Soil Classification Based on Deep Learning Algorithm and Visible Near-Infrared Spectroscopy

<table class="table-group" id="tab9"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left" rowspan="2">Proportion of calibration set</td><td class="align_center" colspan="2">Convolutional neural network</td><td class="align_center" colspan="2">Support vector machine</td></tr><tr class="thead"><td class="align_center">Calibration set</td><td class="align_center">Test set</td><td class="align_center">Calibration set</td><td class="align_center">Test set</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">1/3</td><td class="align_center">100.00% (90/90)</td><td class="align_center">95.58%(173/181)</td><td class="align_center">98.89% (89/90)</td><td class="align_center">91.16% (165/181)</td></tr><tr><td class="align_left">1/4</td><td class="align_center">100.00% (68/68)</td><td class="align_center">94.09% (191/203)</td><td class="align_center">98.53% (67/68)</td><td class="align_center">91.13% (185/203)</td></tr><tr><td class="align_left">1/5</td><td class="align_center">100.00% (56/56)</td><td class="align_center">87.91% (189/215)</td><td class="align_center">100.00%(56/56)</td><td class="align_center">88.37% (190/215)</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The classification results of the calibration set and the test set based on the different number of samples in the calibration set by random method.</div>

Journal of Spectroscopy

tab9

Table 9

Table 9: Soil Classification Based on Deep Learning Algorithm and Visible Near-Infrared Spectroscopy 