Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario
Monitoring pilot's mental states is a relevant approach to mitigate human error and enhance human machine interaction. A promising brain imaging technique to perform such a continuous measure of human mental state under ecological settings is Functional Near-InfraRed Spectroscopy (fNIRS). Howev...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2018-01-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/article/10.3389/fnhum.2018.00006/full |
| _version_ | 1819106429812867072 |
|---|---|
| author | Kevin J. Verdière Raphaëlle N. Roy Frédéric Dehais |
| author_facet | Kevin J. Verdière Raphaëlle N. Roy Frédéric Dehais |
| author_sort | Kevin J. Verdière |
| collection | DOAJ |
| description | Monitoring pilot's mental states is a relevant approach to mitigate human error and enhance human machine interaction. A promising brain imaging technique to perform such a continuous measure of human mental state under ecological settings is Functional Near-InfraRed Spectroscopy (fNIRS). However, to our knowledge no study has yet assessed the potential of fNIRS connectivity metrics as long as passive Brain Computer Interfaces (BCI) are concerned. Therefore, we designed an experimental scenario in a realistic simulator in which 12 pilots had to perform landings under two contrasted levels of engagement (manual vs. automated). The collected data were used to benchmark the performance of classical oxygenation features (i.e., Average, Peak, Variance, Skewness, Kurtosis, Area Under the Curve, and Slope) and connectivity features (i.e., Covariance, Pearson's, and Spearman's Correlation, Spectral Coherence, and Wavelet Coherence) to discriminate these two landing conditions. Classification performance was obtained by using a shrinkage Linear Discriminant Analysis (sLDA) and a stratified cross validation using each feature alone or by combining them. Our findings disclosed that the connectivity features performed significantly better than the classical concentration metrics with a higher accuracy for the wavelet coherence (average: 65.3/59.9 %, min: 45.3/45.0, max: 80.5/74.7 computed for HbO/HbR signals respectively). A maximum classification performance was obtained by combining the area under the curve with the wavelet coherence (average: 66.9/61.6 %, min: 57.3/44.8, max: 80.0/81.3 computed for HbO/HbR signals respectively). In a general manner all connectivity measures allowed an efficient classification when computed over HbO signals. Those promising results provide methodological cues for further implementation of fNIRS-based passive BCIs. |
| first_indexed | 2024-12-22T02:38:00Z |
| format | Article |
| id | doaj.art-ab42c3bc772c470eba76805c89104d22 |
| institution | Directory Open Access Journal |
| issn | 1662-5161 |
| language | English |
| last_indexed | 2024-12-22T02:38:00Z |
| publishDate | 2018-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj.art-ab42c3bc772c470eba76805c89104d222022-12-21T18:41:42ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612018-01-011210.3389/fnhum.2018.00006310096Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing ScenarioKevin J. VerdièreRaphaëlle N. RoyFrédéric DehaisMonitoring pilot's mental states is a relevant approach to mitigate human error and enhance human machine interaction. A promising brain imaging technique to perform such a continuous measure of human mental state under ecological settings is Functional Near-InfraRed Spectroscopy (fNIRS). However, to our knowledge no study has yet assessed the potential of fNIRS connectivity metrics as long as passive Brain Computer Interfaces (BCI) are concerned. Therefore, we designed an experimental scenario in a realistic simulator in which 12 pilots had to perform landings under two contrasted levels of engagement (manual vs. automated). The collected data were used to benchmark the performance of classical oxygenation features (i.e., Average, Peak, Variance, Skewness, Kurtosis, Area Under the Curve, and Slope) and connectivity features (i.e., Covariance, Pearson's, and Spearman's Correlation, Spectral Coherence, and Wavelet Coherence) to discriminate these two landing conditions. Classification performance was obtained by using a shrinkage Linear Discriminant Analysis (sLDA) and a stratified cross validation using each feature alone or by combining them. Our findings disclosed that the connectivity features performed significantly better than the classical concentration metrics with a higher accuracy for the wavelet coherence (average: 65.3/59.9 %, min: 45.3/45.0, max: 80.5/74.7 computed for HbO/HbR signals respectively). A maximum classification performance was obtained by combining the area under the curve with the wavelet coherence (average: 66.9/61.6 %, min: 57.3/44.8, max: 80.0/81.3 computed for HbO/HbR signals respectively). In a general manner all connectivity measures allowed an efficient classification when computed over HbO signals. Those promising results provide methodological cues for further implementation of fNIRS-based passive BCIs.http://journal.frontiersin.org/article/10.3389/fnhum.2018.00006/fullfNIRSpassive brain-computer-interfaceclassificationfunctional connectivitywavelet coherenceengagement |
| spellingShingle | Kevin J. Verdière Raphaëlle N. Roy Frédéric Dehais Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario Frontiers in Human Neuroscience fNIRS passive brain-computer-interface classification functional connectivity wavelet coherence engagement |
| title | Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario |
| title_full | Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario |
| title_fullStr | Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario |
| title_full_unstemmed | Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario |
| title_short | Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario |
| title_sort | detecting pilot s engagement using fnirs connectivity features in an automated vs manual landing scenario |
| topic | fNIRS passive brain-computer-interface classification functional connectivity wavelet coherence engagement |
| url | http://journal.frontiersin.org/article/10.3389/fnhum.2018.00006/full |
| work_keys_str_mv | AT kevinjverdiere detectingpilotsengagementusingfnirsconnectivityfeaturesinanautomatedvsmanuallandingscenario AT raphaellenroy detectingpilotsengagementusingfnirsconnectivityfeaturesinanautomatedvsmanuallandingscenario AT fredericdehais detectingpilotsengagementusingfnirsconnectivityfeaturesinanautomatedvsmanuallandingscenario |