Detection of Odor Presence via Deep Neural Networks

TL;DR

This study demonstrates that deep learning models can accurately detect odor presence from olfactory bulb LFP signals in single trials, offering a promising approach for odor detection in various applications.

Contribution

The paper introduces a novel ensemble of convolutional neural networks that effectively decodes odor presence from LFP signals, validating the sufficiency of spectral features and signals from the olfactory bulb alone.

Findings

Achieved 86.6% accuracy in odor detection

Outperformed previous benchmarks significantly

Confirmed the biological relevance of extracted features

Abstract

Odor detection underpins food safety, environmental monitoring, medical diagnostics, and many more fields. The current artificial sensors developed for odor detection struggle with complex mixtures while non-invasive recordings lack reliable single-trial fidelity. To develop a general system for odor detection, in this study we present a preliminary work where we aim to test two hypotheses: (i) that spectral features of local field potentials (LFPs) are sufficient for robust single-trial odor detection and (ii) that signals from the olfactory bulb alone are adequate. To test two hypotheses, we propose an ensemble of complementary one-dimensional convolutional networks (ResCNN and AttentionCNN) that decodes the presence of odor from multichannel olfactory bulb LFPs. Tested on 2,349 trials from seven awake mice, our final ensemble model supports both hypotheses, achieving a mean accuracy of 86.6%, an F1-score of 81.0%, and an AUC of 0.9247, substantially outperforming previous benchmarks. In addition, the t-SNE visualization confirms that our framework captures biologically significant signatures. These findings establish the feasibility of robust single-trial detection of the presence of odor from extracellular LFPs, as well as demonstrate the potential of deep learning models to provide a deeper understanding of olfactory representations.