The NINA (Neurometrics INdicators for ATM)  project investigated the possibility of using physiological measurements to monitor air traffic controllers’ cognitive state and mental workload.

The project, co-funded by the SESAR Joint Undertaking, within the Long Term Research workpackage (WPE), ran for 27 months, from September 2013 to November 2015.

NINA developed a mental state classifier algorithm that is able to evaluate a controller’s mental state based on electroencephalographic data. (see the NINA presentation video to see how it works).

The system has been designed thanks to the collaboration of Deep Blue, Sapienza University of Rome  and the École Nationale Aviation Civile – ENAC, and validated at ENAC research facilities, with the collaboration of test group of 37 air traffic controller students and experts, who executed realistic scenarios in an air traffic control environment. The NINA mental state classifier provides an assessment of the controller’s workload that is comparable to the traditional NASA-TLX and ISA assessment methods that are typically used by SESAR projects to measure the impact of SESAR Solutions on controllers.

In NINA, the workload metric were specifically tested for research into adaptive automation support (see this proof-of-concept to see how it works).

The NINA objective workload metrics concept may be useful not only in this ATM research domain, but also for the refinement of local complexity metrics (e.g. workload measurements for calibrating sector capacity). 

In addition to workload metrics, the NINA mental state classifier is able to provide information on the degree of training of an individual in certain air-traffic-control-related tasks. The assessment is based on the redistribution of brain activation areas with practice, and NINA researchers believe that the principle could be applied in combination with the traditional performance-based assessment for evaluating the success of individuals in training. Moreover, the level of expertise can also be measured by the mental state classifier, further expanding the possibilities of the use of the NINA concepts in training. 

The NINA team is working on making the EEG-measuring equipment lighter and more user friendly. The improved prototype will look like a flexible “swim cap”, and its use will not require expertise in neuroscience. The NINA team plans the commercial exploitation of the NINA “cap”. Their target market is ANSPs and ATM training institutions.

The NINA neurometrics have been developed and specifically adapted to the air traffic control domain needs and type of tasks, but the same neurometrics can be adapted to other domains. Within the aviation  domain, the concept could be scaled to pilots. Outside of aviation, the NINA neurometrics could be applied in the healthcare domain for assessing the mental states of surgeons.