On the Use of Cognitive Neurometric Indexes in Aeronautic and Air Traffic Management Environments

• Published in: Symbiotic Interaction Vol. 9359; pp. 45 - 56
• Main Authors: Di Flumeri, Gianluca, Borghini, Gianluca, Aricò, Pietro, Colosimo, Alfredo, Pozzi, Simone, Bonelli, Stefano, Golfetti, Alessia, Kong, Wanzeng, Babiloni, Fabio
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2015; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: ATCO; ATM; Data mining; eDEP; EEG; EOG; Information retrieval; Machine learning; Mental workload; Self-assessment
• ISBN: 9783319249162; 3319249169
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-24917-9_5

In this paper the use of neurophysiological indexes for an objective evaluation of mental workload, during an ecological Air Traffic Management (ATM) task, has been proposed. Six professional Air Traffic Controllers from the Italian ENAV (Società Nazionale per l’Assistenza al Volo) have been involved in this study. They had to perform an ecological Air Traffic Management task by using the eDEP software, a validated simulation platform developed by EUROCONTROL. In order to simulate a realistic situation, the task was developed with a continuously varying difficulty level, i.e. starting form an easy level, then increasing up to a harder one and finishing with an easy one again. During the whole task for each subject the electroencephalographic (EEG) signals were recorded in order to compute the neurophysiological workload index, and at the same time the subjective perception of the mental workload by using the Instantaneous Self-Assessment (ISA) technique. Thus, the EEG-based workload index, estimated by means of machine learning approach, by one side, and the subjective assessed workload index by the other side, have been compared in terms of correlation and difficulty levels discrimination. By the results it emerged: i) a high positive and significant correlation between the two measures, and ii) a significantly discriminability of the task different difficulty levels by using the EEG-based workload indexes, according to the ISA results. In conclusion, this study validated the EEG-based mental workload index as an efficient objective evaluation method of the cognitive resources demand in a real operative scenario, and moreover as an index able to monitor its variations.