Prediction of attentional focus from respiration with simple feed-forward and time delay neural networks
- PDF / 1,518,681 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 201 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Prediction of attentional focus from respiration with simple feed-forward and time delay neural networks Michael Christopher Melnychuk1 Paul M. Dockree1
•
Peter R. Murphy1,4 • Ian H. Robertson2 • Joshua H. Balsters3
•
Received: 4 April 2019 / Accepted: 5 March 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Current methods to infer an agent’s state of attentional focus rely on scalp potential recordings and pupil diameter measurements, both of which are unrealistic in many real-world situations, and are also prone to movement and electrical artifacts. Being able to predict attentional performance from a simple and noninvasive measure, such as respiration, could have obvious potential benefit for simplifying measurement and improving task performance in many settings, and could also be employed clinically with attentionally compromised populations for training and rehabilitation. It has been suggested that respiration and attention comprise a neuro-physiologically coupled system, and behavioral data has indicated that attentional performance, including reaction time and reaction time variability (RTV), covary with respiratory dynamics. In the present study, we tested several neural network configurations for the prediction of attentional control state (RTV) from respiratory parameters. We observed significant predictive power derived solely from respiratory input, and conclude that a robust and portable feedback device utilizing soft computation is feasible for this purpose. We suggest specific model and data source improvements to potentially further reduce errors in prediction. Keywords Attention Respiration Neural network Prediction Time delay
1 Introduction Being able to predict attention in a noninvasive way from an individual’s physiological activity in situations where inattention and task fatigue can have dramatic consequences has obvious potential benefit. Previous research has shown that it is possible to predict alertness or attentional state using neural network models applied to electrical scalp potentials (EEG; [8, 9, 12, 24, 26], even from a & Michael Christopher Melnychuk [email protected] 1
Institute of Neuroscience and School of Psychology, Trinity College Dublin, Dublin, Ireland
2
Institute of Neuroscience and Global Brain Health Institute, Trinity College Dublin, Dublin, Ireland
3
Department of Psychology, Royal Holloway University of London, Egham, UK
4
Section Computational Cognitive Neuroscience, Department of Neurophysiology and Pathophysiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
single mastoid electrode [2] but electroencephalographic (EEG) recording equipment is cumbersome and impractical in situations where freedom of movement is required, and the susceptibility of the equipment to physical and electrical artefacts is prohibitive in many contexts. Respiration, by comparison, is relatively straightforward to measure and resilient against movement and elect
Data Loading...
