DeepMUSIC: Multiple Signal Classification via Deep Learning
Yükleniyor...
Dosyalar
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
This letter introduces a deep learning (DL) framework for the classification of multiple signals in direction finding (DF) scenario via sensor arrays. Previous works in DL context mostly consider a single or two target scenario, which is a strong limitation in practice. Hence, in this letter, we propose a DL framework called DeepMUSIC for multiple signal classification. We design multiple deep convolutional neural networks (CNNs), each of which is dedicated to a subregion of the angular spectrum. Each CNN learns the MUltiple SIgnal Classification (MUSIC) spectra of the corresponding angular subregion. Hence, it constructs a nonlinear relationship between the received sensor data and the angular spectrum. We have shown, through simulations, that the proposed DeepMUSIC framework has superior estimation accuracy and exhibits less computational complexity in comparison with both DL- and non-DL-based techniques. © 2017 IEEE.
Açıklama
Anahtar Kelimeler
convolutional neural network (CNN), deep learning (DL), deep MUSIC, direction finding (DF), direction-of-arrival (DOA) estimation, MUltiple SIgnal Classification (MUSIC), Sensor signal processing
Kaynak
IEEE Sensors Letters
WoS Q Değeri
Scopus Q Değeri
Q2
Cilt
4
Sayı
4
