gazeNe t : End-to-end eye-movement event detection with deep neural networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14210%2F19%3A00124621" target="_blank" >RIV/00216224:14210/19:00124621 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.3758/s13428-018-1133-5#citeas" target="_blank" >https://link.springer.com/article/10.3758/s13428-018-1133-5#citeas</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3758/s13428-018-1133-5" target="_blank" >10.3758/s13428-018-1133-5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

gazeNe t : End-to-end eye-movement event detection with deep neural networks

Popis výsledku v původním jazyce

Existing event detection algorithms for eye-movement data almost exclusively rely on thresholding one or more hand-crafted signal features, each computed from the stream of raw gaze data. Moreover, this thresholding is largely left for the end user. Here we present and develop gazeNet, a new framework for creating event detectors that do not require hand-crafted signal features or signal thresholding. It employs an end-to-end deep learning approach, which takes raw eye-tracking data as input and classifies it into fixations, saccades and post-saccadic oscillations. Our method thereby challenges an established tacit assumption that hand-crafted features are necessary in the design of event detection algorithms. The downside of the deep learning approach is that a large amount of training data is required. We therefore first develop a method to augment hand-coded data, so that we can strongly enlarge the data set used for training, minimizing the time spent on manual coding. Using this extended hand-coded data, we train a neural network that produces eye-movement event classification from raw eye-movement data without requiring any predefined feature extraction or post-processing steps. The resulting classification performance is at the level of expert human coders. Moreover, an evaluation of gazeNet on two other datasets showed that gazeNet generalized to data from different eye trackers and consistently outperformed several other event detection algorithms that we tested.

Název v anglickém jazyce

gazeNe t : End-to-end eye-movement event detection with deep neural networks

Popis výsledku anglicky

Existing event detection algorithms for eye-movement data almost exclusively rely on thresholding one or more hand-crafted signal features, each computed from the stream of raw gaze data. Moreover, this thresholding is largely left for the end user. Here we present and develop gazeNet, a new framework for creating event detectors that do not require hand-crafted signal features or signal thresholding. It employs an end-to-end deep learning approach, which takes raw eye-tracking data as input and classifies it into fixations, saccades and post-saccadic oscillations. Our method thereby challenges an established tacit assumption that hand-crafted features are necessary in the design of event detection algorithms. The downside of the deep learning approach is that a large amount of training data is required. We therefore first develop a method to augment hand-coded data, so that we can strongly enlarge the data set used for training, minimizing the time spent on manual coding. Using this extended hand-coded data, we train a neural network that produces eye-movement event classification from raw eye-movement data without requiring any predefined feature extraction or post-processing steps. The resulting classification performance is at the level of expert human coders. Moreover, an evaluation of gazeNet on two other datasets showed that gazeNet generalized to data from different eye trackers and consistently outperformed several other event detection algorithms that we tested.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50103 - Cognitive sciences

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Behavior Research Methods

ISSN

1554-351X

e-ISSN

—

Svazek periodika

51

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

25

Strana od-do

840-864

Kód UT WoS článku

000465552900025

EID výsledku v databázi Scopus

—