CP Decomposition
A tensor decomposition method that represents a tensor as a sum of rank-one tensors, with a rank shared across modes. It is commonly used for tensor dimension reduction and structural analysis.
Timeline (last 90 days)
The core of this research is to construct a low-rank representation based on CP decomposition (CANDECOMP/PARAFAC) to characterize the normal behavior of a process, and to introduce different sparse penalty terms to identify anomalies
CP decomposition retains the structural information across the three dimensions of samples, sensors, and time, enabling simultaneous determination of whether an anomaly has occurred and localization of the sensor and time period where it occurred
All Facts (2)
The core of this research is to construct a low-rank representation based on CP decomposition (CANDECOMP/PARAFAC) to characterize the normal behavior of a process, and to introduce different sparse penalty terms to identify anomalies
50%UnverifiedCP decomposition retains the structural information across the three dimensions of samples, sensors, and time, enabling simultaneous determination of whether an anomaly has occurred and localization of the sensor and time period where it occurred
50%