Search

Search Results

• Comparison of some Feature Extraction and Classification Methods for Bee Sound Data

  Nguyen Thi Huyen, Nguyen Van Hoang

  Date Received: 25-11-2024 / Date Accepted: 18-06-2025 / Date Published: 31-07-2025

   Abstract PDF (VIETNAMESE)

  In this study, we have tested and evaluated several feature extraction methods of bee sound data. The features were extracted by MFCC, Chroma and Wavelet techniques and important features were selected by Random Forest (RF), Extra trees, and XGBoost method from raw data and then provided to machine learning algorithms such as SVM, Random Forest, XGBoost to solve the bee recognition problem. The experiment results show that using Random Forest and XGBoost models with MFCC features, bee sound recognition is fully possible with the accuracy over 99.9%.

  DOI: https://doi.org/10.31817/tckhnnvn.2025.23.7.06