Research Article

Prediction of Drifter Trajectory Using Evolutionary Computation

Table 6

Results on parameters of DE.

ParameterEvaluationCase
1567

Strategy
 DE/best/1MAE0.13510.07610.04940.1308
Euclid0.17720.12180.08400.1931
NCLS0.88790.81530.88950.7627
 DE/rand/1MAE0.09200.08280.03920.0653
Euclid0.154020.13420.05930.0956
NCLS0.90250.79650.92200.8826
 DE/rand-to-best/1MAE0.09200.08280.03920.0653
Euclid0.15400.13420.05930.0956
NCLS0.90250.79650.92200.8826
 DE/best/2MAE0.08890.08420.08250.0966
Euclid0.13370.13640.12590.1400
NCLS0.91540.78540.83440.8280
 DE/rand/2MAE17.03689.629919.01752.8862
Euclid27.027014.679128.93674.2267
NCLS−16.1006−21.0442−37.1143−4.1928

Note. The lower the MAE and Euclidean values, the better. The higher the NCLS values, the better.