scholarly journals Classification of Drivers' Workload Using Physiological Signals in Conditional Automation

2021 ◽  
Vol 12 ◽  
Author(s):  
Quentin Meteier ◽  
Marine Capallera ◽  
Simon Ruffieux ◽  
Leonardo Angelini ◽  
Omar Abou Khaled ◽  
...  
Keyword(s):  
Secondary Task ◽  
Time Window ◽  
Mental Workload ◽  
Cognitive Task ◽  
Physiological Signals ◽  
Machine Learning Techniques ◽  
Physiological Data ◽  
Automated Driving ◽  
Physiological Indicators ◽  
High Level

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 (i.e., conditionally automated driving). 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 (e.g., size of the time window to compute physiological indicators) 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.

scholarly journals Multimodal Study of the Effects of Varying Task Load Utilizing EEG, GSR and Eye-Tracking

2019 ◽  
Author(s):  
Jannis Born ◽  
Babu Ram Naidu Ramachandran ◽  
Sandra Alejandra Romero Pinto ◽  
Stefan Winkler ◽  
Rama Ratnam
Keyword(s):  
Eye Tracking ◽  
Task Performance ◽  
Mental Workload ◽  
Cognitive Task ◽  
Physiological Data ◽  
Postal Code ◽  
Subjective Data ◽  
Task Load ◽  
Minimum Number ◽  
Participant Response

AbstractObjectiveThe effect of task load on performance is investigated by simultaneously collecting multi-modal physiological data and participant response data. Periodic response to a questionnaire is also obtained. The goal is to determine combinations of modalities that best serve as predictors of task performance.ApproachA group of participants performed a computer-based visual search task mimicking postal code sorting. A five-digit number had to be assigned to one of six different non-overlapping numeric ranges. Trials were presented in blocks of progressively increasing task difficulty. The participants’ responses were collected simultaneously with 32 channels of electroencephalography (EEG) data, eye-tracking data, and Galvanic Skin Response (GSR) data. The NASA Task-Load-Index self-reporting instrument was administered at discrete time points in the experiment.Main resultsLow beta frequency EEG waves (12.5-18 Hz) were more prominent as cognitive task load increased, with most activity in frontal and parietal regions. These were accompanied by more frequent eye blinks and increased pupillary dilation. Blink duration correlated strongly with task performance. Phasic components of the GSR signal were related to cognitive workload, whereas tonic components indicated a more general state of arousal. Subjective data (NASA TLX) as reported by the participants showed an increase in frustration and mental workload. Based on one-way ANOVA, EEG and GSR provided the most reliable correlation to perceived workload level and were the most informative measures (taken together) for performance prediction.SignificanceNumerous modalities come into play during task-related activity. Many of these modalities can provide information on task performance when appropriately grouped. This study suggests that while EEG is a good predictor of task performance, additional modalities such as GSR increase the likelihood of more accurate predictions. Further, in controlled laboratory conditions, the most informative or minimum number of modalities can be isolated for monitoring in real work environments.

OpiTrack

2021 ◽  
Vol 5 (3) ◽  
pp. 1-29
Author(s):  
Bhanu Teja Gullapalli ◽  
Stephanie Carreiro ◽  
Brittany P. Chapman ◽  
Deepak Ganesan ◽  
Jan Sjoquist ◽  
...  
Keyword(s):  
Time Window ◽  
Electrodermal Activity ◽  
Clinical Care ◽  
Opioid Use Disorder ◽  
Physiological Signals ◽  
Physiological Data ◽  
Opioid Use ◽  
Painful Condition ◽  
Targeted Interventions ◽  
Opioid Administration

Opioid use disorder is a medical condition with major social and economic consequences. While ubiquitous physiological sensing technologies have been widely adopted and extensively used to monitor day-to-day activities and deliver targeted interventions to improve human health, the use of these technologies to detect drug use in natural environments has been largely underexplored. The long-term goal of our work is to develop a mobile technology system that can identify high-risk opioid-related events (i.e., development of tolerance in the setting of prescription opioid use, return-to-use events in the setting of opioid use disorder) and deploy just-in-time interventions to mitigate the risk of overdose morbidity and mortality. In the current paper, we take an initial step by asking a crucial question: Can opioid use be detected using physiological signals obtained from a wrist-mounted sensor? Thirty-six individuals who were admitted to the hospital for an acute painful condition and received opioid analgesics as part of their clinical care were enrolled. Subjects wore a noninvasive wrist sensor during this time (1-14 days) that continuously measured physiological signals (heart rate, skin temperature, accelerometry, electrodermal activity, and interbeat interval). We collected a total of 2070 hours (≈ 86 days) of physiological data and observed a total of 339 opioid administrations. Our results are encouraging and show that using a Channel-Temporal Attention TCN (CTA-TCN) model, we can detect an opioid administration in a time-window with an F1-score of 0.80, a specificity of 0.77, sensitivity of 0.80, and an AUC of 0.77. We also predict the exact moment of administration in this time-window with a normalized mean absolute error of 8.6% and R2 coefficient of 0.85.

scholarly journals Relevant Physiological Indicators for Assessing Workload in Conditionally Automated Driving, Through Three-Class Classification and Regression

2022 ◽  
Vol 3 ◽  
Author(s):  
Quentin Meteier ◽  
Emmanuel De Salis ◽  
Marine Capallera ◽  
Marino Widmer ◽  
Leonardo Angelini ◽  
...  
Keyword(s):  
Task Performance ◽  
Cognitive Task ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Automated Driving ◽  
Mental Load ◽  
Sinus Arrhythmia ◽  
Physiological Indicators ◽  
Task Modality

In future conditionally automated driving, drivers may be asked to take over control of the car while it is driving autonomously. Performing a non-driving-related task could degrade their takeover performance, which could be detected by continuous assessment of drivers' mental load. In this regard, three physiological signals from 80 subjects were collected during 1 h of conditionally automated driving in a simulator. Participants were asked to perform a non-driving cognitive task (N-back) for 90 s, 15 times during driving. The modality and difficulty of the task were experimentally manipulated. The experiment yielded a dataset of drivers' physiological indicators during the task sequences, which was used to predict drivers' workload. This was done by classifying task difficulty (three classes) and regressing participants' reported level of subjective workload after each task (on a 0–20 scale). Classification of task modality was also studied. For each task, the effect of sensor fusion and task performance were studied. The implemented pipeline consisted of a repeated cross validation approach with grid search applied to three machine learning algorithms. The results showed that three different levels of mental load could be classified with a f1-score of 0.713 using the skin conductance and respiration signals as inputs of a random forest classifier. The best regression model predicted the subjective level of workload with a mean absolute error of 3.195 using the three signals. The accuracy of the model increased with participants' task performance. However, classification of task modality (visual or auditory) was not successful. Some physiological indicators such as estimates of respiratory sinus arrhythmia, respiratory amplitude, and temporal indices of heart rate variability were found to be relevant measures of mental workload. Their use should be preferred for ongoing assessment of driver workload in automated driving.

scholarly journals Cognitive Interaction Analysis in Human–Robot Collaboration Using an Assembly Task

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1317
Author(s):  
Alejandro Chacón ◽  
Pere Ponsa ◽  
Cecilio Angulo
Keyword(s):  
Interaction Analysis ◽  
Mental Workload ◽  
Cognitive Task ◽  
Physical Work ◽  
Work Skills ◽  
Dexterous Manipulation ◽  
Assembly Task ◽  
Cognitive Interaction ◽  
Human Operators ◽  
Assembly Tasks

In human–robot collaborative assembly tasks, it is necessary to properly balance skills to maximize productivity. Human operators can contribute with their abilities in dexterous manipulation, reasoning and problem solving, but a bounded workload (cognitive, physical, and timing) should be assigned for the task. Collaborative robots can provide accurate, quick and precise physical work skills, but they have constrained cognitive interaction capacity and low dexterous ability. In this work, an experimental setup is introduced in the form of a laboratory case study in which the task performance of the human–robot team and the mental workload of the humans are analyzed for an assembly task. We demonstrate that an operator working on a main high-demanding cognitive task can also comply with a secondary task (assembly) mainly developed for a robot asking for some cognitive and dexterous human capacities producing a very low impact on the primary task. In this form, skills are well balanced, and the operator is satisfied with the working conditions.

scholarly journals Early Detection of Exposure to Toxic Chemicals Using Continuously Recorded Multi-Sensor Physiology

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3616
Author(s):  
Jan Ubbo van Baardewijk ◽  
Sarthak Agarwal ◽  
Alex S. Cornelissen ◽  
Marloes J. A. Joosen ◽  
Jiska Kentrop ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Detection ◽  
Physiological Signals ◽  
Machine Learning Techniques ◽  
Detection Accuracy ◽  
Chemical Agent ◽  
Counter Measures ◽  
Detection And Identification ◽  
Life Saving ◽  
Future Work

Early detection of exposure to a toxic chemical, e.g., in a military context, can be life-saving. We propose to use machine learning techniques and multiple continuously measured physiological signals to detect exposure, and to identify the chemical agent. Such detection and identification could be used to alert individuals to take appropriate medical counter measures in time. As a first step, we evaluated whether exposure to an opioid (fentanyl) or a nerve agent (VX) could be detected in freely moving guinea pigs using features from respiration, electrocardiography (ECG) and electroencephalography (EEG), where machine learning models were trained and tested on different sets (across subject classification). Results showed this to be possible with close to perfect accuracy, where respiratory features were most relevant. Exposure detection accuracy rose steeply to over 95% correct during the first five minutes after exposure. Additional models were trained to correctly classify an exposed state as being induced either by fentanyl or VX. This was possible with an accuracy of almost 95%, where EEG features proved to be most relevant. Exposure detection models that were trained on subsets of animals generalized to subsets of animals that were exposed to other dosages of different chemicals. While future work is required to validate the principle in other species and to assess the robustness of the approach under different, realistic circumstances, our results indicate that utilizing different continuously measured physiological signals for early detection and identification of toxic agents is promising.

Use of a Secondary Task Methodology for Determining Acceptability of Flat-Panel Display Technologies in Consumer Environments

1983 ◽  
Vol 27 (5) ◽  
pp. 344-348
Author(s):  
Mark S. Hoffman ◽  
Martin L. Cramer
Keyword(s):  
Behavioral Problems ◽  
Secondary Task ◽  
Cognitive Task ◽  
Experimental Methodology ◽  
Human Information Processing ◽  
Primary Concern ◽  
Flat Panel Display ◽  
Flat Panel ◽  
Cost Constraints ◽  
Ambient Lighting

Flat-panel displays are used in consumer environments for displaying information where limits on content, physical space, power, and cost constraints are critical. Applications have traditionally included Retail Point-of-Service (POS) terminals. Most common flat-panel display technologies found in the consumer markets are Liquid Crystal Displays (LCDs), Plasma, and Vacuum Fluorescent displays. Emitting displays, i.e., Vacuum Fluorescent, Plasma, and LEDs were introduced into the marketplace with few reservations as to their general acceptance since normal ambient lighting conditions other than direct sunlight had minimal impact on readability. However, reflective display technologies, i.e., LCDs have not been widely accepted in POS products because of slower response times and a more restrictive range of ambient light needed to achieve acceptable viewing conditions. Many techniques used for determining the acceptability of a display technology for the POS environment presently used in industry are solely based upon the physical and functional performance characteristics of the display itself. This approach is similar to those used for evaluating video displays in that the primary concern is the stability of the displayed output for the intended user environment. Often these evaluations are conducted in a laboratory and therefore do not compare display performances relative to the intended end user. Even though this approach is cost-effective because the physical attributes of the display can be tailored to maximize readability, it does not consider the effect of the displayed information beyond the properties of the human visual system. Therefore, it would be desirable to develop an experimental methodology for evaluating flat-panel display technologies based upon human information processing capabilities. This requires using the information in cognitive task loadings equivalent to those experienced in the user environment. Studies comparing LCDs and Plasma display technologies were designed to construct a cognitive-perceptual model for usability assessment in the retail POS environment. A secondary task methodology was used to predict mental workload associated with each display. A Choice Reaction Time (CRT) paradigm proved to be an effective method for exploring cognitive-behavioral problems associated with the displays beyond those considered in the traditional methods of display evaluation.

scholarly journals Highly Automated Driving, Secondary Task Performance, and Driver State

2012 ◽  
Vol 54 (5) ◽  
pp. 762-771 ◽  
Author(s):  
Natasha Merat ◽  
A. Hamish Jamson ◽  
Frank C. H. Lai ◽  
Oliver Carsten
Keyword(s):  
Task Performance ◽  
Secondary Task ◽  
Automated Driving ◽  
Highly Automated Driving

The Effects of Practice on Navigation Performance and Mental Workload with a Mirror-In-The-Sky Map

2021 ◽  
Vol 65 (1) ◽  
pp. 1546-1550
Author(s):  
Holland M. Vasquez ◽  
Justin G. Hollands ◽  
Greg A. Jamieson
Keyword(s):  
Task Performance ◽  
Secondary Task ◽  
Mental Workload ◽  
Task Completion ◽  
Practice Performance ◽  
Global Ratings ◽  
Detection Response ◽  
Nasa Tlx ◽  
Response Task ◽  
Completion Times

Some previous research using a new augmented reality map display called Mirror-in-the-Sky (MitS) showed that performance was worse and mental workload (MWL) greater with MitS relative to a track-up map for navigation and wayfinding tasks. The purpose of the current study was to determine—for both MitS and track-up map—how much performance improves and MWL decreases with practice in a simple navigation task. We conducted a three-session experiment in which twenty participants completed a route following task in a virtual environment. Task completion times and collisions decreased, subjective MWL decreased, and secondary task performance improved with practice. The NASA-TLX Global ratings and Detection Response Task Hit Rates showed a larger decrease in MWL with MitS than the track-up map. Additionally, means for performance and workload measures showed that differences between the MitS and track-up map decreased in the first session. In later sessions the differences between the MitS and track-up map were negligible. As such, with practice performance and MWL may be comparable to a traditional track-up map.

Sign in / Sign up

Export Citation Format

Share Document