5 results on '"Zhao, Peipei"'
Search Results
2. Miner action recognition model based on DRCA-GCN
- Author
-
LI Shanhua, XIAO Tao, LI Xiaoli, YANG Fazhan, YAO Yong, and ZHAO Peipei
- Subjects
miner action recognition ,recognition of unsafe action ,graph convolutional network ,combination attention mechanism ,dense residual network ,human pose extraction ,compensation for missing key points ,Mining engineering. Metallurgy ,TN1-997 - Abstract
The underground 'three violations' behavior brings serious safety hazards to coal mine production. It is of great significance to perceive and prevent unsafe actions of underground personnel in advance. The poor video quality in coal mine monitoring leads to limited accuracy of image based action recognition methods. In order to solve the above problem, a dense residual and combined attention-graph convolutional network (DRCA-GCN) is constructed. A miner action recognition model based on DRCA-GCN is proposed. Firstly, the human pose recognition model OpenPose is used to extract human key points. The missing key points are compensated to reduce the impact of missing key points caused by poor video quality. Secondly, DRCA-GCN is used to identify the miner actions. DRCA-GCN introduces a combined attention mechanism and a dense residual network on the basis of the spatio-temporal inception graph convolutional network (STIGCN). By using the combined attention mechanism, the capability of each network layer in the model to extract important time series, spatial key points and channel features is enhanced. By using the dense residual network to compensate for the extracted action features, the feature transmission between different networks is strengthened. It further enhances the model's recognition capability for miner action features. The experimental results indicate the following points. ① On the public dataset NTU-RGB+D120, when using Cross-Subject(X-Sub) and Cross-Setup(X-Set) as evaluation protocols, the recognition precision of DRCA-GCN is 83.0% and 85.1%, respectively. It is 1.1% higher than the precision of STIGCN, and higher than other mainstream action recognition models. The effectiveness of the combined attention mechanism and dense residual network is verified through ablation experiments. ② After compensating for missing key points, on the self built mine personnel action (MPA) dataset, the average recognition accuracy of DRCA-GCN for squatting, standing, crossing, lying down and sitting movements increases from 94.2% to 96.7%. The recognition accuracy of DRCA-GCN for each type of action is above 94.2%. Compared with STIGCN, the average recognition accuracy has been improved by 6.5%. It is not likely to misrecognize similar actions.
- Published
- 2023
- Full Text
- View/download PDF
3. 复方蜂胶提取物提高小鼠的免疫力.
- Author
-
ZHAO Peipei, YIN Xin, XIA Xuekui, ZHANG Yu, LIU Changheng, and SHI Yaping
- Abstract
Copyright of Modern Food Science & Technology is the property of Editorial Office of Modern Food Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2021
- Full Text
- View/download PDF
4. Coal mine underground localization method based on wireless access point selectio
- Author
-
JI Peng, ZHAO Peipei, SONG Mingzhi, and ZHANG Kena
- Subjects
coal mine underground localization ,wireless sensor network ,information gain ,ap selection ,qpso-sbl method ,Mining engineering. Metallurgy ,TN1-997 - Abstract
For problem of low localization accuracy of quantum particle swarm optimization-sequence based localization (QPSO-SBL) method, a wireless access point(AP) selection algorithm based on information gain was used to optimize QPSO-SBL method, and a coal mine underground localization method based on wireless AP selection was proposed. In the method, all APs are ranked in descending order according to comprehensive identifiability of AP, and the first k APs are chosen to form an available AP set. The available AP set is considered as input of QPSO-SBL method, and localization results are obtained by QPSO-SBL method. The test results show that compared with QPSO-SBL method, the average localization error of the coal mine underground localization method based on wireless AP selection is reduced by 10.2% with stronger stability and better localization effect.
- Published
- 2019
- Full Text
- View/download PDF
5. [Advances in CRISPR sensing and detection technology].
- Author
-
Wang J, Zhao P, Qin M, Zhao Y, Liu C, and Xia X
- Subjects
- CRISPR-Cas Systems, RNA, Technology, Exosomes, Nucleic Acids, Biosensing Techniques
- Abstract
The CRISPR sensing and detection technology has the advantages of cheap, simple, portable, high sensitivity, and high specificity, therefore is regarded as the "next-generation molecular diagnostic technology". Due to the specific recognition, cis -cleavage and nonspecific trans -cleavage capabilities, CRISPR-Cas systems have been implemented for the detection of nucleic acid targets (DNA and RNA) as well as non-nucleic acid targets (e.g., proteins, exosomes, cells, and small molecules). This review summarizes the current CRISPR sensing and detection technologies in terms of the activity characteristics of different Cas proteins, with the aim to understand the advantages and development history of different CRISPR sensing and detection technologies, as well as promote its development and application. Moreover, this review summarizes the applications of various CRISPR sensing and detection technologies according to the types of detection targets, hoping to facilitate the development of novel CRISPR sensing detection technology.
- Published
- 2024
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.