Show simple item record

dc.contributor.authorFriedman, Lee ( )
dc.date.accessioned2019-09-30T13:50:43Z
dc.date.available2019-09-30T13:50:43Z
dc.date.issued2019-09-12
dc.identifier.citationFriedman, L. (in press). Three errors and two problems in a recent paper: gazeNet: End-to-end eye-movement event detection with deep neural networks (Zemblys, Niehorster, and Holmqvist, 2019). Behavior Research Methods.en_US
dc.identifier.urihttps://digital.library.txstate.edu/handle/10877/8649
dc.description.abstractThis manuscript was accepted for publication in Behavior Research Methods on December 20, 2019. It is now in press. Zemblys et al. [1] reported on a method for the classification of eye-movements ("gazeNet"). I have found 3 errors and two problems with that paper that are explained herein. Error 1: The gazeNet classification method was built assuming that a hand-scored dataset from Lund University was all collected at 500 Hz, but in fact, six of the 34 recording files were actually collected at 200Hz. Of the six datasets that were used as the training set for the gazeNet algorithm, 2 were actually collected at 200Hz. Problem 1 has to do with the fact that even among the 500Hz data, the inter-timestamp intervals varied widely. Problem 2 is that there are many unusual discontinuities in the saccade trajectories from the Lund University dataset that make it a very poor choice for the construction of an automatic classification method. Error 2 The gazeNet algorithm was trained on the Lund dataset, and then compared to other methods, not trained on this dataset, in terms of performance on this dataset. This is an inherently unfair comparison, and yet no where in the gazeNet paper is this unfairness mentioned. Error 3 arises out of the novel event-related agreement analysis employed by the gazeNet authors. Although the authors intended to classify unmatched events as either false positives or false negatives, many are actually being classified as true negatives. True negatives are not errors, and any unmatched event misclassified as a true negative is actually driving kappa higher, whereas unmatched events should be driving kappa lower.en_US
dc.formatText
dc.format.extent11 pages
dc.format.medium2 files (.pdf)
dc.format.medium1 file (.zip)
dc.format.medium1 file (.txt)
dc.language.isoen_USen_US
dc.relationCorrected Eye-movement Event Matching Procedure and Computation of the Event Level Cohen's Kappa https://digital.library.txstate.edu/handle/10877/8650
dc.subjectEye movement classificationen_US
dc.subjectgazeNeten_US
dc.subjectDeep neural networksen_US
dc.titleThree Errors and Two Problems in a Recent Paper: gazeNet: End-To-End Eye-Movement Event Detection with Deep Neural Networks (Zemblys, Niehorster, and Holmqvist, 2019)en_US
txstate.documenttypeArticle
dc.description.versionPreprint Version.
txstate.departmentComputer Science


Download

Thumbnail
Thumbnail
Icon

This item appears in the following Collection(s)

Show simple item record