Peixu XING

Peixu XING


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
10 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
PXPeixu XING
Peixu XING
MHMengxing Huang
Mengxing Huang
LZLiang Zhu
Liang Zhu
YWYuanyuan Wu
Yuanyuan Wu
Most of the existing trajectory privacy protection methods provide a unified degree of privacy protection for data, and most of the methods mainly focus on the spatial and temporal dimensions of trajectory data, with little consideration of the semantic information of the location. To address these issues, we propose a hierarchical temporal semantic tree-based personalized trajectory privacy protection (HTST-PTPP) scheme, which mainly constructs a hierarchical temporal semantic tree by considering semantic categories and residence time. Then, quantifies the privacy protection requirements of each location, divides the privacy level, and uses differential privacy technology to realize personalized trajectory privacy protection. Finally, experiments are carried out on two real data sets. The experimental results show that our HTST-PTPP scheme has good performance in data availability and privacy protection.

20 October 2025 in Symmetry
Verified
Journal Article
Open access
PDF file
YXYang Xian
Yang Xian
YFYunjin Fu
Yunjin Fu
PXPeixu XING
Peixu XING
HTHongwei Tao
Hongwei Tao
YSYang Sun
Yang Sun
Deep neural network-based approaches have obtained remarkable progress in monaural speech enhancement. Nevertheless, current cutting-edge approaches remain vulnerable to complex acoustic scenarios. We propose a Symmetric Combined Convolution Network with ConvLSTM (SCCN) for monaural speech enhancement. Specifically, the Combined Convolution Block utilizes parallel convolution branches, including standard convolution and two different depthwise separable convolutions, to reinforce feature extraction in depthwise and channelwise. Similarly, Combined Deconvolution Blocks are stacked to construct the convolutional decoder. Moreover, we introduce the exponentially increasing dilation between convolutional kernel elements in the encoder and decoder, which expands receptive fields. Meanwhile, the grouped ConvLSTM layers are exploited to extract the interdependency of spatial and temporal information. The experimental results demonstrate that the proposed SCCN method obtains on average 86.00% in STOI and 2.43 in PESQ, which outperforms the state-of-the-art baseline methods, confirming the effectiveness in enhancing speech quality.