Abnormal Training Samples Detection Method Based on Median Absolute Deviation

Xunqiang Gong; Fangze Zhang; Tieding Lu; Zhigao Chen

doi:10.3788/LOP57.231202

Laser & Optoelectronics Progress, Volume. 57, Issue 23, 231202(2020)

Abnormal Training Samples Detection Method Based on Median Absolute Deviation

Xunqiang Gong^1,2、*, Fangze Zhang^1,2, Tieding Lu^1,2, and Zhigao Chen²

¹Fundamental Science on Radioactive Geology and Exploration Technology Laboratory, East China University of Technology, Nanchang, Jiangxi 330013, China

²Faculty of Geomatics, East China University of Technology, Nanchang, Jiangxi 330013, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(6)

Fig. 1. Verified sample

Download full size

Fig. 2. Different types of training samples. (a) Impure sample; (b) wrong choice sample

Download full size

Fig. 3. Classification results before and after removal impure training samples. (a) Before removal; (b) after removal

Download full size

Fig. 4. Classification results before and after ramoval of wrongly selected training samples. (a) Before removal; (b) after removal

Download full size

Table 1. Classification accuracy before and after removal impure training samples
View table
Table 1. Classification accuracy before and after removal impure training samples
Class Before removal After removal
Producer/% User/% Producer/% User/%
Building 99.494 64.125 96.866 94.571
Vegetation 68.037 100.000 95.658 99.807
Water 71.030 84.295 99.807 97.097
Bare ground 81.883 86.316 98.573 99.711

Table 2. Classification accuracy before and after removal of wrongly selected training samples
View table
Table 2. Classification accuracy before and after removal of wrongly selected training samples
Class Before removal After removal
Producer/% User/% Producer/% User/%
Building 94.439 62.329 97.573 98.469
Vegetation 79.676 99.884 99.307 99.583
Water 79.788 85.508 100.000 98.674
Bare ground 67.475 98.542 98.288 98.569

Tools

Get Citation

Copy Citation Text

Xunqiang Gong, Fangze Zhang, Tieding Lu, Zhigao Chen. Abnormal Training Samples Detection Method Based on Median Absolute Deviation[J]. Laser & Optoelectronics Progress, 2020, 57(23): 231202

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Instrumentation, Measurement and Metrology

Received: Mar. 17, 2020

Accepted: Apr. 15, 2020

Published Online: Dec. 8, 2020

The Author Email: Xunqiang Gong (xqgong1988@163.com)

DOI:10.3788/LOP57.231202

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Classification accuracy before and after removal impure training samples

Table 1. Classification accuracy before and after removal impure training samples

Table 2. Classification accuracy before and after removal of wrongly selected training samples

Table 2. Classification accuracy before and after removal of wrongly selected training samples