Claim Missing Document
Check
Articles

Found 4 Documents
Search

Ensemble Stacking of Machine Learning Approach for Predicting Corrosion Inhibitor Performance of Pyridazine Compounds Ariyanto, Noval; Azies, Harun Al; Akrom, Muhamad
International Journal of Advances in Data and Information Systems Vol. 5 No. 2 (2024): October 2024 - International Journal of Advances in Data and Information System
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v5i2.1346

Abstract

Corrosion is a major challenge affecting various industrial sectors, leading to increased operational costs and decreased equipment efficiency. The use of organic corrosion inhibitors is one of the promising solutions. This study applies an ensemble algorithm with a stacking method to estimate pyridazine-derived compounds corrosion inhibition efficiency. This study utilized various molecular characteristics of pyridazine compounds as inputs to predict inhibition efficiency values. After evaluating several boosting models, the stacking technique was chosen as it showed the best results. Stacking Model 6, which combines XGB, LGBM, and CatBoost as the base model with Random Forest as the meta-model, produced the most accurate prediction with an RMSE of 0.055. These findings indicate that machine learning approaches can effectively and efficiently predict corrosion inhibitor performance. This method offers a faster and more economical alternative to conventional experimental methods.
Analisis Performa Model Random Forest dan CatBoost dengan Teknik SMOTE dalam Prediksi Risiko Diabetes Irfannandhy, Rony; Handoko, Lekso Budi; Ariyanto, Noval
Jurnal Pendidikan Informatika (EDUMATIC) Vol 8 No 2 (2024): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v8i2.27990

Abstract

Diabetes mellitus (DM) is increasing in prevalence globally and is becoming a serious health problem. Early detection reduces long-term complications. The purpose of our research is to evaluate and compare the effectiveness of Random Forest (RF) and CatBoost models with SMOTE technique in predicting DM risk based on test data processed to produce comparative analysis performance of both models in the form of precission, recall, F1-Score and accuracy. Our research type is quantitative using methods that include EDA, transformation, dividing test and training data, implementation of RF and CatBoost methods with SMOTE and evaluation of model performance. The dataset from the platform (Kaggle) includes 768 individual health data consisting of eight independent variables of pregnancy, glucose, blood pressure, skin thickness, insulin, Body Mass Index (BMI), DM history, age as well as one target (outcome) variable of DM status. The SMOTE analysis technique was applied to balance the class distribution and improve the representation of the minority class, making the prediction model more accurate and stable. The findings of the SMOTE-RF model were 82% accuracy and SMOTE CatBoost 81% accuracy. Based on the feature importances analysis, the main variables affecting DM risk prediction of both models are glucose, BMI and age. Glucose variable is the main DM risk indicator used for prediction to be more efficient. The practical implication of improved machine learning early detection has the potential to support doctors' decision making more accurately to prevent more serious complications in diabetes mellitus.
Twitter Sentiment Classification towards Telecommunication Provider Users in Indonesia Syah Putra, Fernanda Mulya; Rakasiwi, Sindhu; Ariyanto, Noval
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9143

Abstract

Internet services have become essential for communication and information sharing. Nowadays, daily activities are conducted through the internet. This study aims to gain a better understanding of the components that influence user perception and satisfaction using textual, sentiment, and statistical analysis techniques. By applying machine learning algorithms such as Naïve Bayes and Support Vector Machine (SVM), this research analyzes customer perceptions of telecommunication service providers in Indonesia. The dataset consists of 300 tweets obtained from the Kaggle platform. The objective is to identify elements that affect customer satisfaction, particularly those related to network stability and service quality. Data preprocessing is carried out using methods such as case folding, normalization, stemming, and stopword removal to enhance sentiment analysis model performance. The results show that SVM outperforms Naïve Bayes in precision and recall, achieving an accuracy of 90% compared to Naïve Bayes' 87%. This demonstrates SVM's ability to classify positive and negative sentiments more accurately. Common topics found in the analysis include customer satisfaction with network stability and affordable pricing, while dissatisfaction arises from poor connectivity and slow customer service response. These findings provide valuable insights for service providers to improve service quality and enhance customer satisfaction. Real-time sentiment analysis using machine learning has great potential, and this study highlights how telecommunication companies can leverage strategic recommendations to improve service quality and retain customers.
GWRPCA ALGORITHMIC FRAMEWORK: ANALYZING SPATIAL DYNAMICS OF POVERTY IN EAST JAVA PROVINCE Al Azies, Harun; Ariyanto, Noval
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i1.3945

Abstract

This study employs Regression Principal Component Analysis (RPCA) and Geographically Weighted Regression Principal Component Analysis (GWRPCA) algorithms to analyze poverty in East Java Province, using data from Statistics Indonesia (BPS). The research investigates regency/city-level poverty percentages and identifies influential factors such as education, literacy rates, housing conditions, and economic indicators. The results reveal that GWRPCA, with an 85.10% R2 value, outperforms RPCA, highlighting its effectiveness in capturing spatial diversity and providing a nuanced portrayal of poverty characteristics across regencies/cities in East Java. In conclusion, GWRPCA emerges as a powerful algorithmic tool for informing targeted poverty alleviation policies, offering insights into spatial variations. The study suggests future research directions to explore evolving spatial patterns and consider additional variables for a more comprehensive analysis. The findings emphasize the significance of spatial considerations in devising effective, context-specific strategies for each regency/city in East Java