Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources

Edwin Simpson, Steven Reece, Stephen Roberts

Research output: Contribution to conferenceConference Paper

25 Downloads (Pure)

Abstract

Unstructured data from diverse sources, such as social media and aerial imagery, can provide valuable up-to-date information for intelligent situation assessment. Mining these different information sources could bring major benefits to applications such as situation awareness in disaster zones and mapping the spread of diseases. Such applications depend on classifying the situation across a region of interest, which can be depicted as a spatial “heatmap". Annotating unstructured data using crowdsourcing or automated classifiers produces individual classifications at sparse locations that typically contain many errors. We propose a novel Bayesian approach that models the relevance, error rates and bias of each information source, enabling us to learn a spatial Gaussian Process classifier by aggregating data from multiple sources with varying reliability and relevance. Our method does not require gold-labelled data and can make predictions at any location in an area of interest given only sparse observations. We show empirically that our approach can handle noisy and biased data sources, and that simultaneously inferring reliability and transferring information between neighbouring reports leads to more accurate predictions. We demonstrate our method on two real-world problems from disaster response, showing how our approach reduces the amount of crowdsourced data required and can be used to generate valuable heatmap visualisations from SMS messages and satellite images.
Original languageEnglish
Number of pages16
Publication statusPublished - 22 Sep 2017
EventECML-PKDD 2017 - Skopje, Macedonia
Duration: 18 Sep 201722 Sep 2017

Conference

ConferenceECML-PKDD 2017
CountryMacedonia
CitySkopje
Period18/09/1722/09/17

Fingerprint Dive into the research topics of 'Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources'. Together they form a unique fingerprint.

  • Cite this

    Simpson, E., Reece, S., & Roberts, S. (2017). Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources. Paper presented at ECML-PKDD 2017, Skopje, Macedonia.