Towards the integration and evaluation of online workload measures in a cognitive architecture

Wortelen, Bertram; Unni, Anirudh; Rieger, Jochem W.; Lüdtke, Andreas

doi:10.1109/coginfocom.2016.7804516

Cited by 9 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we used a linear model for the predicting working memory load levels. However, Wortelen et al (2016) implementing working memory modeling in the cognitive architecture for safety critical task simulation (CASCaS) (Lüdtke et al, 2009), and testing the model on the same paradigm as we have used here, predict a compressive non-linearity for increasing workload levels. One reason for this compression could be that working memory is capacity limited (Miller, 1956; Baddeley, 2003) and therefore increases in task induced working memory load will lead to smaller increases in working memory load levels at high workload levels.…”

Section: Discussionmentioning

confidence: 99%

“…However, relying on peripheral physiology has the disadvantage that changes in arousal are not specific to working memory load, but are also integral to emotions such as anger or joy (Sander et al, 2005) and related to physical activity or fatigue (De Waard, 1996). In order to disentangle different types of workload (Wortelen et al, 2016) from emotional states, and to obtain more specific assessments of cognitive states, multidimensional brain activation measurements could be a promising complement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessing the Driver’s Current Level of Working Memory Load with High Density Functional Near-infrared Spectroscopy: A Realistic Driving Simulator Study

Unni

Ihme

Jipp

et al. 2017

Front. Hum. Neurosci.

Self Cite

View full text Add to dashboard Cite

Cognitive overload or underload results in a decrease in human performance which may result in fatal incidents while driving. We envision that driver assistive systems which adapt their functionality to the driver’s cognitive state could be a promising approach to reduce road accidents due to human errors. This research attempts to predict variations of cognitive working memory load levels in a natural driving scenario with multiple parallel tasks and to reveal predictive brain areas. We used a modified version of the n-back task to induce five different working memory load levels (from 0-back up to 4-back) forcing the participants to continuously update, memorize, and recall the previous ‘n’ speed sequences and adjust their speed accordingly while they drove for approximately 60 min on a highway with concurrent traffic in a virtual reality driving simulator. We measured brain activation using multichannel whole head, high density functional near-infrared spectroscopy (fNIRS) and predicted working memory load level from the fNIRS data by combining multivariate lasso regression and cross-validation. This allowed us to predict variations in working memory load in a continuous time-resolved manner with mean Pearson correlations between induced and predicted working memory load over 15 participants of 0.61 [standard error (SE) 0.04] and a maximum of 0.8. Restricting the analysis to prefrontal sensors placed over the forehead reduced the mean correlation to 0.38 (SE 0.04), indicating additional information gained through whole head coverage. Moreover, working memory load predictions derived from peripheral heart rate parameters achieved much lower correlations (mean 0.21, SE 0.1). Importantly, whole head fNIRS sampling revealed increasing brain activation in bilateral inferior frontal and bilateral temporo-occipital brain areas with increasing working memory load levels suggesting that these areas are specifically involved in workload-related processing.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessing the Driver’s Current Level of Working Memory Load with High Density Functional Near-infrared Spectroscopy: A Realistic Driving Simulator Study

Unni

Ihme

Jipp

et al. 2017

Front. Hum. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method is supported by findings that delta and beta band activity increases with cognitive workload [42], [43] while gamma band activity decreases, providing an objective metric of mental effort in response to a task. This technique allows an automated system to adapt to the workload level of a human operator, beneficial in industrial workplaces and safety critical environments such as human-machine operation [44].…”

Section: Related Work a Eeg In Human-machine Systemsmentioning

confidence: 99%

Investigating the P300 Response as a Marker of Working Memory in Virtual Training Environments

Simpson

Rafferty

2021

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

Conventional performance metrics fail to offer highresolution evaluation of learning and memory during training tasks; the P300 component of the event-related potential (ERP) is a promising tool for enhancing the assessment of training quality in virtual environments, but this technique is yet to be investigated. A driver training simulator and scenario were developed to explore the capability of the P300 for this purpose. A user study was conducted with 32 participants divided into 2 groups objectively determined by driving performance scores, thus enabling observations of the P300 response to be equated to varying levels of learning and memory. Participant electroencephalogram (EEG) data was recorded during the procedure, which was post-processed to filter and extract ERPs to capture neural responses to specific events in the virtual training scenario. These were combined to produce a result for each participant, which was then grand averaged to create an overall ERP for each group. Across the eight electrode sites statistically significant differences were found between the grand average waveforms of the two groups, with high memory retention producing significantly greater peak to peak amplitude (U = 9.00, p = .045), peak latency (U = 0.00, p < .001), and positive area (U = 13.00, p = .05) of the waveform than low memory retention. The evidenced relationship between the P300 response and working memory in this context suggests it has the potential for monitoring learning and memory in stimulus-driven virtual training systems.

show abstract

“…It can be connected to the SiVIC virtual road environment platform to provide very detailed input to a perceptual model of the virtual driver. A workload prediction method based on a cognitive architecture for safety critical task simulation (CASCaS) (Feuerstack et al, 2007) was used to assess the driver's workload in real-time, in order to enable adaptive automation (Wortelen et al, 2016). In contrast to cognitive simulation models, approaches based on task analysis are significantly less complex.…”

Section: Cognitive Simulation Modelsmentioning

confidence: 99%

A Discrete-Event Simulation Model for Driver Performance Assessment: Application to Autonomous Vehicle Cockpit Design Optimization

Iuskevich

Hein

Amokrane‐Ferka

et al. 2020

Proc. Des. Soc.: Des. Conf.

View full text Add to dashboard Cite

The latest advances in the design of vehicles with the adaptive level of automation pose new challenges in the vehicle-driver interaction. Safety requirements underline the need to explore optimal cockpit architectures with regard to driver cognitive and perceptual workload, eyes-off-the-road time and situation awareness. We propose to integrate existing task analysis approaches into system architecture evaluation for the early-stage design optimization. We built the discrete-event simulation tool and applied it within the multi-sensory (sight, sound, touch) cockpit design industrial project.

show abstract

Towards the integration and evaluation of online workload measures in a cognitive architecture

Cited by 9 publications

References 15 publications

Assessing the Driver’s Current Level of Working Memory Load with High Density Functional Near-infrared Spectroscopy: A Realistic Driving Simulator Study

Assessing the Driver’s Current Level of Working Memory Load with High Density Functional Near-infrared Spectroscopy: A Realistic Driving Simulator Study

Investigating the P300 Response as a Marker of Working Memory in Virtual Training Environments

A Discrete-Event Simulation Model for Driver Performance Assessment: Application to Autonomous Vehicle Cockpit Design Optimization

Contact Info

Product

Resources

About