AbstractWe extend Disjunctive Anomaly Detection (DAD) algorithm to handle various data distributions and models of cluster interactions. It enables efficient searching and explanation of multiple disease outbreaks occurring simultaneously. Detected clusters can span multiple values along multiple dimensions, and can impact any subset of dimensions in data. This type of search is known to be exponentially complex, so DAD uses approximations to enable fast processing of large data. We demonstrate DAD's ability to systematically outperform state-of-art alternatives including What's Strange About Recent Events (WSARE) and Large Average Submatrix (LAS) on data of scales and complexities typically encountered in biosurveillance applications.
Authors own copyright of their articles appearing in the Online Journal of Public Health Informatics. Readers may copy articles without permission of the copyright owner(s), as long as the author and OJPHI are acknowledged in the copy and the copy is used for educational, not-for-profit purposes. Share-alike: when posting copies or adaptations of the work, release the work under the same license as the original. For any other use of articles, please contact the copyright owner. The journal/publisher is not responsible for subsequent uses of the work, including uses infringing the above license. It is the author's responsibility to bring an infringement action if so desired by the author.