MétaCan
Menu
Back to cohort
Record W7048774949

Modèle hiérarchique pour l’amélioration de l’évaluation
\nde l’état mental de l’opérateur à l’aide de technologies
\nportables / Hierarchical model for improved operator functional
\nstate assessment based on wearables.

2017· dissertation· fr· W7048774949 on OpenAlexfundno aff

Bibliographic record

VenueEspaceINRS Institutional Digital Repository (Institut National de la Recherche Scientifique) · 2017
Typedissertation
Languagefr
FieldPhysics and Astronomy
TopicSuperconducting and THz Device Technology
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsContext (archaeology)Point (geometry)Homogeneous
DOInot available

Abstract

fetched live from OpenAlex

La classification inter-tâches, c’est-à-dire la classification de la charge mentale pour plusieurs tâches \nà l’aide d’un même modèle, est un problème important pour l’évaluation de l’état fonctionnel de \nl’opérateur. Dans cette étude, nous proposons une nouvelle méthode afin d’améliorer la précision \nde la classification inter-tâches, ainsi que des nouvelles caractéristiques de l’EEG afin d’améliorer la \nprécision intra-tâche et inter-tâches. Notre méthode se fie à un classificateur hiérarchique capable de \ndétecter la tâche à laquelle appartient un point de données, ainsi que sa difficulté. Les caractéristiques \nque nous proposons sont des caractéristiques de couplage entre les fréquences, soit le couplage phaseamplitude \net le taux de changement de la modulation d’amplitude. \nNous avons recueilli de données cardiaques, respiratoires, oculométriques et électroencéphalographiques \nde 16 participants, chacun exécutant trois tâches cognitives, soit la rotation mentale, le \nN-Back et la recherche visuelle. Comme nous voulions évaluer la performance de notre modèle dans \nun environnement réel, nous avons recueilli ces signaux à l’aide d’appareils portables. Afin de rendre \nnotre modèle indépendant de l’utilisateur, nous avons également recueilli des métriques objectives \net subjectives de la performance pour faciliter le processus de sélection des caractéristiques. \nNos résultats montrent que les caractéristiques de l’EEG que nous proposons améliorent la classification \nintra-tâche pour la rotation mentale et la recherche visuelle. De plus, notre modèle hiérarchique \na atteint une précision de 69%, par rapport à 62% pour les méthodes traditionnelles. Ces résultats \nindépendants de l’utilisateur sont comparables aux modèles adaptés à l’utilisateur publiés précédemment. \nLa performance relativement faible de notre modèle est due en grande partie à une mauvaise \ndistribution des électrodes EEG, ainsi qu’à des problèmes survenus avec les signaux de la physiologie \npériphérique. Nous nous attendons à ce que notre modèle produise de bien meilleurs résultats avec \ndes appareils plus appropriés. Cross-task classification, that is the ability of a single model to classify mental workload across many \ndifferent tasks, is an important problem in mental workload assessment. In this work, we propose \na novel approach to improve cross-task accuracy as well as new EEG features to improve withinand \ncross-task accuracy. Our approach relies on a layered classifier to detect both the task being \nperformed and the difficulty condition, while the proposed features are Cross-Frequency Coupling \nfeatures that quantifiy the interactions between EEG sub-bands, namely Phase-Amplitude Coupling \nand Amplitude Modulation Rate-of-Change. \nTo do this, we collected ECG, respiration, eye tracking and EEG data from 16 participants performing \nthree tasks : mental rotation, N-back and visual search. As we wanted to test in-the-field \nperformance of our methods, we collected physiological data using wearable devices. In an effort to \nmake our model user-independant, we also collected objective and subjective perfomance metrics \nto help the feature selection process. \nOur results show that the proposed EEG features improve within-task results for mental rotation \nand visual search. Additionally, our hierarchical method achieved an accuracy of 69% compared to \n62% using traditional methods. These user-independant results compare favourably to previously \npublished user-adapter models. The relatively low performance of our model is due mostly to poor \nEEG electrode distribution and problems encountered with the signals extracted from peripheral \nphysiology. Our approach can be expected to perform much better given better data collection \ndevices.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.027
Threshold uncertainty score0.053

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0020.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.124
GPT teacher head0.343
Teacher spread0.218 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2017
Admission routes1
Has abstractyes

Explore more

Same venueEspaceINRS Institutional Digital Repository (Institut National de la Recherche Scientifique)Same topicSuperconducting and THz Device TechnologyFrench-language works237,207