Accuracy Improvement in DOA Estimation with Deep Learning

Kase, Yuya; Nishimura, Toshihiko; Ohgane, Takeo; Ogawa, Yasutaka; Sato, Takanori; Kishiyama, Yoshihisa

doi:10.1587/transcom.2021ebt0001

Cited by 7 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], [17], we demonstrated that this DNN design achieved good performance in comparison with the traditional root-MUSIC and the compressed sensing technique HQR. However, decline in DOA detection accuracy is heavily influenced by radio waves impinging onto the angle bin border, which causes neighboring bins to be concurrently excited.…”

Section: Authors' Previous Workmentioning

confidence: 92%

“…In [16], [17] a DOA estimation scheme based solely on deep neural networks was proposed. As a primary assessment of its performance, just two incoming radio waves and a rather small-sized array with five antenna elements were considered.…”

Section: Authors' Previous Workmentioning

confidence: 99%

“…3). An effective approach proposed in [17] is to stack up on top of a main DNN (called DNN-A) a second one (DNN-B), whose output grid had been shifted by half DNN-A grid spacing, ranging from −60.5 • to +60.5 • . This method was then named staggered DNN, and it is shown in Fig.…”

Section: Authors' Previous Workmentioning

confidence: 99%

“…Therefore, our 2 and 3 sources consideration is not only realistic in airborne radar applications based on [13], but also it is a first step towards the goal of radio propagation measurements at sub-terahertz bands [14]. Yet, as it will be detailed later, simply expanding our setting from 2 sources [16], [17] to 3 brings new challenges that need to be addressed prior to fully leveraging DNNs as methods for DOA estimation. Next, in the second component, the angular spectrum grid is estimated with an also offline trained DNN.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Neural Networks Based End-to-End DOA Estimation System

ANDO,

KASE,

NISHIMURA

et al. 2023

IEICE Trans. Commun.

Self Cite

View full text Add to dashboard Cite

Direction of arrival (DOA) estimation is an antenna array signal processing technique used in, for instance, radar and sonar systems, source localization, and channel state information retrieval. As new applications and use cases appear with the development of next generation mobile communications systems, DOA estimation performance must be continually increased in order to support the nonstop growing demand for wireless technologies. In previous works, we verified that a deep neural network (DNN) trained offline is a strong candidate tool with the promise of achieving great on-grid DOA estimation performance, even compared to traditional algorithms. In this paper, we propose new techniques for further DOA estimation accuracy enhancement incorporating signal-to-noise ratio (SNR) prediction and an end-to-end DOA estimation system, which consists of three components: source number estimator, DOA angular spectrum grid estimator, and DOA detector. Here, we expand the performance of the DOA detector and angular spectrum estimator, and present a new solution for source number estimation based on DNN with very simple design. The proposed DNN system applied with said enhancement techniques has shown great estimation performance regarding the success rate metric for the case of two radio wave sources although not fully satisfactory results are obtained for the case of three sources.

show abstract

Section: Authors' Previous Workmentioning

confidence: 92%

Section: Authors' Previous Workmentioning

confidence: 99%

Section: Authors' Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Neural Networks Based End-to-End DOA Estimation System

ANDO,

KASE,

NISHIMURA

et al. 2023

IEICE Trans. Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method could improve the DOA estimation resolution effectively under a small antenna array aperture. Kase et al (2022) proposed a deep learning-based method to improve the DOA estimation accuracy. In this method, batch learning and several optimization techniques were used to analyze the DOA estimation capabilities of DNNs with different numbers of layers and units, which solved the problem that the DNN could frequently fail to estimate the correct bin when the received signal had arrived at angles near the grid border.…”

Section: Introductionmentioning

confidence: 99%

High-precision DOA estimation for underwater acoustic signals based on sparsity adaptation

et al. 2022

View full text Add to dashboard Cite

The direction of arrival (DOA) estimation technique is to obtain the direction information of the source when it reaches the array by processing and analyzing the received signal. In recent years, the DOA estimation of an array signal has been a research hotspot. For application scenarios with a small number of snapshots and a low signal-to-noise ratio, the compressive sensing theory has been commonly used to estimate the DOA of an array signal to achieve better estimation performance. However, the DOA estimation methods based on compressive sensing theory require information on source sparsity. Moreover, the influence of a complex underwater acoustic environment limits the accuracy of estimation algorithms. To address this limitation, this study proposes a high-precision DOA estimation model for underwater acoustic signals based on sparsity adaptation. The proposed model includes mainly two parts. In the first part, a source sparsity adaptive model based on a causal convolutional neural network is proposed. The model is used to address the constraint that the source sparsity should be known a priori when compressed sensing is used for DOA estimation. In the second part, a differential combination matching pursuit (DCMP) algorithm is adopted. First, a differentiated path filtering strategy is employed to reduce algorithm complexity and avoid the problem of invalid filtering. In addition, the combined optimization strategy is used to improve the prediction accuracy of the algorithm, providing an efficient error correction idea for the compressed sensing application to DOA estimation. The results of simulations conducted under seven different signal-to-noise ratios and using three different array types show that the proposed source sparsity adaptive model can reach an average prediction accuracy of 89.6%. In addition, compared with the other reconstruction algorithm accuracy, on the basis of ensuring low time complexity, the proposed DCMP algorithm can achieve an accuracy improvement of 9.99%–19.94% under seven different signal-to-noise ratio values. Moreover, the mean absolute error of the proposed DCMP algorithm is lower by approximately 0.05°–14° than those of the OMP and MMP algorithms.

show abstract

A Novel Neural Network Approach for Coherent Source DOA Estimation

Wang

2022

2022 5th International Conference on Information Communication and Signal Processing (ICICSP)

View full text Add to dashboard Cite

Accuracy Improvement in DOA Estimation with Deep Learning

Cited by 7 publications

References 21 publications

Deep Neural Networks Based End-to-End DOA Estimation System

Deep Neural Networks Based End-to-End DOA Estimation System

High-precision DOA estimation for underwater acoustic signals based on sparsity adaptation

A Novel Neural Network Approach for Coherent Source DOA Estimation

Contact Info

Product

Resources

About