Recognition of Impulse of Love at First Sight Based On Photoplethysmography Signal

Love at first sight is a well-known and interesting phenomenon, and denotes the strong attraction to a person of the opposite sex when first meeting. As far as we know, there are no studies on the changes in physiological signals between the opposite sexes when this phenomenon occurs. Although priva...

Full description

Bibliographic Details
Main Authors: Huan Lu, Guangjie Yuan, Jin Zhang, Guangyuan Liu
Format: Article
Language:English
Published: MDPI AG 2020-11-01
Series:Sensors
Subjects:
PPG
Online Access:https://www.mdpi.com/1424-8220/20/22/6572
Description
Summary:Love at first sight is a well-known and interesting phenomenon, and denotes the strong attraction to a person of the opposite sex when first meeting. As far as we know, there are no studies on the changes in physiological signals between the opposite sexes when this phenomenon occurs. Although privacy is involved, knowing how attractive a partner is may be beneficial to building a future relationship in an open society where both men and women accept each other. Therefore, this study adopts the photoplethysmography (PPG) signal acquisition method (already applied in wearable devices) to collect signals that are beneficial for utilizing the results of the analysis. In particular, this study proposes a love pulse signal recognition algorithm based on a PPG signal. First, given the high correlation between the impulse signals of love at first sight and those for physical attractiveness, photos of people with different levels of attractiveness are used to induce real emotions. Then, the PPG signal is analyzed in the time, frequency, and nonlinear domains, respectively, in order to extract its physiological characteristics. Finally, we propose the use of a variety of machine learning techniques (support vector machine (SVM), random forest (RF), linear discriminant analysis (LDA), and extreme gradient enhancement (XGBoost)) for identifying the impulsive states of love, with or without feature selection. The results show that the XGBoost classifier has the highest classification accuracy (71.09%) when using the feature selection.
ISSN:1424-8220