Dynamic noise filtering for multi-class classification of beehive audio data

Dániel Tamás Várkonyi, José Luis Seixas Junior, Tomás Horváth

Abstract: Highlights•A multi-class bee audio classification task with poor state-of-the-art performance.•A noise filtering method improving the performance of bee audio data classification.•Large-scale benchmark data for beehive audio data analytics research.•Comparison of various audio feature extraction and noise filtering approaches.•Highly accurate multi-label bee audio classification with very simple models.