William J. Knottenbelt
Imperial College London
177 Papers
2K Citations
William J. Knottenbelt is an academic researcher from Imperial College London. The author has contributed to research in topics: Computer science & Stochastic Petri net. The author has an hindex of 33, co-authored 165 publications. Previous affiliations of William J. Knottenbelt include University of Edinburgh.
Chat about Author
Papers
The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes
TL;DR: This work presents UK-DALE: an open-access dataset from the UK recording Domestic Appliance-Level Electricity at a sample rate of 16 kHz for the whole-house and at 1/6 Hz for individual appliances, which is the first open access UK dataset at this temporal resolution.
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
TL;DR: In this article, the authors adapt three deep neural network architectures to energy disaggregation: Long Short Term Memory (LSTM), denoising autoencoders and a network which regresses the start time, end time and average power demand of each appliance activation.
781
NILMTK: an open source toolkit for non-intrusive load monitoring
Nipun Batra,John Kelly,Oliver Parson,Haimonti Dutta,William J. Knottenbelt,Alex Rogers,Amarjeet Singh,Mani Srivastava +7 more
- 11 Jun 2014
TL;DR: This work is the first research to compare multiple disaggregation approaches across multiple publicly available data sets, and demonstrates the range of reproducible analyses made possible by the toolkit.
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
John Kelly,William J. Knottenbelt +1 more
- 04 Nov 2015
TL;DR: Three deep neural network architectures are adapted to energy disaggregation and it is found that all three neural nets achieve better F1 scores than either combinatorial optimisation or factorial hidden Markov models and that the neural net algorithms generalise well to an unseen house.
The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes.
TL;DR: UK-DALE as mentioned in this paper is an open-access dataset from the UK recording Domestic Appliance-Level Electricity at a sample rate of 16 kHz for the whole house and at 1/6 kHz for individual appliances.