ZWZhen Wu

Zhen Wu

*This is an algorithmically generated author record based on publicly available information.

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


Zhen Wu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • HIPS: A Spatial-Temporal Attention-Guided Framework for Accurate Indoor Positioning via 5 G/BLE Signal Fusion

    by Zhen Wu, Peng Hu, Yunfei Huang, Ning Liu, Qun Niu, Liwei Liang, Tao Pang

    With the widespread deployment of fifth-generation (5 G) networks and their distinctive signal characteristics, indoor positioning based on 5 G technology has shown great potential. However, in environments with limited coverage of 5 G base station and physical obstructions, positioning accuracy may be compromised. Meanwhile, Bluetooth Low Energy (BLE) technology, with its cost-effectiveness and compact hardware, emerges as an ideal complement to 5 G positioning. This paper proposes a Hybrid Indoor Positioning Scheme (HIPS) that integrates 5 G uplink signal with BLE Received Signal Strength Indicator (RSSI) to enhance positioning accuracy through data fusion. By leveraging self-attention and channel attention mechanisms in spatial and temporal dimensions, respectively, HIPS effectively captures the complementary features of heterogeneous positioning data sources while mitigating the impact of environmental interference and signal variations. Furthermore, we apply the Savitzky-Golay filter to post-process the positions predicted by the network model, further improving positioning accuracy. Experimental results demonstrate that HIPS achieves high-precision positioning with limited 5 G base station deployment, outperforming several state-of-the-art methods in terms of positioning accuracy.


  • Open Access

    Attention Mechanism and LSTM Network for Fingerprint-Based Indoor Location System

    by Zhen Wu, Peng Hu, Shuangyue Liu, Tao Pang

    The demand for precise indoor localization services is steadily increasing. Among various methods, fingerprint-based indoor localization has become a popular choice due to its exceptional accuracy, cost-effectiveness, and ease of implementation. However, its performance degrades significantly as a result of multipath signal attenuation and environmental changes. In this paper, we propose an indoor localization method based on fingerprints using self-attention and long short-term memory (LSTM). By integrating a self-attention mechanism and LSTM network, the proposed method exhibits outstanding positioning accuracy and robustness in diverse experimental environments. The performance of the proposed method is evaluated under two different experimental scenarios, which involve 2D and 3D moving trajectories, respectively. The experimental results demonstrate that our approach achieves an average localization error of 1.76 m and 2.83 m in the respective scenarios, outperforming the existing state-of-the-art methods by 42.67% and 31.64%.


  • Open Access

    Attention Mechanism and LSTM Network for Fingerprint-Based Indoor Location System

    by Zhen Wu, Peng Hu, Shuangyue Liu, Tao Pang

    The demand for precise indoor localization services is steadily increasing. Among various methods, fingerprint-based indoor localization has become a popular choice due to its exceptional accuracy, cost-effectiveness, and ease of implementation. However, its performance degrades significantly as a result of multipath signal attenuation and environmental changes. In this paper, we propose an indoor localization method based on fingerprints using self-attention and long short-term memory (LSTM). By integrating a self-attention mechanism and LSTM network, the proposed method exhibits outstanding positioning accuracy and robustness in diverse experimental environments. The performance of the proposed method is evaluated under two different experimental scenarios, which involve 2D and 3D moving trajectories, respectively. The experimental results demonstrate that our approach achieves an average localization error of 1.76 m and 2.83 m in the respective scenarios, outperforming the existing state-of-the-art methods by 42.67% and 31.64%.


  • Perturbation-Aided Fiber Nonlinearity Compensation in Subcarrier-Multiplexing Systems

    by Du Tang, Zhen Wu, Shuangyue Liu, Jiating Luo, Ji Luo, Bofang Zheng, Yaojun Qiao

    A perturbation-aided advanced digital backpropagation (P-ADBP) is proposed for subcarrier-multiplexing (SCM) coherent systems. To improve the nonlinearity compensation (NLC) performance, for the first time, the first-order perturbation analysis is introduced into the conventional ADBP. Based on the fact that the perturbation-based self-subcarrier nonlinearity (PSSN) has a similar form as the cross-subcarrier nonlinearity (CSN), we approximate that PSSN and CSN can be calculated in parallel and the compensation of them can be fused together. This compensation fusion scheme saves the computational complexity effectively by sacrificing only a little performance. Furthermore, to realize the best performance, gradient descent is used to jointly optimize the perturbation coefficients and other necessary parameters in P-ADBP. Verified by 9×120-GBaud 1600-km wavelength-division multiplexing SCM systems with dual-polarization 16QAM modulation format, 1-Step P-ADBP provides identical Q $^{2}$ improvement as 5-Step ADBP but saves about 72.3% complexity. 5-Step P-ADBP and 10-Step P-ADBP also leapfrog into the NLC level of 10-Step ADBP and 20-Step ADBP, but save about 44.4% and 46.0% complexity, respectively. The proposed algorithm helps achieve an improved performance-complexity trade-off compared to the conventional ADBP and its state-of-the-art modifications.


  • Open Access

    Learned Modified Perturbation Backpropagation for Fiber Nonlinear Equalization in High-Symbol-Rate Transmission Systems

    by Zhen Wu, Du Tang, Yingjie Jiang, Yueming Lu, Yaojun Qiao

    A novel learned modified perturbation backpropagation (L-MPBP) algorithm for high-symbol-rate (HSR) coherent optical transmission system is proposed in this paper. As an extension of perturbation backpropagation (PBP), L-MPBP utilizes deep neural network to adjust the position of nonlinear compensation (NLC) in each compensation step and jointly optimize the perturbation coefficients, which greatly improves the performance of nonlinear equalization in HSR transmission systems. The proposed approach is applied to compensate nonlinear signal distortions in a 90-GBaud, PDM16QAM coherent transmission system. The results show that the proposed L-MPBP achieves 1.75 dB effective SNR improvement compared with PBP while without inducing extra complexity. Our research indicates that the L-MPBP algorithm has great application potential for nonlinear compensation in HSR systems.