Fishing condition prediction method based on extreme learning machine

Abstract

The invention relates to a fishing condition prediction method based on an extreme learning machine. The method comprises the following steps: collecting marine environment factor data and fishing ground operation data; preprocessing the marine environment factor data and the fishery operation data to obtain a preprocessed data set; generating a training data set and a test data set according to the preprocessed data set; and constructing an ELM model, and training the ELM model by using the training data set to obtain a fishing condition prediction model. According to the fish condition prediction method based on the extreme learning machine, the ELM is adopted as the model, the complex iteration process is converted into random generation of hidden layer parameters, the model training speed is high, the generalization ability is very excellent, compared with a traditional fish condition prediction method, the processing speed in the aspect of processing large-scale data is high, and meanwhile the method is simple and convenient. Parameters needing to be adjusted are few, adjustment and use are easy, and prediction precision is high.

Description

technical field [0001] The invention relates to the technical field of constructing a fishery situation prediction model, in particular to a fishing situation prediction method based on an extreme learning machine. Background technique [0002] Albacore tuna is an important part of the development of pelagic fishery in the South Pacific Ocean in my country. Improving the forecasting level of albacore tuna is of great significance for improving the fishing efficiency of albacore tuna and the ocean benefits of our country. [0003] The distribution of fish in the ocean is often affected by environmental factors such as temperature, sea surface height, chlorophyll-a concentration, salinity, and wind, as well as national policies and related climate phenomena such as El Niño. [0004] Many scholars have used different methods to study this issue. However, the formation of fishing grounds is closely related to marine data, and the changeable and complex marine environment also m...

AI Technical Summary

Problems solved by technology

However, the formation of fishing grounds is closely related to marine data, and the changeable and complex marine environment also makes marine data more complex and multidimensional, which reduces the accuracy and efficiency of traditional prediction methods to a certain extent.

However, machine learning methods, such as prediction methods based on Bayesian probability classifiers and prediction methods based on support vector machines, etc., have complex intermediate iterative processes and require analysis of data independence, which increases the complexity of the algorithm to a certain extent. affect the accuracy of the forecast

Images