The Detection of the Liquid Drop Fingerprint’s Abnormal Values Based on Boxplot Method

DOI

10.2991/aiie-15.2015.6How to use a DOI?

Keywords

the liquid drop fingerprint; abnormal values detectio; identification; Boxplot method

Abstract

In order to effectively detect the abnormal data of the liquid drop in the droplet analysis system and to improve the accuracy of the liquid drop fingerprint, a new method based on boxplot is put forward. After optimizing the 12 dimensional feature vectors of the liquid drop fingerprint, visualization of statistics is applied on the optimized 6 dimensional feature vectors by using boxplot method. With the median (±5%) as the threshold values, abnormal droplets are screened. Experimental results show that the detection recognition ratio of the abnormal liquid drop can be ensured after feature optimization, together with the greatly reduced computational complexity. Boxplot method is effective in detection of abnormal liquid drop fingerprint, with its accuracy up to 100% among selected samples.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Q. Song
AU  - M.Y. Qiao
AU  - S.H. Zhang
AU  - L. Yang
PY  - 2015/07
DA  - 2015/07
TI  - The Detection of the Liquid Drop Fingerprint’s Abnormal Values Based on Boxplot Method
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 17
EP  - 20
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.6
DO  - 10.2991/aiie-15.2015.6
ID  - Song2015/07
ER  -