Human error is responsible for up to 80% of workplace accidents, but predictable models that evaluate workers' eye movements and attention can help reduce incidents, according to a study released Tuesday by researchers at George Mason University in Fairfax, Virginia.  By measuring eye movements and cognitive processes for vulnerable workers in the construction industry, the researchers built a fault detection framework that calculates the probability of human error in professional environments. The researchers linked eye movements and workers' attention to research that focused on working memory load and decision making to understand how and why workers in a dynamic environment fail to detect, understand and / or respond to physical risks.
The researchers found that:
- Eye movements can be used as a precursor to workers' safety flaws.
- Working memory load and personality traits play an important role in risk-taking behavior.
- Data mining classifiers can be used to calculate the probability of different types of human error.
The researchers said that the use of predictive models such as the one used for the study could lead to a "significant reduction in accidents" in the workplace and improve workers' risk analysis skills.