摘要
结合粗糙集理论和神经网络在信息处理方面的优势,构建了基于粗糙集理论和人工神经网络相结合的农业病虫害诊断方法的模型;建立了粗糙BP神经网络模型用于诊断推理,引入附加动量法和自适应学习速率法对传统BP神经网络算法进行改进,有效提高了平台的运行效率。同时,以葡萄病害诊断为例,对模型功能以及性能进行检验,结果表明:所建模型与葡萄病虫害诊断专家系统的诊断结果一致,具有较高的实用性、通用性和灵活性。
Considering the advantages of rough set theory and neural Network in information disposal , the paper constructs the model of evaluating methods of agricultural pests diagnosis based on rough set theory and artificial neural network. In the rough back - propagation neural network model which was used in diagnostic reasoning, additional momentum method and adaptive - learning rate method were introduced in order to improve the traditional BP algorithm. In this way, the op- eration efficiency of platform was also improved. Finally, take grape disease diagnosis for example, the function and performance of platform were tested. Tests showed that the diagnosis results of the platform constructed in this paper and single grape disease diagnosis system were same. Therefore, the constructed platform has higher practicability, generality and flexibility.
出处
《农机化研究》
北大核心
2009年第11期197-199,共3页
Journal of Agricultural Mechanization Research
基金
西北农林科技大学人才资金项目(01140409)
国家高技术研究发展计划项目(2006AA100208-2)
