues, improve computational efficiency, and explore real-time predictive application
Image Classification of Rice Leaf Diseases with KNN Based Model using Stratified-KCV
No full textRice is a staple food for people in the world, especially Indonesia. The rice harvest decreased in 2023, reducing harvest productivity and causing losses for farmers. Rice cultivation is often affected by diseases that hinder rice harvests. SKCV is a resampling method that performs more accurately because it can ensure that class frequencies are maintained. RGB and VGG16 are image processing methods that extract images into numerics. RGB image extraction is done by taking the average value of the red, green, and blue layers while VGG16 image extraction is done by taking the value of visual pattern features such as edges, textures, and object shapes. In this study, rice leaf diseases were classified using KNN-based models, including KNN, WKNN, CDNN, and ECDNN. This classification was performed to determine which method had better performance using SKCV and comparing the results of RGB and VGG16 image extraction. This classification also produces a comparison of SKCV and KCV results to determine the best resampling performance. The results of the analysis that have been carried out show that the ECDNN method produces the highest accuracy of 81.20% in classifying rice leaf diseases using SKCV with VGG16 extraction followed by CDNN and WKNN each at 68.80%, and KNN at 56.20% while RGB extraction only produces an accuracy of 43.8% using ECDNN and CDNN, 56.20% using WKNN, and 50% using KNN. The results of this rice leaf diseases classification analysis are expected to help farmers in increasing rice production in Indonesia
IoT-Based Smart Infusion Monitoring and Control System Using ESP32
No full textInfusion is a common medical procedure used to treat conditions such as gastric acid and typhoid, where precise fluid administration is critical. This study presents the development of an IoT-based smart infusion monitoring and control system using an ESP32 microcontroller, designed to automatically monitor infusion volume and regulate drip rate in real-time. The system integrates a load cell sensor to measure infusion fluid weight, a photodiode sensor to detect drip rate, and a servo motor to adjust the flow rate adaptively. It features web-based monitoring, buzzer alerts, and an LCD display for local feedback. The system was tested in a clinical simulation with an infusion requirement of 1500 mL per 24 hours and various drip factors (15, 20, and 60 drops/mL). The infusion volume status is automatically categorized into three levels: FULL (>350 mL), HALF (150–350 mL), and WARNING (<150 mL). Based on 10 test scenarios, the system accurately classified volume levels and triggered warnings when volume dropped below 150 mL. For example, in Test-08 to Test-10, volumes of 139.67 mL, 87.34 mL, and 40.53 mL were correctly detected as “WARNING” with buzzer alerts activated. The load cell sensor achieved excellent accuracy, with an error margin between 0.02% and 0.06%, while the system maintained drip-rate stability within a ±5% tolerance range. It also dynamically adjusted the servo angle to correct under- or over-drip conditions. These results confirm that the system delivers accurate, automated, and responsive infusion control, making it suitable for healthcare settings with limited staff to improve safety and efficiency
Enhancing Agile Defect Prediction with Optimized Machine Learning and Feature Selection
No full textIn Agile software development, efficient defect prediction is crucial because of the rapid and iterative nature of the delivery. Conventional methods that rely on source code or commit logs often fail to capture the critical contextual signals necessary for early bug detection. This study proposes a hybrid machine learning framework that leverages enriched contextual features from Jira issue tickets and combines them with optimized feature selection techniques. Various classification models, including Random Forest, XGBoost, CatBoost, SVM, and Transformer, are employed to predict defects. To further enhance model performance, metaheuristic-based feature selection methods such as the Bat Algorithm (BA) and Particle Swarm Optimization (PSO) are applied to reduce dimensionality and improve predictive relevance. Experimental results show that Random Forest with BA optimization achieves the highest performance, with an F1-score of 0.83 and an AUC-ROC of 0.86, outperforming other models. While the Transformer model does not surpass tree-based algorithms in all metrics, it shows high recall and competitive F1-scores, making it suitable for high-sensitivity applications. These findings highlight the importance of integrating optimized machine learning models and feature selection techniques to improve model robustness, reduce computational complexity, and meet the needs of Agile development. This approach supports software teams in prioritizing quality assurance tasks, reducing long-term maintenance costs, and optimizing defect management processes
Sentiment Classification on Indodax Using Term Frequency, FastText, and Neural Attention Models
No full textThe rapid growth of mobile-based investment platforms such as Indodax has triggered a surge in user-generated reviews that reflect public perception and sentiment. This study aimed to develop and evaluate sentiment classification models that can accurately classify Indonesian user reviews on the Indodax app into negative, neutral, and positive sentiments. A dataset of 11,000 reviews was collected via web scraping from the Google Play Store. Reviews were preprocessed, labeled using a lexicon-based unsupervised method, and balanced using oversampling. Two models were built: a Bidirectional LSTM (BiLSTM) with attention mechanism using FastText embeddings, and a Feedforward Neural Network (FFNN) using a hybrid feature vector combining TF-IDF and FastText. The evaluation was performed using accuracy, classification report, confusion matrix, and PCA visualization. The FFNN model outperformed the BiLSTM-Attention model with an accuracy of 97.07% compared to 96.00%. Both models demonstrated strong performance in classifying three sentiment classes, though the FFNN showed better separation in PCA space and higher macro-average metrics. This study demonstrates the effectiveness of combining statistical and semantic feature representations for sentiment classification in Indonesian text. The proposed approach is particularly valuable for low-resource languages and informal user-generated content