Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition
- Submitting institution
-
University of Sussex
- Unit of assessment
- 12 - Engineering
- Output identifier
- 335131_59271
- Type
- D - Journal article
- DOI
-
10.3390/s16010115
- Title of journal
- Sensors
- Article number
- -
- First page
- 1
- Volume
- 16
- Issue
- 1
- ISSN
- 1424-8220
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2016
- URL
-
http://dx.doi.org/10.3390/s16010115
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "This Google Faculty Research Award-funded paper and associated code is among one of the first showing deep convolutional and LSTM networks used wearable sensor data for human activity recognition. It led to a £168K contract with Huawei for activity recognition on mobile devices and patent PCT/EP2018/085809. It led to contact with ST Microelectronics to explore hardware implementation of deep networks.
This article has been cited as an exemplary approach to activity is the following Apple technical document: https://apple.github.io/turicreate/docs/userguide/activity_classifier/how-it-works.html
This paper has become a baseline for activity recognition in the ML and wearable&mobile computing communities "
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
