Water grade judgment of aquaculture based on IBES and evidence fusion

Abstract

In aquaculture, water measuring data obtained by conventional multi-sensors often have some errors, therefore, a new water grade judgment method is proposed in the paper. First, by using the refractive learning strategy, an improved Bald Eagle Search algorithm (IBES) is studied. IBES can effectively overcome the problem of weak local search ability and slow convergence speed in traditional BES algorithm. Second, an aquaculture water grade judgment method based on IBES and evidence fusion is proposed. The interval number is used to represent the aquaculture water parameters, and the reliability coefficient Nk is optimized by IBES to complete the modification of the mass function. Then, the combination rule of interval evidence and the modified mass function are synthesized to obtain the comprehensive interval evidence. Finally, the water grade is judged according to the decision rule. In the experiments, three sensors (temperature, dissolved oxygen and pH) are used to obtain water data. The experimental results show that the median value of the fusion uncertainty obtained by the proposed method is reduced to 0.3769, its reliability is greatly improved compared with a single sensor. In addition, the performance of the proposed method is compared with other optimization algorithms, including GWO, ABC, PSO, WOA, BES, IBES, the experimental results show that the average probabilities of IBES in judgment of water grades for Excellent (I) and Poor (III) are all 93% which rank first. Therefore, the method can accurately determine the water grade from uncertain measurement data with inevitable error and random error, it can provide a new idea for aquaculture water grade judgment.