Ensembles of deep LSTM Learners for Activity Recognition using Wearables
- Submitting institution
-
University of Newcastle upon Tyne
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 241474-199833-1292
- Type
- D - Journal article
- DOI
-
10.1145/3090076
- Title of journal
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Article number
- 11
- First page
- -
- Volume
- 1
- Issue
- 2
- ISSN
- 2474-9567
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2017
- URL
-
https://doi.org/10.1145/3090076
- 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
- Yes
- Number of additional authors
-
1
- Research group(s)
-
C - Open Lab
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first work that doesn’t use the traditional “sliding window” approaches (which were limited owing to unknown optimal window size) for wearable-based human activity recognition, and the proposed system can well understand context information and perform real-time inference. The results can substantially influence other fields related to modelling complex behaviours in time-series data. This work led to EU IMI grant award: IDEA-FAST (21M Euro), and AMR grant (43K). It has the 2nd highest citation count in a prestigious ACM IMWUT journal.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -