Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition

Open set recognition (OSR) is a technique employed to ascertain whether unknown data belongs to a class in a database when the training class is incomplete. In addressing the OSR challenge associated with ADS-B leading pulse signals, this paper proposes a two-dimensional visualization of open set re...

Full description

Saved in:
Bibliographic Details
Main Author: Tong Xu
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Intelligent Systems with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667305324001388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124974781235200
author Tong Xu
author_facet Tong Xu
author_sort Tong Xu
collection DOAJ
description Open set recognition (OSR) is a technique employed to ascertain whether unknown data belongs to a class in a database when the training class is incomplete. In addressing the OSR challenge associated with ADS-B leading pulse signals, this paper proposes a two-dimensional visualization of open set recognition (VOSR) approach that encompasses the stages of feature extraction, feature selection, and feature learning levels. At the feature extraction level, the I/Q features and phase features of the signal are selected; at the feature selection level, feature similarity analysis and mean decrease impurity-based random forest are employed; at the feature learning level, the framework of fusion residual network and the t-distributed stochastic neighbor embedding and circular surfaces (t-SNE-CS) strategy is constructed, and experiments are carried out on the close set data containing 20 classes of 10,229 samples and open set data containing 10 classes of 1,688 samples. Results show that the accuracy of the optimal combination of the residual network and the constructed features is 94.63% for the test set for the close set classification task. For the VOSR task, the accuracy of the test set is 93.69%, the open set recognition accuracy is 53.97% and Macro-F1 scores is 91.8%.
format Article
id doaj-art-b7878ba406d841599d8118b5917bd97c
institution Kabale University
issn 2667-3053
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Intelligent Systems with Applications
spelling doaj-art-b7878ba406d841599d8118b5917bd97c2024-12-13T11:07:29ZengElsevierIntelligent Systems with Applications2667-30532024-12-0124200464Fusion of residual network and t-SNE-CS for 2D visualization of open set recognitionTong Xu0School of Information Technology, Jiangsu Open University, Nanjing 210000, ChinaOpen set recognition (OSR) is a technique employed to ascertain whether unknown data belongs to a class in a database when the training class is incomplete. In addressing the OSR challenge associated with ADS-B leading pulse signals, this paper proposes a two-dimensional visualization of open set recognition (VOSR) approach that encompasses the stages of feature extraction, feature selection, and feature learning levels. At the feature extraction level, the I/Q features and phase features of the signal are selected; at the feature selection level, feature similarity analysis and mean decrease impurity-based random forest are employed; at the feature learning level, the framework of fusion residual network and the t-distributed stochastic neighbor embedding and circular surfaces (t-SNE-CS) strategy is constructed, and experiments are carried out on the close set data containing 20 classes of 10,229 samples and open set data containing 10 classes of 1,688 samples. Results show that the accuracy of the optimal combination of the residual network and the constructed features is 94.63% for the test set for the close set classification task. For the VOSR task, the accuracy of the test set is 93.69%, the open set recognition accuracy is 53.97% and Macro-F1 scores is 91.8%.http://www.sciencedirect.com/science/article/pii/S2667305324001388ADS-B preamble pulse signals2D visualization of open set recognitionCircular surfacest-distributed stochastic neighbor embedding
spellingShingle Tong Xu
Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
Intelligent Systems with Applications
ADS-B preamble pulse signals
2D visualization of open set recognition
Circular surfaces
t-distributed stochastic neighbor embedding
title Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
title_full Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
title_fullStr Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
title_full_unstemmed Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
title_short Fusion of residual network and t-SNE-CS for 2D visualization of open set recognition
title_sort fusion of residual network and t sne cs for 2d visualization of open set recognition
topic ADS-B preamble pulse signals
2D visualization of open set recognition
Circular surfaces
t-distributed stochastic neighbor embedding
url http://www.sciencedirect.com/science/article/pii/S2667305324001388
work_keys_str_mv AT tongxu fusionofresidualnetworkandtsnecsfor2dvisualizationofopensetrecognition