Research on agricultural monitoring system based on convolutional neural network

Abstract With the rapid development of social media, fluctuations in the price of vegetables are passed on to the people through the Internet in real time, which will certainly attract widespread attention in China. Therefore, Public opinion in social media is regarded as a latent factor contributing to market fluctuation. To predict the vegetable price fluctuation in China’s market, a hybrid prediction model combining convolution neural network with corpora is constructed. Although a direct causality test shows the uncertainty between the vegetable price and public opinion in social media, strong causality is found after removing the seasonal effect of price. This shows that the spread of public opinion through the Internet can strengthen the link between vegetable price changes and external events by affecting the expectations of market traders.

[1]  Susan Sunila Sharma,et al.  Can consumer price index predict gold price returns , 2016 .

[2]  Dieter Urban.  Quantitative measurement of public opinions on new technologies , 2005, Scientometrics.

[3]  Salim Lahmiri,et al.  Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks , 2014, J. King Saud Univ. Comput. Inf. Sci..

[4]  S. Lahmiri.  Long memory in international financial markets trends and short movements during 2008 financial crisis based on variational mode decomposition and detrended fluctuation analysis , 2015 .

[5]  Han Woo Park,et al.  Government organizations’ innovative use of the Internet: The case of the Twitter activity of South Korea’s Ministry for Food, Agriculture, Forestry and Fisheries , 2011, Scientometrics.

[6]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[7]  John R. Nofsinger.  Social Mood and Financial Economics , 2005 .

[8]  U. Soytaş,et al.  Oil price, agricultural commodity prices, and the dollar: A panel cointegration and causality analysis , 2012 .

[9]  Jingwen Zhang,et al.  Consumers' behaviors and concerns on fresh vegetable purchase and safety in Beijing urban areas, China , 2016 .

[10]  Guglielmo Maria Caporale,et al.  Causality and forecasting in incomplete systems , 1997 .

[11]  J. Boussard,et al.  A Simple Model of Endogenous Agricultural Commodity Price Fluctuations with Storage , 2011 .

[12]  Jingbo Xia,et al.  Construction of an Early-Warning System for Vegetable Prices Based on Index Contribution Analysis , 2015 .

[13]  Binghui Wu,et al.  The fractal feature and price trend in the gold future market at the Shanghai Futures Exchange (SFE) , 2017 .

[14]  Krzysztof Drachal,et al.  Forecasting spot oil price in a dynamic model averaging framework — Have the determinants changed over time? , 2016 .

[15]  Haizhong An,et al.  Research on patterns in the fluctuation of the co-movement between crude oil futures and spot prices: A complex network approach , 2014 .

[16]  Christis Hassapis,et al.  Unit roots and Granger causality in the EMS interest rates: the German Dominance Hypothesis revisited , 1999 .

[17]  Jianfeng Guo,et al.  How Does Market Concern Derived from the Internet Affect Oil Prices? , 2013 .

[18]  Xin Li,et al.  How does Google search affect trader positions and crude oil prices , 2015 .

[19]  Rockbill Haklak,et al.  Quantitative evaluation of positive or negative feelings for biotechnology- or health-related scenes in movies , 2006, Scientometrics.

[20]  W. Woon,et al.  Ensemble Prediction Model with Expert Selection for Electricity Price Forecasting , 2016 .