Performance Analysis of DOA Estimation of Two Targets Using Deep Learning

Kase, Yuya; Nishimura, Toshihiko; Ohgane, Takeo; Ogawa, Yasutaka; Kitayama, Daisuke; Kishiyama, Yoshihisa

doi:10.1109/wpmc48795.2019.9096165

Cited by 7 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [71], a DNN outperforms a maximum likelihood estimator in efficiency when the number of sources is unknown, while at the same time providing lower complexity. However, in the case of on-grid estimation, such a DNN performance is very sensitive, when DOA estimation is conducted at the boundaries of bins used to divide the AOA space [72]. In this context, [73] converts a traditional DOA estimation problem to a multilabel classification one, based on a CNN, to discriminate between various sound sources, as well as to reduce the array aperture limitation.…”

Section: State Of the Art In Deep Learningmentioning

confidence: 99%

A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

et al. 2022

View full text Add to dashboard Cite

The key objective of this paper is to explore the recent state-of-the-art artificial intelligence (AI) applications on the broad field of beamforming. Hence, a multitude of AI-oriented beamforming studies are thoroughly investigated in order to correctly comprehend and profitably interpret the AI contribution in the beamforming performance. Starting from a brief overview of beamforming, including adaptive beamforming algorithms and direction of arrival (DOA) estimation methods, our analysis probes further into the main machine learning (ML) classes, the basic neural network (NN) topologies, and the most efficient deep learning (DL) schemes. Subsequently, and based on the prior aspects, the paper explores several concepts regarding the optimal use of ML and NNs either as standalone beamforming and DOA estimation techniques or in combination with other implementations, such as ultrasound imaging, massive multipleinput multiple-output structures, and intelligent reflecting surfaces. Finally, particular attention is drawn on the realization of beamforming or DOA estimation setups via DL topologies. The survey closes with various important conclusions along with an interesting discussion on potential future aspects and promising research challenges.

show abstract

Section: State Of the Art In Deep Learningmentioning

confidence: 99%

A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It has also been applied in the field of radio signal processing, including signal detection [16,17], modulation recognition [18][19][20][21], channel estimation [22], and information recovery [23]. Similarly, in DOA estimation, deep learning-based methods have emerged as an alternative to traditional DOA estimation methods [24,25].…”

Section: Introductionmentioning

confidence: 99%

“…Most deep learning-based DOA estimation methods tackled the problem using a classification model [24][25][26][27][28][29]. In [24], the authors attempted to solve the DOA estimation problem using a deep neural network (DNN) with the lower triangular part of the Covariance Matrix (CM) as input for two signal sources.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based DOA Estimation

Zheng,

Yang,

Shen

et al. 2024

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications in many fields. In recent years, deep learning has been applied to DOA estimation to improve the performance. However, most existing deep learning-based DOA estimation methods extract DOA information from the covariance matrix (CM) input. In this paper, we introduce a novel deep learningbased DOA estimation scheme that utilizes the raw in-phase (I) and quadrature (Q) components of the signal as the input. We formulate the problem as single-label classification and multilabel classification based on the number of signal sources. We design a convolutional neural network to solve the problems and to adapt to different number of snapshots. We also propose a deep learning regression-based method to overcome the limitations of classify-based methods in dealing with off-grid angles. We conduct extensive experiments with simulations and over-theair collected signals to analyze the performance of the proposed method in various scenarios including different SNRs, additive generalized Gaussian noise (AGGN) and extreme multi-source DOA estimation. Results demonstrate that our proposed method outperforms the existing deep learning-based DOA estimation methods.

show abstract

“…* A part of this paper was presented at Wireless Personal Multimedia Communications (WPMC 2019) [1] and 2020 International Conference on Emerging Technologies for Communications (ICETC 2020) [2].…”

Section: Introductionmentioning

confidence: 99%

Accuracy Improvement in DOA Estimation with Deep Learning

Kase

Nishimura

Ohgane

et al. 2022

IEICE Trans. Commun.

Self Cite

View full text Add to dashboard Cite

Direction of arrival (DOA) estimation of wireless signals is demanded in many applications. In addition to classical methods such as MUSIC and ESPRIT, non-linear algorithms such as compressed sensing have become common subjects of study recently. Deep learning or machine learning is also known as a non-linear algorithm and has been applied in various fields. Generally, DOA estimation using deep learning is classified as on-grid estimation. A major problem of on-grid estimation is that the accuracy may be degraded when the DOA is near the boundary. To reduce such estimation errors, we propose a method of combining two DNNs whose grids are offset by one half of the grid size. Simulation results show that our proposal outperforms MUSIC which is a typical off-grid estimation method. Furthermore, it is shown that the DNN specially trained for a close DOA case achieves very high accuracy for that case compared with MUSIC.

show abstract

Performance Analysis of DOA Estimation of Two Targets Using Deep Learning

Cited by 7 publications

References 10 publications

A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

Deep Learning-Based DOA Estimation

Accuracy Improvement in DOA Estimation with Deep Learning

Contact Info

Product

Resources

About