搜索结果: 1-3 共查到“工学 variable selection”相关记录3条 . 查询时间(0.042 秒)
Spectrometric prediction of wood basic density by comparison of different grain angles and variable selection methods
Spectrometric prediction wood basic density
2023/6/2
Background:Wood basic density (WBD) is one of the most crucial wood property in tree and mainly determined the end use of wood for industry. However, the measurement WBD is time- and cost-consuming, w...
VARIABLE SELECTION FOR ROAD SEGMENTATION IN AERIAL IMAGES
Classification Feature Selection Logistic Regression Random Forests Road Extraction
2017/7/12
For extraction of road pixels from combined image and elevation data, Wegner et al. (2015) proposed classification of superpixels into road and non-road, after which a refinement of the classification...
梨可溶性固形物含量NIR与变量筛选无损检测（Measurement of Soluble Solids Content in Pear by FT-NIR Spectroscopy and Variable Selection）
梨 可溶性固形物含量 近红外光谱
2010/12/28
为提高利用近红外光谱技术快速检测梨可溶性固形物含量的精度和稳定性，结合区间偏最小二乘和遗传算法（iPLS-GA）来筛选校正模型中的特征光谱区和变量，通过交互验证法确定模型中的主成分因子数和筛选的变量，并以预测均方根误差（RMSEP）和相关系数（Rp）作为模型评价标准。试验结果显示：iPLS-GA最优模型包含5个光谱区、50个变量和10个主成分因子。最佳预测模型相关系数（Rp）和RMSEP 分别为0...