An Air Traffic Controller Action Extraction-Prediction Model Using Machine Learning Approach
Table 8
Feature importance of random forest models for action prediction.
RC1
FI1 (%)
RC2
FI2 (%)
RC3
FI3 (%)
RC4
FI4 (%)
Speed
14
Latitude
17
Course
19
Latitude
17
V_Speed
10
V_Speed
15
Longitude
16
Course
13
T_Remain
10
T_Remain
15
Latitude
14
Longitude
10
Latitude
8
O_WSSS
14
Altitude
8
T_Remain
9
Course
7
D_WSSS
8
T_Remain
5
V_Speed
9
Altitude
7
Course
4
Speed
4
Speed
7
Longitude
7
D_VTBS
3
V_Speed
4
Altitude
6
Month
4
Altitude
3
O_RKSI
2
D_WSSS
4
Day
4
Longitude
3
Month
2
O_WSSS
3
Hour
3
Hour
2
Day
2
Month
3
We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.