Liwei Wang

TL;DR: There is a considerable gap between clinical studies using EHR data and studies using clinical IE, so a more concrete understanding of the gap is gained and potential solutions to bridge this gap are provided.

TL;DR: The qualitative evaluation shows that the word embeddings trained from EHR and MedLit can find more similar medical terms than those trained from GloVe and Google News, and the intrinsic quantitative evaluation verifies that the semantic similarity captured by the wordEmbedded is closer to human experts' judgments on all four tested datasets.

TL;DR: In this article, a clinical text classification paradigm using weak supervision and deep representation was proposed to reduce human efforts of labeled training data creation and feature engineering for applying machine learning to clinical text classi cation.

TL;DR: In this article, an improved high-frequency motor equivalent circuit model is developed to represent the motor highfrequency behavior for the time and frequency-domain analyses, which is verified on an experimental 2.2kW ABB motor drive benchmark system.

TL;DR: In this paper, an alternate five-level four-quadrant cascaded multilevel converter cell configuration was proposed, which compared to the other cell configurations, for dc fault current limitation, will be more compact and avoid the external dc breaker.