Real-time gait classification for persuasive smartphone apps

Abstract

Persuasive technology is now mobile and context-aware. Intelligent analysis of accelerometer signals in smartphones and other specialized devices has recently been used to classify activity (e.g., distinguishing walking from cycling) to encourage physical activity, sustainable transport, and other social goals. Unfortunately, results vary drastically due to differences in methodology and problem domain. The present report begins by structuring a survey of current work within a new framework, which highlights comparable characteristics between studies; this provided a tool by which we and others can understand the current state-of-the art and guide research towards existing gaps. We then present a new user study, positioned in an identified gap, that pushes limits of current success with a challenging problem: the real-time classification of 15 similar and novel gaits suitable for several persuasive application areas, focused on the growing phenomenon of exercise games. We achieve a mean correct classification rate of 78.1% of all 15 gaits with a minimal amount of personalized training of the classifier for each participant when carried in any of 6 different carrying locations (not known a priori). When narrowed to a subset of four gaits and one location that is known, this improves to means of 92.2% with and 87.2% without personalization. Finally, we group our findings into design guidelines and quantify variation in accuracy when an algorithm is trained for a known location and participant.

One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor

“…In their paper on gait pattern classification, Von Tscharner et al [ 42 ] even conclude that a combination of PCA, SVM and ICA is most reliable dealing with high intra- and inter-subject variability. However, in their survey on mobile gait classification, Schneider et al [ 43 ] make an attempt to settle the disagreement about suitable classification algorithms. In their study, they conclude that random forest is best suited for the classification of gait-related properties.…”

[D71] Periodic Vibrotactile Guidance

“…We will also look into reducing power consumption of our algorithm by reducing sampling and CPU usage when the subject is in low activity mode. Finally, we look forward to deploying RRACE in the real world: we are engaged in employing cadence to measure other useful information about gait such as stride length and type of gait, and exploring deployment in a variety of real applications [143].…”

“…Susceptibility to periodic vibrotactile guidance of human cadence. In Haptics Symposium (HAPTICS), 2014 IEEE, pages [141][142][143][144][145][146]2014 This phase is explained in Chapters 5 and 6.…”

“…Published performance data are a rarity in cadence and gait estimation. Schneider et al elaborate on the challenge of comparing performance of such algorithms for realtime gait classification and accelerometer-based activity recognition[143], which are partly due to the large number of possible parameters and settings, and format of testing. The sheer logistical effort of precise validation may be an even more significant problem: natural walking is best done outdoors, and the technique in question must be compared with one or ideally two additional, independent and highly accurate 'gold standard' methods that are sampled at the same time.…”

Tracking the Evolution of Smartphone Sensing for Monitoring Human Movement

“…Smartphone applications designed to replicate the functionality of a dedicated WAM have the potential to assist subsets of the population with the management of a chronic health condition [ 27 ] or prevent its onset [ 28 , 29 ]. Individuals who suffer from a health condition that affects gross motor function can use smartphone-based monitors to analyse their gait [ 30 , 31 ] or tremor [ 32 ], whilst those who suffer from diabetes or obesity may benefit from an estimate of their energy expenditure [ 33 ].…”