The Gaitprint: Identifying Individuals by Their Running Style

Abstract

<jats:p>Recognizing the characteristics of a well-developed running style is a central issue in athletic sub-disciplines. The development of portable micro-electro-mechanical-system (MEMS) sensors within the last decades has made it possible to accurately quantify movements. This paper introduces an analysis method, based on limit-cycle attractors, to identify subjects by their specific running style. The movement data of 30 athletes were collected over 20 min. in three running sessions to create an individual gaitprint. A recognition algorithm was applied to identify each single individual as compared to other participants. The analyses resulted in a detection rate of 99% with a false identification probability of 0.28%, which demonstrates a very sensitive method for the recognition of athletes based solely on their running style. Further, it can be seen that these differentiations can be described as individual modifications of a general running pattern inherent in all participants. These findings open new perspectives for the assessment of running style, motion in general, and a person’s identification, in, for example, the growing e-sports movement.</jats:p>

Transient Effect at the Onset of Human Running

“…Even though the vast majority of the runs in the current study showed a transient effect, there are also participants who either had no initial oscillations or a mixed outcome with one run showing an effect whereas the other had none. This has also been shown in previous studies [ 3 , 12 ]. Vieten and Weich reported, that the starting value of the deflection is very subject-specific and influenced by randomness.…”

“…The functionality of the Attractor app is based on the Attractor Method developed by Vieten and colleagues [ 21 ] and is available online via . Further, a super attractor of each run was calculated to represent each participant’s individual gait-print as a mean attractor of all single minutes of each session [ 3 ]. To detect, quantify, and validate the transient effect of a running performance, three mathematical procedures were considered ( Figure 1 ):…”

“…The starting value of the oscillation is highly dependent on the individual and is further affected by random processes. The average distance between two attractors, defined as , for the same subject, is small, compared to attractor differences between different subjects [ 3 ].…”

“…In general, human motion, even the movements which are repeated many thousand times, e.g., by athletes, cannot be called absolutely consistent and stable [ 1 , 2 ]. No single movement is like any other and they are always characterized by a high degree of individuality [ 3 , 4 ]. Beyond the actual movement, it is also apparent that changes in movement patterns have an influence on the subsequent motion kinematics and thus must be highly controlled and regulated by the body and the brain, respectively.…”

Individuality decoded by running patterns: Movement characteristics that determine the uniqueness of human running

“…The ability to identify individuals based on their movement patterns (gait recognition) has long fascinated society [1]. In biomechanics and biometrics, the mechanisms of human gait have been explored as biometric features and it has been demonstrated repeatedly that human gait is as unique to an individual as is their fingerprint [2][3][4]. Pataky and colleagues [5], for instance, showed that 104 individuals could be differentiated based only on their dynamic plantar pressure patterns with accuracy rates of over 99%.…”