US 12,242,542 B2
Ordinal time series classification with missing information
Cristian Lumezanu, Princeton Junction, NJ (US); Yuncong Chen, Plainsboro, NJ (US); Takehiko Mizoguchi, West Windsor, NJ (US); Dongjin Song, Princeton, NJ (US); Haifeng Chen, West Windsor, NJ (US); and Jurijs Nazarovs, Madison, WI (US)
Assigned to NEC Corporation, Tokyo (JP)
Filed by NEC Laboratories America, Inc., Princeton, NJ (US)
Filed on Aug. 23, 2021, as Appl. No. 17/408,852.
Claims priority of provisional application 63/075,859, filed on Sep. 9, 2020.
Prior Publication US 2022/0075822 A1, Mar. 10, 2022
Int. Cl. G06F 16/906 (2019.01)
CPC G06F 16/906 (2019.01) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for time series classification of missing labels, comprising:
extracting a feature of an incoming time series segment to be classified during an inference stage;
computing, by a hardware processor using a neural network model trained on training data, rank-based statistics of the feature to attempt to select two candidate labels from the training data that the incoming time series segment most likely belongs to;
classifying the incoming time series segment using k-NN-based classification applied to the training data, responsive to the two candidate labels being present in the training data;
classifying the incoming time series segment by hypothesis testing, responsive to only one of the two candidate labels being present in the training data;
classifying the incoming time series segment into a class with higher values of the rank-based statistics from among a plurality of classes with different values of the rank-based statistics, responsive to none of the two candidate labels being present in the training data; and
correcting a prediction by an applicable one of the classifying steps by majority voting with time windows.