基于EMD-ELM模型的农产品价格预测研究

doi:10.19788/j.issn.2096-6369.200308

摘要/Abstract

摘要： 目的

农产品价格变动关乎国计民生，农产品市场价格波动频率快，波动幅度大，受多方面因素共同影响，并呈现出非平稳、非线性等不规律波动特征，这给农产品市场带来极大的挑战。只有充分地分析农产品价格的变化趋势，提高价格预测精度，才能更好地指引农产品产业健康发展。

方法

文章以马铃薯为研究对象，基于2014年1月至2019年12月共72组月度价格数据，提出一种经验模态分解（EMD）和极限学习机（ELM）的农产品价格组合预测模型。该组合预测模型充分利用了经验模态分解的自主分解能力和极限学习机设置较少的参数的优势。首先利用经验模态分解将原始价格序列分解为若干个本征模态函数（IMF）和余项，然后将这些分量分别用极限学习机进行预测，最后把各个分量的预测结果进行组合得到原始序列的预测值。

结果

将该方法实际应用于马铃薯价格进行预测并对其预测结果进行评价分析，结果表明其平均绝对误差为0.093元/kg，平均百分比误差为4.265%，均方根误差为0.148，并与单独的极限学习机、BP神经网络和ARIMA方法进行比较，结果表明EMD-ELM组合预测模型具有较好的农产品价格预测性能，能够为预测农产品价格波动提供一种思路，为行业和政府主管部门保障农产品供应决策提供参考依据。

关键词: 经验模态分解, 极限学习机, 农产品, 价格预测

Abstract: Objective

The price fluctuation of agricultural products is related to both the national economy and personal livelihoods. The price fluctuation frequency for the agricultural products market is fast, and the fluctuation range is large and is affected by various factors. The fluctuation range presents non-stationary, nonlinear, and other irregular characteristics, which brings great challenges to the agricultural products market. Only by fully analyzing the change trend of agricultural product prices and improving the accuracy of price prediction can we better guide the healthy development of the agricultural product industry.

Methods

Taking potatoes as the research object and using 72 sets of monthly price data from January 2014 to December 2019, this paper proposed an Empirical Mode Decomposition and Extreme Learning Machine agricultural product price combination prediction model. The combinatorial prediction model used the autonomous decomposition ability of Empirical Mode Decomposition and the advantage of the Extreme Learning Machine’s fewer parameters. Firstly, the original price series is decomposed into several Intrinsic Mode Functions and remainder terms by Empirical Mode Decomposition, then these components are separately predicted by Extreme Learning Machines, and finally the prediction results of each component are combined to obtain the original sequence Predicted Value.

Result

This method is applied to the prediction of potato prices and the evaluation and analysis of their prediction results. The results showed that the average absolute error was 0.093 yuan/kg, the average percentage error is 4.265%, and the root mean square error was 0.148. We compared our results with the results obtained by using the single Extreme Learning Machine, the BP Neural Network, and the ARIMA method. The results of this comparison showed that the prediction model combined with Empirical Mode Decomposition and Extreme Learning Machine performed better at agricultural product price prediction than the other methods. The results provide a method of predicting the price fluctuation of agricultural products, and they provide a reference for the industry and government department in charge to use in guaranteeing the decision of agricultural product supply.

Key words: Empirical Mode Decomposition, Extreme Learning Machine, agricultural products, price prediction

中图分类号:

F323.7

刘合兵, 韩晶晶, 马新明, 席磊. 基于EMD-ELM模型的农产品价格预测研究[J]. 农业大数据学报, 2020, 2(3): 68-74.

Hebing Liu, Jingjing Han, Xinming Ma, Lei Xi. Research on Agricultural Product Price Prediction Based on the EMD-ELM Mode[J]. Journal of Agricultural Big Data, 2020, 2(3): 68-74.

图/表 6

图1

图2

图3

图4

图5

表1

参考文献 20

1	许世卫,李哲敏,李干琼,等.农产品市场价格短期预测研究进展[J].中国农业科学,2011,44(17):3666-3675.
	Xu S W, Li Z M, Li G Q, et al. Research progress on short-term forecast of agricultural product market prices [J].Chinese Agricultural Science,2011,44(17):3666-3675.
2	马孝斌,王婷,董霞,等.向量自回归法在生猪价格预测中的应用[J].安徽农业科学,2008,36(5):1721.
	Ma X B, Wang T, Dong X, et al. Application of vector autoregressive method in price prediction of live pigs [J] .Anhui Agricultural Sciences, 2008,36 (5): 1721.
3	李哲敏,李干琼.禽蛋市场价格短期预测[J].中国食物与营养,2010,(6):36-39.
	Li Z M, Li G Q.Short-term forecast of poultry egg market price [J] .Chinese Food and Nutrition, 2010, (6): 36-39.
4	张标,张领先,傅泽田,等.基于季节指数的蔬菜价格变动趋势分析及预测[J].北方园艺(农业经济),2017,(18):185-191.
	Zhang B, Zhang Q F, Fu Z T, et al. Analysis and Forecast of Vegetable Price Changes Based on Seasonal Index [J] .Northern Horticulture (Agricultural Economics), 2017,(18): 185-191.
5	刘峰,王儒敬,李传席.ARIMA模型在农产品价格预测中的运用[J].计算机工程与应用,2009,45(25):238-239.
	Liu F, Wang R J, Li C X.Application of ARIMA model in agricultural product price prediction [J] .Computer Engineering and Applications, 2009,45 (25): 238-239.
6	苗开超.基于指数平滑模型的农产品价格预测研究[D].安徽:合肥工业大学计算机学院,2009.
	Miao K C. Research on agricultural product price prediction based on exponential smoothing model [D]. Anhui: School of Computer, Hefei University of Technology, 2009.
7	解建强.基于BP神经网络的赣南脐橙价格预测研究[D].湖北：华中农业大学,2017.
	Xie J Q.Research on price prediction of Gannan navel orange based on BP neural network [D] .Hubei： Huazhong Agricultural University, 2017.
8	任青山,方逵,朱幸辉.基于多元回归的BP神经网络生猪价格预测模型[J].江苏农业科学,2019,47(14):277-281.
	Ren Q S, Fang K, Zhu X H. BP neural network prediction model of pig price based on multiple regression [J] .Jiangsu Agricultural Sciences, 2019,47 (14): 277-281.
9	张劲珊,谢祥添.基于人工神经网络的蔬菜价格预测[J].江苏商论,2011,(4):47-48.
	Zhang J S,Xie X T.Vegetable price prediction based on artificial neural network [J] .Jiangsu Commercial Forum, 2011, (4): 47-48.
10	李芬妮,张俊飚,曾杨梅.基于GM(1,1)模型的食用菌价格预测[J].长江蔬菜,2017,(10):25-30.
	Li F N, Zhang J B, Zeng Y M. Price prediction of edible fungi based on GM (1,1) model [J] .Changjiang Vegetables, 2017,(10): 25-30.
11	姜百臣,冯凯杰,彭思喜.基于改进支持向量机的猪肉价格预测研究[J].广东农业科学,2018,45(12):158-164.
	Jiang B C, Feng K J, Peng S X. Research on pork price prediction based on improved support vector machine [J] .Guangdong Agricultural Sciences, 2018,45 (12): 158-164.
12	平平,刘大有,杨博,等.组合预测模型在猪肉价格预测中的应用研究[J].计算机工程与科学,2010,32(5):109-112.
	Ping P, Liu D Y, Yang B, et al. Application Research of Combination Forecasting Model in Pork Price Forecast [J] .Computer Engineering and Science, 2010,32 (5): 109-112.
13	翟静,曹俊.基于时间序列ARIMA与BP神经网络的组合预测模型[J].统计与决策,2016,(04):29-32.
	Zhai J, Cao J. Combined prediction model based on time series ARIMA and BP neural network [J] .Statistics and Decision, 2016,(04): 29-32.
14	闪利平,刘世江.基于小波理论和ARIMA-EGARCH模型的农产品短期价格预测[J].中国市场(前沿理论),2017,(5):30-31.
	Shan L P, Liu S J.Short-term price prediction of agricultural products based on wavelet theory and ARIMA-EGARCH model [J] .Chinese Market (Forefront Theory), 2017, (5) :30-31.
15	曹霜,何玉成.基于小波分解的SVM-ARIMA农产品价格预测模型[J].统计与决策(方法应用),2015,433(13):92-95.
	Cao S, He Y C.SVM-ARIMA agricultural product price prediction model based on wavelet decomposition [J] .Statistics and Decision (Method Application), 2015,433 (13): 92-95.
16	Guang-Bin Huang,Qin-Yu Zhu,Siew Chee-Kheong.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1-3): 489-501.
17	廖洪一,王欣.基于极限学习机的股票价格预测[J].计算机与现代化,2014,(12):19-22.
	Liao H Y, Wang X. Stock price prediction based on extreme learning machine [J] .Computer and Modernization, 2014, (12): 19-22.
18	穆昌.基于小波变换和极限学习机的网络流量预测模型[J].微型电脑应用,2020,36(1):138-140.
	Mu C.Network traffic prediction model based on wavelet transform and extreme learning machine [J] .Microcomputer Applications, 2020,36 (1): 138-140.
19	张翌辉,王贺,胡志坚,等.基于集合经验模态分解和改进极限学习机的短期风速组合预测研究[J].电力系统保护与控制,2014,42(10):29-34.
	Zhang Y H, Wang H, Hu Z J, et al. Short-term wind speed combined forecasting based on set empirical mode decomposition and improved extreme learning machine [J] .Power System Protection and Control, 2014,42 (10): 29-34.
20	李干琼,许世卫,李哲敏,等.农产品市场价格超短期预测研究——基于西红柿日批发价格的现代时间序列法建模[J].华中农业大学学报(社会科学报),2010,(6):40-45.
	Li Q Q, Xu S W, Li Z M, et al. Research on ultra-short-term forecasting of agricultural product market prices—Modern time series modeling based on tomato daily wholesale prices [J] .Journal of Huazhong Agricultural University (Social Science News), 2010, (6): 40- 45.

结果评价指标	EMD-ELM	ELM	BP	ARIMA
MAE（元/kg）	0.093	0.182	0.214	0.233
MAPE（%）	4.265	7.62	9.68	10.92
RMSE（元/kg）	0.148	0.233	0.236	0.275

[1]	金语泽, 贾昕为, 赖望峰, 周宏立, 陈乃赫, 李涛. 大数据技术在猪肉价格预测与调控上的探索与应用[J]. 农业大数据学报, 2023, 5(1): 126-134.
[2]	李佳利, 杨涵, 钱建平. 新冠肺炎疫情下中国农产品冷链物流可信追溯研究[J]. 农业大数据学报, 2022, 4(1): 14-24.
[3]	张哲, 杨信廷, 于合龙, 李珊珊, 孙传恒. 基于区块链技术的生鲜农产品追溯系统研究进展[J]. 农业大数据学报, 2022, 4(1): 25-34.
[4]	张新, 彭祥贞, 李悦, 王小艺, 赵峙尧, 许继平. 基于可信区块链和可信标识的粮油食品全供应链信息追溯模型[J]. 农业大数据学报, 2022, 4(1): 35-48.
[5]	周大森, 陈静, 张鑫, 李继兰, 李志成, 郑晓冬, 公维敏, 宋烨. 果蔬冷链追溯体系研究现状与应用建议[J]. 农业大数据学报, 2022, 4(1): 49-54.
[6]	张茜, 田乙慧, 肖文, 鲁燕. 大数据在农产品冷链物流中的应用[J]. 农业大数据学报, 2022, 4(1): 55-61.
[7]	周蓉蓉, 陈栋, 刘思远. 基于K均值聚类算法的生鲜运输路径优化模型[J]. 农业大数据学报, 2022, 4(1): 89-97.
[8]	贺苗, 李鑫, 朱志强, 冯建英. 基于PCA-GA-SVR的鲜食葡萄运输过程品质建模[J]. 农业大数据学报, 2022, 4(1): 98-108.
[9]	陈志军, 刘艳, 钱永忠. 基于风险熵的农产品安全定量评价研究[J]. 农业大数据学报, 2020, 2(4): 47-54.
[10]	洪涛, 李瑞, 洪勇. 数字农产品“拉式供应链”模式研究[J]. 农业大数据学报, 2020, 2(3): 21-30.
[11]	李干琼, 李欣, 赵龙华, 许世卫. 农业供应链管理研究进展综述及展望[J]. 农业大数据学报, 2020, 2(3): 3-12.
[12]	杨娟, 钱婷婷, 郑秀国, 赵京音, 许叶颖. 蔬菜价格短期波动传导机制分析——以上海青菜为例[J]. 农业大数据学报, 2020, 2(3): 31-41.
[13]	李冬男, 潘国杨, 周倩, 李斌. 新冠疫情后我国生鲜农产品供应链发展方向[J]. 农业大数据学报, 2020, 2(3): 42-51.
[14]	杨晨雪, 孙志国. 基于区块链技术的农产品供应链数据管理系统设计[J]. 农业大数据学报, 2020, 2(2): 74-83.
[15]	江琳莉, 史磊. 从梁平柚到梅州柚—区块链技术助力农产品溯源[J]. 农业大数据学报, 2020, 2(2): 94-103.