Predicting Changes in Affective States using Neural Networks

TL;DR

This paper explores predicting patients' affective state changes using neural networks and physiological signals, achieving high prediction accuracy to aid healthcare without frequent or verbal self-reporting.

Contribution

It introduces a neural network-based approach for predicting affective state changes from physiological data, outperforming traditional linear regression methods.

Findings

Neural networks achieved 91.88% accuracy.

Linear regression achieved 89.10% accuracy.

Neural networks slightly outperform linear regression in prediction accuracy.

Abstract

Knowledge of patients affective state could prove to be crucial for health-care professionals in both diagnosis and treatment, however, this requires patients to report how they feel. In practice the sampling rate of affective states needs to be kept low, in order to ensure that the patients can rest. Furthermore using traditional methods of measuring affective states, is not always possible, e.g. patients can be incapable of verbal communications. In this study we explore the prediction of peoples self-reported affective state by measuring multiple physiological signals. We use different Neural networks (NN) setups and compare with different multiple linear regression (MLR) setups for prediction of changes in affective states. The results showed that NN and MLR predicted the change in affective states with accuracies of 91.88% and 89.10%, respectively.