XZXinpeng Zheng

Xinpeng Zheng

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xinpeng Zheng has a total of 9 co-authors. Here are the top co-authors by number of shared publications:

  • Jianchu Zou

    Key Laboratory of AI and Information Processing(Hechi University), Education Department of Guangxi Zhuang Autonomous Region, Yizhou, 546300, People’s Republic of China

    2 shared publications
  • Jinming Liu

    Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin, 541006, People’s Republic of China

    2 shared publications
  • Lieping Zhang

    Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin, 541006, People’s Republic of China

    2 shared publications
  • Cui Zhang

    Nanning College of Technology

    1 shared publication
  • Haizhao Lu

    1 shared publication
  • Jiatang Cheng

    Key Laboratory of Advanced Manufacturing and Automation Technology, Guilin University of Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China

    1 shared publication

Latest Publications

  • Multi-strategy hybrid dung beetle optimization algorithm for parameter identification in photovoltaic systems

    by Zhentao Yu, Jiatang Cheng, Xinpeng Zheng

    The dung beetle optimization algorithm (DBO) is a novel meta-heuristic algorithm inspired by the behaviors of dung beetle populations, including rolling, dancing, foraging, breeding and stealing. As so far, the DBO algorithm has demonstrated success in addressing a wide range of complex engineering optimization problems. However, like many other meta-heuristic algorithms, it is also prone to certain limitations, such as slow convergence rates and the tendency to become trapped in local optima during the later stages of optimization. To overcome these limitations, this paper proposes a multi-strategy hybrid dung beetle optimization algorithm (MSDBO), which introduces the tangent flight strategy, golden sine search strategy, adaptive t-distribution sparrow perturbation strategy, and vertical crossover mutation strategy. To comprehensively evaluate the performance of MSDBO, simulations are conducted on 59 benchmark functions from CEC2014 and CEC2017. Experimental results demonstrate that MSDBO outperforms DBO, four advanced DBO variants, and several other popular algorithms in overall performance. Furthermore, MSDBO is employed for parameter identification in photovoltaic system models, further showcasing its effectiveness and reliability in real-world engineering applications.


  • A method for mitigating NLOS error for UWB based on CNN-stacked-LSTM model

    by Lieping Zhang, Jinming Liu, Xinpeng Zheng, Jianchu Zou

    To address the shortcomings of traditional Long Short-Term Memory (LSTM) network in Non-Line-of-Sight (NLOS) mitigation, such as the large amount of training data required and the lengthy training times, in order to enhance the model’s ability to process spatial features and multi-level features, this paper proposes an NLOS mitigation method based on Stacked Long Short-Term Memory (Stacked-LSTM) network and Convolutional Neural Network (CNN). This method combines CNN and Stacked-LSTM models to efficiently extract spatial and higher-level temporal features from the Channel Impulse Response (CIR) signal, reducing the input dimension and improving the performance of the model. The constructed CNN-Stacked-LSTM model is used to mitigate NLOS errors and reduce the impact of NLOS in the original ranging data. In the model performance validation experiment, the accuracy of the CNN-Stacked-LSTM model was improved by 4%–14% compared with the CNN-LSTM, Transformer, Attention-LSTM and LSTM models, and the training time was reduced by 0.07h compared with the traditional LSTM model. The experimental results in the two actual Ultra-WideBand (UWB) environments show that compared with the other four models, the RMSE value of the CNN-Stacked-LSTM model proposed in this paper is reduced by 19.55%–58.96% and 8.64%–45.52%, respectively. It has the best mitigation effect on NLOS and the highest positioning accuracy.


  • A Method for Mitigating NLOS Error for UWB Based on CNN-Stacked-LSTM Model

    by Lieping Zhang, Jinming Liu, Xinpeng Zheng, Jianchu Zou

    To address the shortcomings of traditional Long Short-Term Memory (LSTM) network in Non-Line-of-Sight (NLOS) mitigation, such as the large amount of training data required and the lengthy training times, in order to enhance the model's ability to process spatial features and multi-level features, this paper proposes an NLOS mitigation method based on Stacked Long Short-Term Memory (Stacked-LSTM) network and Convolutional Neural Network (CNN). This method combines CNN and Stacked-LSTM models to efficiently extract spatial and higher-level temporal features from the Channel Impulse Response (CIR) signal, reducing the input dimension and improving the performance of the model. The constructed CNN-Stacked-LSTM model is used to mitigate NLOS errors and reduce the impact of NLOS in the original ranging data. In the model performance validation experiment, the accuracy of the CNN-Stacked-LSTM model was improved by 4%-14% compared with the CNN-LSTM, Transformer, Attention-LSTM and LSTM models, and the training time was reduced by 0.07h compared with the traditional LSTM model. The experimental results in the two actual Ultra-WideBand (UWB) environments show that compared with the other four models, the RMSE value of the CNN-Stacked-LSTM model proposed in this paper is reduced by 19.55%-58.96% and 8.64%-45.52%, respectively. It has the best mitigation effect on NLOS and the highest positioning accuracy.

  • Indoor fingerprint localization algorithm based on WKNN and LightGBM-GA

    by Lieping Zhang, Xinpeng Zheng, Yao Chen, Haizhao Lu, Cui Zhang

    WiFi-based indoor fingerprint localization is widely used in indoor localization owing to its high accuracy and low deployment costs. Changes in the indoor signal environment directly affect localization accuracy. To improve localization accuracy and stability, this paper proposes a novel indoor fingerprint localization algorithm based on Weighted K-Nearest Neighbors (WKNN) and an enhanced Light Gradient Boosting Machine (LightGBM). First, in the offline phase, Gaussian filtering and K-Nearest Neighbors-Random Forest information completion algorithm with fusion of Euclidean and Manhattan distances are used to remove outliers from the fingerprint database dataset and fill in missing fingerprint information, ensuring the integrity of the fingerprint database. During the online phase, the fingerprint database is divided into training and testing sets. The LightGBM algorithm is used for modeling. Additionally, Genetic Algorithm (GA) is use d to optimize the parameters of LightGBM algorithm to find the best parameters by fitness evaluation. Then, the nearest neighbor set found by the WKNN algorithm is introduced into the LightGBM-GA model. Combining the predictions from the standalone LightGBM algorithm and performing weighted fusion yields the final predicted coordinates. The experiments are conducted in 8 m × 10 m laboratory containing 5 access points and 80 reference points to collect the Received Signal Strength Indication values of 5 WiFi hotspots. The experimental results show that the average localization error of the proposed algorithm is 1.11 m, which is reduced by 6.7%–38.3% compared to K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), LightGBM, KNN + XGBoost, WKNN + LightGBM, and WKNN + XGBoost-GA localization algorithms. The localization curve is smoother, and the cumulative distribution function converges faster. Moreover, the localization time is reduced by 13.3%–36.7%, effectively enhancing localization accuracy and decreasing localization time.