Agreement between Fitbit and ActiGraph Estimates of Physical Activity in Young Children.

Physical activity (PA) estimates from the Fitbit Flex 2 were compared to those from the ActiGraph GT9X Link in 123 elementary school children. Steps and intensity-specific estimates of PA and 3-month PA change were calculated using two different ActiGraph cut-points (Evenson and Romanzini). Fitbit estimates were 35% higher for steps compared to the ActiGraph. Fitbit and ActiGraph intensity-specific estimates were closest for sedentary and light PA while estimates of moderate and vigorous PA varied substantially depending upon the ActiGraph cut-points used. Spearman correlations between device estimates were higher for steps (rs=.70) than for moderate (rs =.54 to .55) or vigorous (rs =.29 to .48) PA. There was low concordance between devices in assessing PA changes over time. Agreement between Fitbit Flex 2 and ActiGraph estimates may depend upon the cut-points used to classify PA intensity. However, there is fair to good agreement between devices in ranking children's steps and MVPA.

Knowledge-Guided Article Embedding Refinement for Session-Based News Recommendation.

Personalized news recommendation aims to recommend news articles to customers, by exploiting the personal preferences and short-term reading interest of users. A practical challenge in personalized news recommendations is the lack of logged user interactions. Recently, the session-based news recommendation has attracted increasing attention, which tries to recommend the next news article given previous articles in an active session. Current session-based news recommendation methods mainly extract latent embeddings from news articles and user-item interactions. However, many existing methods could not exploit the semantic-level structural information among news articles. And the feature learning process simply relies on the news articles in training data, which may not be sufficient to learn semantically rich embeddings. This brief presents a context-aware graph embedding (CAGE) approach for session-based news recommendation. It employs external knowledge graphs to improve the semantic-level representations of news articles. Moreover, graph neural networks are incorporated to further enhance the article embeddings. In addition, we consider the similarity among sessions and design attention neural networks to model the short-term user preferences. Extensive results on multiple news recommendation benchmark datasets show that CAGE performs better than some competitive baselines in most cases.