[Mental fatigue state recognition method based on convolution neural network and long short-term memory].

The pace of modern life is accelerating, the pressure of life is gradually increasing, and the long-term accumulation of mental fatigue poses a threat to health. By analyzing physiological signals and parameters, this paper proposes a method that can identify the state of mental fatigue, which helps to maintain a healthy life. The method proposed in this paper is a new recognition method of psychological fatigue state of electrocardiogram signals based on convolutional neural network and long short-term memory. Firstly, the convolution layer of one-dimensional convolutional neural network model is used to extract local features, the key information is extracted through pooling layer, and some redundant data is removed. Then, the extracted features are used as input to the long short-term memory model to further fuse the ECG features. Finally, by integrating the key information through the full connection layer, the accurate recognition of mental fatigue state is successfully realized. The results show that compared with traditional machine learning algorithms, the proposed method significantly improves the accuracy of mental fatigue recognition to 96.3%, which provides a reliable basis for the early warning and evaluation of mental fatigue.

Quantitative identification of daily mental fatigue levels based on multimodal parameters.

Fatigue has become an important health problem in modern life; excessive mental fatigue may induce various cardiovascular diseases. Most current mental fatigue recognition is based only on specific scenarios and tasks. To improve the accuracy of daily mental fatigue recognition, this paper proposes a multimodal fatigue grading method that combines three signals of electrocardiogram (ECG), photoplethysmography (PPG), and blood pressure (BP). We collected ECG, PPG, and BP from 22 subjects during three time periods: morning, afternoon, and evening. Based on these three signals, 56 characteristic parameters were extracted from multiple dimensions, which comprehensively covered the physiological information in different fatigue states. The extracted parameters were compared with the feature optimization ability of recursive feature elimination (RFE), maximal information coefficient, and joint mutual information, and the optimum feature matrix selected was input into random forest (RF) for a three-level classification. The results showed that the accuracy of classification of fatigue using only one physiological feature was 88.88%, 92.72% using a combination of two physiological features, and 94.87% using all three physiological features. This study indicates that the fusion of multiple physiological traits contains more comprehensive information and better identifies the level of mental fatigue, and the RFE-RF model performs best in fatigue identification. The BP variability index is useful for fatigue classification.

Investigating real-time physical activity behavior using ecological momentary assessment: Effects of mental fatigue and benefit-cost valuations.

BACKGROUND: Current research investigating the relationship between mental fatigue and physical activity behaviors relies on laboratory-based, experimental studies which lack ecological validity. OBJECTIVE: This study used ecological momentary assessment (EMA) to assess feelings of mental fatigue and subjective evaluations (benefits and costs) as predictors of moderate-to-vigorous intensity physical activity in the everyday lives of young adults. METHODS: One hundred participants (n = 22 males, n = 78 females, Mage = 20.60 years, 70% meeting or exceeding physical activity guidelines) responded to digital survey prompts up to four times a day and wore an accelerometer for seven consecutive days. Moderate-to-vigorous intensity physical activity in the 180-min time window following each survey prompt was recorded. Data from the 28 survey-moderate-to-vigorous intensity physical activity epochs were analyzed using multilevel mixed-effects linear modelling. RESULTS: Higher levels of mental fatigue than one's average level were associated with engaging in fewer moderate-to-vigorous intensity physical activity minutes (p = .004) and lower benefit vs. cost scores (p = .001). Higher benefit vs. cost scores than one's average level were associated with engaging in more minutes of moderate-to-vigorous intensity physical activity (p < .001). CONCLUSIONS: Results are the first to demonstrate outside the lab, that mental fatigue experienced in everyday life may amplify the perceived costs of moderate-to-vigorous intensity physical activity, with both factors playing a potential role in moderate-to-vigorous intensity physical activity decision-making. Future research may apply insights gained from this study in design and testing of real-time interventions promoting moderate-to-vigorous intensity physical activity.

Understanding mental fatigue and its detection: a comparative analysis of assessments and tools.

Mental fatigue has shown to be one of the root causes of decreased productivity and overall cognitive performance, by decreasing an individual's ability to inhibit responses, process information and concentrate. The effects of mental fatigue have led to occupational errors and motorway accidents. Early detection of mental fatigue can prevent the escalation of symptoms that may lead to chronic fatigue syndrome and other disorders. To date, in clinical settings, the assessment of mental fatigue and stress is done through self-reported questionnaires. The validity of these questionnaires is questionable, as they are highly subjective measurement tools and are not immune to response biases. This review examines the wider presence of mental fatigue in the general population and critically compares its various detection techniques (i.e., self-reporting questionnaires, heart rate variability, salivary cortisol levels, electroencephalogram, and saccadic eye movements). The ability of these detection tools to assess inhibition responses (which are sensitive enough to be manifested in a fatigue state) is specifically evaluated for a reliable marker in identifying mentally fatigued individuals. In laboratory settings, antisaccade tasks have been long used to assess inhibitory control and this technique can potentially serve as the most promising assessment tool to objectively detect mental fatigue. However, more studies need to be conducted in the future to validate and correlate this assessment with other existing measures of mental fatigue detection. This review is intended for, but not limited to, mental health professionals, digital health scientists, vision researchers, and behavioral scientists.

The measurement of mental fatigue following an overnight on-call duty among doctors using electroencephalogram.

This study aimed to measure the spectral power differences in the brain rhythms among a group of hospital doctors before and after an overnight on-call duty. Thirty-two healthy doctors who performed regular on-call duty in a tertiary hospital in Sarawak, Malaysia were voluntarily recruited into this study. All participants were interviewed to collect relevant background information, followed by a self-administered questionnaire using Chalder Fatigue Scale and electroencephalogram test before and after an overnight on-call duty. The average overnight sleep duration during the on-call period was 2.2 hours (p<0.001, significantly shorter than usual sleep duration) among the participants. The mean (SD) Chalder Fatigue Scale score of the participants were 10.8 (5.3) before on-call and 18.4 (6.6) after on-call (p-value < 0.001). The theta rhythm showed significant increase in spectral power globally after an overnight on-call duty, especially when measured at eye closure. In contrast, the alpha and beta rhythms showed reduction in spectral power, significantly at temporal region, at eye closure, following an overnight on-call duty. These effects are more statistically significant when we derived the respective relative theta, alpha, and beta values. The finding of this study could be useful for development of electroencephalogram screening tool to detect mental fatigue.

An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN.

OBJECTIVES: Electroencephalogram (EEG) is often used to detect mental fatigue because of its real-time characteristic and objective nature. However, because of the individual variability of EEG among different individuals, tedious and time-consuming calibration sessions are needed. METHODS: Therefore, we propose a multi-source domain adaptation network for inter-subject mental fatigue detection named FLDANN, which is short for focal loss based domain-adversarial training of neural network. As for mental state feature extraction, power spectrum density is extracted based on the Welch method from four sub-bands of EEG signals. The features of the source domain and target domain are fed into the FLDANN network. The contributions of FLDANN include: (1) It uses the idea of adversarial to reduce feature differences between the source and target domain. (2) A loss function named focal loss is used to assign weights to source and target domain samples. RESULTS: The experiment result shows that when the number of the source domains increases, the classification accuracy of domain-adversarial training of neural network (DANN) gradually decreases and finally tends to be stable. The proposed method achieves an accuracy of 84.10% ± 8.75% on the SEED-VIG dataset and 65.42% ± 7.47% on the self-designed dataset. In addition, the proposed method is compared with other domain adaptation methods and the results show that the proposed method outperforms those state-of-the-art methods. CONCLUSIONS: The result proves that the proposed method is able to solve the problem of individual differences across subjects and to solve the problem of low classification performance of multi-source domain transfer learning.

EEG-based mental fatigue detection using linear prediction cepstral coefficients and Riemann spatial covariance matrix.

Objective. Establishing a mental fatigue monitoring system is of great importance as for severe fatigue may cause unimaginable consequences. Electroencephalogram (EEG) is often utilized for mental fatigue detection because of its high temporal resolution and ease of use. However, many EEG-based approaches for detecting mental fatigue only take into account the feature extraction of a single domain and do not fully exploit the information that EEG may offer.Approach. In our work, we propose a new algorithm for mental fatigue detection based on multi-domain feature extraction and fusion. EEG components representing fatigue are closely related in the past and present because fatigue is a dynamic and gradual process. Accordingly, the idea of linear prediction is used to fit the current value with a set of sample values in the past to calculate the linear prediction cepstral coefficients (LPCCs) as the time domain feature. Moreover, in order to better capture fatigue-related spatial domain information, the spatial covariance matrix of the original EEG signal is projected into the Riemannian tangent space using the Riemannian geometric method. Then multi-domain features are fused to obtain comprehensive spatio-temporal information.Main results. Experimental results prove the suggested algorithm outperforms existing state-of-the-art methods, achieving an average accuracy of 87.10% classification on the public dataset SEED-VIG (three categories) and 97.40% classification accuracy (two categories) on the dataset made by self-designed experiments.Significance. These findings show that our proposed strategy perform more effectively for mental fatigue detection based on EEG.

Post-viral fatigue in COVID-19: A review of symptom assessment methods, mental, cognitive, and physical impairment.

Coronavirus 2 is responsible for Severe Acute Respiratory Syndrome-Coronavirus-2 (SARS-CoV-2), and the main sequela is persistent fatigue. Post-viral fatigue is common and affects patients with mild, asymptomatic coronavirus disease-2019 (COVID-19). However, the exact mechanisms involved in developing post-COVID-19 fatigue remain unclear. Furthermore, physical and cognitive impairments in these individuals have been widely described. Therefore, this review aims to summarize and propose tools from a multifaceted perspective to assess COVID-19 infection. Herein, we point out the instruments that can be used to assess fatigue in long-term COVID-19: fatigue in a subjective manner or fatigability in an objective manner. For physical and mental fatigue, structured questionnaires were used to assess perceived symptoms, and physical and cognitive performance assessment tests were used to measure fatigability using reduced performance.

Do Cognitive, Physical, and Combined Tasks Induce Similar Levels of Mental Fatigue? Testing the Effects of Different Moderating Variables.

Experts have highlighted the importance of coaches knowing the level of mental fatigue (MF) induced by different tasks. This study aimed to compare the mentally fatiguing nature of cognitive, physical, and combined tasks and, additionally, assess the effect of different moderating variables on MF. Twenty-three physically active (16 males: Mage = 24 years; seven females: Mage = 22.57 years) participants performed three experimental sessions: (a) physically fatiguing: 30 min of cycloergometer work (at 65%-75% of maximum heart rate), (b) mentally fatiguing: 30 min of an incongruent Stroop task, and (c) mixed fatiguing: 30 min of combining the physically and mentally fatiguing protocols. Subjective MF (visual analog scale), reaction time (psychomotor vigilance task), and cognitive performance (Stroop) were measured throughout the different protocols. Results showed significant increments in subjective MF after all tasks, with the mental and mixed protocols showing significantly higher increases. Only the mentally fatiguing protocol caused significant impairments in reaction time. No significant effects of sex, years of experience, or degree of mental toughness were observed. These results suggest that the use of all these tasks, and especially the mentally fatiguing exercises, should be avoided immediately prior to competitions due to the negative consequences of MF on performance. Moreover, this effect seems to be independent of the sex, years of experience, or mental toughness of athletes.

Development and Evaluation of Pediatric Versions of the Vanderbilt Fatigue Scale for Children With Hearing Loss.

PURPOSE: Growing evidence suggests that fatigue associated with listening difficulties is particularly problematic for children with hearing loss (CHL). However, sensitive, reliable, and valid measures of listening-related fatigue do not exist. To address this gap, this article describes the development, psychometric evaluation, and preliminary validation of a suite of scales designed to assess listening-related fatigue in CHL: the pediatric versions of the Vanderbilt Fatigue Scale (VFS-Peds). METHOD: Test development employed best practices, including operationalizing the construct of listening-related fatigue from the perspective of target respondents (i.e., children, their parents, and teachers). Test items were developed based on input from these groups. Dimensionality was evaluated using exploratory factor analyses (EFAs). Item response theory (IRT) and differential item functioning (DIF) analyses were used to identify high-quality items, which were further evaluated and refined to create the final versions of the VFS-Peds. RESULTS: The VFS-Peds is appropriate for use with children aged 6-17 years and consists of child self-report (VFS-C), parent proxy-report (VFS-P), and teacher proxy-report (VFS-T) scales. EFA of child self-report and teacher proxy data suggested that listening-related fatigue was unidimensional in nature. In contrast, parent data suggested a multidimensional construct, composed of mental (cognitive, social, and emotional) and physical domains. IRT analyses suggested that items were of good quality, with high information and good discriminability. DIF analyses revealed the scales provided a comparable measure of fatigue regardless of the child's gender, age, or hearing status. Test information was acceptable over a wide range of fatigue severities and all scales yielded acceptable reliability and validity. CONCLUSIONS: This article describes the development, psychometric evaluation, and validation of the VFS-Peds. Results suggest that the VFS-Peds provide a sensitive, reliable, and valid measure of listening-related fatigue in children that may be appropriate for clinical use. Such scales could be used to identify those children most affected by listening-related fatigue, and given their apparent sensitivity, the scales may also be useful for examining the effectiveness of potential interventions targeting listening-related fatigue in children. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.19836154.

[Mental fatigue - possible explanations, diagnostic methods and possible treatments]. / Hjärntrötthet ­ ett osynligt gissel.

Mental fatigue or brain fatigue is a pathological and disabling symptom with diminished mental energy. It can be a long-lasting consequence after trauma or disease affecting the brain. The person can do most things in the moment and can be perceived as completely healthy, but the mental energy is insufficient over time and affects the ability to work and participate in social activities. After a conversation, for example, the person can be completely drained of energy and the recovery time is disproportionally long. Here we describe the phenomenon of mental fatigue, provide an explanatory model for how the condition can arise, point out diagnostic methods and possible treatments, which are currently in the research stage but may be implemented in healthcare within the foreseeable future.

APOE ε4 associates with increased risk of severe COVID-19, cerebral microhaemorrhages and post-COVID mental fatigue: a Finnish biobank, autopsy and clinical study.

Apolipoprotein E ε4 allele (APOE4) has been shown to associate with increased susceptibility to SARS-CoV-2 infection and COVID-19 mortality in some previous genetic studies, but information on the role of APOE4 on the underlying pathology and parallel clinical manifestations is scarce. Here we studied the genetic association between APOE and COVID-19 in Finnish biobank, autopsy and prospective clinical cohort datasets. In line with previous work, our data on 2611 cases showed that APOE4 carriership associates with severe COVID-19 in intensive care patients compared with non-infected population controls after matching for age, sex and cardiovascular disease status. Histopathological examination of brain autopsy material of 21 COVID-19 cases provided evidence that perivascular microhaemorrhages are more prevalent in APOE4 carriers. Finally, our analysis of post-COVID fatigue in a prospective clinical cohort of 156 subjects revealed that APOE4 carriership independently associates with higher mental fatigue compared to non-carriers at six months after initial illness. In conclusion, the present data on Finns suggests that APOE4 is a risk factor for severe COVID-19 and post-COVID mental fatigue and provides the first indication that some of this effect could be mediated via increased cerebrovascular damage. Further studies in larger cohorts and animal models are warranted.

Evaluation of a Fast Test Based on Biometric Signals to Assess Mental Fatigue at the Workplace-A Pilot Study.

Non-pathological mental fatigue is a recurring, but undesirable condition among people in the fields of office work, industry, and education. This type of mental fatigue can often lead to negative outcomes, such as performance reduction and cognitive impairment in education; loss of focus and burnout syndrome in office work; and accidents leading to injuries or death in the transportation and manufacturing industries. Reliable mental fatigue assessment tools are promising in the improvement of performance, mental health and safety of students and workers, and at the same time, in the reduction of risks, accidents and the associated economic loss (e.g., medical fees and equipment reparations). The analysis of biometric (brain, cardiac, skin conductance) signals has proven to be effective in discerning different stages of mental fatigue; however, many of the reported studies in the literature involve the use of long fatigue-inducing tests and subject-specific models in their methodologies. Recent trends in the modeling of mental fatigue suggest the usage of non subject-specific (general) classifiers and a time reduction of calibration procedures and experimental setups. In this study, the evaluation of a fast and short-calibration mental fatigue assessment tool based on biometric signals and inter-subject modeling, using multiple linear regression, is presented. The proposed tool does not require fatigue-inducing tests, which allows fast setup and implementation. Electroencephalography, photopletismography, electrodermal activity, and skin temperature from 17 subjects were recorded, using an OpenBCI helmet and an Empatica E4 wristband. Correlations to self-reported mental fatigue levels (using the fatigue assessment scale) were calculated to find the best mental fatigue predictors. Three-class mental fatigue models were evaluated, and the best model obtained an accuracy of 88% using three features, ß/θ (C3), and the α/θ (O2 and C3) ratios, from one minute of electroencephalography measurements. The results from this pilot study show the feasibility and potential of short-calibration procedures and inter-subject classifiers in mental fatigue modeling, and will contribute to the use of wearable devices for the development of tools oriented to the well-being of workers and students, and also in daily living activities.

Mental Fatigue after Mild Traumatic Brain Injury in Relation to Cognitive Tests and Brain Imaging Methods.

Most people recover within months after a mild traumatic brain injury (TBI) or concussion, but some will suffer from long-term fatigue with a reduced quality of life and the inability to maintain their employment status or education. For many people, mental fatigue is one of the most distressing and long-lasting symptoms following an mTBI. No efficient treatment options can be offered. The best method for measuring fatigue today is with fatigue self-assessment scales, there being no objective clinical tests available for mental fatigue. The aim here is to provide a narrative review and identify fatigue in relation to cognitive tests and brain imaging methods. Suggestions for future research are presented.

Effect of Mindfulness Training on Fatigue and Recovery in Elite Volleyball Athletes: A Randomized Controlled Follow-Up Study.

Volleyball is a team sport with high physical and perceptual-cognitive demand, hence, increasing the perception of physical and mental fatigue during a competition. To alleviate fatigue (physical and mental), mindfulness and music have been proposed. The aim of this study was to analyze the effect of mindfulness-based mental versus music training on mental fatigue, physical fatigue, and recovery in elite competitive female volleyball athletes using a randomized two-controlled study with follow-up. Participants were 30 elite female Brazilian volleyball athletes. Athletes were randomly assigned to the following groups: 1) mindfulness-based mental training group (MBMT); 2) music-based training group (MBT); or 3) control group (CG). Three variables were evaluated as follows: 1) recovery based on total quality recovery; 2) mental fatigue visual analog scale; and 3) physical fatigue visual analog scale. Regarding recovery, there was no difference between the MBMT, MBT, and CG groups (p > 0.05). A difference in mental fatigue was noted between MBT and CG at follow-up [F(2,26) = 5.71, p = 0.009; large]. Regarding physical fatigue, there was no difference between the MBMT, MBT, and CG groups (p > 0.05). The mindfulness intervention effectively attenuated the mental fatigue caused by competition in volleyball athletes. These results will assist coaches and staff in providing fatigue management and reinforce the applicability of mental training in sports.

Validation of Perceived Mental Fatigability Using the Pittsburgh Fatigability Scale.

OBJECTIVES: Establish reliability, concurrent and convergent validity of the Pittsburgh Fatigability Scale (PFS) Mental subscale. DESIGN: Cross-sectional. SETTING: Older adults from two University of Pittsburgh registries, Baltimore Longitudinal Study of Aging (BLSA), and Long Life Family Study (LLFS). PARTICIPANTS: PFS Mental subscale validation was conducted using three cohorts: (1) Development Sample (N = 664, 59.1% women, age 74.8 ± 6.4 years, PFS Mental scores 10.3 ± 9.1), (2) Validation Sample I-BLSA (N = 430, 51.9% women, age 74.5 ± 8.2 years, PFS Mental scores 9.4 ± 7.9), and (3) Validation Sample II-LLFS (N = 1,917, 54.5% women, age 72.2 ± 9.3 years, PFS Mental scores 7.5 ± 8.2). MEASUREMENTS: Development Sample, Validation Sample I-BLSA, and Validation Sample II-LLFS participants self-administered the 10-item Pittsburgh Fatigability Scale. Validation Sample II-LLFS completed cognition measures (Trail Making Tests A and B), depressive symptomatology (Center for Epidemiologic Studies-Depression Scale, CES-D), and global fatigue from two CES-D items. RESULTS: In the Development Sample and Validation Sample I-BLSA, confirmatory factor analysis showed all 10 items loaded on two factors: social and physical activities (fit indices: SRMSR = 0.064, RMSEA = 0.095, CFI = 0.91). PFS Mental scores had strong internal consistency (Cronbach's α = 0.85) and good test-retest reliability (ICC = 0.78). Validation Sample II-LLFS PFS Mental scores demonstrated moderate concurrent and construct validity using Pearson (r) or Spearman (ρ) correlations against measures of cognition (Trail Making Tests A (r = 0.14) and B (r = 0.17) time), depressive symptoms (r = 0.31), and global fatigue (ρ = 0.21). Additionally, the PFS Mental subscale had strong convergent validity, discriminating according to established clinical or cognitive testing cut points, with differences in PFS Mental scores ranging from 3.9 to 7.6 points (all P < .001). All analyses were adjusted for family relatedness, field center, age, sex, and education. CONCLUSIONS: The validated PFS Mental subscale may be used in clinical and research settings as a sensitive, one-page self-administered tool of perceived mental fatigability in older adults.

Predicting task performance from biomarkers of mental fatigue in global brain activity.

Objective.Detection and early prediction of mental fatigue (i.e. shifts in vigilance), could be used to adapt neuromodulation strategies to effectively treat patients suffering from brain injury and other indications with prominent chronic mental fatigue.Approach.In this study, we analyzed electrocorticography (ECoG) signals chronically recorded from two healthy non-human primates (NHP) as they performed a sustained attention task over extended periods of time. We employed a set of spectrotemporal and connectivity biomarkers of the ECoG signals to identify periods of mental fatigue and a gradient boosting classifier to predict performance, up to several seconds prior to the behavioral response.Main results.Wavelet entropy and the instantaneous amplitude and frequency were among the best single features across sessions in both NHPs. The classification performance using higher order spectral-temporal (HOST) features was significantly higher than that of conventional spectral power features in both NHPs. Across the 99 sessions analyzed, average F1 scores of 77.5% ± 8.2% and 91.2% ± 3.6%, and accuracy of 79.5% ± 8.9% and 87.6% ± 3.9% for the classifier were obtained for each animal, respectively.Significance.Our results here demonstrate the feasibility of predicting performance and detecting periods of mental fatigue by analyzing ECoG signals, and that this general approach, in principle, could be used for closed-loop control of neuromodulation strategies.

Exploratory factor analysis and validity of the virtual reality symptom questionnaire and computer use survey.

The widespread use of virtual reality head-mounted-displays (HMDs) calls for a re-examination of the impact of prolonged exposure to fixed visual displays at close ocular proximity. The purpose of this study is to validate the Virtual Reality Symptoms Questionnaire (VRSQ), created to understand symptoms of prolonged HMDs use, and Computer Use Survey (CUS), created to assess general physical and visual discomfort symptoms. Participants (N = 100) recorded their general discomfort symptoms using the CUS, performed an interactive task using a HMD for thirty minutes, and then answered the CUS again along with the VRSQ. VRSQ, analysed using an exploratory factor analysis, indicated a clear two-factor solution, and demonstrated very good internal consistency (α = 0.873). The CUS, also analysed using an exploratory factor analysis, indicated a four-factor solution, and demonstrated good internal consistency (α = 0.838). Practitioner Summary: A quantitative-experimental study was conducted to explore the factor structure and validate both the Virtual Reality Symptoms Questionnaire (VRSQ), and the Computer Use Survey (CUS). Findings indicate the VRSQ and CUS are precise and accurate survey instruments for evaluating discomfort after VR-HMD use and the latter for computer use. Abbreviations: VRSQ: virtual reality symptom questionnaire; CUS: computer use survey; OLED: organic light-emitting diode; MSQ: pensacola motion symptom questionnaire; SSQ: simulator sickness questionnaire; 3 D: three-dimensional computer generated space; VR: virtual reality; VR-HMD: virtual reality head-mounted-display; HMDs: head-mounted-displays; EFA: exploratory factor analysis.

Audio, Visual, and Electrodermal Arousal Signals as Predictors of Mental Fatigue Following Sustained Cognitive Work.

Lapses in vigilance and slowed reactions due to mental fatigue can increase risk of accidents and injuries and degrade performance. This paper describes a method for rapid, unobtrusive detection of mental fatigue based on changes in electrodermal arousal (EDA), and changes in neuromotor coordination derived from speaking. Twenty-nine Soldiers completed a 2-hour battery of cognitive tasks intended to induce fatigue. Behavioral markers derived from audio and video during speech were acquired before and after the 2hour cognitive load tasks, as was EDA. Exposure to cognitive load produced detectable increases in neuromotor variability in speech and facial measures after load and even after a recovery period. A Gaussian mixture model classifier with crossvalidation and fusion across speech, video, and EDA produced an accuracy of AUC=0.99 in detecting a change in cognitive fatigue relative to a personalized baseline.