Artificial neural networks for classifying the time series sensor data generated by medical detection dogs

Lucy Withington, David Díaz Pardo de Vera, Claire Guest, Clara Mancini, Paul Piwek

Abstract: Highlights•A novel application of machine learning in the field of Animal-Computer Interaction.•Pressure sensors record dogs’ sniffing pattern to generate time series data.•Neural network time series classifiers applied to detection dogs' scenting signals.•Neural network classifier matches dogs’ true positive rate.•Machine learning models show promise to augment dog response interpretation accuracy.