Research on the Use of Smartphone Technologies in the Field of Interactive Fitness Apps : How can we learn more about a user’s physical condition?

Abstract: Interactive Ątness apps can motivate people to lead an active lifestyle. However, it is not yet fully understood how smartphone data collected during exercise is related to the user's actual physical condition. The aim of this work is to investigate in what way and how accurately fitness-related parameters can be estimated using a smartphone. To achieve this, three separate tests were conducted: The first test examined how acceleration data (external intensity) and % of heart rate reserve (internal intensity) correlate with each other during three different exercises (bodyweight squats, jumping jacks, and standing mountain climbers). Results (n=6) show that regardless of accelerometer position, there is a moderate to strong correlation between internal and external intensity for squats (r=0.656-0.789) and mountain climbers (r=0.592-0.782), and a weak to moderate correlation for jumping jacks (r=0.291-0.587). The second test determined how accurately heart rate can be estimated with a smartphone camera (contactless and contact-based). Heart rate was determined simultaneously with a heart rate monitor and a smartphone. The mean absolute error of the contact-based method (n=120) was 5.42 ± 1.44 beats per minute. The mean absolute error of the contactless method (n=30) was 3.60 ± 0.81. However, the contactless method did not provide reliable readings for heart rates above the resting level. The third test evaluated how accurately a VO2max test, in this case, the 3-minute step-in-place test, can be monitored with a smartphone. The results show that step count could be computed from a video recording with a mean absolute error of 2.69 ± 1.89 steps per minute. The knee height could be distinguished as high or low in 98% of cases (n=4). The results of this work can help developers create highly personalized and meaningful fitness apps.