A coarse-to-fine strategy based on a supervised learning method for non-intrusive load identification.
Deng KaiHuo ZihangYi ShiqiWang PengWang ShuaiZhengmin KongPublished in: BIGCOM (2023)
Keyphrases
- significant improvement
- fully automatic
- detection method
- high accuracy
- experimental evaluation
- synthetic data
- clustering method
- theoretical analysis
- image processing
- optimization method
- segmentation method
- unsupervised learning
- supervised learning
- semi supervised
- computational cost
- dynamic programming
- cost function
- pairwise
- preprocessing
- prior knowledge
- multiscale
- similarity measure
- image segmentation
- load balancing
- classification method
- decision trees
- learning algorithm
- identification rate