.png){kind=icon}
.png){kind=icon}
Return
Deep classifier-based clustering of long and incomplete multivariate time series from wastewater treatment plants
.png){kind=icon}
OA
AI
B
F
DOI：10.1016/j.jwpe.2026.110659.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Classical clustering fails on water data due to high regime variability and length. • Novel clustering method uses classifier confusion to measure time series similarity. • Partial convolutions enable robust clustering with up to 80% missing values in our experiments. • Our method scales to time series with 200,000 data points from wastewater data. • Our method outperforms benchmarks under the evaluated settings for the water-related time series data.
Keywords:
Machine learning
Wastewater treatment
Time series clustering
Deep learning
Missing data imputation
Attention mechanism
Journal
IF:
6.7
Papers:
1.0W
Citations:
3.3W
Organization
Cited Papers