Loading...
Loading...

Go to the content (press return)

Unsupervised online clustering and detection algorithms using crowdsourced data for malaria diagnosis

Author
Pagès-Zamora, A.; Cabrera-Bean, Margarita; Diaz, C.
Type of activity
Journal article
Journal
Pattern recognition
Date of publication
2019-02-01
Volume
86
First page
209
Last page
223
DOI
https://doi.org/10.1016/j.patcog.2018.09.001 Open in new window
Repository
http://hdl.handle.net/2117/124243 Open in new window
URL
https://www.sciencedirect.com/science/article/abs/pii/S0031320318303200 Open in new window
Abstract
Crowdsourced data in science might be severely error-prone due to the inexperience of annotators participating in the project. In this work, we present a procedure to detect specific structures in an image given tags provided by multiple annotators and collected through a crowdsourcing methodology. The procedure consists of two stages based on the Expectation–Maximization (EM) algorithm, one for clustering and the other one for detection, and it gracefully combines data coming from annotators ...
Citation
Pagès-Zamora, A., Cabrera, M., Diaz, C. Unsupervised online clustering and detection algorithms using crowdsourced data for malaria diagnosis. "Pattern recognition", 1 Febrer 2019, vol. 86, p. 209-223.
Keywords
Crowdsourcing, MalariaSpot, Online EM algorithm, Unreliable annotators, Unsupervised method
Group of research
SPCOM - Signal Processing and Communications Group

Participants

Attachments