Enhancing Female Representation in Automotive Research: GAN-driven rPPG Signal Synthesis

This paper presents a novel application of Generative Adversarial Networks (GANs) to synthesize remote Photoplethysmography (rPPG) signals, with a focus on enhancing female representation in automotive research datasets. By employing advanced GAN architectures, the study addresses the significant underrepresentation of female physiological data in current automotive safety systems. The synthesized rPPG signals incorporate realistic noise and physiological dynamics to better reflect real-world conditions, thereby improving the authenticity and applicability of the data. This approach not only contributes to reducing bias in automated systems but also supports the development of more inclusive and effective safety technologies tailored to diverse user groups.