A computational model to support in-network data analysis in federated ecosystems
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96002028
- Type
- D - Journal article
- DOI
-
10.1016/j.future.2017.05.032
- Title of journal
- Future Generation Computer Systems
- Article number
- -
- First page
- 342
- Volume
- 80
- Issue
- -
- ISSN
- 0167-739X
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2017
- URL
-
http://dx.doi.org/10.1016/j.future.2017.05.032
- 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
-
5
- Research group(s)
-
C - Cybersecurity, privacy and human centred computing
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper proposes a mechanism to utilise spare computational capacity in network data centres for analysis while data is in transit. The approach is demonstrated for a smart building use case with real data from the EU SPORTE2. This approach has the potential to deploy machine learning models on edge resources (e.g. TinyML/MLCommons) to support applications requiring data inferencing (e.g., https://doi.org/10.1109/AIVR.2018.00061). The work involves close collaboration with Rutgers University (US), which has continued (e.g. https://doi.org/10.1109/MIC.2020.3039551) and led to a special journal section (https://doi.org/10.1109/TCC.2019.2936075).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -