Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations

Ordonez Morales, Francisco Javier and Roggen, Daniel (2016) Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations. In: 20th International Symposiumon Wearable Computers (ISWC) 2016, 12-16 September 2016, Heidelberg, Germany.

[img] PDF - Accepted Version
Restricted to SRO admin only

Download (1MB)

Abstract

Deep convolutional neural networks are powerful image and signal classifiers. One hypothesis is that kernels in the convolutional layers act as feature extractors, progressively highlighting more domain-specific features in upper layers of the network. Thus lower-level features might be suitable for transfer. We analyse this in wearable activity recognition by reusing kernels learned on a source domain on another target domain. We consider transfer between users, application domains, sensor modalities and sensor locations. We characterise the trade-offs of transferring various convolutional layers along model size, learning speed, recognition performance and training data. Through a novel kernel visualisation technique and comparative evaluations we identify what learned kernels are predominantly sensitive to, amongst sensor characteristics, motion dynamics and on-body placement. We demonstrate a ~17% decrease in training time at equal performance thanks to kernel transfer and we derive recommendations on when transfer is most suitable.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Subjects: Q Science > QA Mathematics > QA0276 Mathematical statistics
Q Science > QA Mathematics > QA0299 Analysis. Including analytical methods connected with physical problems
Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Q Science > QA Mathematics > QA0076 Computer software
T Technology > T Technology (General)
Related URLs:
Depositing User: Daniel Roggen
Date Deposited: 29 Jun 2016 11:57
Last Modified: 17 Nov 2016 11:51
URI: http://sro.sussex.ac.uk/id/eprint/61768

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
Is deep learning useful for wearable activity recognition?G1460GOOGLEUnset