Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data
Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:7 |
---|---|
Enthalten in: |
Journal of imaging - 7(2021), 5 vom: 03. Mai |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Elbattah, Mahmoud [VerfasserIn] |
---|
Links: |
---|
Themen: |
Data augmentation |
---|
Anmerkungen: |
Date Revised 03.09.2021 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3390/jimaging7050083 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM330034456 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM330034456 | ||
003 | DE-627 | ||
005 | 20231225210425.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/jimaging7050083 |2 doi | |
028 | 5 | 2 | |a pubmed24n1100.xml |
035 | |a (DE-627)NLM330034456 | ||
035 | |a (NLM)34460679 | ||
035 | |a (PII)83 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Elbattah, Mahmoud |e verfasserin |4 aut | |
245 | 1 | 0 | |a Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 03.09.2021 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a data augmentation | |
650 | 4 | |a deep learning | |
650 | 4 | |a eye-tracking | |
650 | 4 | |a variational autoencoder | |
700 | 1 | |a Loughnane, Colm |e verfasserin |4 aut | |
700 | 1 | |a Guérin, Jean-Luc |e verfasserin |4 aut | |
700 | 1 | |a Carette, Romuald |e verfasserin |4 aut | |
700 | 1 | |a Cilia, Federica |e verfasserin |4 aut | |
700 | 1 | |a Dequen, Gilles |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of imaging |d 2016 |g 7(2021), 5 vom: 03. Mai |w (DE-627)NLM26971538X |x 2313-433X |7 nnns |
773 | 1 | 8 | |g volume:7 |g year:2021 |g number:5 |g day:03 |g month:05 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/jimaging7050083 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 7 |j 2021 |e 5 |b 03 |c 05 |