Open AccessOpen set HRRP recognition based on convolutional neural network
Author(s) -
Chen Wei,
Wang Yanhua,
Song Jia,
Li Yang
Publication year - 2019
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2019.0706
Subject(s) - softmax function , convolutional neural network , computer science , pattern recognition (psychology) , artificial intelligence , set (abstract data type) , test set , open set , class (philosophy) , sample (material) , range (aeronautics) , layer (electronics) , artificial neural network , mathematics , engineering , chemistry , organic chemistry , discrete mathematics , programming language , aerospace engineering , chromatography
Most existing algorithms in high‐resolution range profile recognition focus on the closed set cases, where the test sample is from a known class. However, a sample could be drawn from unknown classes in realistic scenario, which is named as open set recognition. Here, open set HRRP recognition is achieved by incorporating extreme value theory into convolutional neural network. The softmax layer is replaced by a so‐called openmax layer which estimates probabilities of the test sample belonging to known and unknown classes. Experimental results demonstrate that the proposed method outperforms the state‐of‐art algorithms such as NN, 1‐vs‐set machine, and W‐SVM in terms of correct rejection rate.