A Two-Stage Exon Recognition Model Based on Synergetic Neural Network

Algorithm 3

Parameter optimization based on artificial fish swarm algorithm.

(1) Initialize the parameters of artificial fish, such as 𝑠𝑡𝑒𝑝, 𝑣𝑖𝑠𝑢𝑎𝑙, the number of exploratory,

  maximum number of iterations, and randomly generated 𝑛 fishes;

(2) Set bulletin board to record the current status of each fish, and select the optimal value;

(3) Implementation of prey behavior, swarm behavior and follow behavior;

(4) Optimal value in bulletin board is updated;

(5) If termination condition is satisfied, output the result; otherwise return to step 2.