Study on a Pattern Classification Method of Soil Quality Based on Simplified Learning Sample Dataset
暂无分享,去创建一个
Based on the massive soil information in current soil quality grade evaluation, this paper constructed an intelligent classification approach of soil quality grade depending on classical sampling techniques and disordered multiclassification Logistic regression model. As a case study to determine the learning sample capacity under certain confidence level and estimation accuracy, and use c-means algorithm to automatically extract the simplified learning sample dataset from the cultivated soil quality grade evaluation database for the study area, Long chuan county in Guangdong province, a disordered Logistic classifier model was then built and the calculation analysis steps of soil quality grade intelligent classification were given. The result indicated that the soil quality grade can be effectively learned and predicted by the extracted simplified dataset through this method, which changed the traditional method for soil quality grade evaluation.
[1] Tim Oates,et al. Efficient progressive sampling , 1999, KDD '99.
[2] Lu Wang,et al. [Planning of monitoring points for agricultural products security based on integrated weighted clustering method]. , 2009, Ying yong sheng tai xue bao = The journal of applied ecology.
[3] Alex B. McBratney,et al. Soil pattern recognition with fuzzy-c-means : application to classification and soil-landform interrelationships , 1992 .
[4] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.