English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Many areas of research are characterised by the deluge of large-scalehighly-dimensional time-series data. However, using the data available forprediction and decision making is hampered by the current lag in our ability touncover and quantify true interactions that explain the outcomes.We areinterested in areas such as intensive care medicine, which are characterised byi) continuous monitoring of multivariate variables and non-uniform sampling ofdata streams, ii) the outcomes are generally governed by interactions between asmall set of rare events, iii) these interactions are not necessarily definableby specific values (or value ranges) of a given group of variables, but rather,by the deviations of these values from the normal state recorded over time, iv)the need to explain the predictions made by the model. Here, while numerousdata mining models have been formulated for outcome prediction, they are unableto explain their predictions.  We present a model for uncovering interactions with the highest likelihood ofgenerating the outcomes seen from highly-dimensional time series data.Interactions among variables are represented by a relational graph structure,which relies on qualitative abstractions to overcome non-uniform sampling andto capture the semantics of the interactions corresponding to the changes anddeviations from normality of variables of interest over time. Using theassumption that similar templates of small interactions are responsible for theoutcomes (as prevalent in the medical domains), we reformulate the discoverytask to retrieve the most-likely templates from the data.

Modeling Rare Interactions in Time Series Data Through Qualitative Change: Application to Outcome Prediction in Intensive Care Units