Jiao Peng

Jiao Peng

Auto-generated profile, based on publicly available information

Jiao Peng

Telecommunication Branch State Grid Hebei Electric Power CO. LTD, Shijiazhuang, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
25 October 2024
Verified
Conference Paper
Open access
YLYanyan Lu
Yanyan Lu
JPJiao Peng
Jiao Peng
XXXing Xu
Xing Xu
YHYue He
Yue He
TLTao Li
Tao Li
HSHui Song
Hui Song

17 March 2023
Verified
Conference Paper
Open access
YDYanjun Dong
Yanjun Dong
SWShigeng Wang
Shigeng Wang
XYXiaoyu Yin
Xiaoyu Yin
XCXi Chen
Xi Chen
JPJiao Peng
Jiao Peng
Due to the tiny size and dense connection of the objects in the transmission line components, the occlusion between the objects is severe, resulting in the problems of missed and false detection of the transmission line components. We propose a tiny object detection method for transmission lines based on dynamic-NMS to solve the problems. First, we used the Gaussian kernel function method to automatically generate the density map labels from the object detection labels. Next, the CSRNet density estimation network model was trained to predict the transmission line objects' density adaptively. Finally, the predicted density values were mapped to the dynamic NMS threshold to post-process the object detection model and accurately identify unevenly distributed objects through different NMS thresholds. In the experimental stage, we have implemented the dynamic NMS method on three object detection models. Compared with the original model, the test results have been improved, with a maximum increase of 6.2%. Among them, we achieved better performance in detecting dense tiny objects.

2 August 2021
Verified
Conference Paper
Closed access
JPJiao Peng
Jiao Peng
LLLinley Li Lin
Linley Li Lin
Jian YeJian Ye
Jian Ye
Silver (Ag) plays an important role in the field of surface-enhanced Raman scattering (SERS) due to its excellent plasmonic enhancement. In particular, Ag nanocubes (Ag NCs) have garnered extensive attention due to their sharp corners that are beneficial for SERS applications. However, their easy oxidation and cytotoxicity hinder their biomedical application, particularly in vivo. Comparing with Ag, gold (Au) is more stable and has good biocompatibility. Therefore, the synthesis of a bimetallic substrate with Ag as the core can effectively combine both advantages. In this work, we reported a method of introducing sodium sulfite ligand to alleviate the galvanic replacement reaction and synthesized the Ag core-Ag/Au alloy shell bimetallic nanoprobes embedded with Raman reporter molecules 1,4-benzenedithiol (BDT), named as Ag@BDT@Ag-Au NCs. These nanoprobes have a high SERS enhancement with Ag nanostructure inside and their SERS performance reach the best when the alloy shell thickness is 19 nm. Additionally, the nanoprobes exhibited improved SERS activity, higher chemical stability, and photostability than Ag@BDT. Thus, they can achieve cell SERS imaging with high signals and strong stability under 30-min long-term irradiation with a high laser power (10.36 mW). Therefore, Ag core-Raman reporter-Au/Ag alloy shell nanoprobes can combine the excellent plasmon properties of Ag and the good stability of Au, which are very suitable for SERS bioimaging in biological environment.

17 November 2023
Verified
Conference Paper
Closed access
RWRui Wang
Rui Wang
WXWei Xue
Wei Xue
JPJiao Peng
Jiao Peng
XYXinya Yang
Xinya Yang
In recent years, radar based gesture recognition technology has attracted more and more attention. Among different types of radars, frequency modulated continuous wave (FMCW) radar has the greatest application potential due to its high range and velocity resolution and low cost. However, insufficient gesture information extraction and interference signals affect the performance of FMCW radar gesture recognition. To address the problems, a gesture recognition method based on multi-dimensional features and deep neural network is proposed in this paper. First, the range-time map (RTM) and velocity-time map (VTM) of the gesture are constructed from the range-Doppler map (RDM) with two-dimensional fast Fourier transform (2D-FFT). Then, the angle-time map (ATM) is constructed with the multiple signal classification (MUSIC) algorithm. Subsequently, RTM, VTM and ATM are normalized and adaptively filtered to suppress interference signals, and the three maps are fused to construct the range-velocity-angle-time map (RV ATM) of the gesture. Finally, an improved VGG16 network with self-attention mechanism module is used for feature extraction and recognition. The experimental results show that the proposed method achieves an average accuracy of 98.3% for six gestures, and the improved VGG16 network outperforms other traditional convolutional neural networks.