A High-Efficiency Fatigued Speech Feature Selection Method for Air Traffic Controllers Based on Improved Compressed Sensing

Table 2

The fatigue dataset utilized in this study.

Fatigue data set	Number	Expression	Explanation
	1	Control category	R, area control; A, approach control; T, tower control
	2	ATC rank	5, level 5; 4, level 4; 3, level 3; 2, level 2; 1, level 1; 0, trainee
	3–10	Time (UTC)	3–6, time of starting work; 7–10, time of ending work
	11	Sex	F, female; M, male
	12 and 13	Age	Arabic numeral (age in years)
	14 and 15	Order	Nn, N is a digital indicator and n is an Arabic numeral indicating the n^th instruction issued by the ATC while working
	16 and 17	Status	14^th, “-;” 15^th, voice command; 1, error; 2, ambiguity; 3, hesitation or pause; 4, fatigue