Measuring Cognitive States Through Eye Movements
This article explores how eye movements can reveal mental states at work.
― 6 min read
Table of Contents
In many job settings, it’s crucial to know how people are thinking and feeling as they work. This includes understanding how much they can handle (workload), if they feel they need to act quickly (sense of urgency), and if their minds are wandering away from the task. These states can greatly affect how well a person performs their job, especially in safety-sensitive areas.
When a person is overloaded with tasks, they are more likely to make mistakes. Similarly, if someone starts daydreaming during an important task, they might miss something crucial. Therefore, figuring out how to measure these cognitive states is key to improving performance in both people and teams.
This article will discuss how these mental states can be identified using simple signs from our bodies, like how we move our eyes or how our brains and bodies respond quickly.
The Need for Understanding Cognitive States
Being able to accurately identify cognitive states can help us in various settings. For instance, in situations that require close attention, like driving or working in a control room, knowing if someone is feeling overwhelmed or distracted could allow for better support or adjustments in their tasks. This can help prevent errors that may arise from these cognitive states.
Additionally, for teams that include both humans and machines, understanding cognitive states can improve how these agents work together. If machines can sense when their human teammates are struggling, they can change their actions to help out, such as by reducing their workload or providing alerts.
To assess these cognitive states, researchers have looked into using signals from our bodies. These include movements of the eyes, Brain Activity, and other physiological responses.
The Three Key Cognitive States
Workload
Workload refers to how much mental effort is needed for someone to complete tasks. If a task is too hard or if there are too many tasks at once, the workload increases. This can create stress, which can affect how well a person performs.
Sense of Urgency
Sense of urgency is the feeling that something needs to be done quickly. This feeling can influence how we make decisions. For example, if someone is told that they have a short time to complete a task, they are likely to make quicker decisions, which may lead to mistakes if they cannot think things through properly.
Mind Wandering
Mind wandering happens when a person’s attention drifts away from the main task. Instead of focusing on what they should be doing, they start thinking about unrelated thoughts. This can occur when someone feels bored or when they don’t find the task engaging enough.
Using Physiological Signals to Identify Cognitive States
To find out how to measure these cognitive states, researchers collected data from people performing tasks while their physiological responses were recorded. They studied different types of signals to assess cognitive workload, sense of urgency, and mind wandering.
Eye Movements
One of the physiological signals studied is eye movements. Tracking where people look and how their pupils change can provide valuable insights. For example, if someone is paying attention and engaged, their pupils may dilate or constrict in response to the task.
Brain Activity
Another important signal is brain activity, which can be measured through a method called EEG (electroencephalography). This technique allows researchers to see how brain waves change depending on the cognitive workload and levels of urgency. Different patterns of brain waves can indicate whether a person is focused or distracted.
Other Physiological Responses
Additional signals that were examined include skin conductance (sweating), respiration rates, and blood flow. These changes in the body can point to how stressed or engaged someone is in their tasks.
The Study Conducted
In this study, researchers gathered data from participants who were involved in a driving simulation. These participants were asked to complete driving tasks while also handling secondary tasks like answering questions. During this time, their eye movements and other physiological data were collected to assess the three cognitive states.
Different Tasks and Sessions
The study had participants go through different tasks over two sessions. In each session, they drove and completed secondary tasks. The researchers wanted to see how different Workloads and urgency levels affected their cognitive states.
Analyzing the Data
Researchers used statistical methods to analyze the data collected from these physiological signals.
Finding the Best Indicators
Through analysis, they looked at which signals were the best at predicting the cognitive states. The percentage change in pupil size (PCPS) stood out as a very reliable indicator of workload, sense of urgency, and mind wandering. This means that by simply monitoring eye movements, one can get a good sense of how a person is managing their tasks.
Using Machine Learning
Researchers also applied machine learning models to predict the cognitive states based on the physiological data. They tested five different machine learning methods to see which performed best in classifying the states based on the collected information.
Key Findings
Workload Detection
The study found that the percentage change in pupil size was particularly useful in distinguishing between different levels of workload. The researchers were able to determine whether participants were experiencing low, medium, or high workloads based on their eye movements.
Sense of Urgency Classification
Similarly, the PCPS also effectively differentiated between low and high sense of urgency during tasks. This means that monitoring eye movements can effectively signal when someone feels pressured to act quickly.
Mind Wandering Indicators
The results indicated that the participants showed clearer signs of mind wandering when they were less engaged in their tasks. Again, eye movements provided valuable insight into when attention dropped.
Conclusion
Overall, understanding how to measure cognitive states using physiological signals like eye movements can greatly enhance how we approach task management in various fields. This research highlights the importance of eye movements as a primary indicator of cognitive workload, urgency, and mind wandering.
With technology continuing to advance, integrating these assessments into everyday task settings could be a game changer, allowing for better support and improving performance in critical areas where human attentiveness is essential. Future research could look into how these findings hold up across different populations and tasks, as well as how real-time tracking can be implemented effectively.
Future Directions
The next steps should involve creating systems that can monitor these cognitive states in real-time. By using easy-to-collect data like eye movements, teams could receive instant feedback about their cognitive workload or attention levels. This could lead to enhanced performance across various industries, especially in high-stakes situations.
Additionally, it would be beneficial to expand this research to include more diverse participants to understand how different factors influence cognitive states. Exploring more systemic cognitive states like distraction and interference can also be valuable, providing a deeper insight into how we process and manage information while working.
In conclusion, recognizing and measuring cognitive states through physiological signals like eye movements can lead to better human performance and well-balanced workloads in the future.
Title: Assessing the Effects of Various Physiological Signal Modalities on Predicting Different Human Cognitive States
Abstract: Robust estimation of systemic human cognitive states is critical for a variety of applications, from simply detecting inefficiencies in task assignments, to the adaptation of artificial agents behaviors to improve team performance in mixed-initiative human-machine teams. This study showed that human eye gaze, in particular, the percentage change in pupil size (PCPS), is the most reliable biomarker for assessing three human cognitive states including workload, sense of urgency, and mind wandering compared to electroencephalogram (EEG), functional near-infrared spectroscopy (fNIRS), respiration, and skin conductance. We used comprehensive multi-modal driving dataset to examine the accuracy of signals to assess these cognitive states. We performed comprehensive statistical tests to validate the performance of several physiological signals to determine human cognitive states and demonstrated that PCPS shows noticeably superior performance. We also characterized the link between workload and sense of urgency with eye gaze and observed that consecutive occurrences of higher sense of urgency were prone to increase overall workload. Finally, we trained five machine learning (ML) models and showed that four of them had similar accuracy in cognitive state classification (with one, random forest, showing inferior performance). The results provided evidence that the PCPS is a reliable physiological marker for cognitive state estimation.
Authors: Ayca Aygun, T. D. Nguyen, M. Scheutz
Last Update: 2024-03-04 00:00:00
Language: English
Source URL: https://www.biorxiv.org/content/10.1101/2024.02.29.582708
Source PDF: https://www.biorxiv.org/content/10.1101/2024.02.29.582708.full.pdf
Licence: https://creativecommons.org/licenses/by/4.0/
Changes: This summary was created with assistance from AI and may have inaccuracies. For accurate information, please refer to the original source documents linked here.
Thank you to biorxiv for use of its open access interoperability.