Surveillance of respiration, body posture and/or other physical activity are essential in a wide range of early childhood diagnostics and health monitoring. 1,2 Many advanced technologies exist for their tracking in laboratory or intensive care environments 3 ; however, they are challenging to assess in long-term surveillance, especially in out-of-hospital settings. While assessment of respiration rate (RR) would be crucial in situations like early detection of childhood pneumonia, 1,4,5 it has proven to be a challenge even when using human-assisted methods. [6][7][8][9][10] A viable solution for such surveillance should strike a balance between three interests: it should be sufficiently reliable and accurate,