Grant: Engage Grants Program
Institut national de la recherche scientifique
$25,000.00
Model calibration and selection for individualized workload assessment
EF 2014-15
Résumé
In certain safety-critical jobs, such as in chemical and nuclear plants, aviation, air traffic control, shipping,transportation, and railways, the rate of information flow, the number of decisions, and the numerous actionsthat must be carried out can be overwhelming for an operator. The results of such intense mental workload (i.e.,when cognitive resources are stretched beyond availability) can be disastrous. For example, recent statisticshave suggested that 90% of the accidents in the transport industry are due to human factors, such as fatigue andstress. To overcome these issues, automated operator functional state (OFS) assessment tools have beendeveloped. Many such tools are based either on conventional features extracted from electrocardiograms(ECG) or from electroencephalograms (EEG). Typically, such tools are developed based on data collected froma large number of participants. It is well known, however, that ECGs and EEGs have high inter-operatorvariability, thus existing OFS models do not perform well across different tasks, persons, or environments. Thisproject aims to fill this gap. To achieve this goal, two major innovations are proposed herein. First, amultimodal OFS model is proposed based on the integration of new EEG and ECG features developed by theapplicant, as well as existing features available from the OFS model developed by our industry partner (e.g.,breathing rate, eye gaze). Second, two user-specific calibration strategies are proposed to tailor a ""generic"" OFSmodel to a specific user: one relies on pre-session OFS model parameter optimization and the other on OFSmodel parameter updates during runtime based on user feedback. An exploratory aim of the project is toinvestigate the benefits of each of the two calibration strategies. By the end of the project, a next-generation,user-specific multimodal OFS model will be developed, thus positively impacting the Canadian technological,financial, and health sectors. The outcomes of the project also have the potential of impacting other areas, suchas serious gaming and entertainment.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
476310-2014
Name nom
Falk, Tiago
Department département
Centre Énergie, Matériaux et Télécommunication - Montréal
Organization id
56
Institution établissement
Institut national de la recherche scientifique
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
1900
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical engineering
Research subject fr
Génie biomédical
Partie
1
Nb partie
1
Application title
Model calibration and selection for individualized workload assessment
Keyword
NSERC
Application summary
In certain safety-critical jobs, such as in chemical and nuclear plants, aviation, air traffic control, shipping,transportation, and railways, the rate of information flow, the number of decisions, and the numerous actionsthat must be carried out can be overwhelming for an operator. The results of such intense mental workload (i.e.,when cognitive resources are stretched beyond availability) can be disastrous. For example, recent statisticshave suggested that 90% of the accidents in the transport industry are due to human factors, such as fatigue andstress. To overcome these issues, automated operator functional state (OFS) assessment tools have beendeveloped. Many such tools are based either on conventional features extracted from electrocardiograms(ECG) or from electroencephalograms (EEG). Typically, such tools are developed based on data collected froma large number of participants. It is well known, however, that ECGs and EEGs have high inter-operatorvariability, thus existing OFS models do not perform well across different tasks, persons, or environments. Thisproject aims to fill this gap. To achieve this goal, two major innovations are proposed herein. First, amultimodal OFS model is proposed based on the integration of new EEG and ECG features developed by theapplicant, as well as existing features available from the OFS model developed by our industry partner (e.g.,breathing rate, eye gaze). Second, two user-specific calibration strategies are proposed to tailor a ""generic"" OFSmodel to a specific user: one relies on pre-session OFS model parameter optimization and the other on OFSmodel parameter updates during runtime based on user feedback. An exploratory aim of the project is toinvestigate the benefits of each of the two calibration strategies. By the end of the project, a next-generation,user-specific multimodal OFS model will be developed, thus positively impacting the Canadian technological,financial, and health sectors. The outcomes of the project also have the potential of impacting other areas, suchas serious gaming and entertainment.