dc.contributor.author | Tekin, C. | en_US |
dc.contributor.author | Schaar, Mihaela van der | en_US |
dc.date.accessioned | 2019-02-13T08:07:10Z | |
dc.date.available | 2019-02-13T08:07:10Z | |
dc.date.issued | 2015-11 | en_US |
dc.identifier.issn | 1057-7149 | |
dc.identifier.uri | http://hdl.handle.net/11693/49385 | |
dc.description.abstract | We propose an image stream mining method in
which images arrive with contexts (metadata) and need to be
processed in real time by the image mining system (IMS), which
needs to make predictions and derive actionable intelligence from
these streams. After extracting the features of the image by
preprocessing, IMS determines online the classifier to use on
the extracted features to make a prediction using the context
of the image. A key challenge associated with stream mining is
that the prediction accuracy of the classifiers is unknown, since
the image source is unknown; thus, these accuracies need to be
learned online. Another key challenge of stream mining is that
learning can only be done by observing the true label, but this
is costly to obtain. To address these challenges, we model the
image stream mining problem as an active, online contextual
experts problem, where the context of the image is used to guide
the classifier selection decision. We develop an active learning
algorithm and show that it achieves regret sublinear in the
number of images that have been observed so far. To further
illustrate and assess the performance of our proposed methods,
we apply them to diagnose breast cancer from the images of
cellular samples obtained from the fine needle aspirate of breast
mass. Our findings show that very high diagnosis accuracy can
be achieved by actively obtaining only a small fraction of true
labels through surgical biopsies. Other applications include video
surveillance and video traffic monitoring. | en_US |
dc.language.iso | English | en_US |
dc.source.title | IEEE Transactions on Image Processing | en_US |
dc.relation.isversionof | https://doi.org/10.1109/TIP.2015.2446936 | en_US |
dc.subject | Image stream mining | en_US |
dc.subject | Active learning | en_US |
dc.subject | Online classification | en_US |
dc.subject | Online learning | en_US |
dc.subject | Contextual experts | en_US |
dc.subject | Breast cancer diagnosis | en_US |
dc.title | Active learning in context-driven stream mining with an application to ımage mining | en_US |
dc.type | Article | en_US |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.citation.spage | 3666 | en_US |
dc.citation.epage | 3679 | en_US |
dc.citation.volumeNumber | 24 | en_US |
dc.citation.issueNumber | 11 | en_US |
dc.identifier.doi | 10.1109/TIP.2015.2446936 | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.identifier.eissn | 1941-0042 | |