一种基于并行聚类的温室天窗开度预测方法

doi:10.16182/j.issn1004731x.joss.201710029

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (10): 2459-2467.doi: 10.16182/j.issn1004731x.joss.201710029

一种基于并行聚类的温室天窗开度预测方法

邓丽^1,2, 余玥^1,2, 庞洪霖^1,2, 费敏锐^1,2

1.上海大学机电工程与自动化学院,上海 200072;
2.上海市电站自动化技术重点实验室,上海 200072

收稿日期:2017-05-02 发布日期:2020-06-04
作者简介:邓丽(1978-),女,安徽,博士后,副教授,研究方向为机器学习、智能优化算法等;余玥(1993-),女,江苏,硕士生,研究方向为机器学习与分布式计算。
基金资助:
上海市科委重点项目(14DZ1206302)

Skylight Opening Degree Prediction Method Based on Parallel Clustering

Deng Li^1,2, Yu Yue^1,2, Pang Honglin^1,2, Fei Minrui^1,2

1. School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China;
2. Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200072, China

Received:2017-05-02 Published:2020-06-04

摘要/Abstract

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。

关键词: Dirichlet过程混合模型聚类, 农业环境数据, 天窗开度预测, Spark

Abstract: 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.

Key words: DPMM, agriculture environmental data, skylight opening value prediction, Spark

中图分类号:

TP338.8

邓丽, 余玥, 庞洪霖, 费敏锐. 一种基于并行聚类的温室天窗开度预测方法[J]. 系统仿真学报, 2017, 29(10): 2459-2467.

Deng Li, Yu Yue, Pang Honglin, Fei Minrui. Skylight Opening Degree Prediction Method Based on Parallel Clustering[J]. Journal of System Simulation, 2017, 29(10): 2459-2467.

参考文献

[1] 詹嘉放, 宋治文, 李凤菊, 等. 日本、荷兰和以色列发展设施农业对中国的启示[J]. 天津农业科学, 2011, 17(6): 97-101.
(Zhan Jiafang, Song Zhiwen, Li Fengju, et al.Enlightenment of the Development of Agricultural Facilities in Japan, the Netherlands and Israel to China[J]. Tianjin Agricultural Sciences, 2011, 17(6): 97-101.)
[2] Gunasundari Ananthara M, Arunkumar Dr T, Hemavathy Ms R.CRY - An improved Crop Yield Prediction model using Bee Hive Clustering Approach for Agricultural data sets[C]// 2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering (PRIME). Piscataway, NJ: IEEE, 2013: 473-478.
[3] 时雷, 马新明. 基于物联网的小麦生长环境数据采集与数据挖掘技术研究 [D]. 郑州: 河南农业大学, 2013: 61-64.
(Lei Shi, Ma Xinming.Research on Data Collection and Data Mining of Wheat Growth Environment based on the Internet of Things [D]. Zhengzhou, China: Henan Agricultural University, 2013: 61-64.)
[4] Russ G, Kruse R.Machine Learning Methods for Spatial Clustering on Precision Agriculture Data[C]// Scandinavian Conference on Artificial Intelligence. Otto- vonGuericke-Universitat Magdeburg, Germany: SCAI, 2011:40-49.
[5] Cao L, Zhang X, San X, et al.Application of fuzzy clustering algorithm in precision agriculture[C]// World Automation Congress (WAC), 2012. USA: IEEE, 2012: 1-4.
[6] Wu M, Wang Y, Liao Z.A New Clustering Algorithm for Sensor Data Streams in an Agricultural IoT[C]// IEEE International Conference on High Performance Computing and Communications. USA: IEEE, 2013: 2373-2378.
[7] Yu G, Huang R, Wang Z.Document clustering via dirichlet process mixture model with feature selection[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, July, 2010. New York, NY, USA: ACM, DBLP, 2010: 763-772.
[8] Crook N, Granell R, Pulman S.Unsupervised classification of dialogue acts using a dirichlet process mixture model[C]// Sigdial 2009 Conference: the, Meeting of the Special Interest Group on Discourse and Dialogue. Stroudsburg, PA, USA: Association for Computational Linguistics, 2009: 341-348.
[9] Hu W, Li X, Tian G, et al.An incremental DPMM-based method for trajectory clustering, modeling, and retrieval[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2013, 35(5): 1051-1065.
[10] Zaharia M, Chowdhury M, Franklin M J, et al.Spark: cluster computing with working sets[C]// Usenix Conference on Hot Topics in Cloud Computing. USA: USENIX Association, 2010: 1765-1773.
[11] 唐振坤. 基于Spark的机器学习平台设计与实现[M]. 厦门: 厦门大学, 2014: 5-8.
(Tang Zhenkun.Design and Implementation of Machine Learning Platform Based on Spark[M]. Xiamen, China: Xiamen University, 2014: 5-8.)
[12] 杨其长, 魏灵玲, 刘文科, 等. 中国设施农业研究现状及发展战略[J]. 中国农业信息, 2012(11) : 22-27.
(Yang Qichang, Wei Lingling, Liu Wenke, et al.The research situation and development strategy of controlled environmental agriculture in China[J]. China Agriculture Information, 2012(11): 22-27.)

一种基于并行聚类的温室天窗开度预测方法

Skylight Opening Degree Prediction Method Based on Parallel Clustering

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	刘东江, 黎建辉. 基于Spark的并行图聚类算法研究[J]. 系统仿真学报, 2020, 32(6): 1038-1050.
[2]	李莉, 朱永利, 宋亚奇. 泄漏电流数据的Spark-KNN并行模式识别方法[J]. 系统仿真学报, 2018, 30(4): 1473-1481.