*4.1. Simulation Experiment*

We assume that the radar monitoring area is approximately 20 km to 38 km in the x axis and approximately 20 km to 32 km in the y axis, where four vessels maneuvering with multiple models are simulated with MATLAB (MathWorks, Natick, MA, USA). For the conventional tracking method [13], the vessel track breaks into segments, as shown in Figure 5a. Combined with a trained ELM network, the proposed method realizes correct track segment association. As is shown in Figure 5b, different types of track segments are colored according to the classification results obtained by the ELM.

**Figure 5.** Results of a simulation experiment: (**a**) track segments obtained by a conventional tracking method; (**b**) association results of the proposed method.

In order to verify the rationality and superiority of the proposed method, we carried out simulations on the basis of different combinations of features and different machine learning methods. To evaluate the association performance, the correct association probability (*Rt*), the error association probability (*Rf*) and the missing association probability (*Rn*) are defined as follows:

$$R\_t = \frac{n\_t}{n} \tag{28}$$

$$R\_f = \frac{n\_f}{n} \tag{29}$$

$$R\_{\text{ll}} = \frac{n\_{\text{ll}}}{n} \tag{30}$$

where *n* represents the total number of track segments in the experiment, *nt* represents the number of correctly associated track segments, *nf* represents the number of incorrectly associated track segments, and *nn* represents the number of missed track segments.
