Jiankun Zhang

Jiankun Zhang

Auto-generated profile, based on publicly available information

Jiankun Zhang

Huawei Technologies Co., Ltd, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
24 March 2022 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
HJHao Jiang
Hao Jiang
SBShuangkaisheng Bi
Shuangkaisheng Bi
LDLinglong Dai
Linglong Dai
HWHao Wang
Hao Wang
JZJiankun Zhang
Jiankun Zhang
Leveraging powerful deep learning techniques, the end-to-end (E2E) learning of communication system is able to outperform the classical communication system. Unfortunately, this communication system cannot be trained by deep learning without known channel. To deal with this problem, a generative adversarial network (GAN) based training scheme has been recently proposed to imitate the real channel. However, the gradient vanishing and overfitting problems of GAN will result in the serious performance degradation of E2E learning of communication system. To mitigate these two problems, we propose a residual aided GAN (RA-GAN) based training scheme in this paper. Particularly, inspired by the idea of residual learning, we propose a residual generator to mitigate the gradient vanishing problem by realizing a more robust gradient backpropagation. Moreover, to cope with the overfitting problem, we reconstruct the loss function for training by adding a regularizer, which limits the representation ability of RA-GAN. Simulation results show that the trained residual generator has better generation performance than the conventional generator, and the proposed RA-GAN based training scheme can achieve the near-optimal block error rate (BLER) performance with a negligible computational complexity increase in both the theoretical channel model and the ray-tracing based channel dataset.

13 February 2025 in IEEE Communications Letters
Verified
Journal Article
Closed access
MXManyu Xue
Manyu Xue
ZXZhendong Xu
Zhendong Xu
JZJiankun Zhang
Jiankun Zhang
HWHao Wang
Hao Wang
YSYuan Shen
Yuan Shen
Deep learning methods have been widely applied in indoor localization to mitigate the impact of non-line-of-sight (NLOS) and multipath effects, achieving high-precision results. However, these methods have to integrate large amounts of data for training and often struggle to adapt to new and unseen scenarios. This letter proposes a domain generalization method based on domain adversarial training (DAT) and mutual information (MI) estimation, where cross-environment generalization localization is achieved by extracting domain-invariant features, eliminating the need for training data from new scenes. Experimental results demonstrate that the proposed method outperforms other deep learning approaches in terms of localization accuracy across various indoor environments.

21 November 2023
Verified
Conference Paper
Closed access
OSOleg Shmonin
Oleg Shmonin
VKVitaliy Kuptsov
Vitaliy Kuptsov
STSergey Trushkov
Sergey Trushkov
KPKirill Ponur
Kirill Ponur
GSGeorgij Serebryakov
Georgij Serebryakov
JZJiankun Zhang
Jiankun Zhang
The paper is dedicated to Direction of Arrival (DOA) estimation of multiple sources using a single port phased antenna array. We consider the case of the received signal with randomly varying phase that may be caused by both hardware constraints and waveform design. The well-known subspace-based algorithms such as Multiple Signal Classification (MUSIC) show good performance with digital antenna arrays but they cannot be applied under the mentioned restrictions. Moreover, the existing beamspace approaches intended for phased antenna arrays cannot also be applied because of the phase variation. In this paper we propose a novel phase-independent beamspace MUSIC algorithm that uses the spatial power spectrum measured with a finite number of beams as the input. It builds an approximation of the signal covariance matrix and applies the MUSIC’s approach for DOA estimation. The simulation results shows that the developed algorithm has a superresolution ability and allows one to distinguish a weak source masked by the sidelobe power leakage of the stronger one.

29 January 2019 in IEEE Photonics Technology Letters
Verified
Journal Article
Closed access
JZJiankun Zhang
Jiankun Zhang
RLRuijie Li
Ruijie Li
ZGZhan Gao
Zhan Gao
ADAnhong Dang
Anhong Dang
The knowledge of atmospheric turbulence is quite imperative for free space optical (FSO) communications. This Letter reveals the relation between spatial and temporal phase fluctuations in a FSO link. We demonstrate the phase fluctuation is an ergodic process in stationary and homogeneous turbulence. On the basis of wave structure which sets up a bridge between spatial and temporal phase characteristics, we theoretically derive the power spectrum and autocorrelation function which predicts the conditions of ergodicity. A series of experiments were carried out to test theoretical predictions where coordinate optical phase were measured for a wide range of turbulent strengths. As a result, we show both the temporal and spatial phase spectra have low-pass characteristics, and both their average and autocorrelation show ergodic behavior, following the same law with the variation of turbulent strength. This work indicates the spatial and temporal statistics of phase fluctuations could be interconverted for free-space optical communication and other applications related to propagation of optical signals in the atmosphere.

28 June 2024 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
JZJiankun Zhang
Jiankun Zhang
HXHongxiang Xie
Hongxiang Xie
HWHao Wang
Hao Wang
Millimeter wave (mmWave) communication stands as a crucial technology for X-reality and cloud gaming due to its extensive bandwidth. Nevertheless, its user experience suffers from degradation caused by obstacles like humans and objects. Unlike base station (BS) solutions, user-side approaches offer greater flexibility in addressing blockage issues. This paper introduces an innovative beam management architecture named reference-signal-received-power (RSRP)-based blockage-prediction-aided compressive sensing (RSRP-BPCS). Unlike existing methods, our proposed algorithm accounts for real communication system constraints and protocol procedures, ensuring practicality. The key advantage lies in deriving channel information based on RSRP without requiring signal phase knowledge. Additionally, we present two novel strategies on the user side: a multiple-beam-sweeping procedure (MBSP) and a proactive blockage prediction approach. These techniques enable the monitoring of different beam pair links and early anticipation of blockage instances. To achieve rapid recovery, we design an explainable deep learning beam tracking scheme which is joint data and model-based to explore the compressive projection of the power spectrum. The best part is that our strategies are standard-compatible, demanding no supplementary side information, which significantly simplifies implementation with minimal complexity. Through extensive simulations, our proposed algorithm demonstrates exceptional performance in mitigating the impact of blockage, proving its efficacy and practicality.

25 August 2025 in IEEE Communications Letters
Verified
Journal Article
Closed access
XXXuemei Xiong
Xuemei Xiong
YLYi Liu
Yi Liu
ZXZhendong Xu
Zhendong Xu
JZJiankun Zhang
Jiankun Zhang
HWHao Wang
Hao Wang
YSYuan Shen
Yuan Shen
Ranging error mitigation is key to improving indoor localization accuracy, but diverse environments challenge algorithm generalization. This letter proposes a multi-source domain adaptation framework for ranging error mitigation, where a weighted maximum mean discrepancy (MMD) is design to dynamically balances domain similarity and regression accuracy during feature alignment. By dynamically aligning domain mappings, the proposed method reduces negative transfer effects caused by varying discrepancies between different source and target domains. Experimental results show that the proposed network outperforms existing deep learning approaches in reducing ranging error across diverse indoor scenarios.