考虑环境参数的农业生产数据深度挖掘仿真

Deep Mining Simulation of Agricultural Production Data Considering Environmental Parameters

农业生产数据受到多种因素的影响,如气候、土壤、病虫害等,这些因素会导致数据存在较大的误差和不确定性,从而影响数据挖掘的准确性。为了能够获取精准的农业生产数据深度挖掘结果,提出一种环境参数影响下农业生产数据深度挖掘算法。分析环境参数对农业生产数据和农业生产数据深度挖掘的影响。采用支持向量机聚类和数据域描述方法,对全部农业生产数据展开样本数据归类处理。根据原始空间农业生产数据属性值的极值,确定样本的属性范围。利用获取的支持向量提取规则,完成农业生产数据深度挖掘。实验结果表明,所提算法的农业生产数据拟合度大于0.75,且挖掘准确性保持在0.9以上,表明上述算法可以获取高精度和高效率的农业生产数据深度挖掘结果。

Agricultural production data are affected by many factors,such as climate,soil,pests and diseases,etc.These factors will lead to large errors and uncertainties in the data,thus affecting the accuracy of data mining.In order to obtain accurate agricultural production data mining results,a deep mining algorithm for agricultural production data under the influence of environmental parameters is proposed.The influence of environmental parameters on agricultural production data and deep mining of agricultural production data is analyzed.Support vector machine clustering and data domain description methods are used to categorize all the sample data of agricultural production data.The attribute range of the samples is determined according to the extreme values of the attribute values of the original spatial agricultural production data.The acquired support vector extraction rules are used to complete the deep mining of agricultural production data.The experimental results show that the proposed algorithm has a goodness-of-fit of more than 0.75 for the agricultural production data,and the mining accuracy stays above 0.9,which indicates that the algorithm can obtain high-precision and high-efficiency agricultural production data deep mining results.