RISS 검색 - 국내학술지논문

무료
기관 내 무료
유료

내보내기
내책장담기
한글로보기

정확도순

내림차순

내림차순

10개씩 출력

1
Weather Recognition Based on 3C-CNN

( Ling Tan ),( Dawei Xuan ),( Jingming Xia ),( Chao Wang ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.8
- 원문보기 2
  ScienceON
  
  KISS
Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.
2
Flexible Cu2O/Cu film self-powered photodetector for high visible light selection and fast response

Liu Yonghao,Zhao Dawei,Sun Ximing,Cui Feng,Zhang Shan,Shang Xue,Xuan Zhen,Xiao Juqing,Wang Jiapeng,Ren Yandong 한국물리학회 2024 Current Applied Physics Vol.58 No.-
Spectral selection is one of the key performance parameters for visible light photodetectors (VLPD). However, as the absorbing layer of the VLPD, the semiconductor has strong ultraviolet light absorption, leading to poor visible light selectivity of the VLPD. This work fabricated a flexible photovoltaic VLPD based on Cu2O/Cu Schottky junction by annealing Cu foil. Under zero bias, the Cu2O/Cu VLPD showed the responsivity of 14 mA/W, the response time of 1 ms, and the detectivity of 8.8 × 1011 Jones to 620 nm light. Moreover, the detection band of the device is in the range of 500–640 nm, indicating excellent visible light selectivity. Optical and electrical characterization shows that the high visible selectivity of the device is mainly attributed to the fact that the penetration depth of visible light in Cu2O film matches the position of the Cu2O/Cu Schottky junction. This, in turn, induces the effective separation of the photogenerated carriers excited by the visible light. In addition, the bend detection performance of the device is demonstrated. This work provides a reference for improving the spectral selectivity of visible photodetectors.
3
Three-Dimensional Analysis of Chloroplast Structures Associated with Virus Infection

Jin, Xuejiao,Jiang, Zhihao,Zhang, Kun,Wang, Pengfei,Cao, Xiuling,Yue, Ning,Wang, Xueting,Zhang, Xuan,Li, Yunqin,Li, Dawei,Kang, Byung-Ho,Zhang, Yongliang American Society of Plant Biologists 2018 Plant Physiology Vol.176 No.1
- 원문보기
<P>Three-dimensional visualization identifies structural remodeling in chloroplasts during barley stripe mosaic virus infection.</P><P>Chloroplasts are multifunctional organelles whose morphology is affected by environmental stresses. Although the three-dimensional (3D) architecture of thylakoid membranes has been reported previously, a 3D visualization of chloroplast under stress has not been explored. In this work, we used a positive-strand RNA ((+)RNA) virus, barley stripe mosaic virus (BSMV) to observe chloroplast structural changes during infection by electron tomography. The analyses revealed remodeling of the chloroplast membranes, characterized by the clustering of outer membrane-invaginated spherules in inner membrane-derived packets. Diverse morphologies of cytoplasmic invaginations (CIs) were evident with spherules at the periphery and different sized openings connecting the CIs to the cytoplasm. Immunoelectron microscopy of these viral components verified that the aberrant membrane structures were sites for BSMV replication. The BSMV αa replication protein localized at the surface of the chloroplasts and played a prominent role in eliciting chloroplast membrane rearrangements. In sum, our results have revealed the 3D structure of the chloroplasts induced by BSMV infection. These findings contribute to our understanding of chloroplast morphological changes under stress conditions and during assembly of plant (+)RNA virus replication complexes.</P>