Publication
Adversarial Robustness and Feature Impact Analysis for Driver Drowsiness Detection
| dc.contributor.author | Vitorino, João | |
| dc.contributor.author | Rodrigues, Lourenço | |
| dc.contributor.author | Maia, Eva | |
| dc.contributor.author | Praça, Isabel | |
| dc.contributor.author | Lourenço, André | |
| dc.date.accessioned | 2023-09-05T13:45:50Z | |
| dc.date.available | 2023-09-05T13:45:50Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Drowsy driving is a major cause of road accidents, but drivers are dismissive of the impact that fatigue can have on their reaction times. To detect drowsiness before any impairment occurs, a promising strategy is using Machine Learning (ML) to monitor Heart Rate Variability (HRV) signals. This work presents multiple experiments with different HRV time windows and ML models, a feature impact analysis using Shapley Additive Explanations (SHAP), and an adversarial robustness analysis to assess their reliability when processing faulty input data and perturbed HRV signals. The most reliable model was Extreme Gradient Boosting (XGB) and the optimal time window had between 120 and 150 s. Furthermore, the 18 most impactful features were selected and new smaller models were trained, achieving a performance as good as the initial ones. Despite the susceptibility of all models to adversarial attacks, adversarial training enabled them to preserve significantly higher results, so it can be a valuable approach to provide a more robust driver drowsiness detection. | pt_PT |
| dc.description.sponsorship | This work was done and funded in the scope of the European Union's Horizon 2020 research and innovation program, under project VALU3S (grant agreement no. 876852). This work has also received funding from UIDP/00760/2020. A publicly available dataset was utilized in this work. The data can be found at: https://hdl.handle.net/2268/191620. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.arxiv | 10.48550/arXiv.2303.13649 | |
| dc.identifier.doi | 10.1007/978-3-031-34344-5_13 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.22/23453 | |
| dc.language.iso | eng | pt_PT |
| dc.publisher | Springer | pt_PT |
| dc.relation | Verification and Validation of Automated Systems' Safety and Security | |
| dc.relation | Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development | |
| dc.relation.publisherversion | https://link.springer.com/chapter/10.1007/978-3-031-34344-5_13 | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | pt_PT |
| dc.subject | Adversarial robustness | pt_PT |
| dc.subject | Explainability | pt_PT |
| dc.subject | Machine learning | pt_PT |
| dc.subject | Heart rate variability | pt_PT |
| dc.subject | Driver drowsiness detection | pt_PT |
| dc.title | Adversarial Robustness and Feature Impact Analysis for Driver Drowsiness Detection | pt_PT |
| dc.type | conference object | |
| dspace.entity.type | Publication | |
| oaire.awardTitle | Verification and Validation of Automated Systems' Safety and Security | |
| oaire.awardTitle | Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development | |
| oaire.awardURI | info:eu-repo/grantAgreement/EC/H2020/876852/EU | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00760%2F2020/PT | |
| oaire.citation.endPage | 113 | pt_PT |
| oaire.citation.startPage | 108 | pt_PT |
| oaire.citation.title | International Conference on Artificial Intelligence in Medicine - AIME 2023 | pt_PT |
| oaire.citation.volume | 13897 | pt_PT |
| oaire.fundingStream | H2020 | |
| oaire.fundingStream | 6817 - DCRRNI ID | |
| person.familyName | Machado Vitorino | |
| person.familyName | Maia | |
| person.familyName | Praça | |
| person.givenName | João Pedro | |
| person.givenName | Eva | |
| person.givenName | Isabel | |
| person.identifier | HlqCxhoAAAAJ | |
| person.identifier | 299522 | |
| person.identifier.ciencia-id | 3312-592F-B628 | |
| person.identifier.ciencia-id | 4F14-EF83-C4B9 | |
| person.identifier.ciencia-id | C710-4218-1BFF | |
| person.identifier.orcid | 0000-0002-4968-3653 | |
| person.identifier.orcid | 0000-0002-8075-531X | |
| person.identifier.orcid | 0000-0002-2519-9859 | |
| person.identifier.rid | K-8430-2014 | |
| person.identifier.scopus-author-id | 57579914600 | |
| person.identifier.scopus-author-id | 22734900800 | |
| project.funder.identifier | http://doi.org/10.13039/501100008530 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | European Commission | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | conferenceObject | pt_PT |
| relation.isAuthorOfPublication | 4435bb64-8a77-407b-ba18-4833d26e72ae | |
| relation.isAuthorOfPublication | 47a108c4-cf8a-46f3-8954-90624174e8fc | |
| relation.isAuthorOfPublication | ee4ecacd-c6c6-41e8-bca1-21a60ff05f50 | |
| relation.isAuthorOfPublication.latestForDiscovery | 47a108c4-cf8a-46f3-8954-90624174e8fc | |
| relation.isProjectOfPublication | 1b3082bd-64c8-41d8-9f32-bb7f4b0d7bde | |
| relation.isProjectOfPublication | 6eb94c83-adf9-4d9d-a75c-be95f44e3ca5 | |
| relation.isProjectOfPublication.latestForDiscovery | 6eb94c83-adf9-4d9d-a75c-be95f44e3ca5 |