Sensors, Vol. 20, Pages 6559: Recognition of Typical Locomotion Activities Based on the Sensor Data of a Smartphone in Pocket or Hand

Sensors, Vol. 20, Pages 6559: Recognition of Typical Locomotion Activities Based on the Sensor Data of a Smartphone in Pocket or Hand Sensors doi: 10.3390/s20226559 Authors: Ebner Fetzer Bullmann Deinzer Grzegorzek With the ubiquity of smartphones, the interest in indoor localization as a research areagrew. Methods based on radio data are predominant, but due to the susceptibility of these radiosignals to a number of dynamic influences, good localization solutions usually rely on additionalsources of information, which provide relative information about the current location. Part of this roleis often taken by the field of activity recognition, e.g., by estimating whether a pedestrian is currentlytaking the stairs. This work presents different approaches for activity recognition, considering thefour most basic locomotion activities used when moving around inside buildings: standing, walking,ascending stairs, and descending stairs, as well as an additional messing around class for rejections.As main contribution, we introduce a novel approach based on analytical transformations combinedwith artificially constructed sensor channels, and compare that to two approaches adapted fromexisting literature, one based on codebooks, the other using statistical features. Data is acquiredusing accelerometer and gyroscope only. In addition to the most widely adopted use-case of carryingthe smartphone in the trouser pockets, we will equally consider the novel use-case o...
Source: Sensors - Category: Biotechnology Authors: Tags: Article Source Type: research