Locomotion Activity Recognition Using Stacked Denoising Autoencoders | IEEE Journals & Magazine | IEEE Xplore

Locomotion Activity Recognition Using Stacked Denoising Autoencoders

Publisher: IEEE

Abstract:

Locomotion activity recognition (LAR) is important for a number of applications, such as indoor localization, fitness tracking, and aged care. Existing methods usually us...View more

Abstract:

Locomotion activity recognition (LAR) is important for a number of applications, such as indoor localization, fitness tracking, and aged care. Existing methods usually use handcrafted features, which requires expert knowledge and is laborious, and the achieved result might still be suboptimal. To relieve the burden of designing and selecting features, we propose a deep learning method for LAR by using data from multiple sensors available on most smart devices. Experimental results show that the proposed method, which learns useful features automatically, outperforms conventional classifiers that require the hand-engineering of features. We also show that the combination of sensor data from four sensors (accelerometer, gyroscope, magnetometer, and barometer) achieves a higher accuracy than other combinations or individual sensors.
Published in: IEEE Internet of Things Journal ( Volume: 5, Issue: 3, June 2018)
Page(s): 2085 - 2093
Date of Publication: 04 April 2018

ISSN Information:

Publisher: IEEE

Funding Agency:


References

References is not available for this document.