Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing

TL;DR

This study compares deep learning and signal processing methods for detecting respiratory events and measuring respiratory rate in exercising horses using microphone recordings, demonstrating the superiority of deep learning models, especially temporal convolutional networks.

Contribution

First to automatically detect equine respiratory sounds and compute dynamic respiratory rates during exercise using deep learning, outperforming traditional signal processing methods.

Findings

Deep learning models achieved median F1 score of 0.94 in detecting exhalation sounds.

Temporal convolutional networks outperformed LSTM and signal processing in accuracy and error metrics.

Deep learning methods show promise for non-invasive, real-time monitoring of horse respiratory health.

Abstract

Monitoring respiration parameters such as respiratory rate could be beneficial to understand the impact of training on equine health and performance and ultimately improve equine welfare. In this work, we compare deep learning-based methods to an adapted signal processing method to automatically detect cyclic respiratory events and extract the dynamic respiratory rate from microphone recordings during high intensity exercise in Standardbred trotters. Our deep learning models are able to detect exhalation sounds (median F1 score of 0.94) in noisy microphone signals and show promising results on unlabelled signals at lower exercising intensity, where the exhalation sounds are less recognisable. Temporal convolutional networks were better at detecting exhalation events and estimating dynamic respiratory rates (median F1: 0.94, Mean Absolute Error (MAE) $\pm$ Confidence Intervals (CI): 1.44$\pm$1.04 bpm, Limits Of Agreements (LOA): 0.63$\pm$7.06 bpm) than long short-term memory networks (median F1: 0.90, MAE$\pm$CI: 3.11$\pm$1.58 bpm) and signal processing methods (MAE$\pm$CI: 2.36$\pm$1.11 bpm). This work is the first to automatically detect equine respiratory sounds and automatically compute dynamic respiratory rates in exercising horses. In the future, our models will be validated on lower exercising intensity sounds and different microphone placements will be evaluated in order to find the best combination for regular monitoring.