I. Introduction
Mental workload monitoring is of particular interest in safety-critical applications where human performance is often the last controllable factor. In general as cognitive workload increases, maintaining task performance within an acceptable range becomes more difficult. Increased cognitive workload may demand more cognitive resources than that available by the operator, thus resulting in a performance degradation and an increased occurrence of errors [1]. Objective measures of mental workload based on biomarkers could be used to evaluate alternative system designs, to appropriately allocate imposed workload to minimize errors due to overloads. Such system could intervene in real-time before the operator become overloaded while performing safety-critical tasks [2]. Different systems to estimate the mental workload has been previously presented by using EEG or HR or other biometric signals [3], [4], [5]. However, all of these works presented the use of a single modality each time (e.g. only EEG, or only HR etc etc). Since it has been noted in literature as the EEG and HR are sensitive to different components of the mental workload [6], the question whether the reliability of the mental workload detection could benefit from the simultaneous use of multimodal signals (EEG, HR) arose. The purpose of the present work is to investigate the combined use of EEG and HR for the detection of the mental workload when compared to the use of the single modality alone. In this way it has been designed, implemented and evaluated a framework to quantify online the mental workload in subjects involved in managing concurrent tasks at different difficulty levels. All of these tasks are with a clear relevance for the flight control.