当前位置: 首页 > 文章 > 基于改进型人工神经网络的温室大棚蔬菜作物苗期杂草识别技术 北方园艺 2017 (22) 79-82
Position: Home > Articles > Weed Identification Technology of Greenhouse Vegetable Crops in Greenhouse Based on Improved Artificial Neural Network Northern Horticulture 2017 (22) 79-82

基于改进型人工神经网络的温室大棚蔬菜作物苗期杂草识别技术

作  者:
董亮;雷良育;李雪原;刘兵;张辉
单  位:
浙江农林大学工程学院
关键词:
神经网络;改进;温室大棚;杂草识别
摘  要:
温室大棚在蔬菜培育中有着广泛应用,在高效生产的同时,除草问题亟待解决。该设计采用一种改进型的人工神经网络算法应对大棚作物苗期杂草识别,通过对遗传算法的神经元参数的优化,以减少错误的发生次数。结果表明:与采用径向基核函数的支持向量机算法相比较,改进型人工神经网络算法识别正确率更高,达到94%以上,可为进一步的除草机器人开发提供技术支持。
译  名:
Weed Identification Technology of Greenhouse Vegetable Crops in Greenhouse Based on Improved Artificial Neural Network
作  者:
DONG Liang;LEI Liangyu;LI Xueyuan;LIU Bing;ZHANG Hui;School of Engineering,Zhejiang A & F University;
单  位:
School of Engineering,Zhejiang A & F University
关键词:
neural network;;improvement;;greenhouse;;weed identification
摘  要:
The greenhouse has been widely used in the cultivation of vegetables,in the production of high efficiency,weed control problems need to be solved urgently.The design was used an improved artificial neural network algorithm to deal with the weed identification in the seedling stage,and the optimization of the parameters of the genetic algorithm in order to reduce the number of errors.The results showed that with the radial basis kernel function of support vector machine algorithm,improved artificial neural network algorithm to identify the correct rate was more high,more than 94% and high efficiency of identification could provide technical support for further weeding robot development.

相似文章

计量
文章访问数: 17
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊