Learning Machines for Computational Epidemiology
2014 (English)In: Proceedings - 2014 IEEE International Conference on Big Data, Washington DC: IEEE conference proceedings, 2014, 1-5 p.Conference paper (Refereed)
Resting on our experience of computational epidemiologyin practice and of industrial projects on analytics ofcomplex networks, we point to an innovation opportunity forimproving the digital services to epidemiologists for monitoring,modeling, and mitigating the effects of communicable disease.Artificial intelligence and intelligent analytics of syndromicsurveillance data promise new insights to epidemiologists, butthe real value can only be realized if human assessments arepaired with assessments made by machines. Neither massivedata itself, nor careful analytics will necessarily lead to betterinformed decisions. The process producing feedback to humanson decision making informed by machines can be reversed toconsider feedback to machines on decision making informed byhumans, enabling learning machines. We predict and argue forthe fact that the sensemaking that such machines can perform intandem with humans can be of immense value to epidemiologistsin the future.
Place, publisher, year, edition, pages
Washington DC: IEEE conference proceedings, 2014. 1-5 p.
IdentifiersURN: urn:nbn:se:kth:diva-159147DOI: 10.1109/BigData.2014.7004419ScopusID: 2-s2.0-84921755559OAI: oai:DiVA.org:kth-159147DiVA: diva2:782667
2nd IEEE International Conference on Big Data, IEEE Big Data 2014; Washington; United States
QC 201502162015-01-222015-01-222015-02-16Bibliographically approved