Wei Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Wei Ji has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ling Qiu
Key Laboratory of Wireless-Optical Communications, Chinese Academy of Sciences, School of Information Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Chenhao Ren
Department of Electrical and Computer Engineering, University of California at Davis, Davis, CA, USA
1 shared publication - Chuan Yu
China Electronic Device System Engineering Corporation, China
1 shared publication - Feng Zhang
Key Laboratory of Wireless-Optical Communications, Chinese Academy of Sciences, School of Information Science and Technology, University of Science and Technology of China, Hefei, China
1 shared publication - Fengyi Tang
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Gaofeng Chen
China Electronic Equipment Systems Engineering Corporation
1 shared publication
Latest Publications
- Open Access
- 7 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 50-56
Towards Semi-Supervised Direction Finding With Manifold Regularization
Machine learning based Direction-of-arrival (DOA) estimation methods heavily depends on the labeled data. When it is difficult to obtain a large number of labeled samples, semi supervised learning can use unlabeled samples to improve the training performance. Therefore, this paper proposes a direction finding method based on semi supervised learning, which uses a small number of labeled samples and a large number of unlabeled samples to gradually modify the DOA estimation function through manifold regularization constraints, so as to improve the DOA estimation performance when labeled data is limited. Simulation results have demonstrated the superiority of the proposed method compared with purely supervised learning when limited labeled samples are available.
- 7 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 50-56
Open AccessTowards Semi-Supervised Direction Finding With Manifold Regularization
Machine learning based Direction-of-arrival (DOA) estimation methods heavily depends on the labeled data. When it is difficult to obtain a large number of labeled samples, semi supervised learning can use unlabeled samples to improve the training performance. Therefore, this paper proposes a direction finding method based on semi supervised learning, which uses a small number of labeled samples and a large number of unlabeled samples to gradually modify the DOA estimation function through manifold regularization constraints, so as to improve the DOA estimation performance when labeled data is limited. Simulation results have demonstrated the superiority of the proposed method compared with purely supervised learning when limited labeled samples are available.
- 30 August 2022
- Published by Springer Nature
- p. 757-764
IGCE: A Compositional Energy Concept Based Deep Image Generation Neural Network
- 30 August 2022
- Published by Springer Nature
- p. 757-764
IGCE: A Compositional Energy Concept Based Deep Image Generation Neural Network
- Open Access
- 17 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 75349-75361
Multipath Extraction Based UL/DL Channel Estimation for FDD Massive MIMO-OFDM Systems
In this paper, we propose a multipath extraction based uplink/downlink channel estimation scheme for wideband massive multiple-input multiple-output (MIMO) systems, where orthogonal frequency division multiplexing (OFDM) is adopted and the beam squint effect is considered. Firstly, we investigate the spatial- and frequency-wideband effects and obtain the relationship between angle-delay information and coordinates of on-grid paths. Secondly, according to the spatial- and frequency-wideband effects, we design a pilot pattern in uplink training to ensure that exact paths can be acquired from limited potential paths. Combined with pilot pattern design, a modified density-based spatial clustering of applications with noise (M-DBSCAN) approach is proposed to acquire the on-grid potential paths. Potential paths are used for initialization in uplink channel extraction. Due to the fact that coordinates of only a few potential paths are close to those of true paths, the uplink multipath extraction problem can be regarded as an off-grid sparse signal reconstruction problem. To deal with this issue, an off-grid sparsity adaptive matching pursuit (OSAMP) based compressive sensing method with low computational complexity is proposed. In OSAMP, angle-delay information as well as path gains of exact paths are accurately estimated, which are further used for accomplishing the uplink channel reconstruction. Angle-delay reciprocity between uplink and downlink channels is exploited, and downlink channel estimation is accomplished with the help of uplink multipath extraction. Downlink pilots are only used for downlink path gain estimation, therefore, the downlink training overhead will be significantly reduced. Simulation results are provided to demonstrate the effectiveness of our proposed low computational complexity channel estimation method.
- 17 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 75349-75361
Open AccessMultipath Extraction Based UL/DL Channel Estimation for FDD Massive MIMO-OFDM Systems
In this paper, we propose a multipath extraction based uplink/downlink channel estimation scheme for wideband massive multiple-input multiple-output (MIMO) systems, where orthogonal frequency division multiplexing (OFDM) is adopted and the beam squint effect is considered. Firstly, we investigate the spatial- and frequency-wideband effects and obtain the relationship between angle-delay information and coordinates of on-grid paths. Secondly, according to the spatial- and frequency-wideband effects, we design a pilot pattern in uplink training to ensure that exact paths can be acquired from limited potential paths. Combined with pilot pattern design, a modified density-based spatial clustering of applications with noise (M-DBSCAN) approach is proposed to acquire the on-grid potential paths. Potential paths are used for initialization in uplink channel extraction. Due to the fact that coordinates of only a few potential paths are close to those of true paths, the uplink multipath extraction problem can be regarded as an off-grid sparse signal reconstruction problem. To deal with this issue, an off-grid sparsity adaptive matching pursuit (OSAMP) based compressive sensing method with low computational complexity is proposed. In OSAMP, angle-delay information as well as path gains of exact paths are accurately estimated, which are further used for accomplishing the uplink channel reconstruction. Angle-delay reciprocity between uplink and downlink channels is exploited, and downlink channel estimation is accomplished with the help of uplink multipath extraction. Downlink pilots are only used for downlink path gain estimation, therefore, the downlink training overhead will be significantly reduced. Simulation results are provided to demonstrate the effectiveness of our proposed low computational complexity channel estimation method.
- 31 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (1) , 59-63
Common Sparsity and Cluster Structure Based Channel Estimation for Downlink Massive MIMO-OFDM Systems
In this paper, we propose a new channel estimation scheme for downlink channels in massive multiple-input multiple-output (MIMO) systems, where orthogonal frequency division multiplexing (OFDM) is adopted. To estimate the downlink channels in the multi-subcarrier scenario, the common sparsity and cluster structure is exploited, which is unknown to the user. The common sparsity property is described and a local beta process (LBP) is assumed on each of the common local clusters in a new constructed Bayesian framework. Then a common structure based multi-subcarrier Bayesian compressive sensing (CSMBCS) downlink channel estimation approach is proposed. Simulation results verify the effectiveness of our proposed algorithm.
- 31 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (1) , 59-63
Common Sparsity and Cluster Structure Based Channel Estimation for Downlink Massive MIMO-OFDM Systems
In this paper, we propose a new channel estimation scheme for downlink channels in massive multiple-input multiple-output (MIMO) systems, where orthogonal frequency division multiplexing (OFDM) is adopted. To estimate the downlink channels in the multi-subcarrier scenario, the common sparsity and cluster structure is exploited, which is unknown to the user. The common sparsity property is described and a local beta process (LBP) is assumed on each of the common local clusters in a new constructed Bayesian framework. Then a common structure based multi-subcarrier Bayesian compressive sensing (CSMBCS) downlink channel estimation approach is proposed. Simulation results verify the effectiveness of our proposed algorithm.