Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal Journal of Soft Computing Exploration Journal of Information System Exploration and Research
Tanga, Yulizchia Malica Pinkan
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Improving car price prediction performance using stacking ensemble learning based on ann and random forest Tanga, Yulizchia Malica Pinkan; Simanjuntak, Robert Panca R.; Rofik, Rofik; Muslim, Much Aziz
Journal of Soft Computing Exploration Vol. 5 No. 3 (2024): September 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v5i3.462

Abstract

Determining the right selling price for a car can be a challenge for car sales companies. The selling price of a car is highly influenced by car characteristics such as brand, type, year of production, fuel type, and mileage. Therefore, the research aims to develop a more accurate model of car price prediction model by using a stacking ensemble technique that combines Random Forest and ANN. Random Forest is effective in handling outliers and reducing the risk of overfitting, while ANN has the advantage of capturing complex nonlinear patterns. The results show that the stacking ensemble model combining ANN and Random Forest can predict car sales prices by achieving an R2 value of 0.97. The results of this study can help distributors in selling cars make the right decisions regarding the sales price of cars. To improve the generalization of the model, future research is recommended to try a combination of different ensemble methods and the use of larger and more diverse datasets.
Machine Learning Techniques for Classifying Indonesian Foods and Drinks by Nutritional Profiles Al Qohar, Bagus; Tanga, Yulizchia Malica Pinkan; Darmawan, Aditya Yoga
Journal of Information System Exploration and Research Vol. 3 No. 1 (2025): January 2025
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v3i1.528

Abstract

Local ingredients and Indonesia's diverse culinary traditions play an important role in shaping people's health and eating habits. Understanding the nutritional profile of Indonesian food is crucial to promoting healthier food choices. This study aims to classify Indonesian food and beverages based on their nutritional content, with a focus on calories, protein, fat, and carbohydrates. To achieve this, a dataset of 1,346 food items was preprocessed using normalization techniques to improve model performance. Each food item was categorized as High Protein, High Fat, or High Carbohydrate based on its dominant macronutrient content. Five machine learning models which are K-Nearest Neighbors, Decision Trees, Support Vector Machines, Random Forest, and Multilayer Perceptron-were used and compared. Among these models, the Support Vector Machine achieved the highest classification accuracy of 99.1%. These findings demonstrate the potential of machine learning in nutrition research, providing a basis for developing data-driven dietary recommendations tailored to individual nutritional needs. This research bridges traditional dietary research with modern computational approaches, offering insights for public health initiatives and personalized nutrition planning.
Grape leaf disease classification using efficientnet feature extraction and catboostclassifier Darmawan, Aditya Yoga; Tanga, Yulizchia Malica Pinkan; Unjung, Jumanto
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.507

Abstract

Grapes are one of the most extensively cultivated crops worldwide due to their significant economic importance. However, the productivity of grape crops is often threatened by diseases caused by bacterial, fungal, or viral infections. Traditionally, the detection of infected grape leaves has been conducted through manual visual inspections, a method that is both time-consuming and prone to biases. Recent studies have leveraged transfer learning models to classify grape leaf diseases with high accuracy. Despite this progress, there is a notable gap in research exploring the integration of transfer learning for feature extraction and machine learning for feature classification in detecting grape leaf diseases. This study introduces a novel approach that combines transfer learning using EfficientNetB0 for feature extraction with a machine learning model, specifically Categorical Boosting (CatBoost), for feature classification. The proposed model demonstrates outstanding performance, achieving an accuracy of 99.56% on the test dataset, surpassing traditional transfer learning methods reported in previous studies.
Enhancing Abusive Language Detection on Twitter Using Stacking Ensemble Learning Utami, Putri; Tanga, Yulizchia Malica Pinkan; Unjung, Jumanto; Muslim, Much Aziz
Journal of Information System Exploration and Research Vol. 3 No. 2 (2025): July 2025
Publisher : shmpublisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v3i2.594

Abstract

Detecting abusive language on Twitter is an important step in reducing the prevalence of negative content and harassment. This study aims to improve the accuracy and effectiveness of abusive language detection on Twitter by addressing the limitations of the single model commonly used previously. The stacking method is employed by combining Term Frequency-Inverse Document Frequency (TF-IDF) as the feature extraction method, along with the Naive Bayes and XGBoost algorithms as classification models. Naive Bayes is known for its simplicity in handling text classification, while XGBoost excels in processing complex data and achieving high accuracy. The combination of these two models is expected to improve performance in detecting coarse language. The research results show that the proposed model outperforms the methods in previous studies, with an accuracy of 91.91% and an AUC of 96.76%. These findings demonstrate the effectiveness of the stacking approach in reducing classification errors in coarse language detection. Further research could explore the use of larger datasets or more complex models to improve detection accuracy.
Co-Authors Al Qohar, Bagus Darmawan, Aditya Yoga Jumanto Unjung Much Aziz Muslim Putri Utami, Putri Rofik Rofik, Rofik Simanjuntak, Robert Panca R.