The aim of this chapter is to identify the most representative measures of subjective and objective mental workload in driving, and to understand how the subjective and objective levels of mental workload influence the performance as a function of situation complexity and driving experience, i.e. to verify whether the increase of situation complexity and the lack of experience increase the subjective and physiological levels of mental workload and lead to driving performance impairments. This chapter will be useful (...) to carry out an experimental study and to improve the driver training. In the first part, we will broach the theoretical approach with two factors of mental workload and performance, i.e. situation complexity and driving experience. Indeed, a low complex situation (e.g., highways), or conversely a high complex situation (e.g., town) can provoke an overload. Additionally, performing the driving tasks implies producing a high effort for novice drivers who have not totally automated the driving activity. In the second part, we will focus on subjective measures of mental workload. A comparison of questionnaires usually used in driving will allow identifying the most appropriate ones as a function of different criteria. Moreover, we will review the empirical studies to verify if the subjective level of mental workload is high in simple and very complex situations, especially for novice drivers compared to the experienced ones. In the third part, we will focus on physiological measures. A comparison of physiological indicators will be realized in order to identify the most correlated to mental workload. An empirical review will also take the effect of situation complexity and experience on these physiological indicators into consideration. Finally, a more nuanced comparison between subjective and physiological measures will be established from the impact on situation complexity and experience. (shrink)

The paper analyses the problem of workload quotas for district court judges in relation to the standard statutory work time duration. The problem is set against the general tendency of increase in the number of cases brought before courts each year. District courts as the courts of first instance are faced with an ever growing flow of cases. With regard to civil cases, the numbers are increasing especially in the field of the law of obligations (disputes in relation to (...) sale, loan, credit, consumer credit, lease contracts, as well as contracts for the provision of services, etc.). As far as criminal cases are concerned, the numbers are increasing especially in the fields of robbery, theft, in particular car theft, disturbance of public order and other crimes. In these circumstances, it is extremely important to conduct the analysis of the activity of courts in order to obtain a picture of the current situation with regard to the workload of courts and judges. District courts deserve special attention. Uneven distribution of workload among courts and judges is often the reason for the increase of the number of cases where a final decision (judgement) is reached later than 6 months after the start of proceedings. This was pointed out in the Overview of Activities of the Lithuanian Courts and their Self-Governance Institutions (2009–2010), as well as in the report of the National Courts Administration (2010). Those documents underline the importance to analyse the workload of district court judges for the purposes of optimising work organisation, setting the number of judges, distribution of resources, evaluation of judges’ activity, etc. The said analysis is crucial in order to avoid exceeding working time quotas and excessive workload of judges. At present, the workload of district court judges is calculated in accordance with the regulation adopted by the Courts Council in 2004 (as amended in 2005) and it reflects the number of standard cases (civil, criminal cases and cases of administrative offences) as well as other types of procedural documents dealt with by a judge within a period of one month. However, there are no quotas set for judge’s workload with regard to the duration of the statutory work time. The quotas for separate procedural stages (preparation for hearings, hearings, adoption of decision (judgement), other procedural actions that a judge performs while administering justice) are inexistent. The calculation does not take into account whether those standard cases are heard by a single judge or by a panel of judges, the complexity of a particular case is neither reflected. Establishing quotas for district court judges and other court clerks (judge assistants, secretaries, etc.) should consist of legal, organisational-procedural and technical-economical activity. The Ministry of Justice of the Republic of Lithuania, the National Courts Administration, the Courts Council as well as chairmen and experienced judges of district courts should play an active part in the process of establishing quotas. A special role should be assumed by the General Assembly of Judges. (shrink)

Changing and often class-dependent non-stationarities of signals are a big challenge in the transfer of common findings in cognitive workload estimation using Electroencephalography (EEG) from laboratory experiments to realistic scenarios or other experiments. Additionally, it often remains an open question whether actual cognitive workload reflected by brain signals was the main contribution to the estimation or discriminative and class-dependent muscle and eye activity, which can be secondary effects of changing workload levels. Within this study, we investigated a (...) novel approach to spatial filtering based on beamforming adapted to changing settings. We compare it to no spatial filtering and Common Spatial Patterns (CSP). We used a realistic maneuvering task, as well as an auditoryn-backsecondary task on a tugboat simulator as two different conditions to induce workload changes on professional tugboat captains. Apart from the typical within condition classification, we investigated the ability of the different classification methods to transfer between then-backcondition and the maneuvering task. The results show a clear advantage of the proposed approach over the others in the challenging transfer setting. While no filtering leads to lowest within-condition normalized classification loss on average in two scenarios (22 and 10%), our approach using adaptive beamforming (30 and 18%) performs comparably to CSP (33 and 15%). Importantly, in the transfer from one to another setting, no filtering and CSP lead to performance around chance level (45 to 53%), while our approach in contrast is the only one capable of classifying in all other scenarios (34 and 35%) with a significant difference from chance level. The changing signal composition over the scenarios leads to a need to adapt the spatial filtering in order to be transferable. With our approach, the transfer is successful due to filtering being optimized for the extraction of neural components and additional investigation of their scalp patterns revealed mainly neural origin. Interesting findings are that rather the patterns slightly change between conditions. We conclude that the approaches with low normalized loss depend on eye and muscle activity which is successful for classification within conditions, but fail in the classifier transfer since eye and muscle contributions are highly condition-specific. (shrink)

We studied the capability of a Hybrid functional neuroimaging technique to quantify human mental workload (MWL). We have used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) as imaging modalities with 17 healthy subjects performing the letter n -back task, a standard experimental paradigm related to working memory (WM). The level of MWL was parametrically changed by variation of n from 0 to 3. Nineteen EEG channels were covering the whole-head and 19 fNIRS channels were located on the forehead to (...) cover the most dominant brain region involved in WM. Grand block averaging of recorded signals revealed specific behaviors of oxygenated-hemoglobin level during changes in the level of MWL. A machine learning approach has been utilized for detection of the level of MWL. We extracted different features from EEG, fNIRS, and EEG+fNIRS signals as the biomarkers of MWL and fed them to a linear support vector machine (SVM) as train and test sets. These features were selected based on their sensitivity to the changes in the level of MWL according to the literature. We introduced a new category of features within fNIRS and EEG+fNIRS systems. In addition, the performance level of each feature category was systematically assessed. We also assessed the effect of number of features and window size in classification performance. SVM classifier used in order to discriminate between different combinations of cognitive states from binary- and multi-class states. In addition to the cross-validated performance level of the classifier other metrics such as sensitivity, specificity, and predictive values were calculated for a comprehensive assessment of the classification system. The Hybrid (EEG+fNIRS) system had an accuracy that was significantly higher than that of either EEG or fNIRS. Our results suggest that EEG+fNIRS features combined with a classifier are capable of robustly discriminating among various levels of MWL. Results suggest that EEG+fNIRS should be preferred to only EEG or fNIRS, in developing passive BCIs and other applications which need to monitor users' MWL. (shrink)

Car driving is considered a very complex activity, consisting of different concomitant tasks and subtasks, thus it is crucial to understand the impact of different factors, such as road complexity, traffic, dashboard devices, and external events on the driver’s behavior and performance. For this reason, in particular situations the cognitive demand experienced by the driver could be very high, inducing an excessive experienced mental workload and consequently an increasing of error commission probability. In this regard, it has been demonstrated (...) that human error is the main cause of the 57 % of road accidents and a contributing factor in most of them. In this study, 20 young subjects were involved in a real driving experiment, performed under different traffic conditions (rush hour and not) and along different road types (main and secondary streets). Moreover, during the driving tasks different specific events, in particular a pedestrian crossing the road and a car entering the traffic flow just ahead of the experimental subject, were acted. A Workload Index based on the Electroencephalographic (EEG), i.e. brain activity, of the drivers has been employed to investigate the impact of the different factors on the driver’s workload. Eye-Tracking technology and subjective measures were also employed in order to have a comprehensive overview of the driver’s perceived workload and to investigate the different insights obtainable from the employed methodologies. The employment of such EEG-based Workload index confirmed the significant impact of both traffic and road types on the drivers’ behavior (increasing their workload), with the advantage of being under real settings. Also, it allowed to highlight the increased workload related to external events while driving, in particular with a significant effect during those situations when the traffic was low. Finally, the comparison between methodologies revealed the higher sensitivity of neurophysiological measures with respect to Eye-Tracking and subjective ones. In conclusion, such an EEG-based Workload index would allow to assess objectively the mental workload experienced by the driver, standing out as a powerful tool for research aimed to investigate drivers’ behavior and providing additional and complementary insights with respect to traditional methodologies employed within road safety research. (shrink)

Injuries in professional soccer are a significant concern for teams, and they are caused amongst others by high training load. This cohort study describes the relationship between workload parameters and the occurrence of non-contact injuries, during weeks with high and low workload in professional soccer players throughout the season. Twenty-one professional soccer players aged 28.3 ± 3.9 yrs. who competed in the Iranian Persian Gulf Pro League participated in this 48-week study. The external load was monitored using global (...) positioning system and the type of injury was documented daily by the team's medical staff. Odds ratio and relative risk were calculated for non-contact injuries for high- and low-load weeks according to acute, chronic, acute to chronic workload ratio, and AW variation values. By using Poisson distribution, the interval between previous and new injuries were estimated. Overall, 12 non-contact injuries occurred during high load and 9 during low load weeks. Based on the variables ACWR and Δ-AW, there was a significantly increased risk of sustaining non-contact injuries during high-load weeks for ACWR, and Δ-AW. Finally, the expected time between injuries was significantly shorter in high load weeks for ACWR [1.25 vs. 3.33, rate ratio time ] and Δ-AW respectively, compared to low load weeks. The risk of sustaining injuries was significantly larger during high workload weeks for ACWR, and Δ-AW compared with low workload weeks. The observed high OR in high load weeks indicate that there is a significant relationship between workload and occurrence of non-contact injuries. The predicted time to new injuries is shorter in high load weeks compared to low load weeks. Therefore, the frequency of injuries is higher during high load weeks for ACWR and Δ-AW. ACWR and Δ-AW appear to be good indicators for estimating the injury risk, and the time interval between injuries. (shrink)

Physicians play a substantial role in facilitating communication regarding life-supporting treatment decision-making including do-not-resuscitate in the intensive care units. Physician-related fact...

Background Many studies have investigated the adherence to professional codes of ethics by nurses. However, no study has explicitly examined the relationship between workload and adherence to professional codes of ethics among Iranian nurses. Objective This study aimed to explore the relationships between workload and adherence to professional codes of ethics among a sample of Iranian nurses. Materials and Methods A cross-sectional descriptive study was conducted on 213 nurses who were randomly selected from the different wards of Shahid (...) Beheshti Hospital of Kashan, Iran. Data collection instruments included a personal characteristics questionnaire, the Nursing Ethics Questionnaire, and the National Aeronautics and Space Administration Task Load Index. The Chi-square, the Spearman correlation coefficient, the Kruskal–Wallis, and Mann–Whitney U tests were used to analyze the data. Results A majority of nurses were females, married, and permanently employed. The mean of the overall perceived workload and adherence to professional codes of ethics were 76.36 ± 13.64 and 13.98 ± 2.58, that were at high and moderated level, respectively. Spearman correlation test showed no significant correlation between perceived workload and adherence to professional codes of ethics. A significant difference was found between the mean scores of adherence to professional codes of ethics in nurses working in different departments. Conclusion Participating nurses perceived high levels of workload but their mean adherence to professional codes of ethics was at a moderate level. The perceived workload was indirectly correlated with adherence to professional codes of ethics. (shrink)

The radical changes deriving from the COVID-19 emergency have heavily upset some of the most familiar routines of daily work life. Abruptly, many workers have been forced to face the difficulties that come with switching to remote working. Basing on the theoretical framework proposed by the Job Demands-Resources model, the purpose of this paper was to explore the effect of work overload, on behavioral stress, meant as an outcome linked to the health impairment process. Furthermore, the aim of the study (...) was to explore the mediating role of job crafting, considered as a second-order construct consisting of two dimensions in the abovementioned relation. Participants were 530 workers experiencing remote working or work-from-home during the first COVID-19 lockdown in Italy. Hypotheses were explored by using three different latent variables, measured reflexively through indicators on a 5-point scale, extracted from validated questionnaires. Data analysis was performed through Structural Equation Modeling; to test the mediation, bootstrap validation was computed. Results showed that the mediation of job crafting was partial. More specifically, the direct effect between work overload and behavioral stress was positive; moreover, the indirect, negative effect through the mediation of job crafting was also significant. Therefore, results showed that job crafting can play a crucial role as a protective factor supporting the activation and adjustment of suitable resources; these resources can be useful to deal with the negative effects of work overload, particularly under the condition of heavy remote working and use of technologies, on individual outcomes. Starting from the current global scenario of the pandemic that has not yet ceased its effects, the study suggested decisive theoretical and practical implications. Accordingly, findings extended the current trends in occupational health psychology research, with special reference to the mainstream topic “work and COVID-19” in the Italian context. Finally, results can give suggestions to companies engaged in managing change, recommending that they build a collaborative workplace at the individual and collective level to implement job crafting interventions and enrich the personal and organizational resources of workers, which is useful cope with the current demands. (shrink)

Human mental workload is arguably the most invoked multidimensional construct in Human Factors and Ergonomics, getting momentum also in Neuroscience and Neuroergonomics. Uncertainties exist in its characterization, motivating the design and development of computational models, thus recently and actively receiving support from the discipline of Computer Science. However, its role in human performance prediction is assured. This work is aimed at providing a synthesis of the current state of the art in human mental workload assessment through considerations, definitions, (...) measurement techniques as well as applications, Findings suggest that, despite an increasing number of associated research works, a single, reliable and generally applicable framework for mental workload research does not yet appear fully established. One reason for this gap is the existence of a wide swath of operational definitions, built upon different theoretical assumptions which are rarely examined collectively. A second reason is that the three main classes of measures, which are self-report, task performance, and physiological indices, have been used in isolation or in pairs, but more rarely in conjunction all together. Multiple definitions complement each another and we propose a novel inclusive definition of mental workload to support the next generation of empirical-based research. Similarly, by comprehensively employing physiological, task-performance, and self-report measures, more robust assessments of mental workload can be achieved. (shrink)

A lot of research has been done on the detection of mental workload using various bio-signals. Recently, deep learning has allowed for novel methods and results. A plethora of measurement modalities have proven to be valuable in this task, yet studies currently often only use a single modality to classify MWL. The goal of this research was to classify perceived mental workload using a deep neural network that flexibly makes use of multiple modalities, in order to allow for (...) feature sharing between modalities. To achieve this goal, an experiment was conducted in which MWL was simulated with the help of verbal logic puzzles. The puzzles came in five levels of difficulty and were presented in a random order. Participants had 1 h to solve as many puzzles as they could. Between puzzles, they gave a difficulty rating between 1 and 7, seven being the highest difficulty. Galvanic skin response, photoplethysmograms, functional near-infrared spectrograms and eye movements were collected simultaneously using LabStreamingLayer. Marker information from the puzzles was also streamed on LSL. We designed and evaluated a novel intermediate fusion multimodal DNN for the classification of PMWL using the aforementioned four modalities. Two main criteria that guided the design and implementation of our DNN are modularity and generalisability. We were able to classify PMWL within-level accurate on a seven-level workload scale using the aforementioned modalities. The model architecture allows for easy addition and removal of modalities without major structural implications because of the modular nature of the design. Furthermore, we showed that our neural network performed better when using multiple modalities, as opposed to a single modality. The dataset and code used in this paper are openly available. (shrink)

Radiation therapy therapists face challenging daily tasks that leave them prone to high attrition and burnout and subsequent deficits in performance. Here, we employed an accelerated alpha-theta neurofeedback protocol that is implementable in a busy medical workplace to test if 12 RTTs could learn the protocol and exhibit behavior and brain performance-related benefits. Following the 3-week protocol, participants showed a decrease in subjective cognitive workload and a decrease in response time during a performance task, as well as a decrease (...) in desynchrony of the alpha electroencephalogram band. Additionally, novel microstate analysis for neurofeedback showed a significant decrease in global field power following neurofeedback. These results suggest that the RTTs successfully learned the protocol and improved in perceived cognitive workload following 3 weeks of neurofeedback. In sum, this study presents promising behavioral improvements as well as brain performance-related evidence of neurophysiological changes following neurofeedback, supporting the feasibility of implementing neurofeedback in a busy workplace and encouraging the further study of neurofeedback as a tool to mitigate burnout. (shrink)

The study aim was 2-fold (i) to describe and compare the in-season variations of acute: chronic workload ratio (ACWR) coupled, ACWR uncoupled, and exponentially weighted moving average (EWMA) through session-rated perceived exertion (s-RPE), total distance (TD), high-speed running distance (HSRD), and sprint distance across different periods of a professional soccer season (early, mid, and end-season) between starters and non-starters; (ii) to analyze the relationship the aforementioned measures across different periods of the season for starters and non-starters. Twenty elite soccer (...) players (mean ± SD age, 29.4 ± 4.4 y; height, 1.8 ± 0.1 m; and body mass, 74.8 ± 2.3 kg). They were divided into starter and non-starter groups and were evaluated for 20 weeks. ACWR had general changes throughout the season. At the beginning and end of the mid-season, the highest ACWR was observed in three parameters: s-RPE, TD, and HSRD. ACWR and EWMA through sprint distance were higher at the beginning of the early-season than at any other time of the season.The ACWR coupled of s-RPE shows a significant higher value for non-starters than starters (p = 0.015;g = −1.01 [−1.98, −0.09]) and the ACWR coupled of TD shows a significant higher value for starters than non-starters in early-season (p < 0.01;g = 3.01 [1.78, 4.46]) and shows a significant higher value for non-starters than starters in mid-season (p < 0.01;g = −2.52 [−3.83, −1.39]), and end-season (p < 0.01;g = −2.57 [−3.89, −1.43]). While the EWMA of TD shows a significant higher value for starters than non-starters in early-season (p < 0.01;g = 2.25 [1.17, 3.49]) and mid-season (p < 0.01;g = 2.42 [1.31, 3.71]), and shows a significant higher value for non-starters than starters in end-season (p < 0.01;g = −2.23 [−3.47, −1.16]). Additionally, we found some correlations between external and internal load measures during three periods of the in-season. The study’s main finding was that the indexes of ACWR and EWMA were useful to detect differences between period and between playing status with the exception for the sprint variable. In addition, the necessary work for non-starter players’ improvement is not done during training, and these players lose their readiness as the season progresses. Consequently, these players perform poorly during the match. Therefore, coaches and their staff should consider devising new activities to keep non-starter players physically fit. This deficit must be accounted for in training because they compete in fewer matches and have less burden than starters. (shrink)

Background: Walking while performing a secondary task walking) increases cognitive workload in young adults. To date, few studies have used neurophysiological measures in combination to subjective measures to assess cognitive workload during a walking task. This combined approach can provide more insights into the amount of cognitive resources in relation with the perceived mental effort involving in a walking task.Research Question: The objective was to examine cognitive workload in young adults during walking conditions varying in complexity.Methods: Twenty-five (...) young adults performed four conditions: usual walking, simple DT walking, complex DT walking and standing while subtracting. During the walking task, mean speed, cadence, stride time, stride length, and their respective coefficient of variation were recorded. Cognitive workload will be measured through changes in oxy- and deoxy-hemoglobin during walking in the dorsolateral prefrontal cortex and perceived mental demand score from NASA-TLX questionnaire.Results: In young adults, ΔHbO2 in the DLPFC increased from usual walking to both DT walking conditions and standing while subtracting condition. ΔHbO2 did not differ between the simple and complex DT and between the complex DT and standing while subtracting condition. Perceived mental demand gradually increased with walking task complexity. As expected, all mean values of gait parameters were altered according to task complexity. CV of speed, cadence and stride time were significantly higher during DT walking conditions than during usual walking whereas CV of stride length was only higher during complex DT walking than during usual walking.Significance: Young adults had greater cognitive workload in the two DT walking conditions compared to usual walking. However, only the mental demand score from NASA-TLX questionnaire discriminated simple from complex DT walking. Subjective measure provides complementary information to objective one on changes in cognitive workload during challenging walking tasks in young adults. These results may be useful to improve our understanding of cognitive workload during walking. (shrink)

The use of automation in cars is increasing. In future vehicles, drivers will no longer be in charge of the main driving task and may be allowed to perform a secondary task. However, they might be requested to regain control of the car if a hazardous situation occurs. Performing a secondary task might increase drivers' mental workload and consequently decrease the takeover performance if the workload level exceeds a certain threshold. Knowledge about the driver's mental state might hence (...) be useful for increasing safety in conditionally automated vehicles. Measuring drivers' workload continuously is essential to support the driver and hence limit the number of accidents in takeover situations. This goal can be achieved using machine learning techniques to evaluate and classify the drivers' workload in real-time. To evaluate the usefulness of physiological data as an indicator for workload in conditionally automated driving, three physiological signals from 90 subjects were collected during 25 min of automated driving in a fixed-base simulator. Half of the participants performed a verbal cognitive task to induce mental workload while the other half only had to monitor the environment of the car. Three classifiers, sensor fusion and levels of data segmentation were compared. Results show that the best model was able to successfully classify the condition of the driver with an accuracy of 95%. In some cases, the model benefited from sensors' fusion. Increasing the segmentation level increased the performance of the model for windows smaller than 4 min, but decreased for windows larger than 4 min. In conclusion, the study showed that a high level of drivers' mental workload can be accurately detected while driving in conditional automation based on 4-min recordings of respiration and skin conductance. (shrink)

At the present time, we know that there is a positive relationship between self-efficacy and self-esteem in which positive beliefs about one’s own efficacy increase one’s sense of self-worth as stressful situations of a heavy workload are coped with successfully, and this, in turn, affects the nurses' plans to work longer. Analyze the mediating role of self-efficacy and self-esteem in the effect of workload, measured as the number of users attended to during a workday, on burnout in nursing (...) professionals. A sample of 1307 nurses aged 22 to 60 years who were administered the Brief Burnout Questionnaire, the General Self-Efficacy Scale and the Rosenberg Self-Esteem Scale, and workload, measured as the number of users attended to during the workday. The results show that professionals with high levels of self-efficacy also scored higher on global self-esteem. Burnout correlated negatively with both variables (Self-efficacy and Self-esteem). Three clusters were found with the variables (Self-efficacy, Self-esteem and Workload) showing significant differences in burnout scores among clusters. Self-efficacy and self-esteem function as buffers of the negative effects of workload on burnout. Organizations should design interventions for promoting the personal resources of their workers through training activities and organizational resources (e.g., redesigning job positions) to promote satisfaction and wellbeing of employees, making their stay at work greater. (shrink)

Faculty workload inequities have important consequences for faculty diversity and inclusion. On average, women faculty spend more time engaging in service, teaching, and mentoring, while men, on average, spend more time on research, with women of color facing particularly high workload burdens. We explore how faculty members perceive workload in their departments, identifying mechanisms that can help shape their perceptions of greater equity and fairness. White women perceive that their departments have less equitable workloads and are less (...) committed to workload equity than white men. Women of color perceive that their departments are less likely to credit their important work through departmental rewards systems than white men. Workload transparency and clarity, and consistent approaches to assigning classes, advising, and service, can reduce women’s perceptions of inequitable and unfair workloads. Our research suggests that departments can identify and put in place a number of key practices around workload that will improve gendered and racialized perceptions of workload. (shrink)

Enacting fairness remains a persistent challenge for managers, prompting the need to understand how they can better treat their subordinates. Addressing this challenge, we investigate whether, how, and when mindfulness facilitates managers’ adherence to fairness. Through the lens of Social Cognitive Theory, we frame mindfulness as a metacognitive skill and propose that it enhances managers’ enactment of justice by fostering their moral potency, while this effect is diminished under high-workload conditions. We tested these ideas across two studies. Study 1 (...) (N = 201), an experiment conducted with graduate business students from cooperative education programs, showed that a brief 15-min mindfulness intervention significantly increased moral potency relative to an active control condition, providing causal evidence for the proposed mechanism. Study 2 (N = 419), a three-wave study of managers in the United States and the United Kingdom, offered full support for the overall moderated mediation model. Together, these studies advance the mindfulness and justice literature by clarifying moral implications and contextual boundaries of mindfulness. (shrink)

Behavioral and physiological synchronization have important implications for work teams with regard to workload management, coordinated behavior and overall functioning. This study extended previous work on the nonlinear statistical structure of GSR series in dyads to larger teams and included subjective ratings of workload and contributions to problem solving. Eleven teams of 3 or 4 people played a series of six emergency response (ER) games against a single opponent. Seven of the groups worked under a time pressure instruction (...) at the beginning of the first game. The other four groups were not given that instruction until the beginning of the fourth game. The optimal lag length for the teams, which appeared to be phase-locked, was substantially shorter than that obtained previously for loosely-coupled dyads. There was a complex nonlinear effect from the time pressure manipulation on the autocorrelation over time that reflected workload and fatigue dynamics that were operating. The R2 values for linear and nonlinear statistical models differed by less than.01. The average amount of influence from one ER team member to another was 4.5-4.7% of the variance in GSR readings. ER team members were classified as drivers and empaths, based on the autocorrelations and transfer influences to and from other players in the GSR time series. Empaths were rated by their peers as making more types of positive contributions to the problem solving discussions than others, and drivers received the lowest ratings. Larger Lyapunov exponents that were calculated from the GSR time series were positively correlated with individuals’ ratings of subjective workload and were negatively correlated with leadership indicators. Several directions for further research are outlined. (shrink)

This paper discusses the utilization of pilots' physiological indications such as electroencephalographic signals, ocular parameters, and pilot performance-based quantitative metrics to estimate cognitive workload. The study aims to derive a non-invasive technique to estimate pilot's cognitive workload and study their correlation with standard physiological parameters. Initially, we conducted a set of user trials using well-established psychometric tests for evaluating the effectiveness of pupil and gaze-based ocular metrics for estimating cognitive workload at different levels of task difficulty and (...) lighting conditions. Later, we conducted user trials with the NALSim flight simulator using a business class Learjet aircraft model. We analyzed participants' ocular parameters, power levels of different EEG frequency bands, and flight parameters for estimating variations in cognitive workload. Results indicate that introduction of secondary task increases pilot's cognitive workload significantly. The beta frequency band of EEG, nearest neighborhood index specifying distribution of gaze fixation, L1 Norm of power spectral density of pupil diameter, and the duty cycle metric indicated variations in cognitive workload. (shrink)

There are a number of key data-centric questions that must be answered when developing classifiers for operator functional states. “Should a supervised or unsupervised learning approach be used? What degree of labeling and transformation must be performed on the data? What are the trade-offs between algorithm flexibility and model interpretability, as generally these features are at odds?” Here, we focus exclusively on the labeling of cognitive load data for supervised learning. We explored three methods of labeling cognitive states for three-state (...) classification. The first method labels states derived from a tertiary split of trial difficulty during a spatial memory task. The second method was more adaptive; it employed a mixed-effects stress–strain curve and estimated an individual’s performance asymptotes with respect to the same spatial memory task. The final method was similar to the second approach; however, it employed a mixed-effects Rasch model to estimate individual capacity limits within the context of item response theory for the spatial memory task. To assess the strength of each of these labeling approaches, we compared the area under the curve (AUC) for receiver operating curves (ROCs) from elastic net and random forest classifiers. We chose these classifiers based on a combination of interpretability, flexibility, and past modeling success. We tested these techniques across two groups of individuals and two tasks to test the effects of different labeling techniques on cross-person and cross-task transfer. Overall, we observed that the Rasch model labeling paired with a random forest classifier led to the best model fits and showed evidence of both cross-person and cross-task transfer. (shrink)

In the study of human cognitive activity using electroencephalogram (EEG), the brain dynamics parameters and characteristics play a crucial role. They allow to investigate the changes in functionality depending on the environment and task performance process, and also to access the intensity of the brain activity in various locations of the cortex and its dependencies. Usually, the dynamics of activation of different brain areas during the cognitive tasks are being studied by spectral analysis based on power spectral density (PSD) estimation, (...) and coherence analysis, which are de facto standard tools in quantitative characterization of brain activity. PSD and coherence reflect the strength of oscillations and similarity of the emergence of these oscillations in the brain, respectively, while the concept of stability of brain activity over time is not well defined and less formalized. We propose to employ the detrended fluctuation analysis (DFA) as a measure of the EEG persistence over time, and use the DFA scaling exponent as its quantitative characteristics. We applied DFA to the study of the changes in activation in brain dynamics during mental calculations and united it with PSD and coherence estimation. In the experiment, EEGs during resting state and mental serial subtraction from 36 subjects were recorded and analyzed in four frequency ranges: θ1 (4.1–5.8 Hz), θ2 (5.9–7.4 Hz), β1 (13–19.9 Hz), and β2 (20–25 Hz). PSD maps to access the intensity of cortex activation and coherence to quantify the connections between different brain areas were calculated, the distribution of DFA scaling exponent over the head surface was exploited to measure the time characteristics of the dynamics of brain activity. Obtained arrangements of DFA scaling exponent suggest that normal functioning of the brain is characterized by long-term temporal correlations in the cortex. Topographical distribution of the DFA scaling exponent was comparable for θ and β frequency bands, demonstrating the largest values of DFA scaling exponent during cognitive activation. The study shows that the long-term temporal correlations evaluated by DFA can be of great interest for diagnosis of the variety of brain dysfunctions of different etiology in the future. (shrink)

Cognitive assessment and training through computerized methods are excellent concepts for maintaining cognitive function during occupational/operational challenges. Multitasking is required during various military operations, which creates a mental workload. Optimum working memory (visual, spatial, and auditory) capacity helps to maintain mental workload. The proposed research emphasizes assessing the mental workload using eye-tracking measures during a desktop-based dual N-back task comprising three sub-stages (n = 1, n = 2, n = 3). A wearable eye tracker was used to (...) acquire the eye tracking data from 29 individuals, and the NASA Task Load Index (NASA-TLx) Score was utilized to calculate the assessed mental workload. The study found associations between participant accuracy on the Dual N-Back test and Pupil Diameter, Shannon Entropy, and Fixation Count. These results expand our understanding of the cognitive mechanisms behind dual N-Back tasks and their connection to mental workload. Higher mental workload has been associated with lower fixation count and accuracy, as fixation count and accuracy showed inverse associations with workload. On the other hand, pupil diameter showed a positive association with workload, indicating that higher levels of mental workload were associated with larger pupil dilation. The K-Means Clustering Algorithm, Decision Tree, and Random Forest Classifiers were trained using the generated dataset, and the corresponding accuracies were also derived to use the study results conclusively. (shrink)

The Brazilian Supreme Court serves as the highest judicial authority in Brazil and is responsible for adjudicating constitutional matters presented as extraordinary appeals. These appeals undergo a rigorous screening process guided by established legal principles known as Topics of General Repercussion. Seeking to streamline this procedure, we developed LegalAnalytics to explore the research question: Can machine learning and explainable AI techniques enhance the classification of appeals in legal workflows? LegalAnalytics harnesses advanced natural language processing algorithms and classification models to categorize (...) each appeal according to the most pertinent topics accurately. In addition, it incorporates LIME (Local Interpretable Model-agnostic Explanations) to highlight the key sections of an appeal and compare them with relevant precedents. This approach ensures a transparent justification for every classification. The system is thoughtfully designed with a user-friendly interface tailored for public servants, judges, and lawyers. Extensive testing with dozens of legal experts confirmed the effectiveness of LegalAnalytics, with consistently positive feedback underscoring its significant practical impact. (shrink)