Shun Zhou

Shun Zhou

Auto-generated profile, based on publicly available information

Shun Zhou

Sixty-third Research Institute, National University of Defense Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 September 2024 in IEEE Transactions on Machine Learning in Communications and Networking
Verified
Journal Article
Open access
CWChenlong Wang
Chenlong Wang
BABo Ai
Bo Ai
RHRuisi He
Ruisi He
Mi YangMi Yang
Mi Yang
SZShun Zhou
Shun Zhou
JFJianhua Fan
Jianhua Fan
With the advancement of communication technology, there is a higher demand for high-precision and high-generalization channel path loss models as it is fundamental to communication systems. For traditional stochastic and deterministic models, it is difficult to strike a balance between prediction accuracy and generalizability. This paper proposes a novel deep learning-based path loss prediction model using satellite images. In order to efficiently extract environment features from satellite images, residual structure, attention mechanism, and spatial pyramid pooling layer are developed in the network based on expert knowledge. Using a convolutional network activation visualization method, the interpretability of the proposed model is improved. Finally, the proposed model achieves a prediction accuracy with a root mean square error of 5.05 dB, demonstrating an improvement of 3.07 dB over a reference empirical propagation model.

2 October 2023 in IEEE Antennas and Wireless Propagation Letters
Verified
Journal Article
Closed access
ZQZhicheng Qiu
Zhicheng Qiu
RHRuisi He
Ruisi He
Mi YangMi Yang
Mi Yang
SZShun Zhou
Shun Zhou
LYLong Yu
Long Yu
BABo Ai
Bo Ai
Precise path loss models play a crucial role in design and optimization of wireless communication systems, requiring a careful balance between accuracy and efficiency. Deep learning presents a promising approach for improving both aspects. This paper proposes a novel approach that uses satellite images to construct a comprehensive dataset with rich environmental information. By incorporating environmental features into a convolutional neural network based model, accuracy of path loss prediction is significantly enhanced. Comparisons and validation demonstrate the approach in improving accuracy of path loss prediction, particularly with the assistance of road information.

2 July 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Mi YangMi Yang
Mi Yang
RHRuisi He
Ruisi He
SZShun Zhou
Shun Zhou
YLYi Li
Yi Li
YLYujian Li
Yujian Li
BABo Ai
Bo Ai
The characterization and modeling of wireless channels are crucial prerequisites for designing and deploying communication systems, which have been widely recognized. It must be measured and investigated, especially for vehicle-to-vehicle (V2V) channels, because it differs from the general cellular network in propagation environment, transceiver height, and communication frequency. Vegetation in the road environment is expected to block the propagation signal and have an uncertain impact on channels. Therefore, the loss of communication quality due to vegetation can not be ignored for safety-related applications. This paper measures V2V channels in a vegetated environment, emphasizing the changes in large-scale fading, power delay features, spatial stationarity, and multipath characteristics caused by vegetation obstruction. Specifically, this paper points out that vegetation obstruction makes the wireless system need about 8 dB of extra fading margin and causes the average delay spread to increase by 30 ns. At the same time, vegetation obstruction intensifies the non-stationarity of V2V channels, resulting in a smaller stationary distance. In addition, in terms of multipath spatial characteristics, the azimuth spread has increased to about two times that of the general line-of-sight (LoS) scenario, which means more significant spatial dispersion. In this paper, the influence of vegetation obstruction on channel key parameters is quantified and modeled comprehensively. It is helpful to deepen the excavation of V2V channel propagation mechanisms and assist the revision and evolution of the existing general channel model.

13 September 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ZQZhicheng Qiu
Zhicheng Qiu
RHRuisi He
Ruisi He
Mi YangMi Yang
Mi Yang
SZShun Zhou
Shun Zhou
LYLong Yu
Long Yu
BABo Ai
Bo Ai
Accurate wireless channel models are essential in design and optimization of wireless communication systems. Deep learning provides a promising approach for wireless channel modeling with the help of environmental information. One important application is satellite image-based path loss prediction, which has attracted much attention recently. For path loss prediction, environmental characteristics play a crucial role, with the most intuitive manifestation on images being coverage and resolution, referred to as environmental granularity . By adopting absolute measurement metric m/pixel , this paper investigates the impact of environmental granularities on deep learning-based path loss prediction through extensive experiments. Results indicate that with increasing environmental granularity, network prediction error exhibits a non- monotonic change. When environment granularity is low, increasing image resolution helps reduce error. However, when environment granularity is high, further increasing resolution actually leads to reduced prediction accuracy. These insights offer guidance for designing deep learning based networks for wireless channel prediction.

2 February 2022 in IET Radar, Sonar & Navigation
Verified
Journal Article
Open access
PDF file
SZShun Zhou
Shun Zhou
GOGang Ou
Gang Ou
XTXiaomei Tang
Xiaomei Tang
WMWeihua Mou
Weihua Mou
Recently, there has been an increasing interest in modelling and simulation of time‐varying (TV) non‐line‐of‐sight (NLOS) channels for global navigation satellite systems (GNSS) as an assisted means of resolving the GNSS urban canyon problem. In the above context, modelling and simulation of TV NLOS channels for GNSS have been investigated and studied due to their rapidly TV characteristics. However, conventional simulation approaches for TV multipath channels suffer from inconsistency and lack physical soundness, resulting in a non‐smooth transition of the Doppler shift and low simulation output accuracy. The authors propose an improved satellite navigation channel modelling and simulation method for TV NLOS reception scenarios. The multiple‐point‐scatterer model framework is applied to the TV NLOS satellite navigation channel model. The major novelty of the proposed method is integrating the multiple‐point‐scatterer model with online planning of a kinematics trajectory to map changes in the continuous velocity to the Doppler shift, which can keep consistency and accuracy. As a side benefit of the authors' work, numerical integration based on the efficient composite trapezoidal rule is proposed to calculate the precise changes in signal path length, phase, and Doppler shift. The numerical simulation results show that the proposed modelling and simulation method can not only accurately simulate the TV characteristics of the channel multipath with the continuous phase and the Doppler shift, but also reproduce the Rayleigh fading statistics of the TV channel, thus effectively approximating the physical propagation model and generating the TV NLOS satellite navigation channel.

10 May 2022
Verified
Book Chapter
Closed access
PDF file
SZShun Zhou
Shun Zhou
GOGang Ou
Gang Ou
XTXiaomei Tang
Xiaomei Tang
WXWei Xiao
Wei Xiao
PLPengpeng Li
Pengpeng Li