Personalized Convolutional Dictionary Learning of Physiological Time Series
This work addresses the need for personalized modeling in physiological signal analysis, such as gait cycles, which is incremental as it builds on existing CDL methods.
The paper tackled the problem of representing physiological time series with both global and local structures by extending Convolutional Dictionary Learning to Personalized CDL, which models local information as a learnable transformation of a global dictionary, and demonstrated its effectiveness on synthetic and real human locomotion data.
Human physiological signals tend to exhibit both global and local structures: the former are shared across a population, while the latter reflect inter-individual variability. For instance, kinetic measurements of the gait cycle during locomotion present common characteristics, although idiosyncrasies may be observed due to biomechanical disposition or pathology. To better represent datasets with local-global structure, this work extends Convolutional Dictionary Learning (CDL), a popular method for learning interpretable representations, or dictionaries, of time-series data. In particular, we propose Personalized CDL (PerCDL), in which a local dictionary models local information as a personalized spatiotemporal transformation of a global dictionary. The transformation is learnable and can combine operations such as time warping and rotation. Formal computational and statistical guarantees for PerCDL are provided and its effectiveness on synthetic and real human locomotion data is demonstrated.