Zhiqiang Yu

Dr. Zhiqiang Yu


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JDJianhe Du
Jianhe Du
HMHang Ma
Hang Ma
ZYZhiqiang Yu
Zhiqiang Yu
Xingwang LiXingwang Li
Xingwang Li
Shahid MumtazShahid Mumtaz
Shahid Mumtaz
Chau YuenChau Yuen
Chau Yuen
In this paper, we propose a novel integrated sensing and communication (ISAC) algorithm for massive multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems with spatial-frequency wideband (SFW) effects. To obtain high accuracy of channel state information (CSI), the proposed algorithm initially utilizes a deep neural network (DNN) for channel estimation. Then, the estimated channel is expressed as a third-order low-rank tensor model, on which the canonical polyadic (CP) decomposition is performed to obtain three factor matrices. These factor matrices hold the information pertaining to channel parameters. By fitting the constructed tensor model, channel parameters such as angles of departure (AoDs), angles of arrival (AoAs), time delay, and complex gains can be extracted. Ultimately, the positions of mobile station (MS) and scattering points are determined by utilizing the mapping relationship between the channel parameters and position coordinates. In contrast to existing algorithms, the proposed algorithm delivers greater precision in both channel estimation and positioning. The simulation results demonstrate that the proposed algorithm maintains outstanding ISAC performance, persisting even with diminished compression rate. Furthermore, the proposed algorithm proves effective in more complex scenarios lacking a line-of-sight (LOS) path.

9 January 2025 in Alexandria Engineering Journal
Verified
Journal Article
Open access
EZEnchang Zhu
Enchang Zhu
YHYuxin Huang
Yuxin Huang
YXYantuan Xian
Yantuan Xian
JZJunguo Zhu
Junguo Zhu
MGMinghu Gao
Minghu Gao
ZYZhiqiang Yu
Zhiqiang Yu

1 October 2012
Verified
Conference Paper
Closed access
HYHui Yu
Hui Yu
JLJinhang Li
Jinhang Li
LZLixin Zhang
Lixin Zhang
ZYZhiqiang Yu
Zhiqiang Yu
As information and digitalization technologies are applied in hospital management systems, medical images play a more important role in medical activities. Correspondingly the application of PACS becomes more and more popular in hospital information management. This paper proposes a three-dimensional visualization PACS display system integrated with HIS. The integrated system solves interface problems caused by different apparatuses. It can display medical images in an omnidirectional way, which can meet various need for observation such as viewing surface structure, observing spatial structure, or checking any section. In addition, applicable functions are provided for users to view medical images and other relevant information clearly and freely.

21 May 2023 in Information
Verified
Journal Article
Open access
PDF file
YWYonghua Wen
Yonghua Wen
JGJunjun Guo
Junjun Guo
ZYZhiqiang Yu
Zhiqiang Yu
ZYZhengtao Yu
Zhengtao Yu
Parallel sentences play a crucial role in various NLP tasks, particularly for cross-lingual tasks such as machine translation. However, due to the time-consuming and laborious nature of manual construction, many low-resource languages still suffer from a lack of large-scale parallel data. The objective of pseudo-parallel sentence extraction is to automatically identify sentence pairs in different languages that convey similar meanings. Earlier methods heavily relied on parallel data, which is unsuitable for low-resource scenarios. The current mainstream research direction is to use transfer learning or unsupervised learning based on cross-lingual word embeddings and multilingual pre-trained models; however, these methods are ineffective for languages with substantial differences. To address this issue, we propose a sentence extraction method that leverages image information fusion to extract Chinese–Vietnamese pseudo-parallel sentences from collections of bilingual texts. Our method first employs an adaptive image and text feature fusion strategy to efficiently extract the bilingual parallel sentence pair, and then, a multimodal fusion method is presented to balance the information between the image and text modalities. The experiments on multiple benchmarks show that our method achieves promising results compared to a competitive baseline by infusing additional external image information.

11 December 2023 in Physical Communication
Verified
Journal Article
Closed access
ZYZhiqiang Yu
Zhiqiang Yu
HZHongfei Zhang
Hongfei Zhang

17 November 2023
Verified
Conference Paper
Closed access
PWPeng Wu
Peng Wu
YWYujie Wang
Yujie Wang
CWChangzhe Wu
Changzhe Wu
ZLZhifu Liu
Zhifu Liu
ZYZhiqiang Yu
Zhiqiang Yu
CLChangjiang Liu
Changjiang Liu
The MP-3000A Microwave Radiometer is a passive remote sensing instrument with 35 vertically oriented bright-temperature observation channels capable of inverting atmospheric parameters based on atmospheric bright-temperature values. Microwave radiometer inversion accuracy can be affected by the atmospheric temperature background field. In order to select a suitable atmospheric temperature background field, this paper proposes a method to construct a physical model to generate the background. The physical model was set up according to the natural laws of atmospheric temperature. In order to verify its reasonableness, the atmospheric temperature profile generated from the background field is compared with the real atmospheric temperature profile. The results were analyzed by means of Frechette distance and root mean square error (RMSE). It shows that, compared with the fall and winter seasons, Atmospheric temperature background fields are more realistic in spring and summer. The root mean square error is 1.4664 and 1.4888. Compared to the height of 0-3km, the height of 3-7km and 7-10km, temperature profiles are more realistic in the middle and upper height. The errors are 1.6403 and 1.8894. The research in this paper is helpful for the accuracy improvement of atmospheric microwave remote sensing observation.