A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights. (15th August 2018)

• Record Type: Journal Article
• Authors: Wang, Wenxu; Tang, Ruichun; Li, Cheng; Liu, Peishun; Luo, Liang
• Is Part Of: Ocean engineering. Volume 162(2018)
• Page Start: 98
• Page End: 107
• Publication Date: 2018-08-15
• Subjects: MEA-BP -- Ocean wave heights -- Optimization of BPnn -- Generalization ability; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2018.04.039
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: In the field of marine detection and warning, predicting the heights of ocean wave is a very important project. In order to predict the ocean wave heights accurately and quickly, our methodology utilizes a hybrid Mind Evolutionary Algorithm-BP neural network strategy (MEA-BP). This paper investigates how the BP neural network (BPnn) evolution with MEA improves the generalization ability and predictability of BPnn. The MEA-BP model combines the local searching ability of the BPnn and the global searching ability of the MEA which can avoid premature convergence and poor prediction effect. In order to search individuals which contain optimal weights and thresholds, the MEA searches all the initial weights and thresholds intelligently by similartaxis and dissimilation operation, finally assign them to the initial BPnn. The study is conducted using data collected from 12 observation points across two geographically distinct regions, Bohai Sea, Yellow Sea, for the period from Jan 1, 2016 to Dec 31, 2016. The data is chosen such that the study covers a wide range of geographical locations and different weather. We compare the prediction performance and generalization capabilities of MEA-BP with the Genetic Algorithm-BP neural network model (GA-BP) which also developed with the BPnn. The performance study results demonstrate that MEA-BP performs better than the GA-BP and Standard BP neural network model (St-BP) with faster running time and higher prediction accuracy. Highlights: MEA can remember more than one generation of evolutionary information. Similartaxis and dissimilation operations towards a correct direction, never become worse. Similartaxis and dissimilation operations are easier to find the optimal individual, saving the number of iterations. Crossover and mutation operations in GA can produce good genes, or destroy the original genes. The study data covers a wide range of geographical locations and different weather to eliminate the effects of geography and weather.