摘要
为了处理大量分布式存储的农业环境数据,实现农业设施智能控制,基于内存计算框架Spark提出一种并行化的Dirichlet过程混合模型聚类方法,对农业环境及设施数据进行训练得到预测模型,执行对温室大棚天窗开度的预测任务。通过对比实验验证了模型预测的可行性,对预测正确率进行统计,并测试了所提出的并行化聚类的执行效率。实验结果表明,提出的方法具有较高的执行效率及准确性。
To process the massive distributed data and control the agricultural facilities intelligently, a parallel Dirichlet Process Mixture Model （DPMM） clustering method was proposed based on Spark. With this method, the prediction model of greenhouse skylight opening degree was obtained by training the agricultural environmental and facilities data. The model was used to predict the greenhouse skylight opening degree. Through several comparison experiments, both the feasibility and the efficiency of the proposed parallel clustering were verified, the prediction accuracy was calculated. The experimental results show that the proposed approach has higher efficiency and accuracy.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2017年第10期2459-2467,共9页
Journal of System Simulation
基金
上海市科委重点项目(14DZ1206302)
