Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/6485
Title: Deep Neural Network Initialization Methods for Micro-Doppler Classification With Low Training Sample Support
Authors: Seyfioğlu, Mehmet Saygın
Gürbüz, Sevgi Zübeyde
Keywords: Convolutional autoencoders (CAEs)
convolutional neural networks (CNN)
gait classification
micro-Doppler
radar
transfer learning
VGGNet
Publisher: IEEE-Inst Electrical Electronics Engineers Inc
Abstract: Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however, acquiring a measured data set of the order of thousands is challenging due to constraints on manpower, cost, and other resources. In this letter, the efficacy of two neural network initialization techniques-unsupervised pretraining and transfer learning-for dealing with training DNNs on small data sets is compared. Unsupervised pretraining is implemented through the design of a convolutional autoencoder (CAE), while transfer learning from two popular convolutional neural network architectures (VGGNet and GoogleNet) is used to augment measured RF data for training. A 12-class problem for discrimination of micro-Doppler signatures for indoor human activities is utilized to analyze activation maps, bottleneck features, class model, and classification accuracy with respect to training sample size. Results show that on meager data sets, transfer learning outperforms unsupervised pretraining and random initialization by 10% and 25%, respectively, but that when the sample size exceeds 650, unsupervised pretraining surpasses transfer learning and random initialization by 5% and 10%, respectively. Visualization of activation layers and learned models reveals how the CAE succeeds in representing the micro-Doppler signature.
URI: https://doi.org/10.1109/LGRS.2017.2771405
https://hdl.handle.net/20.500.11851/6485
ISSN: 1545-598X
1558-0571
Appears in Collections:Elektrik ve Elektronik Mühendisliği Bölümü / Department of Electrical & Electronics Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record



CORE Recommender

SCOPUSTM   
Citations

54
checked on Dec 21, 2024

WEB OF SCIENCETM
Citations

83
checked on Aug 31, 2024

Page view(s)

74
checked on Dec 16, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.