检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yu, Yuyuan Zhou, Guoxu Huang, Haonan Xie, Shengli Zhao, Qibin School Of Automation Guangdong University Of Technology Guangzhou510006 China Key Laboratory Of Intelligent Detection And The Internet Of Things In Manufacturing Ministry Of Education Guangzhou510006 China Jt. Intl. Research Laboratory Of Intelligent Information Processing And System Integration Of IoT Ministry Of Education Guangdong University Of Technology Guangzhou510006 China Guangdong-Hong Kong-Macao Joint Laboratory For Smart Discrete Manufacturing Guangdong University Of Technology Guangzhou510006 China RIKEN Tokyo103-0027 Japan

Distinguishing the importance of views has proven to be quite helpful for semi-supervised multi-view learning models. However, existing strategies cannot take advantage of semi-supervised information, only distinguishing the importance of views from a data feature perspective, which is often influenced by low-quality views then leading to poor performance. In this paper, by establishing a link between labeled data and the importance of different views, we propose an auto-weighted strategy to evaluate the importance of views from a label perspective to avoid the negative impact of unimportant or low-quality views. Based on this strategy, we propose a transductive semi-supervised auto-weighted multi-view classification model. The initialization of the proposed model can be effectively determined by labeled data, which is practical. The model is decoupled into three small-scale sub-problems that can efficiently be optimized with a local convergence guarantee. The experimental results on classification tasks show that the proposed method achieves optimal or sub-optimal classification accuracy at the lowest computational cost compared to other related methods, and the weight change experiments show that our proposed strategy can distinguish view importance more accurately than other related strategies on multi-view datasets with low-quality views. Copyright © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

3D Printed Microlens Probe for Optical Coherence Tomography

3D Printed Microlens Probe for Optical Coherence Tomography

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Yalong Tai Zhuorong Li Dejun Liu Bozhe Li Rui Zhu Jianan Li Qiang Li Haiping Liu Changrui Liao Yiping Wang Shenzhen Key Laboratory of Photonic Devices and Sensing Systems for Internet of Things Guangdong and Hong Kong Joint Research Centre for Optical Fibre Sensors State Key Laboratory of Radio Frequency Heterogeneous Integration Shenzhen University Shenzhen China Shenzhen Key laboratory of Ultrafast Laser Micro/Nano Manufacturing Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education/Guangdong Province College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen China International Graduate School at Shenzhen Tsinghua University Shenzhen China Shenzhen Vivolight Medical Device & Technology Co. Ltd. Shenzhen China State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an China

Microsized endoscopy is increasingly demanded in medical clinical diagnosis for imaging in small blood vessels or delicate organs. In this paper, we propose a 3D printed side-viewing microlens on fiber tip by using the femtosecond laser two-photon polymerization (TPP) method for optical coherence tomography (OCT) imaging applications. The printed microlens is only 210 μm in width and 270 μm in height, its measured lateral resolution is around 9.4 μm in air. It is demonstrated that the proposed microlens can easily profile the depth resolved inner structure of a homemade plastic pipe.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bird Detection Algorithm for Transmission Line Based on Improved YOLOv7

Bird Detection Algorithm for Transmission Line Based on Impr...

引用

Power and Energy (PandaFPE), Panda Forum on

作者： Yong Kang Zheng Jia Lin Liu Chao Wang Xu Xu Li Xin Yu Tang Ling Hao Zhang Yong Liu System Technology Center State Grid Sichuan Electric Power Research Institute Chengdu China School of Electrical Engineering Northeast Electric Power University Jilin China Equipment Department State Grid Sichuan electric power company Chengdu China Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science & Engineering Yibin China Power Internet of Things Key Laboratory of Sichuan Province State Grid Sichuan Electric Power Research Institute Chengdu China Digital Department ABA power supply company of State Grid Sichuan electric power company Chengdu China

With the increase in the number of birds, the life of birds will seriously endanger the safety of transmission lines or transmission towers. To ensure peaceful coexistence between transmission towers or lines and birds, this paper proposes to identify birds based on the improved YOLOv7 network structure, which lays the foundation for driving or guiding different birds. Replace part of the Conv layer in YOLOv7 with DOConv layer, improve the network performance through deeply over-parameterized convolution, and do not over-parameterize in reasoning; Add SPDConv layer in small target recognition to improve the recognition rate of small target; SimAM attention mechanism is added to feature extraction to enhance feature extraction. Some birds fly at high speed, resulting in blurred pictures taken by traditional cameras, which will greatly reduce the recognition rate of birds. In this paper, motion blur processing of data sets is beneficial to the recognition of blurred bird images. The model can accurately identify birds in the collected images of power transmission lines, providing a reference for the prevention and control of bird-related faults on power transmission lines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SA Sketch: A self-adaption sketch framework for high-speed network

SA Sketch: A self-adaption sketch framework for high-speed n...

引用

作者： Zhu, Haiting Zhang, Yuan Zhang, Lu He, Gaofeng Liu, Linfeng Liu, Ning School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing China School of Information Engineering Nanjing University of Finance and Economics Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China

Sketch is a compact data structure used to summarize data streams. It is widely used in the measurement of network traffic, and its accuracy is higher than traditional methods. Currently, there are some typical sketches: Count-Min Sketch, CU Sketch, and Count Sketch. According to the characteristics of network traffic, we propose a new sketch framework called Self-Adaption Sketch, which is combined Sketch with Bloom Filter. In the framework, the sketch is created dynamically and the memory space is adjusted timely according to the network traffic by using the concept carrying. Our experiment results showed that the space utilization and accuracy are significantly improved while the throughput of self-adaption sketch is maintained at a relatively good level. © 2020 John Wiley & Sons, Ltd.

关键词： HIgh speed networks

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of IoT networks with Mobile Data Collectors

Performance Analysis of IoT networks with Mobile Data Collec...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yajun Ma Hongguang Sun Shuqin Li Xijun Wang Tony Q. S. Quek College of Information Engineering Northwest A&F University Yangling China Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Information System Technology and Design Pillar Singapore University of Technology and Design Singapore

ISBN: (纸本)9781728195056;9781728195063

Efficient data collection has been treated as a key challenge especially in the sparsely deployed internet of things (IoT) networks. Compared with the conventional data collection methods using static sinks, mobile data collectors (MDCs) are considered as a more efficient approach where MDCs transfer data from sensors to access points (APs) by roaming over different geographical regions. In this work, we propose an analytical framework to study the coverage performance of IoT with MDCs where MDCs follow a simple random waypoint (SRWP) mobility model. To characterize the interference distribution of the whole network, we first derive exact expressions for the average contact time (CT) and inter-contact time (ICT) between a typical sensor and its associated MDC. Then we determine the active probability of the typical sensor by using the derived CT and ICT. The coverage probability is finally derived by taking into account the communication range of sensors, velocity of MDCs, density of sensors and MDCs, and the SINR threshold. Our results reveal the fact that the velocity of MDCs has little effect on coverage probability while a higher velocity can significantly lower the end-to-end delay.

关键词： Analytical models Transmitters Design methodology Interference Sensor phenomena and characterization Data collection Delays

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Learning in Crop Planting 2

A Survey on Deep Learning in Crop Planting

引用

2nd International Symposium on Application of Materials Science and Energy Materials, SAMSE 2018

作者： Yang, Xiaofen Sun, Ming College of Information and Electrical Engineering China Agricultural University Key Laboratory of Modern Precision Agriculture System Integration Research Ministry of Education Key Laboratory of Agricultural Information Acquisition Technology Ministry of Agriculture Beijing Engineering and Technology Research Centre for Internet of Things in Agriculture Beijing100083 China

In recent years, with the explosive growth of data, deep learning has become one of the hottest research areas in artificial intelligence. Deep learning has been widely used in many fields such as medical field, industry, transportation system, agriculture is no exception. Crop planting is a vital part of agriculture. Here, we review deep learning applications in crop planting. In addition, we discuss the challenges and future trend of deep learning in crop planting. We hope that this review could promote more researchers to apply deep learning methods in crop planting field. © Published under licence by IOP Publishing Ltd.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Intelligent Crop Planting Management and Quality Traceability system 2

Intelligent Crop Planting Management and Quality Traceabilit...

引用

2nd International Symposium on Application of Materials Science and Energy Materials, SAMSE 2018

Aiming at the farmland management problems, soil heavy metal pollutions problems and the agricultural product quality security problems, the system develops a link planting, acquisition, processing, logistics and distribution each link of intelligent crop planting management and achieves quality tracing based centralized service data gateway. This system extracts the information in real time from crop planting to agricultural product sales. It is conducive to the implementation of scientific planting and the sustainable development of agriculture, and it enables consumers to trace the quality of agricultural products. The main work of this research is as follow. The first is the construction of crop planting information management subsystem. It contains the information about field information, seeding, fertilizing, irrigation, weeding, pest controlling, spraying insecticide and harvest. The second is the construction of crop planting environmental monitoring subsystem based on sensor technology. It contains real-time environmental information in the process of crop growth, such as soil temperature and humidity, air temperatures and humidity, light intensity and video information, and it realizes remote monitoring of crops. The third is agricultural product quality traceability subsystem oriented to consumers. © 2019 Institute of Physics Publishing. All rights reserved.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Area-variant Type MEMS Capacitive Sensor Based on A Novel Bionic Swallow Structure for High Sensitive Nano-indentation Measurement

TechRxiv

引用

TechRxiv 2022年

作者： Gao, Wendi Liu, Cunlang Liu, Tao Zhao, Libo Wang, Chenying Shakoor, Adnan Luo, Tao Jing, Weixuan Yang, Ping Lin, Qijing He, Yongqing Dong, Tao Jiang, Zhuangde Sun, Dong Research Institute for Intelligent Sensing Technology and System Xi’an Jiaotong University Xi’an710049 China School of Mechanical Engineering Xi’an Jiaotong University Xi’an710049 China Harbin150006 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing10081 China Chongqing Key Laboratory of Micro-Nano Systems and Intelligent Sensing Chongqing Academician Workstation Chongqing 2011 Collaborative Innovation Center of Micro/Nano Sensing and Intelligent Ecological Internet of Things Chongqing Technology and Business University Chongqing400067 China Department of Biomedical Engineering City University of Hong Kong 999099 Hong Kong Department of Mechanical & Electrical Engineering Xiamen University Xiamen361101 China

In this paper, a high sensitive area-variant type MEMS capacitive sensor was proposed for nano-indentation measurement. The proposed bionic swallow structure processed a high mechanical sensitivity without influences from the load coupling effect. Six comb arrays were optimized and integrated into the proposed sensor with a novel comb sensing configuration for eliminating electrostatic interferences resulting from multiple combs and maintaining compact chip size. Based on the proposed micro-machined process, comb arrays have been fabricated with great consistency, which exhibited a static differential output of 0.0554 pF. The fabricated sensor has been characterized with rigid glass cube and AFM cantilevers, and the measured force sensitivity can reach 98.54 aF/nN for a larger measurement range of 142 µN with a linearity of 0.9996. The fabricated sensor also exhibited a high resolution of 0.9819 nN, indicating its great feasibility in nano-indentation measurement at the sub-nano-Newton level. © 2022, CC BY-NC-SA.

关键词： Indentation

来源：评论

学校读者我要写书评

暂无评论

Unified feature extraction framework based on contrastive learning

arXiv

引用

arXiv 2021年

作者： Zhang, Hongjie Qiang, Wenwen Zhang, Jinxin Jing, Ling College of Information and Electrical Engineering China Agricultural University Beijing100083 China Beijing Engineering and Technology Research Center for Internet of Things in Agriculture Beijing100083 China University of Chinese Academy of Sciences Beijing China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China National Innovation Center for Digital Fishery China Agricultural University Beijing100083 China College of Science China Agricultural University Beijing100083 China Key Laboratory of Agricultural Information Acquisition Technology Ministry of Agriculture Beijing100083 China

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable attention. In this study, we proposed a unified framework based on a new perspective of contrastive learning (CL) that is suitable for both unsupervised and supervised feature extraction. The proposed framework first constructed two CL graph for uniquely defining the positive and negative pairs. Subsequently, the projection matrix was determined by minimizing the contrastive loss function. In addition, the proposed framework considered both similar and dissimilar samples to unify unsupervised and supervised feature extraction. Moreover, we propose the three specific methods: unsupervised contrastive learning method, supervised contrastive learning method 1,and supervised contrastive learning method 2. Finally, the numerical experiments on five real datasets demonstrated the superior performance of the proposed framework in comparison to the existing methods. © 2021, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：