Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
This work addresses the need for adjustable error trade-offs in environmental acoustic sensing, particularly for mosquito detection, but appears incremental as it adapts existing methods to a specific domain.
The paper tackled the problem of lacking flexible control over false positive and false negative rates in environmental acoustic sensing by proposing a cost-sensitive classification paradigm using variational autoencoders within a Neyman-Pearson framework, applied to detect mosquitoes in audio data from the HumBug project.
Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings. While large-scale acoustic data make manual analysis infeasible, they provide a suitable playground for machine learning approaches. Most existing machine learning techniques developed for environmental acoustic sensing do not provide flexible control of the trade-off between the false positive rate and the false negative rate. This paper presents a cost-sensitive classification paradigm, in which the hyper-parameters of classifiers and the structure of variational autoencoders are selected in a principled Neyman-Pearson framework. We examine the performance of the proposed approach using a dataset from the HumBug project which aims to detect the presence of mosquitoes using sound collected by simple embedded devices.