检索结果-内蒙古大学图书馆

Computing Open 2024年第2期computing-open卷

作者： Guanghong Deng Liangpei Lin Baihao Lin Wenlong Jing Xiaodan Zhao Yong Li Rui Yang Shidun Xie Pengfeng Wei GuangDong Engineering Technology Research Center of UAV Remote Sensing Network Guangzhou iMapCloud Intelligent Technology Co. Ltd. Guangzhou 510095 P. R. China Guangdong Province Engineering Laboratory for Geographic Spatiotemporal Big Data Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou 510070 P. R. China Foshan iMapCloud Intelligent Technology Co. Ltd. Foshan 528251 P. R. China

The application of the combination of unmanned aerial vehicles (UAVs) and artificial intelligence is a hot topic in the intelligent inspection of substations, and meter reading is a very challenging task. This paper proposes a method based on the combination of YOLOv6n object detection and Deeplabv3 + image segmentation and performs post-processing on the segmented images to obtain meter readings. First, YOLOv6n is used to detect the meter area of the aerial image and classify the meters. Second, the detected meter images are fed into the image segmentation model. The backbone network of the Deeplabv3 + algorithm is improved by using the MobileNetv3 network, which not only effectively extracts pointers and scales, but also makes the model more lightweight. Third, License Plate Recognition Network (LPRNet) is used to recognize digital meter images. In order to solve the problem of inaccurate pointer meter readings, to begin with, the segmented image is corroded; in addition, the circular dial area is flattened into a rectangular area by concentric circle sampling method. Finally, the meter reading is calculated by the position of the pointer, the scale and the total range of the meter. The post-processing part uses numba to optimize the inference speed. The experimental results show that in two datasets, The mean average precision of 50 (mAP50) accuracy of the YOLOv6n model using this method reached 99.71% and 98.60%, respectively, and the inference speed of a single image was 17.1 ms and 13.2 ms, respectively. The mean intersection over union (mIoU) of the image segmentation model reached 82.00%, 74.73%, 73.50%, 82.26% and 73.20%, respectively, and the single segmentation speed reached 33.7 ms. The LPRNet model has a recognition accuracy of 99.17% and a single image inference speed of 14.7 ms. At the same time, several mainstream object detection and semantic segmentation algorithms are compared. The experimental results show that the method in this paper greatly im

关键词： Object detection image segmentation YOLOv6n Deeplabv3 + meter reading

来源：评论

学校读者我要写书评

暂无评论

LUneXt: Simple and Efficient U-shaped Network Design for Medical Image Segmentation with Nonlinear Activation

Computing Open

引用

Computing Open 2024年第2期computing-open卷

作者： Guanghong Deng Bing Yu Wenlong Jing Yong Li Xiaodan Zhao GuangDong Engineering Technology Research Center of UAV Remote Sensing Network Guangzhou iMapCloud Intelligent Technology Co. Ltd. Guangzhou 510095 P. R. China Guangdong Province Engineering Laboratory for Geographic Spatiotemporal Big Data Key Laboratory of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou 510070 P. R. China Foshan iMapCloud Intelligent Technology Co. Ltd. Foshan 528251 P. R. China

Medical image segmentation has always been a challenging task. This paper proposes a new LUneXt medical image segmentation model based on the characteristics analysis of medical image data sets and testing of different nonlinear activation units. Both normalized activations for the original negative input image activation have good optimization capabilities for the tokenization module parameters proposed in the original UneXt model. Using different activation coefficients for different foreground and background areas has achieved better results. The experimental results of this paper on the Breast Ultrasound Images (BUSI) data set reached an intersection over union (IoU) value of 62.64%, a Dice value of 76.12%, and a single inference speed of 807.57 ms. The experimental IoU value of the International Skin Imaging Collaboration (ISIC 2018) data set reached 82.95%, and the Dice value reached 90.50%. The single inference speed reached 842.58 ms. The LUneXt model is more robust than other models. While improving model performance, it does not introduce higher computational complexity and does not have a major impact on the processing speed of a single image.

关键词： Image segmentation medical images neural networks activation function

来源：评论

学校读者我要写书评

暂无评论

A New Free-Standing Aqueous Zinc-Ion Capacitor Based on MnO2–CNTs Cathode and MXene Anode

引用

Nano-Micro Letters 2019年第4期11卷 227-238页

作者： Siliang Wang Qiang Wang Wei Zeng Min Wang Limin Ruan Yanan Ma Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityNo.3 Feixi RoadHefei 230039Anhui ProvincePeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601Anhui ProvincePeople’s Republic of China School of Sciences Hubei University of Automotive TechnologyNo.167 Checheng West RoadShiyan 442002Hubei ProvincePeople’s Republic of China

Restricted by their energy storage mechanism,current energy storage devices have certain drawbacks,such as low power density for batteries and low energy density for ***,the nearest ion capacitors,such as lithium-ion and sodium-ion capacitors containing battery-type and capacitor-type electrodes,may allow achieving both high energy and power *** the inspiration,a new zinc-ion capacitor(ZIC)has been designed and realized by assembling the free-standing manganese dioxide-carbon nanotubes(MnO2-CNTs)battery-type cathode and MXene(Ti3C2Tx)capacitortype anode in an aqueous *** ZIC can avoid the insecurity issues that frequently occurred in lithium-ion and sodium-ion capacitors in organic *** expected,the ZIC in an aqueous liquid electrolyte exhibits excellent electrochemical performance(based on the total weight of cathode and anode),such as a high specific capacitance of 115.1 F g?1(1 mV s?1),high energy density of 98.6 Wh kg?1(77.5 W kg?1),high power density of 2480.6 W kg?1(29.7 Wh kg?1),and high capacitance retention of^83.6%of its initial capacitance(15,000 cycles).Even in an aqueous gel electrolyte,the ZIC also exhibits excellent *** work provides an essential strategy for designing next-generation high-performance energy storage devices.

关键词： Energy storage Zinc-ion capacitor Battery-type and capacitor-type electrodes MXene Electrochemical performance

来源：评论

学校读者我要写书评

暂无评论

QuesNet: A unified representation for heterogeneous test questions

arXiv

引用

arXiv 2019年

作者： Yin, Yu Liu, Qi Huang, Zhenya Chen, Enhong Tong, Wei Wang, Shijin Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology School of Data Science University of Science and Technology of China IFLYTEK Research IFLYTEK CO. LTD. State Key Laboratory of Cognitive Intelligence

Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To alleviate this problem, an effective solution is to use pre-trained representations for question understanding. However, existing pretraining methods in NLP area are infeasible to learn test question representations due to several domain-specific characteristics in education. First, questions usually comprise of heterogeneous data including content text, images and side information. Second, there exists both basic linguistic information as well as domain logic and knowledge. To this end, in this paper, we propose a novel pre-training method, namely QuesNet, for comprehensively learning question representations. Specifically, we first design a unified framework to aggregate question information with its heterogeneous inputs into a comprehensive vector. Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way. Here, a novel holed language model objective is developed to extract low-level linguistic features, and a domain-oriented objective is proposed to learn high-level logic and knowledge. Moreover,we showthat Ques- Net has good capability of being fine-tuned in many question-based tasks. We conduct extensive experiments on large-scale real-world question data, where the experimental results clearly demonstrate the effectiveness of QuesNet for question understanding as well as its superior applicability. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Quantitative estimation of the factors impacting spatiotemporal variation in NPP in the Dongting Lake wetlands using Landsat time series data for the last two decades” [Ecol. Indic. 135 (2022) 108544]

引用

Ecological Indicators 2022年 144卷

作者： Meng Zhang Naiquan Yuan Hui Lin Yang Liu Huaiqing Zhang Research Center of Forestry Remote Sensing & Information Engineering Central South University of Forestry & Technology Changsha 410004 China Key Laboratory of State Forestry Administration on Forest Resources Management and Monitoring in Southern Area Changsha 410004 China Key Laboratory of Forestry Remote Sensing Based Big Data & Ecological Security for Hunan Province Changsha 410004 China Hunan Academy of Geosciences Planning and Design Co. Ltd Changsha 410118 China Research Institute of Forest Resources Information Techniques Chinese Academy of Forestry Beijing 100091 China

来源：评论

学校读者我要写书评

暂无评论

A Diverse Biases Non-negative Latent Factorization of Tensors Model for Dynamic Network Link Prediction

A Diverse Biases Non-negative Latent Factorization of Tensor...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Xuke Wu Hang Gou Hao Wu Juan Wang Minzhi Chen Siyu Lai Computer School China West Normal University Nanchong China Computer School of China West Normal University Nanchong Sichuan China University of Chinese Academy of Sciences Beijing China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China North Sichuan Medical College Nanchong China Medical College Nanchong Sichuan China

ISBN: (数字)9781728168555

ISBN: (纸本)9781728168562

Dynamic networks vary over time, making it vital to capture networks temporal patterns for predicting missing links with high accuracy. A biased non-negative latent factorization of tensors (BNLFT) model is very effective in extracting such patterns from dynamic data. However, a BNLFT model only integrates single bias, which cannot adequately represents the volatility of the dynamic data. To address this issue, this paper presents a Diverse Biases Non-negative Latent Factorization of Tensors (DBNT) model for accurate prediction of missing links in dynamic networks. Meanwhile, for further prediction accuracy improvement, the preprocessing bias is integrated into the DBNT model. Empirical studies on two dynamic networks datasets from real applications show that compared with state of the art predictors, a DBNT model achieves higher prediction accuracy.

关键词： Tensors Conferences Predictive models data models Sensors data mining

来源：评论

学校读者我要写书评

暂无评论

Optimizing the spatial organization of rural settlements based on life quality

引用

Journal of Geographical Sciences 2018年第5期28卷 685-704页

作者：唐承丽贺艳华周国华曾山山肖路遥 College of Resource and Environment Science Hunan Normal University Hunan Key Laboratory of Geospatial Big Data Mining and Application Hunan Normal University Urban and Rural Planning Bureau of Wangcheng District

Optimizing rural settlements is an important measure to cope with rural decline, and improve the quality of rural life and attractions. This study introduces the "life quality theory". Based on the mechanisms governing the interactions between rural settlement space and life quality, this study examines how to optimize the spatial organization of rural settlements. Three aspects are evaluated – the integration of rural settlement spatial functions, optimization of spatial structure, and regulation of spatial scale – with the objective of building an optimization mode and framework for the spatial organization of rural settlements with high life quality. Our results suggest the following:(1) The settlement is the spatial carrier of life quality, which is an essential settlement component, and these two aspects influence and improve each other. Therefore, reasonable rural settlement space is an important precondition for higher life quality.(2) The spatial function types of rural settlements can be divided into those that maintain livelihoods, develop industry, and upgrade life quality. Optimizing spatial organization of rural settlements based on life quality requires promoting the maintenance of livelihood, integration of industrial development, and implantation in quality improvement.(3) There are two important components of optimizing the spatial organization of rural settlements. One is promoting the organic concentration of living, agricultural, and industrial spaces, the reasonable distribution of social intercourse, recreational, and services spaces, and the organic balance of living, production, and ecological spaces, so as to reasonably optimize the combination of internal spatial types in settlements. The other is forming a functional structure level of a "comprehensive village–featured village" and building spatial organization settlement modes connected by rural roads by relocating and adjusting the function of villages. These changes would require the de

关键词： rural settlement life quality spatial optimization RROD model

来源：评论

学校读者我要写书评

暂无评论

User Identity Authentication and Identification Based on Multi-Factor Behavior Features

User Identity Authentication and Identification Based on Mul...

引用

IEEE Globecom Workshops

作者： Xing Ding Changgen Peng Hongfa Ding Maoni Wang Hui Yang Qinyong Yu College of Computer Science & Technology State Key Laboratory of Public Big Data Guizhou University Guiyang China College of Information Guizhou University of Financial and Economics Guiyang China National Engineering Laboratory Big Data Application on Improving Government Governance Capabilities Guiyang China CETC Big Data Research Institute Co. Ltd Guiyang China

ISBN: (数字)9781728109602

ISBN: (纸本)9781728109619

Behavior-based identity authentication has been of research interests due to its low cost and the fact that such authentication factors cannot easily copied nor stolen. However, single behavior feature authentication usuall cannot gaurantee sufficient accuracy. In this paper, a multi-factor behavior features identity authentication method is proposed by combining factors of mouse, keystroke and address. We apply support vector machine by using the information divergence of features as the weight of the linear kernel function to solve quantification's problem of features influence degree on authentication. The tailored support vector machine is applied to multi-factor behavior features to identity authentication. Our experimental results show that the improved support vector machine is better than both the linear and Gaussian kernel support vector machines for identity authentication in accuracy. The proppsed method can be applied to large volume users' identity authentication cases where their behavior features are likely to be similar.

关键词： Authentication Mice IP networks Feature extraction Support vector machines Hidden Markov models Presses

来源：评论

学校读者我要写书评

暂无评论

Clinical characteristics and plasma antibody titer of patients with COVID-19 in Zhejiang,China

引用

Journal of Zhejiang University-Science B(Biomedicine & Biotechnology) 2020年第12期21卷 955-960页

作者： Wei-ling XIANG Jing-jing CHENG Lian-peng WU Bing-yu CHEN Wen-xin LI Dan-ying QIU Wei ZHANG Fei-hang GE Dong CHEN Zhen WANG Research Center of Blood Transfusion Medicine Ministry of Education Key Laboratory of Laboratory MedicineDepartment of Blood TransfusionZhejiang Provincial People's HospitalPeople's Hospital of Hangzhou Medical CollegeHangzhou 310014China Department of Laboratory Medicine Wenzhou Central Hospital and Sixth People's Hospital of WenzhouWenzhou 325000China Rehabilitation&Sports Medicine Research Institute of Zhejiang Province Zhejiang Provincial People's HospitalPeople's Hospital of Hangzhou Medical CollegeHangzhou 310014China Research on the Application of Big Data-driven Integrated Blood Collection and Supply Auxiliary Diagnosis and Treatment System Dongyang People's HospitalDongyang 322100China

目的:利用胶体金快速检测试剂盒测定恢复期患者血浆中IgG/IgM的抗体滴度,回顾性分析新型冠状病毒肺炎(COVID-19)患者临床特征、抗体效价变化特点,以及两者间的相关性.创新点:利用胶体金检测试剂盒检测恢复期血浆抗体滴度,结合重症及危... 详细信息

目的:利用胶体金快速检测试剂盒测定恢复期患者血浆中IgG/IgM的抗体滴度,回顾性分析新型冠状病毒肺炎(COVID-19)患者临床特征、抗体效价变化特点,以及两者间的相关性.创新点:利用胶体金检测试剂盒检测恢复期血浆抗体滴度,结合重症及危重症患者病例特点及实验室检测指标分析血浆抗体效价变化规律,及其临床特征的关系,为临床重症及危重症患者诊治以及筛选恢复期血浆供者提供参考依据.方法:收集293份来自COVID-19康复者随访过程中的血液标本,取血浆原液,用生理盐水按不同比例(1:80、1:160、1:320和1:640)稀释后进行胶体金试纸法IgG/IgM抗体检测,并记录相应患者检验指标水平.通过电子病历系统检索回顾性分析温州市第六人民医院截至2020年2月24日确诊的COVID-19患者的流行病学特征和临床信息.通过线性回归分析两变量之间的相关性,P<0.05时具有统计学意义.结论:症状出现4~6周时,COVID-19患者恢复期血浆IgG滴度水平可达到1:320~1:640或者更高水平.此时部分患者的血浆IgM仍为阳性.COVID-19患者恢复期血浆IgM抗体滴度检测结果显示男性较女性高.本研究中危重症患者均需要无创通气来维持生命,且重症和极危重症患者均易发生水、电解质紊乱.COVID-19发病早期发生凝血功能障碍及炎症,与恢复期血浆中IgG和IgM的抗体滴度水平存在一定相关性.

关键词：新型冠状病毒肺炎(COVID-19) 恢复期血浆临床特征抗体滴度

来源：评论

学校读者我要写书评

暂无评论

Waterline mapping of inland great lake with subpixel accuracy from GF-3 SAR images 6

Waterline mapping of inland great lake with subpixel accurac...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Li, Ning Niu, Shilin Wang, Robert Wu, Lin Guo, Zhengwei College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Kaifeng475004 China Department of Space Microwave Remote Sensing System Institute of Electronics Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781728129129

High-accuracy waterline mapping with Synthetic Aperture Radar (SAR) images is a challenging task because of the inhomogeneities of SAR imagery caused by the speckle noise and complex terrain. This paper presents a novel method for waterline mapping with subpixel accuracy. The proposed method mainly consists of three steps. Firstly, an improved Non-Local filter is adapted to suppress the speckle noise. Secondly, a Fuzzy C-Means (FCM) clustering algorithm is used to extract the pixel-level waterline. Thirdly, along the pixel-level waterline, a novel subpixel-scale waterline extraction method based on bicubic convolution and Geometric Active Contour (GAC) model is presented to further improve the accuracy of the waterline. Without loss of generality, the Danjiangkou reservoir (DJKR), which is the largest artificial freshwater lake in Asia, is selected as a study case. SAR images from Chinese GaoFen-3 (GF-3) satellite working on different modes are processed to demonstrate the effectiveness of the proposed method. © 2019 IEEE.

关键词： Synthetic aperture radar

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：