Sea Clutter Prediction Model Based On ICOA-ELM

To effectively detect targets in sea clutter, accurate prediction of sea clutter is particularly important. To this end, this paper proposes a sea clutter prediction model based on the Extreme Learning Machine (ELM)network optimized by the improved Crayfish Optimization Algorithm (COA). Firstly, because sea clutter has chaotic characteristics, the phase space reconstruction of sea clutter data is carried out, and the reconstructed data are input to the ELM network; secondly, the COA algorithm is improved to enhance its optimization searching ability, and the weight of the ELM network are optimized by using this algorithm; finally, the optimized ELM network is used to predict the sea clutter. From the experimental results, it is easy to find that compared with several other prediction models, the ICOA-ELM network has a higher prediction accuracy, which provides a new way to predict sea clutter effectively.