http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Youxiang Huang (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
A Lightweight Pedestrian Intrusion Detection and Warning Method for Intelligent Traffic Security
Xinyun Yan,Zhengran He,Youxiang Huang,Xiaohu Xu,Jie Wang,Xiaofeng Zhou,Chishe Wang,Zhiyi Lu 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.12
As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.
-
Yang-Jie Zhao,Huang Xingrui,Wen Fasheng,Huang Xinglong,Liu Zhixiao,Zhang Youxiang 한국응용곤충학회 2023 Journal of Asia-Pacific Entomology Vol.26 No.2
Glutathione S-transferases (GSTs) are multifunctional detoxification enzymes which play important roles in protecting the organisms from environmental stress and are widely used as biomarkers for environmental bio monitoring studies. In this study, We investigated the GST activity in Protohermes costalis larvae, aquatic insects mainly found in oligotrophic fresh water environments, in response to cadmium (Cd) exposure. Eight GST genes in the larvae were identified and their expression patterns under Cd stress were determined by real-time quantitative polymerase chain reaction (RT-qPCR). The GST activity in the whole body was up-regulated by CdCl 2 in a dose-dependent manner and the midgut and malpighian tubules may be the main sites involved in GST activity regulation. The identified PcGSTs are members of cytosolic GST family containing the conserved glutathione-binding domain and substrate-binding domain. Six of them are highly enriched in malpighian tu bules, midgut or/and fat body. The expression level of PcGSTe1 was significantly up-regulated by 0.05, 0.1, 0.5, and 1 mM CdCl 2 treatments when compared with no Cd control. PcGSTs1 expression was significantly higher in 0.05 mM CdCl 2 and lower in 1 mM CdCl 2 compared with no Cd control. Other PcGSTs were up-regulated by different concentrations of CdCl 2 . Our results suggested that P. costalis midgut and malpighian tubules may be the main sites for GST activity regulation that induced by Cd in aqueous phase and increasing expression levels of different PcGST genes may be responsible for the GST activity up-regulation. Moreover, GST activity and gene expression in this insect may be used as biomarkers for future aquatic biomonitoring studies.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
