Huiping Cao

TL;DR: It is shown that simple observation-based features capturing shape and statistics of disturbance waveforms work better than some well-known features derived from domain transformations and are shown to be satisfactory and suitable for the intended applications.

TL;DR: A probabilistic feature significance measure is developed and described how to use this for ranking results in the presence of dependencies between the path features and a novel LazyDFA+ algorithm for managing hard feedback is presented.

TL;DR: A new USDA-NIFA Coordinated Agricultural Project designed to fill these knowledge gaps and advance sustainability with a boundary-spanning approach of education, participatory research, and extension, the project is identifying tradeoffs of the three strategies with explicit attention to pericoupling of two adjacent regions and full consideration of the coupled ecological and social systems across those regions.

TL;DR: A novel Cross Attention Stabilized Fully Convolutional Neural Network (CA-SFCN) is proposed to classify multivariate time series data and introduces a temporal attention mechanism to extract long and short-term memories across all time steps.

TL;DR: Four major classifiers are evaluated to classify disturbance events residing within the disturbance data obtained from the Phasor Data Concentrator owned by a local utility to improve security of power system using classification of PMU data.