Activity recognition invariant to sensor orientation with wearable motion sensors
Date
2017Source Title
Sensors (Switzerland)
Print ISSN
1424-8220
Publisher
MDPI AG
Volume
17
Issue
8
Language
English
Type
ArticleItem Usage Stats
264
views
views
166
downloads
downloads
Abstract
Most activity recognition studies that employ wearable sensors assume that the sensors are attached at pre-determined positions and orientations that do not change over time. Since this is not the case in practice, it is of interest to develop wearable systems that operate invariantly to sensor position and orientation. We focus on invariance to sensor orientation and develop two alternative transformations to remove the effect of absolute sensor orientation from the raw sensor data. We test the proposed methodology in activity recognition with four state-of-the-art classifiers using five publicly available datasets containing various types of human activities acquired by different sensor configurations. While the ordinary activity recognition system cannot handle incorrectly oriented sensors, the proposed transformations allow the sensors to be worn at any orientation at a given position on the body, and achieve nearly the same activity recognition performance as the ordinary system for which the sensor units are not rotatable. The proposed techniques can be applied to existing wearable systems without much effort, by simply transforming the time-domain sensor data at the pre-processing stage. © 2017 by the authors. Licensee MDPI, Basel, Switzerland.
Keywords
AccelerometerArtificial neural networks
Bayesian decision making
Human activity recognition
Inertial sensors
K-nearest-neighbor classifier
Machine learning
Magnetometer
Motion sensors
Orientation-invariant sensing
Sensor orientation
Singular value decomposition
Support vector machines
Wearable sensing
Accelerometers
Bayesian networks
Classification (of information)
Decision making
Gyroscopes
Learning systems
Magnetometers
Metadata
Nearest neighbor search
Neural networks
Pattern recognition
Singular value decomposition
Support vector machines
Time domain analysis
Wearable technology
Bayesian decision makings
Human activity recognition
Inertial sensor
K-nearest neighbor classifier
Sensor orientation
Wearable sensing
Wearable sensors
Permalink
http://hdl.handle.net/11693/37003Published Version (Please cite this version)
http://dx.doi.org/10.3390/s17081838Collections
Related items
Showing items related by title, author, creator and subject.
-
Pedestrian dead reckoning employing simultaneous activity recognition cues
Altun, K.; Barshan, B. (Institute of Physics Publishing, 2012-01-11)We consider the human localization problem using body-worn inertial/magnetic sensor units. Inertial sensors are characterized by a drift error caused by the integration of their rate output to obtain position information. ... -
Classifying daily and sports activities invariantly to the positioning of wearable motion sensor units
Barshan, Billur; Yurtman, Aras (IEEE, 2020)We propose techniques that achieve invariance to the positioning of wearable motion sensor units on the body for the recognition of daily and sports activities. Using two sequence sets based on the sensory data allows each ... -
A memory efficient novel deep learning architecture enabling diverse feature extraction on wearable motion sensor data
Koşar, Enes (Bilkent University, 2022-09)Extracting representative features to recognize human activities through the use of wearables is an area of on-going research. We propose a novel hybrid net-work architecture to recognize human activities through the use ...