Personalized PPG Normalization based on Subject Heartbeat in Resting State Condition

TL;DR

This paper introduces a personalized PPG normalization method based on individual heartbeat frequency to reduce inter-subject variability, improving stress and cognitive load classification accuracy.

Contribution

A novel normalization technique using resting heartbeat frequency for PPG signals that enhances classification performance across subjects.

Findings

Normalization improves binary classification accuracy for stress detection.

Proposed method outperforms other normalization procedures.

Effective across multiple datasets.

Abstract

Physiological responses are nowadays widely used to recognize the affective state of subjects in real-life scenarios. However, these data are intrinsically subject-dependent, making machine learning techniques for data classification not easily applicable due to inter-subject variability. In this work, the reduction of inter-subject heterogeneity is considered in the case of PhotoPlethysmoGraphy (PPG), which is successfully used to detect stress and evaluate experienced cognitive load. To face the inter-subject heterogeneity, a novel personalized PPG normalization is here proposed. A subject-normalized discrete domain where the PPG signals are properly re-scaled is introduced, considering the subject's heartbeat frequency in resting state conditions. The effectiveness of the proposed normalization is evaluated in comparison with other normalization procedures in a binary classification task, where cognitive load and relaxing state are considered. The results obtained on two different datasets available in the literature confirm that applying the proposed normalization strategy permits to increase classification performance.