Limits...
Predicting Fatigue and Psychophysiological Test Performance from Speech for Safety-Critical Environments.

Baykaner KR, Huckvale M, Whiteley I, Andreeva S, Ryumin O - Front Bioeng Biotechnol (2015)

Bottom Line: We show that voice features and test scores are affected by both the total time spent awake and the time position within each subject's circadian cycle.However, we show that time spent awake and time-of-day information are poor predictors of the test results, while voice features can give good predictions of the psychophysiological test scores and sleep latency.Mean absolute errors of prediction are possible within about 17.5% for sleep latency and 5-12% for test scores.

View Article: PubMed Central - PubMed

Affiliation: Speech Hearing and Phonetic Sciences, Psychology and Language Sciences, University College London , London , UK.

ABSTRACT
Automatic systems for estimating operator fatigue have application in safety-critical environments. A system which could estimate level of fatigue from speech would have application in domains where operators engage in regular verbal communication as part of their duties. Previous studies on the prediction of fatigue from speech have been limited because of their reliance on subjective ratings and because they lack comparison to other methods for assessing fatigue. In this paper, we present an analysis of voice recordings and psychophysiological test scores collected from seven aerospace personnel during a training task in which they remained awake for 60 h. We show that voice features and test scores are affected by both the total time spent awake and the time position within each subject's circadian cycle. However, we show that time spent awake and time-of-day information are poor predictors of the test results, while voice features can give good predictions of the psychophysiological test scores and sleep latency. Mean absolute errors of prediction are possible within about 17.5% for sleep latency and 5-12% for test scores. We discuss the implications for the use of voice as a means to monitor the effects of fatigue on cognitive performance in practical applications.

No MeSH data available.


Related in: MedlinePlus

Scatter plots showing the relationship between “time only” model predictions and observations for the psychophysiological tests. The solid line is the line y = x, which shows all possible perfect predictions.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4548483&req=5

Figure 3: Scatter plots showing the relationship between “time only” model predictions and observations for the psychophysiological tests. The solid line is the line y = x, which shows all possible perfect predictions.

Mentions: Although some indication of the model performance can be gained by observing the correlation coefficients and RAEs of the test z-scores, it is easier to interpret when the predictions and observations are de-normalized so that error can be considered in its original units. Figure 3 shows scatterplots indicating the relationship between the PPT scores and the de-normalized predictions for all test folds of a single 10-fold cross-validation of the time-features only MLR model (for each PPT). Recalculating the correlations and MAEs for the denormalised predictions of the time based MLR model gives R = 0.64, 0.83, 0.56, and 0.78, and MAE = 41.90 ms, 12.42 ms, 2.54 errors, and 35.55 s, for the simple RT, planned RT, memory, and cognition tests, respectively. The correlations are much higher than those calculated based on the z-standardized data, indicating that the subject means are responsible for the largest portion of the prediction accuracy (i.e., individual differences in subject performance account for a large part of the variation in the data).


Predicting Fatigue and Psychophysiological Test Performance from Speech for Safety-Critical Environments.

Baykaner KR, Huckvale M, Whiteley I, Andreeva S, Ryumin O - Front Bioeng Biotechnol (2015)

Scatter plots showing the relationship between “time only” model predictions and observations for the psychophysiological tests. The solid line is the line y = x, which shows all possible perfect predictions.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4548483&req=5

Figure 3: Scatter plots showing the relationship between “time only” model predictions and observations for the psychophysiological tests. The solid line is the line y = x, which shows all possible perfect predictions.
Mentions: Although some indication of the model performance can be gained by observing the correlation coefficients and RAEs of the test z-scores, it is easier to interpret when the predictions and observations are de-normalized so that error can be considered in its original units. Figure 3 shows scatterplots indicating the relationship between the PPT scores and the de-normalized predictions for all test folds of a single 10-fold cross-validation of the time-features only MLR model (for each PPT). Recalculating the correlations and MAEs for the denormalised predictions of the time based MLR model gives R = 0.64, 0.83, 0.56, and 0.78, and MAE = 41.90 ms, 12.42 ms, 2.54 errors, and 35.55 s, for the simple RT, planned RT, memory, and cognition tests, respectively. The correlations are much higher than those calculated based on the z-standardized data, indicating that the subject means are responsible for the largest portion of the prediction accuracy (i.e., individual differences in subject performance account for a large part of the variation in the data).

Bottom Line: We show that voice features and test scores are affected by both the total time spent awake and the time position within each subject's circadian cycle.However, we show that time spent awake and time-of-day information are poor predictors of the test results, while voice features can give good predictions of the psychophysiological test scores and sleep latency.Mean absolute errors of prediction are possible within about 17.5% for sleep latency and 5-12% for test scores.

View Article: PubMed Central - PubMed

Affiliation: Speech Hearing and Phonetic Sciences, Psychology and Language Sciences, University College London , London , UK.

ABSTRACT
Automatic systems for estimating operator fatigue have application in safety-critical environments. A system which could estimate level of fatigue from speech would have application in domains where operators engage in regular verbal communication as part of their duties. Previous studies on the prediction of fatigue from speech have been limited because of their reliance on subjective ratings and because they lack comparison to other methods for assessing fatigue. In this paper, we present an analysis of voice recordings and psychophysiological test scores collected from seven aerospace personnel during a training task in which they remained awake for 60 h. We show that voice features and test scores are affected by both the total time spent awake and the time position within each subject's circadian cycle. However, we show that time spent awake and time-of-day information are poor predictors of the test results, while voice features can give good predictions of the psychophysiological test scores and sleep latency. Mean absolute errors of prediction are possible within about 17.5% for sleep latency and 5-12% for test scores. We discuss the implications for the use of voice as a means to monitor the effects of fatigue on cognitive performance in practical applications.

No MeSH data available.


Related in: MedlinePlus