摘要
渔业水质评价智能化对提高渔业生产水平起到关键促进作用。本文针对渔业水质评价设计了基于LBFGS优化的神经网络模型,深入讨论选取特征的有效性并优化了特征选择,实现了模型压缩,更适合前端嵌入式环境。实验表明,本文设计模型能够有效提供水质评价信息。
The intelligent evaluation of water quality plays a key role in increasing the fishery production.In this paper,a neural network model based on LBFGS optimization is designed for fishery water quality evaluation.The effectiveness of features is discussed,and the model is compressed.This mode is more suitable for the front-end embedded environment.Experiments show that the model designed in this paper can effectively provide water quality evaluation information.
作者
杨晓峰
YANG Xiaofeng(Department of Computer Engineering,Shanxi College of Architectural,Jinzhong Shanxi 030600,China)
出处
《智能计算机与应用》
2021年第3期134-137,142,共5页
Intelligent Computer and Applications
关键词
水质
评价
LBFGS
神经网络
water quality
evaluation
limited-memory Broyden-Fletcher-Goldfarb-Shanno
artificial neural network