Pilot's cognitive states induced by mental fatigue, distraction, and workload could be a cause of catastrophic accidents. Therefore, many methods for the detection of pilot cognitive states have been proposed in previous studies. Especially, neuro-and peripheral physiological measures (PPMs) such as electroencephalogram (EEG), electrocardiogram (ECG), respiration, and electrodermal activity (EDA) were employed to develop the novel flight assistant technologies for assurance of pilot's safety. However, each study investigated only one kind of state. Also, they did not consider the feature optimization for each subject. In this paper, we propose a method for the recognition of pilot's diversified mental states during simulated flight. The method selects the most fitted features for each subject based on the statistical analysis. The results show that the proposed method is superior to previous methods. Consequently, it shows that the pilot assistant system based on human-computer interaction (HCI) technologies could be facilitated in real-world.