The experiment with AI will help researchers to recognize people in work stress 

Researchers at the Massachusetts Institute of Technology (MIT) are working on intelligent machines that can help sense cognitive fatigue and suggest interventions to assist a person to improve performance. This AI-powered project towards recognizing work stress and fatigue aims to leverage the abilities of human-machine teams, cooperating to solve complex problems. According to MIT Lincoln Laboratory researchers, much of the development of these human-machine teams focuses on the machine, addressing the technology challenges of training AI algorithms to perform their role in a mission effectively.

Pointing out to the collaboration between humans and machines, Michael Pietrucha, a tactical systems specialist at the laboratory, said that in the area of human-machine collaboration, he and his team often think about the technology, such as how do they monitor it, understand it, and make sure it is working right. But he further noted that teamwork is a two-way street, and the machine can help humans to boost their performance. Pietrucha is one of the laboratory researchers that intends to develop AI systems that can sense a person's cognitive fatigue interfering with their work performance.

Furthermore, Megan Blackwell, former deputy lead of internally funded biological science and technology research at the laboratory, explained that neuromonitoring is becoming more specific and portable today. "We envision using technology to monitor for fatigue or cognitive overload. Is this person attending to too much? Will they run out of gas, so to speak? If you can monitor the human, you could intervene before something bad happens." she said. Using technology to read a person's cognitive or emotional state has been the laboratory's decade-long research.

The stress and fatigue recognition system operates on biometric data such as video and audio recordings of a person speaking. By processing these data with advanced AI algorithms, researchers found biomarkers of various psychological and neurobehavioral conditions. These biomarkers have been used to train models that can accurately estimate the level of a person's depression, for example.

As part of the study, the team will apply their biomarker research to an artificial intelligence-powered system to assess an individual's cognitive state, encapsulating how fatigued, stressed, or overloaded a person is feeling. The system will use biomarkers derived from physiological data such as vocal and facial recordings, heart rate, EEG and optical indications of brain activity, and eye movement to excerpt these insights.

According to researchers, the first step will be to build a cognitive model of an individual. This will integrate the physiological inputs and monitor the inputs to see how they change as a person performs particular fatiguing tasks, according to Thomas Quatieri, who leads several neurobehavioral biomarker research efforts at the MIT Lincoln laboratory. This process will enable the AI system to establish patterns of activity and learn a person's baseline cognitive state involving basic task-related functions needed to prevent injury or undesirable outcomes, such as auditory and visual attention and response time. When this individualized baseline is established, the system can begin recognizing deviations from normal and predict if those deviations will lead to mistakes or poor performance.

Currently, the project is in its early stage as researchers are collecting data to train their algorithms and develop the technology further.