Yunye Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yunye Su has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Xianpeng Wang
Hainan Provincial Key Laboratory of Low-Altitude Intelligent Sensing and Information Processing, School of Information and Communication Engineering, Hainan University, Haikou 570228, China
4 shared publications - Yuehao Guo
Hainan University
3 shared publications - Dandan Meng
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China
1 shared publication - Feifei Gao
Tsinghua University
1 shared publication - Gaojie Chen
Sun Yat-sen University
1 shared publication - Han Wang
Faculty of Data Science, City University of Macau, Macao, China
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 10450-10465
Cascaded Multi-Head Attention Transformer Framework for Direction of Arrival Estimation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 10450-10465
Cascaded Multi-Head Attention Transformer Framework for Direction of Arrival Estimation
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP, 1
A Data-Driven DOA Estimation Based Target Localization for Internet of Unmanned System
With the rapid development of autonomous unmanned systems, the internet of unmanned agents (IUA) has emerged as a prominent research field. Direction of Arrival (DOA) estimation enables intelligent base stations (IBS) to detect the direction of unmanned device, facilitating essential functions such as target localization and tracking, and cooperative navigation, significantly enhancing the environmental perception capabilities and task execution efficiency of IUA systems. However,the traditional DOA estimation algorithms in practical complex electromagnetic mutual coupling environments are computationally intensive, incompatible with IUA’s high real-time requirements. To address these challenges, this paper proposes a data-driven (DD) DOA estimation method for unmanned device localization in IUA. The IUA localization system comprises four IBS equipped with uniform linear arrays (ULAs). Device localization is achieved through DOA estimates from these four IBS. A Deep Learning (DL) is proposed to jointly address two key challenges: IUA’s demand for real-time algorithm performance and mutual coupling effects between IBS sensors. A novel DL architecture is designed to estimate off-grid angle parameters and mutual coupling coefficients. The framework incorporates two learnable modules, one focusing on mutual coupling coefficients and another aimed at precise DOA estimation and associated confidence levels. The target unmanned device position is estimated using the least squares method applied to the DOA measurements from all IBSs. The proposed DL-based algorithm surpasses existing methods while maintaining low computational complexity. Extensive simulations demonstrate the high performance and real-time capabilities of the DD-based solution.
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP, 1
A Data-Driven DOA Estimation Based Target Localization for Internet of Unmanned System
With the rapid development of autonomous unmanned systems, the internet of unmanned agents (IUA) has emerged as a prominent research field. Direction of Arrival (DOA) estimation enables intelligent base stations (IBS) to detect the direction of unmanned device, facilitating essential functions such as target localization and tracking, and cooperative navigation, significantly enhancing the environmental perception capabilities and task execution efficiency of IUA systems. However,the traditional DOA estimation algorithms in practical complex electromagnetic mutual coupling environments are computationally intensive, incompatible with IUA’s high real-time requirements. To address these challenges, this paper proposes a data-driven (DD) DOA estimation method for unmanned device localization in IUA. The IUA localization system comprises four IBS equipped with uniform linear arrays (ULAs). Device localization is achieved through DOA estimates from these four IBS. A Deep Learning (DL) is proposed to jointly address two key challenges: IUA’s demand for real-time algorithm performance and mutual coupling effects between IBS sensors. A novel DL architecture is designed to estimate off-grid angle parameters and mutual coupling coefficients. The framework incorporates two learnable modules, one focusing on mutual coupling coefficients and another aimed at precise DOA estimation and associated confidence levels. The target unmanned device position is estimated using the least squares method applied to the DOA measurements from all IBSs. The proposed DL-based algorithm surpasses existing methods while maintaining low computational complexity. Extensive simulations demonstrate the high performance and real-time capabilities of the DD-based solution.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (8) , 5993-6005
DOA Estimation With Deep Learning: A Limited Training Data Framework
Deep Learning (DL) achieves significant performance in estimating the direction of arrival (DOA) in array signal processing. However, many existing DL methods require a large amount of data to train a specialized DL network. To reduce data requirements for training, this paper presents a novel DL-based DOA estimation algorithm for limited training data(LTDDOA-net). The proposed algorithm utilizes the properties of second-order derivatives of the loss function and the ’learn to learn’ approach to construct a framework that can achieve good performance with minimal data training. Initially, we developed a neural network designed for DOA estimation. This network was subsequently trained using proposed method and loss function on a limited dataset. Ultimately, we validated the practicality and benefits of our approach through simulations and hardware experiment. The results of simulations and hardware experiment have verified the superiority of the proposed approach.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (8) , 5993-6005
DOA Estimation With Deep Learning: A Limited Training Data Framework
Deep Learning (DL) achieves significant performance in estimating the direction of arrival (DOA) in array signal processing. However, many existing DL methods require a large amount of data to train a specialized DL network. To reduce data requirements for training, this paper presents a novel DL-based DOA estimation algorithm for limited training data(LTDDOA-net). The proposed algorithm utilizes the properties of second-order derivatives of the loss function and the ’learn to learn’ approach to construct a framework that can achieve good performance with minimal data training. Initially, we developed a neural network designed for DOA estimation. This network was subsequently trained using proposed method and loss function on a limited dataset. Ultimately, we validated the practicality and benefits of our approach through simulations and hardware experiment. The results of simulations and hardware experiment have verified the superiority of the proposed approach.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Co-Prime Array Interpolation for DOA Estimation Using Deep Matrix Iterative Network
Co-prime arrays achieve a significant number of virtual arrays in the same physical sensors by difference co-arrays. There are however, many existing methods that do not utilize all the information that the coprime array receives due to the difference co-array having defects that cause empty holes in the virtual arrays. For the purpose of estimation of the direction of arrival (DOA), we present in this paper an algorithm for co-prime array interpolation based on Deep Learning. The proposed interpolation algorithm employs the covariance matrix of the interpolated virtual array to construct a self-supervision loss function based on the Hermitian semi-definite Toeplitz condition. And build a novel net structure to learn the mapping of the loss function described above. Firstly, we build a matrix iterative network (MIN) by the idea of array interpolation such that all the information of the virtual array can be utilized. Subsequently, we fill in zero elements in each empty hole of virtual arrays, put it into the MIN and receive the interpolated covariance matrix. By exploiting MIN, we recover the covariance matrix for DOA estimation. The simulation performance and experimental result have verified the superiority of the proposed algorithm.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Co-Prime Array Interpolation for DOA Estimation Using Deep Matrix Iterative Network
Co-prime arrays achieve a significant number of virtual arrays in the same physical sensors by difference co-arrays. There are however, many existing methods that do not utilize all the information that the coprime array receives due to the difference co-array having defects that cause empty holes in the virtual arrays. For the purpose of estimation of the direction of arrival (DOA), we present in this paper an algorithm for co-prime array interpolation based on Deep Learning. The proposed interpolation algorithm employs the covariance matrix of the interpolated virtual array to construct a self-supervision loss function based on the Hermitian semi-definite Toeplitz condition. And build a novel net structure to learn the mapping of the loss function described above. Firstly, we build a matrix iterative network (MIN) by the idea of array interpolation such that all the information of the virtual array can be utilized. Subsequently, we fill in zero elements in each empty hole of virtual arrays, put it into the MIN and receive the interpolated covariance matrix. By exploiting MIN, we recover the covariance matrix for DOA estimation. The simulation performance and experimental result have verified the superiority of the proposed algorithm.