Sequence-to-Point Learning with Neural Networks for Non-Intrusive Load Monitoring
- Submitting institution
-
University of Aberdeen
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 171255598
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Thirty-second AAAI conference on artificial intelligence
- First page
- 2604
- Volume
- -
- Issue
- -
- ISSN
- 2374-3468
- Open access status
- Technical exception
- Month of publication
- April
- Year of publication
- 2018
- URL
-
-
- 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
-
4
- Research group(s)
-
-
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a generic model namely sequence-to-point (seq2point) learning for Non-Intrusive Load Monitoring (NILM). This is original and significant because the proposed model opens the door for applying various supervised learning models including deep neural networks, Gaussian Process regression, and other various regression models to NILM. This model is adopted by most of NILM algorithms in the literature using deep learning. In addition, this model has been adapted and deployed in commercial smart energy products; for example, in the EU NILM workshop 2019, the company Fludia presented that seq2point is used to develop their light-weight deep learning model (https://tinyurl.com/y3nhp3jm).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
