Multi-objective Feature Selection in Remote Health Monitoring Applications

• DOI: 10.48550/arxiv.2401.05538
• Publication Date: 2024-01-01
• Authors: Le Ngu Nguyen; Constantino Álvar...; Manuel Lage Cañellas; Anirban Mukherjee; Nhi Nguyen; Dinesh Babu Jayagopi; Miguel Bordallo L...
• Keywords: Discriminative model; Identification; Activity Recognition; Feature (linguistics); SIGNAL (programming language)

Radio frequency (RF) signals have facilitated the development of non-contact human monitoring tasks, such as vital signs measurement, activity recognition, and user identification. In some specific scenarios, an RF signal analysis framework may prioritize performance one task over that others. response to this requirement, we employ a multi-objective optimization approach inspired by biological principles select discriminative features enhance accuracy breathing patterns recognition while simultaneously impeding identification individual users. This is validated using novel dataset consisting 50 subjects engaged in four distinct patterns. Our findings indicate remarkable result: substantial divergence between As complementary viewpoint, present contrariwise result maximize minimize system's capacity for recognition.