Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using ...Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using J2EE and ArcGIS Server technology. The service platform is able to predict the occurrence period, amount of pest, occurrence tendency, and pest zones in the B/S environment and realized the display, querying, analysis and editing of the spatial data and the automatically integrated control of multilevel Data,. Additionaly, the service platform offers the visualization of geographic service and predicted results. It provides a solution for prediction of forest pest and forest resource management.展开更多
Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using ...Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using J2EE and ArcGIS Server technology. The service platform is able to predict the occurrence period, amount of pest, occurrence tendency, and pest zones in the B/S environment and realized the display, querying, analysis and editing of the spatial data and the automatically integrated control of multilevel Data,. Additionaly, the service platform offers the visualization of geographic service and predicted results. It provides a solution for prediction of forest pest and forest resource management.展开更多
Pork is common in people's daily life consumption,and it accounts for more than half of all meats. By collecting data information published by Bureau of Statistics and Bureau of Agriculture,this paper makes a stat...Pork is common in people's daily life consumption,and it accounts for more than half of all meats. By collecting data information published by Bureau of Statistics and Bureau of Agriculture,this paper makes a statistical analysis of the influence of price fluctuation in the pork market on China's pork production,and finds that China's pork production shows a general trend of fluctuations due to the impact of price factors.According to the predecessors' studies on the factors influencing pig market price,combined with the actual situation of pig breeding in China,this paper uses the latest website data released by the government's public information platform to establish a forecasting model.展开更多
建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性...建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性与电力负荷数据的相关性不强并且Transformer无法捕捉电力负荷数据的时间相关性,而导致电力负荷预测不够准确的问题,基于SR(Székely and Rizzo)距离相关系数、融合时间定位编码和Transformer,提出了一种短期电力负荷预测模型SF-Transformer.SF-Transformer通过SR距离相关系数对影响电力负荷数据的属性进行筛选,选择与电力负荷数据之间SR距离相关系数较大的属性.SF-Transformer采用一种全局时间编码与局部位置编码相结合的融合时间定位编码,有助于模型全面获取电力负荷数据的时间定位信息.在数据集上开展了实验,实验结果表明SF-Transformer与其他模型相比,在两种时长上进行电力负荷预测具有更低的均方根误差和平均绝对误差.展开更多
基金supported by the 11th Five Years KeyPrograms for Science and Technology Development of China(2006BAD10A03-5)Heilongjiang Programs for Science and Technology Development in 2006(GB06A110)Haerbin Technologies R&D Programin 2007(2007AA1CG077-1)
文摘Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using J2EE and ArcGIS Server technology. The service platform is able to predict the occurrence period, amount of pest, occurrence tendency, and pest zones in the B/S environment and realized the display, querying, analysis and editing of the spatial data and the automatically integrated control of multilevel Data,. Additionaly, the service platform offers the visualization of geographic service and predicted results. It provides a solution for prediction of forest pest and forest resource management.
文摘Taking Linkou Forestry Bureau, Heilongjiang Province, China as the demonstration plot and Dendrolimus pinidiatrea as an example, we developed a WebGIS-based information service platform for forest pest forecast using J2EE and ArcGIS Server technology. The service platform is able to predict the occurrence period, amount of pest, occurrence tendency, and pest zones in the B/S environment and realized the display, querying, analysis and editing of the spatial data and the automatically integrated control of multilevel Data,. Additionaly, the service platform offers the visualization of geographic service and predicted results. It provides a solution for prediction of forest pest and forest resource management.
基金Supported by Shaoxing"13th Five-Year Plan"Key Philosophy and Social Sciences Project in 2016-"Study on Promoting the Development of Agricultural Products Supply Chain in Shaoxing by Information Technology"Zhejiang Provincial Society of Commercial Economy Project in 2016(2016SJYB02)+1 种基金Jiyang College of Zhejiang A&F University Classroom Teaching Reform Project(kgyb201504)Shaoxing Classroom Teaching Reform Project in 2015
文摘Pork is common in people's daily life consumption,and it accounts for more than half of all meats. By collecting data information published by Bureau of Statistics and Bureau of Agriculture,this paper makes a statistical analysis of the influence of price fluctuation in the pork market on China's pork production,and finds that China's pork production shows a general trend of fluctuations due to the impact of price factors.According to the predecessors' studies on the factors influencing pig market price,combined with the actual situation of pig breeding in China,this paper uses the latest website data released by the government's public information platform to establish a forecasting model.
文摘建设智能教育平台是推动教育智能化的一个重要过程,但智能教育平台依赖的人工智能模型在训练过程中会消耗大量电力,因此,开展短期电力负荷预测对建设智能教育平台具有重要意义.针对在考虑多个属性开展短期电力负荷预测时,由于部分属性与电力负荷数据的相关性不强并且Transformer无法捕捉电力负荷数据的时间相关性,而导致电力负荷预测不够准确的问题,基于SR(Székely and Rizzo)距离相关系数、融合时间定位编码和Transformer,提出了一种短期电力负荷预测模型SF-Transformer.SF-Transformer通过SR距离相关系数对影响电力负荷数据的属性进行筛选,选择与电力负荷数据之间SR距离相关系数较大的属性.SF-Transformer采用一种全局时间编码与局部位置编码相结合的融合时间定位编码,有助于模型全面获取电力负荷数据的时间定位信息.在数据集上开展了实验,实验结果表明SF-Transformer与其他模型相比,在两种时长上进行电力负荷预测具有更低的均方根误差和平均绝对误差.