Publication Search

This research uses the Support Vector Machine (SVM) algorithm to predict Persebaya Surabaya's ranking in BRI Liga 1. The data used includes goals scored, goals given away, total end-of-season points, and status as champions. The results of the analysis using Orange software show that Persebaya Surabaya does not necessarily become a champion if it has a point value of 42 and an SVM value of 41. To become a champion, Persebaya Surabaya must score 69 points or more in a season and achieve an average of more than 54 goals per season. The suggestion of this research is to have more data so that the results of data processing using Orange software are more optimal and accuracy is more precise.

Chronic Kidney Disease (CKD) is a serious health problem, with significant impact on patients' quality of life and healthcare costs. In an effort to improve early diagnosis, a comparison was made between several Machine Learning algorithms used for analysis of patient clinical data. This clinical data contains the medical history or health records of patients. The Machine Learning algorithms used in this study include K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Logistic Regression. By searching for the best algorithm through the calculation of Accuracy, Precision, and Recall with comparasion when using SMOTE (Synthetic Minority Oversampling) to balancing the class attribute.   

Brain tumors are abnormal cell growths in brain tissue that can be life-threatening. This study aims to classify brain tumors to help early diagnosis. The method used is to extract features from brain MRI images using Local Binary Pattern (LBP) and then classified with Support Vector Machine (SVM). The data used were 2044 brain MRI images consisting of 3 classes namely meningioma, no tumor, and pituitary. The best results were obtained using LBP with a radius of 1 and the number of neighbors 8, while the best SVM model used the RBF kernel with a C value of 50, resulting in 88% accuracy, 86% precision, and 87% recall. It can be concluded that the combination of LBP and SVM methods is effective enough to classify brain tumor types to support early diagnosis.

This study aims to analyze the communication of marine mammals, especially whales and dolphins, through a bioacoustic approach combined with computational science as an effort to support conservation in the Tropical Ocean region. The focus of the location is on the Banda Sea, the Seram Sea, and the tropical Pacific region which are important migration routes for marine mammals. Data were obtained from underwater sound recordings using hydrophones, accompanied by visual observations to validate the behavior and existence of species. The analysis is carried out through several stages, including signal pre-processing with noise filtering and sound segmentation, spectral analysis using Fast Fourier Transform (FFT), as well as the creation of a spectrogram to visualize vocalization patterns. Machine learning algorithms such as Support Vector Machine (SVM) are used to classify interspecies voices, while deep learning approaches are applied to identify more complex communication patterns, including dialect variations. The results showed that whales produced low-frequency vocalizations (20–200 Hz) for long-distance communication, while dolphins used high-frequency clicks and whistles (5–20 kHz) for echolocation and social interaction. The integration of bioacoustics and artificial intelligence improves the accuracy of sound classification by more than 90%. These findings confirm the effectiveness of computational-based non-invasive methods in monitoring the presence and behavior of marine mammals and provide a scientific basis for sustainable conservation.

PeduliLindungi is an application from the Government of Indonesia that was made in response to the COVID-19 pandemic. Since its initial release in 2020, this application has received many updates with the goal of improving its overall performance. One of the basics of updating applications is to process the reviews given by users at the Google Play Store using sentiment analysis. The methods used this time are Naive Bayes Classifier (NBC) and Support Vector Machine (SVM). The sample data used were 300 reviews with positive feedback and 300 reviews with negative feedback, for a total of 600 user reviews. The results of the NBC algorithm calculations produce an accuracy of 76%, a precision of 76%, a recall of 82%, and an f1-score of 79%. As for the SVM algorithm, it produces an accuracy rate of 80%, a precision of 83%, a recall of 80%, and an f1-score of 81%.