Systems and methods for segmenting and correcting time-series data for machine learning model training

Abstract

A device may receive time-series data, may divide the time-series data into sets, and may identify data gaps in each of the sets of time-series data. The device may normalize the data gaps to generate normalized data gaps, may generate images of the normalized data gaps, and may extract features from the images of the normalized data gaps. The device may compute spatial distances based on the features, may transform the spatial distances to vector form spatial distances, and may perform hierarchical and agglomerative clustering on the vector form spatial distances to generate clusters. The device may select a set of the clusters, may perform a data fill method on the set of the clusters to generate a final set of the clusters, and may train the machine learning model, with the final set of the clusters, to generate a trained machine learning model.