Publication Search

This research focuses on the application of predictive analytics in digital classrooms to track and predict student performance. The study aims to address the limitations of traditional teacher judgment, which often relies on limited data points and subjective assessments. The research proposes a machine learning-driven approach that utilizes data from Learning Management Systems (LMS), including student engagement, academic performance, and attendance, to predict student success or failure with greater accuracy. Various machine learning techniques, such as Support Vector Machine (SVM) and Random Forest (RF), are applied to develop a predictive model that can identify at-risk students early. The findings show that the model achieves an accuracy rate of over 85%, with key predictors including past academic performance and student engagement. This model outperforms traditional assessment methods by providing real-time, data-driven insights that enable timely interventions. The study concludes that predictive analytics has significant potential to enhance educational outcomes by offering personalized support and improving curriculum design. However, challenges such as data integration, fairness, and privacy concerns must be addressed for broader implementation.

Penelitian ini bertujuan untuk mengimplementasikan metode K-Nearest Neighbors (K-NN) dalam klasifikasi minat calon siswa-siswi di Able Ballet berdasarkan profil mereka. Metode K-NN digunakan karena kemampuannya dalam mengklasifikasikan data dengan tingkat akurasi yang tinggi. Penelitian dilakukan dengan mengumpulkan data profil siswa baru dan menggunakan metode K-NN untuk memprediksi minat mereka terhadap berbagai program yang ditawarkan. Hasil penelitian menunjukkan bahwa metode K-NN dapat mencapai tingkat akurasi sebesar 90% dalam klasifikasi minat siswa. Hal ini menunjukkan bahwa metode ini efektif dalam mendukung pengambilan keputusan untuk penempatan program yang sesuai bagi siswa baru. Penelitian ini juga menyarankan penggunaan dataset yang lebih besar dan eksplorasi metode lain seperti Support Vector Machine (SVM) untuk meningkatkan akurasi model di masa depan.

Penelitian ini bertujuan untuk mengimplementasikan metode K-Nearest Neighbors (K-NN) dalam klasifikasi minat calon siswa-siswi di Able Ballet berdasarkan profil mereka. Metode K-NN digunakan karena kemampuannya dalam mengklasifikasikan data dengan tingkat akurasi yang tinggi. Penelitian dilakukan dengan mengumpulkan data profil siswa baru dan menggunakan metode K-NN untuk memprediksi minat mereka terhadap berbagai program yang ditawarkan. Hasil penelitian menunjukkan bahwa metode K-NN dapat mencapai tingkat akurasi sebesar 90% dalam klasifikasi minat siswa. Hal ini menunjukkan bahwa metode ini efektif dalam mendukung pengambilan keputusan untuk penempatan program yang sesuai bagi siswa baru. Penelitian ini juga menyarankan penggunaan dataset yang lebih besar dan eksplorasi metode lain seperti Support Vector Machine (SVM) untuk meningkatkan akurasi model di masa depan.

The policy for using the MyPertamina application issued does not rule out the possibility of differences of opinion due to changes in the policy. There are many positive, neutral, and negative responses to the MyPertamina application implementation policy. To see the public's reaction to the MyPertamina application implementation policy, it can be seen through various media, including social media. Twitter is a social network that is widely used by people in Indonesia. The number of Twitter users in Indonesia reached 18.45 million in 2022, making Indonesia the fifth largest Twitter user country in the world. Researchers conducted a sentiment analysis of the search results for tweets containing the keyword "MyPertamina" using the support vector machine algorithm. 382 tweet data were obtained and classified using the support vector machine algorithm. Support vector machine is a supervised learning algorithm for data classification. SVM is very fast and effective in solving text data problems. Text data is suitable for classification with the SVM algorithm because the basic nature of text tends to be high-dimensional. Of the 382 data analyzed, the support vector machine classification using the RBF kernel with parameter C=2 gave the highest accuracy value of 80.51%, precision value of 81%, recall value of 81%, and F1 score value of 80%.

This study compares the performance of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) algorithms in detecting and classifying smoking activities. Using an image dataset containing two classes, Smoking and Non-Smoking, this research implements transfer learning using the InceptionResNetV2 model for CNN and the SVM method. Evaluation results show that CNN has higher accuracy compared to SVM in detecting smoking activities. This research contributes to the development of surveillance systems for smoke-free areas in smart cities.

Rohingya in Indonesia has become trending conversation on social media. Sentiment analysis can get public responds. Big data makes the problem time efficiency labeling process, therefore the lexicon dictionary is needed for the labeling process. Data is growing and circulating very rapidly so it takes a fast and efficient time. Although it is fast and makes it easier to solve problems, it is still necessary to question the accuracy produced when using the lexicon labeling. A comparison of the labeling process between the InSet lexicon and the VADER lexicon was conducted to determine the accuracy of the labeling. It was done by combining lexicon with machine learning method of support vector machine and TF-IDF weighting and accuracy result calculated using confusion marix. Data from social media X as many as 9117 lines and labeled with InSet lexicon result 5241 negative sentiments, 1369 positive, and 521 neutral. Then the labeling results with VADER produced 2749 positive, 2523 negative, and 1881 neutral. After labeled, processed SVM and calculated accuracy with results of InSet lexicon accuracy having an average of 85.8% while the VADER SVM lexicon has an average of 82.65%.  

Land classification for oil palm plantations is an important topic in agricultural and plantation development. In this research, the local binary pattern (LBP) method and support vector machine (SVM) classification were used to identify oil palm plantations from aerial photography images. The main challenge in this process is accurately distinguishing oil palm fields and forests that have similar patterns and colors in satellite images. The LBP method is used to extract important texture features from images, while SVM is used to build a classification model based on these features. The test results show that using this method provides an accuracy value of 83.33% in the classification of oil palm land images. The development of oil palm plantations in Indonesia is becoming increasingly important as investment prospects strengthen. This research helps develop image classification technology to support the agricultural industry.

Hijaiyah letters are the alphabet used in Arabic and the Koran. Automatic recognition of hijaiyah letters has many benefits, especially in the fields of education and learning Arabic and the Koran. This research aims to classify hijaiyah letter recognition using image processing techniques and the Support Vector Machine (SVM) algorithm. We collected a dataset of images of 5 hijaiyah letters with a total of 400 images obtained from Google and also Iqro'.  The train:test ratio is 8:2. Experimental results show that the proposed approach can achieve high accuracy in recognizing hijaiyah letters with an accuracy rate of 99.16%.

Diagnosis of a disease is usually carried out in a laboratory test, where this test requires a lot of money and time. As time goes by in the world of health, there is one method that can be used to detect the level of condition in the body by recognizing the patterns that form on the iris of the eye or better known as Iridology. By using digital image processing, the disease diagnosis process using the iridology method can be carried out. The aim of this program is to identify diabetes milletus by processing digital images in the form of iris images using Matlab . The research data used comes from the open source website, namely Github , which consists of diabetic iris image data and normal iris image data. Data is taken in the form of digital images. In this research there are several stages, including pre-processing, feature extraction, and classification. The feature extraction process is based on statistical characteristics (contrast, correlation, energy, homogeneity) from the iris image, then classified using the K-Nearest Neighbors (KNN) algorithm and Support Vector Machine (SVM) as a comparison algorithm. The results obtained from this research show that K-NN has better performance with accuracy values ​​of 84%, sensitivity 72%, and specificity 96%.    

Background: Additive manufacturing (AM) requires reliable and efficient defect detection mechanisms to ensure structural integrity and product quality, yet conventional inspection approaches remain time-consuming and often unsuitable for real-time industrial deployment. Objective: This study aims to develop and experimentally validate an artificial intelligence based vision inspection system capable of accurately detecting surface defects in AM components. Methods: A Convolutional Neural Network (CNN) architecture utilizing pretrained backbones (ResNet and EfficientNet) was implemented with a transfer learning strategy and data augmentation techniques. High-resolution AM surface images representing porosity, cracks, and layer misalignment were used for training and evaluation. Model performance was assessed using Accuracy, Precision, Recall, F1-score, and mean Average Precision (mAP), and comparative benchmarking was conducted against traditional machine learning models such as Support Vector Machine and Random Forest. Results: The proposed CNN-based models significantly outperformed conventional approaches, achieving up to 95.1% Accuracy and 92.8% mAP. The EfficientNet backbone demonstrated superior generalization capability, particularly in balancing Precision and Recall, indicating robust defect detection performance across multiple categories. These findings confirm that AI-driven inspection frameworks provide scalable and reliable quality assurance solutions for advanced manufacturing environments.

The aim of this research is to classify Indonesia's trade balance data using the SVM (Support Vector Machine) method with two features, namely Gross Regional Domestic Product (X1) and Wholesale Price Index (X2). Classification is carried out by comparing two types of kernels, namely polynomial kernels and RBF (Radial Basis Function) kernels. Equality Hyperplaneobtained from the polynomial kernel is: . The Hyperplane equation obtained from the RBF kernel is:  Experimental results show that classification with polynomial kernels provides better performance than RBF kernels. This can be seen in the evaluation results which show that the Polynomial kernel has an average model goodness of 75.93% and for the RBF kernel the average model goodness is 74.07%. Leave One Out cross validation (LOOCV) simulation for training data obtained an average accuracy of 76.67% for the polynomial kernel and 66.67% for the RBF kernel. This shows that in this classification context, kernel polynomials are more effective in separating data classes.

Skin diseases are highly prevalent and transmissible. It has been one of the major health problems that most people face. The diseases are dangerous to the skin and tend to spread over time. A patient can be cured of these skin diseases if they are detected on time and treated early. However, it is difficult to identify these diseases and provide the right medications. This study's research objectives involve developing an ensemble machine learning based model for classifying Erythemato-Squamous Diseases (ESD). The ensemble techniques combine five different classifiers, Naïve Bayes, Support Vector Classifier, Decision Tree, Random Forest, and Gradient Boosting, by merging their predictions and utilizing them as input features for a meta-classifier during training. We tested and validated the ensemble model using the dataset from the University of California, Irvine (UCI) repository to assess its effectiveness. The Individual classifiers achieved different accuracies: Naïve Bayes (85.41%), Support Vector Machine (98.61%), Random Forest (97.91%), Decision Tree (95.13%), Gradient Boosting (95.83%). The stacking method yielded a higher accuracy of 99.30% and a precision of 1.00, recall of 0.96, F1 score of 0.97, and specificity of 1.00 compared to the base models. The study confirms the effectiveness of ensemble learning techniques in classifying ESD.

The rapid growth of data-intensive applications has posed significant challenges for classical machine learning (ML) algorithms, particularly in terms of computational efficiency and scalability. This study explores the role of quantum computing in optimizing machine learning performance through the implementation of Quantum Machine Learning (QML), specifically using the Quantum Support Vector Machine (QSVM) model. The research adopts a Design Science Research approach, involving problem identification, model development, system implementation, and performance evaluation. Both classical Support Vector Machine (SVM) and QSVM models are developed and tested using benchmark classification datasets. The results indicate that QSVM outperforms the classical SVM model across multiple evaluation metrics, including accuracy, precision, recall, and F1-score. Additionally, QSVM demonstrates improved computational efficiency by reducing training time, particularly when handling high-dimensional data. These improvements are attributed to the ability of quantum computing to utilize quantum kernel methods and map data into higher-dimensional feature spaces, enabling better pattern recognition and classification performance.  Despite these promising outcomes, the study also identifies several limitations related to current quantum hardware, such as noise, decoherence, and limited qubit availability, which may affect scalability and practical implementation. Therefore, further research is required to enhance quantum hardware reliability and develop hybrid quantum-classical models. In conclusion, quantum machine learning offers a promising solution to overcome the limitations of classical approaches, providing enhanced performance and efficiency for complex data processing tasks in future intelligent systems.

The rapid growth of digital technologies has significantly increased the complexity and frequency of cyber threats, making network security a critical concern in modern information systems. Traditional security approaches, such as rule-based and signature-based systems, are often limited in detecting sophisticated and unknown attacks. Therefore, this study proposes an Anomaly-Based Intrusion Detection System (AbIDS) utilizing machine learning and deep learning techniques to enhance detection capabilities. The research adopts a Design Science Research approach, involving stages of problem identification, data collection, preprocessing, model development, system implementation, and evaluation. Several models, including Decision Tree (DT), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are implemented and compared. The results indicate that deep learning models, particularly LSTM and CNN, outperform traditional machine learning methods in terms of accuracy, precision, recall, and F1-score, while maintaining a lower false positive rate. Additionally, the integration of incremental learning enables the system to adapt to new attack patterns without requiring complete retraining, improving scalability and real-time performance. Despite the promising results, challenges such as computational complexity and false positives remain. Overall, the proposed IDS model demonstrates strong potential as an effective and adaptive solution for enhancing network security in dynamic environments.

Disease control of chili leaf citra plants is an important aspect in modern agriculture to increase crop yields and reduce losses due to pest attacks on chili leaf citra plants. In this research, identification of chili leaf diseases uses Gray Level Co-Occurrence to obtain image features, and the Support Vector Machine (SVM) method is used to classify the feature extraction results according to leaf disease categories in the test image. Based on the disease class using the test image. .As a classification tool for identifying plant pests in images of chili leaves, the dataset used in this research consists of images of leaves that represent normal conditions and conditions attacked by pests. The pest identification process consists of several stages, including image pre-processing, feature extraction, as well as training and testing. SVM model.

Background: Public opinion analysis has become increasingly important in the digital era, where social media platforms generate large-scale textual data reflecting public perceptions toward environmental policies. Advances in Natural language processing (NLP) and machine learning enable systematic sentiment classification to support data-driven decision-making. Objective: This study aims to evaluate the effectiveness of several sentiment classification models in analyzing Indonesian-language social media data related to environmental policies. Method: The research employed a text mining pipeline including data crawling, preprocessing (case folding, tokenization, stopword removal, and stemming), and vectorization using TF-IDF. Three classification models Logistic Regression, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) were trained and evaluated using accuracy and F1-score metrics. Results: Experimental findings indicate that LSTM achieved the highest performance with 91.7% accuracy and 91.2% F1-score, outperforming SVM (88.5%) and Logistic Regression (84.2%). Sentiment distribution analysis shows that public opinion is dominated by positive sentiment (47.5%), followed by neutral (32.0%) and negative (20.5%). Overall: The results demonstrate that deep learning-based models provide more robust contextual understanding and more reliable sentiment mapping for environmental policy analysis.

Fraudsters increasingly exploit unauthorized credit card information for financial gain, targeting un-suspecting users, especially as financial institutions expand their services to semi-urban and rural areas. This, in turn, has continued to ripple across society, causing huge financial losses and lowering user trust implications for all cardholders. Thus, banks cum financial institutions are today poised to implement fraud detection schemes. Five algorithms were trained with and without the application of the Synthetic Minority Over-sampling Technique (SMOTE) to assess their performance. These algorithms included Random Forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machines (SVM), and Logistic Regression (LR). The methodology was implemented and tested through an API using Flask and Streamlit in Python. Before applying SMOTE, the RF classifier outperformed the others with an accuracy of 0.9802, while the accuracies for LR, KNN, NB, and SVM were 0.9219, 0.9435, 0.9508, and 0.9008, respectively. Conversely, after the application of SMOTE, RF achieved a prediction accuracy of 0.9919, whereas LR, KNN, NB, and SVM attained accuracies of 0.9805, 0.9210, 0.9125, and 0.8145, respectively. These results highlight the effectiveness of combining RF with SMOTE to enhance prediction accuracy in credit card fraud detection.

This research aims to improve the effectiveness of lung cancer classification performance using Support Vector Machines (SVM) with hyperparameter tuning. Using Radial Basis Function (RBF) kernels in SVM helps deal with non-linear problems. At the same time, hyperparameter tuning is done through Random Grid Search to find the best combination of parameters. Where the best parameter settings are C = 10, Gamma = 10, Probability = True. Test results show that the tuned SVM improves accuracy, precision, specificity, and F1 score significantly. However, there was a slight decrease in recall, namely 0.02. Even though recall is one of the most important measuring tools in disease classification, especially in imbalanced datasets, specificity also plays a vital role in avoiding misidentifying negative cases. Without hyperparameter tuning, the specificity results are so poor that considering both becomes very important. Overall, the best performance obtained by the proposed method is 0.99 for accuracy, 1.00 for precision, 0.98 for recall, 0.99 for f1-score, and 1.00 for specificity. This research confirms the potential of tuned SVMs in addressing complex data classification challenges and offers important insights for medical diagnostic applications.

This paper compares various machine learning models in their ability to predict financial trends, with a focus on time-series analysis. We evaluate models such as linear regression, decision trees, support vector machines, and deep learning, measuring their performance based on accuracy, computational cost, and interpretability. Our results reveal that deep learning models offer superior accuracy but are less interpretable, while simpler models, though less accurate, provide better insight into the underlying data. This research provides guidelines for selecting suitable models based on specific financial applications.

The occurrence of scorch during the production of flexible polyurethane is a significant issue that negatively impacts foam products' resilience and generally jeopardizes their integrity. The likelihood of foam product failure can be decreased by optimizing production variables based on machine learning algorithms used to predict the occurrence of scorch. Investigating technology is required because prevention is the best approach to dealing with this problem. Hence, machine learning algorithms were trained to predict the occurrence of scorch using the thermodynamic profile of polyurethane foam, which is made up of recorded production variables. A variety of heuristics algorithms were trained and assessed for how well they performed, namely XGBoost, Decision trees, Random Forest, K-nearest neighbors, Naive Bayes, Support Vector Machines, and Logistic Regression. The XGboost ensemble was found to perform best. It outperformed others with an accuracy of 98.3% (i.e., 0.983), followed by logistic regression, decision tree, random forest, K-nearest neighbors, and naïve Bayes, yielding a training accuracy of 88.1%, 66.7%, 84.2%, 87.5%, and 67.5% respectively. The XGBoost was finally used, yielding 2-distinct cases of non(occurrence) of scorch. Ensemble demonstrates that it is quite capable and is an effective way to predict the occurrence of scorch.