摘要：
Watermelon is a crop susceptible to diseases. Rapid and effective detection of watermelon diseases is of great significance to ensure the yield of watermelon. Aiming at the interference of the environment and obstacles in the natural environment, resulting in low target detection accuracy and poor robustness, this paper takes watermelon leaves as the research object, considering anthracnose, leaf blight, leaf spot and normal leaves as examples. A disease recognition method based on deep learning is proposed. This paper has improved the pre-selected box setting formula of the SSD model and tested it in multiple SSD models. Experiments show that the average accuracy of the final SSD768 model is 92.4%, and the average accuracy of the IOU is 88.9%. It shows that this method can be used to detect watermelon diseases in natural environment.
作者机构：
College of Information Science and Technology,Hunan Agricultural University
会议名称：
2019计算智能、工程与信息技术世界大会
会议时间：
2019-06-29
会议地点：
中国上海
会议论文集名称：
Proceedings of The 2019 World Congress on Computational Intelligence, Engineering and Information Technology (WCEIT 2019)
摘要：
In order to obtain the fluctuation and cycles of intra-annual and inter-annual,the weekly data was studied and analyzed of the pig price in China.However,the study shows the fluctuation is high at both ends and low in the middle of the year and the cycle of price variation is about 3 years.Based on this research,a comprehensive analysis for the factors affecting the price fluctuation is supply,demand and external.Further,the stepwise regression analysis and the correlation coefficient analysis are used to analyze the influencing factors of pig price.Whatever,the analysis shows that pork price,piglet price,corn price and soybean price have significant fluctuations for pig price.
期刊：
IPPTA: Quarterly Journal of Indian Pulp and Paper Technical Association,2018年30(6):509-516 ISSN：0379-5462
通讯作者：
Chen, Y.
作者机构：
[Fang K.; Chen Y.; He X.] College of Information Science and Technology, Hunan Agricultural University, Changsha, Hunan, 410128, China;[Hu Y.] Changsha Branch, Agricultural Bank of China, Changsha, Hunan, 410132, China
通讯机构：
College of Information Science and Technology, Hunan Agricultural University, Changsha, Hunan, China
摘要：
Scientific classification of land production functions can promote the efficient use of land. In this paper, 16 land production functions were collected, and 10 characteristic features of land production function were put forward according to the different attributes of each function. The characteristics of the land production functions are assigned to obtain the land production function score table, Then use the hierarchical clustering and K-means clustering analysis those data, and the results of three kinds of hierarchical clustering and one K-means clustering were obtained. By comparing with the results of sequence classification, 16 land production functions are classified into three categories.
摘要：
The meteorological factors play an important role in rice yield. In this paper, according to the current agricultural meteorological factors on the impact of agricultural production, an the rice yield prediction model was established by using multiple stepwise regression analysis. The experimental results show that the average forecast accuracy is more than 98%, and the prediction result is consistent with the trend of the measured results, and the prediction results are credible.
期刊：
Journal of Computational Methods in Sciences and Engineering,2016年16(2):369-377 ISSN：1472-7978
通讯作者：
Fang, Kui
作者机构：
[Fang, Kui; Yu, Hexiang] Information Science and Technology Institute, Hunan Agricultural University, Changsha, Hunan, China;[Fang, Kui; Yu, Hexiang] College of Resources and Environment, Hunan Agricultural University, Changsha, Hunan, China
通讯机构：
Information Science and Technology Institute, Hunan Agricultural University, Changsha, Hunan, China
关键词：
Three rural loans;Support vector machine;Classification prediction
摘要：
Based on the data mining method, Support Vector Machine technology, Correlated Analytical Variable Selection method and Principal Component Analytical Variable Dimension Reduction method, setting five-category classification and prediction model for “Three rural” loan risk of commercial bank, then make classification prediction for an Agricultural Bank of China in Changsha and verify the outcome through this prediction model, and make comparative analysis with the classification prediction accuracy of neural network and the time consumed for processing, the advantage of this method is obvious. This five-category classification and prediction model for loan risk have great meanings for bank to establish more robust customer relationship management system and attract more high-quality customer resources.
