Pre-processing Blood-Volume-Pulse for In-the-wild Applications

TL;DR

This paper evaluates and improves preprocessing methods for blood-volume-pulse signals in real-world noisy environments, proposing a new approach that enhances feature extraction accuracy for affect recognition applications.

Contribution

It introduces a novel preprocessing method for BVP signals that outperforms standard filtering techniques in noisy, real-world conditions.

Findings

Proposed method improves most time features under noise.

Performance is comparable or better than Butterworth filter when noise is estimated.

Both methods struggle with some features under high noise conditions.

Abstract

Blood-volume-pulse (BVP) is a biosignal commonly used in applications for non-invasive affect recognition and wearable technology. However, its predisposition to noise constitutes limitations for its application in real-life settings. This paper revisits BVP processing and proposes standard practices for feature extraction from empirical observations of BVP. We propose a method for improving the use of features in the presence of noise and compare it to a standard signal processing approach of a 4th order Butterworth bandpass filter with cut-off frequencies of 1 Hz and 8 Hz. Our method achieves better results for most time features as well as for a subset of the frequency features. We find that all but one time feature and around half of the frequency features perform better when the noisy parts are known (best case). When the noisy parts are unknown and estimated using a metric of skewness, the proposed method in general works better or similar to the Butterworth bandpass filter, but both methods also fail for a subset features. Our results can be used to select BVP features that are meaningful under different SNR conditions.