The Detection of the Liquid Drop Fingerprint’s Abnormal Values Based on Boxplot Method
Lists
Only you see this
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.
BibTeX
@inproceedings{song2015detection,
author = {Quanjian Song and Mingyong Qiao and S.H. Zhang and Lu Yang},
title = {{The Detection of the Liquid Drop Fingerprint’s Abnormal Values Based on Boxplot Method}},
booktitle = {Advances},
year = {2015},
doi = {10.2991/aiie-15.2015.6},
}