Bee-mediated pollination greatly increases the size and weight of tomato fruits. Therefore,distinguishing between the local set of bees–those that are efficient pollinators–is essentialto improve the economic returns for farmers. To achieve this, it is important to know theidentity of the visiting bees. Nevertheless, the traditional taxonomic identification of bees isnot an easy task, requiring the participation of experts and the use of specialized equipment.Due to these limitations, the development and implementation of new technologies for theautomatic recognition of bees become relevant. Hence, we aim to verify the capacity ofMachine Learning (ML) algorithms in recognizing the taxonomic identity of visiting beesto tomato flowers based on the characteristics of their buzzing sounds. We compared theperformance of the ML algorithms combined with the Mel Frequency Cepstral Coefficients(MFCC) and with classifications based solely on the fundamental frequency, leading to adirect comparison between the two approaches. In fact, some classifiers powered by theMFCC–especially the SVM–achieved better performance compared to the randomized andsound frequency-based trials. Moreover, the buzzing sounds produced during sonicationwere more relevant for the taxonomic recognition of bee species than analysis based onflight sounds alone. On the other hand, the ML classifiers performed better in recognizingbees genera based on flight sounds. Despite that, the maximum accuracy obtained here(73.39% by SVM) is still low compared to ML standards. Further studies analyzing largerrecording samples, and applying unsupervised learning systems may yield better classifica tion performance. Therefore, ML techniques could be used to automate the taxonomic recognition of flower-visiting bees of the cultivated tomato and other buzz-pollinated crops. Thiswould be an interesting option for farmers and other professionals who have no experiencein bee taxonomy but are interested in improving crop yields by increasing pollination.
展开▼