检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wu, Yicheng Ge, Zongyuan Zhang, Donghao Xu, Minfeng Zhang, Lei Xia, Yong Cai, Jianfei Department of Data Science & AI Faculty of Information Technology Monash University MelbourneVIC3800 Australia Monash-Airdoc Research Monash University MelbourneVIC3800 Australia Monash Medical AI Monash eResearch Centre MelbourneVIC3800 Australia DAMO Academy Alibaba Group Hangzhou311121 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi'an710072 China

In this paper, we propose a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled data for semi-supervised medical image segmentation. The MC-Net+ model is motivated by the observation that deep models trained with limited annotations are prone to output highly uncertain and easily mis-classified predictions in the ambiguous regions (e.g., adhesive edges or thin branches) for medical image segmentation. Leveraging these challenging samples can make the semi-supervised segmentation model training more effective. Therefore, our proposed MC-Net+ model consists of two new designs. First, the model contains one shared encoder and multiple slightly different decoders (i.e., using different up-sampling strategies). The statistical discrepancy of multiple decoders' outputs is computed to denote the model's uncertainty, which indicates the unlabeled hard regions. Second, we apply a novel mutual consistency constraint between one decoder's probability output and other decoders' soft pseudo labels. In this way, we minimize the discrepancy of multiple outputs (i.e., the model uncertainty) during training and force the model to generate invariant results in such challenging regions, aiming at regularizing the model training. We compared the segmentation results of our MC-Net+ model with five state-of-the-art semi-supervised approaches on three public medical datasets. Extension experiments with two standard semi-supervised settings demonstrate the superior performance of our model over other methods, which sets a new state of the art for semi-supervised medical image segmentation. Our code is released publicly at https://***/ycwu1997/MC-Net. © 2021, CC BY-NC-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Identifying the effectiveness of arabica drip coffee on individual human brainwave 4

Identifying the effectiveness of arabica drip coffee on indi...

引用

4th Joint International Conference on Digital Arts, Media and technology and 2nd ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT-NCON 2019

作者： Chenghu, Cui Jinna, Hu Visavakitcharoen, Arnon Temdee, Punnarumol Chaisricharoen, Roungsan Brain Science and Engineering Innovation Research Group School of Information Technology Mae Fah Luang University Chiang Rai Thailand State Key Laboratory of Integrated Services Network Xidian Univerisity Shaanxi China Department of Computer Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand

ISBN: (纸本)9781538680728

Caffeine is one of the core substances in coffee. It can directly influence human brain nerve status. Arabica drip coffee is a widely known beverage;drinker often drinks it to keep the brain awake, sensitive, and focus on mental activity. Previous studies have shown that the level of attention in the human brain is controlled by Beta frequency and caffeine can affect the level of Beta frequency. Therefore, this study focuses on the Influence of attention level of local Arabica coffee to the individual human brainwave, thus proving the value of the local Arabica coffee. The research applied twenty participants: ten males and ten females which age between 19 to 22. This research performed human brainwave detection via Electroencephalography (EEG) and interpreted the data through the k-means algorithm. The t-Test study verified that the individual Beta frequency increases significantly after drinking the coffee. Additionally, the classification of k-mean showed that the individual effectiveness could be classified into three groups including low, medium, and high-efficiency level for both before and after drinking the coffee. © 2019 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Drone-vs-Bird Detection Challenge at IEEE AVSS2021

Drone-vs-Bird Detection Challenge at IEEE AVSS2021

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Angelo Coluccia Alessio Fascista Arne Schumann Lars Sommer Anastasios Dimou Dimitrios Zarpalas Fatih Cagatay Akyon Ogulcan Eryuksel Kamil Anil Ozfuttu Sinan Onur Altinuc Fardad Dadboud Vaibhav Patel Varun Mehta Miodrag Bolic Iraj Mantegh University of Salento via Monteroni Lecce Italy Fraunhofer IOSB Fraunhoferstrasse 1 Karlsruhe Germany Vision and Fusion Lab Karlsruhe Institute of Technology KIT Adenauerring 4 Karlsruhe Germany Centre for Research and Technology Hellas (CERTH) Information Technologies Institute 6th km Harilaou - Thermi Thessaloniki Greece OBSS AI OBSS Technology Universiteler Mah. Ankara Computational Analysis and Acceleration Research Group (CARG) School of Electrical Engineering and Computer Science (SEECS) University of Ottawa 800 King Edward Ottawa On. Canada National Research Council Canada (NRC) Montreal Qc Canada

ISBN: (纸本)9781665433976

This paper presents the 4-th edition of the “drone-vs-bird” detection challenge, launched in conjunction with the the 17-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS). The objective of the challenge is to tackle the problem of detecting the presence of one or more drones in video scenes where birds may suddenly appear, taking into account some important effects such as the background and foreground motion. The proposed solutions should identify and localize drones in the scene only when they are actually present, without being confused by the presence of birds and the dynamic nature of the captured scenes. The paper illustrates the results of the challenge on the 2021 dataset, which has been further extended compared to the previous edition run in 2020.

关键词： Surveillance Conferences Dynamics Object detection Birds Convolutional neural networks Drones

来源：评论

学校读者我要写书评

暂无评论

Paddy rice methane emissions across Monsoon Asia

引用

Remote Sensing of Environment 2023年 284卷

作者： Ouyang, Zutao Jackson, Robert B. McNicol, Gavin Fluet-Chouinard, Etienne Runkle, Benjamin R.K. Papale, Dario Knox, Sara H. Cooley, Sarah Delwiche, Kyle B. Feron, Sarah Irvin, Jeremy Andrew Malhotra, Avni Muddasir, Muhammad Sabbatini, Simone Alberto, Ma. Carmelita R. Cescatti, Alessandro Chen, Chi-Ling Dong, Jinwei Fong, Bryant N. Guo, Haiqiang Hao, Lu Iwata, Hiroki Jia, Qingyu Ju, Weimin Kang, Minseok Li, Hong Kim, Joon Reba, Michele L. Nayak, Amaresh Kumar Roberti, Debora Regina Ryu, Youngryel Swain, Chinmaya Kumar Tsuang, Benjei Xiao, Xiangming Yuan, Wenping Zhang, Geli Zhang, Yongguang Department of Earth System Science Stanford University StanfordCA United States Woods Institute for the Environment Stanford University StanfordCA United States Precourt Institute for Energy Stanford University StanfordCA United States Department of Earth and Environmental Sciences University of Illinois Chicago ChicagoIL United States Department of Biological and Agricultural Engineering University of Arkansas FayettevilleAR United States University of Tuscia Viterbo Italy IAFES division Viterbo Italy Department of Geography The University of British Columbia VancouverBC Canada Department of Geography University of Oregon EugeneOR United States Department of Environmental Science Policy And Management UC Berkeley BerkeleyCA United States Campus Fryslan University of Groningen Groningen Netherlands Department of Computer Science Stanford University StanfordCA United States Department of Geography University of Zurich Zurich Switzerland International Rice Research Institute Laguna Philippines Ispra Italy Taiwan Agricultural Research Institute Taichung Wufeng Taiwan Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China USDA ARS Delta Water Management Research Unit JonesboroAR United States Fudan University Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering and Coastal Ecosystems Research Station of the Yangtze River Estuary Shanghai China / Jiangsu Key Laboratory of Agricultural Meteorology Nanjing University of Information Science and Technology Nanjing China Department of Environmental Science Shinshu University Matsumoto Japan China Meteorological Administration Institute of Atmospheric Environment Shenyang China International Institute for Earth System Sciences Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing University Jiangsu Nanjing210023 China National Center for AgroM

Although rice cultivation is one of the most important agricultural sources of methane (CH4) and contributes ∼8% of total global anthropogenic emissions, large discrepancies remain among estimates of global CH4 emissions from rice cultivation (ranging from 18 to 115 Tg CH4 yr−1) due to a lack of observational constraints. The spatial distribution of paddy-rice emissions has been assessed at regional-to-global scales by bottom-up inventories and land surface models over coarse spatial resolution (e.g., > 0.5°) or spatial units (e.g., agro-ecological zones). However, high-resolution CH4 flux estimates capable of capturing the effects of local climate and management practices on emissions, as well as replicating in situ data, remain challenging to produce because of the scarcity of high-resolution maps of paddy-rice and insufficient understanding of CH4 predictors. Here, we combine paddy-rice methane-flux data from 23 global eddy covariance sites and MODIS remote sensing data with machine learning to 1) evaluate data-driven model performance and variable importance for predicting rice CH4 fluxes;and 2) produce gridded up-scaling estimates of rice CH4 emissions at 5000-m resolution across Monsoon Asia, where ∼87% of global rice area is cultivated and ∼ 90% of global rice production occurs. Our random-forest model achieved Nash-Sutcliffe Efficiency values of 0.59 and 0.69 for 8-day CH4 fluxes and site mean CH4 fluxes respectively, with land surface temperature, biomass and water-availability-related indices as the most important predictors. We estimate the average annual (winter fallow season excluded) paddy rice CH4 emissions throughout Monsoon Asia to be 20.6 ± 1.1 Tg yr−1 for 2001–2015, which is at the lower range of previous inventory-based estimates (20–32 CH4 Tg yr−1). Our estimates also suggest that CH4 emissions from paddy rice in this region have been declining from 2007 through 2015 following declines in both paddy-rice growing area and emission rates per unit

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Probabilistic diagnostic tests for degradation problems in supervised learning

arXiv

引用

arXiv 2020年

作者： Valencia-Zapata, Gustavo A. Gonzalez-Canas, Carolina Zentner, Michael G. Ersoy, Okan Klimeck, Gerhard Network for Computational Nanotechnology Purdue University West LafayetteIN United States School of Electrical and Computer Engineering Purdue University West LafayetteIN United States School of Industrial Engineering Purdue University West LafayetteIN United States HUBzero Research Group Information Technology at Purdue West LafayetteIN United States

Several studies point out different causes of performance degradation in supervised machine learning. Problems such as class imbalance, overlapping, small-disjuncts, noisy labels, and sparseness limit accuracy in classification algorithms. Even though a number of approaches either in the form of a methodology or an algorithm try to minimize performance degradation, they have been isolated efforts with limited scope. Most of these approaches focus on remediation of one among many problems, with experimental results coming from few datasets and classification algorithms, insufficient measures of prediction power, and lack of statistical validation for testing the real benefit of the proposed approach. This paper consists of two main parts: In the first part, a novel probabilistic diagnostic model based on identifying signs and symptoms of each problem is presented. Thereby, early and correct diagnosis of these problems is to be achieved in order to select not only the most convenient remediation treatment but also unbiased performance metrics. Secondly, the behavior and performance of several supervised algorithms are studied when training sets have such problems. Therefore, prediction of success for treatments can be estimated across classifiers. Copyright © 2020, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Demonstration of Hybrid FSO/RF System with Adaptive Link Selection and Switching

Experimental Demonstration of Hybrid FSO/RF System with Adap...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Song Song Lei Guo Tianming Xu Qianyuan Yang Yejun Liu School of Computer Science and Engineering Northeastern University P. R. China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications P. R. China The 34th Research Institute of China Electronics Technology Group Corporation P. R. China

We propose and experimentally demonstrate a hybrid FSO/RF system with adaptive link selection and switching. FSO and RF links can be switched adaptively to different channel conditions for a robust transmission in cha... 详细信息

ISBN: (数字)9781943580828

ISBN: (纸本)9781728176567

关键词： Radio frequency Adaptive systems Optical switches Tools Optical fiber communication Monitoring Photonics

来源：评论

学校读者我要写书评

暂无评论

Towards efficient content discovery in NDN with enhanced component-based bloom filters 21

Towards efficient content discovery in NDN with enhanced com...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Zhang, Cuiping Wang, Yunmin School of Electronic and Computer Engineering Peking University China Shenzhen Key Lab of Information Theory and Future Network Architecture Future Network PKU Lab of National Major Research Infrastructure PKU Institute of Big Data Technology Shenzhen Engineering Lab of Converged Networking Technology Huawei and PKU Jointly Engineering Lab of Future Network Based on SDN Shenzhen Graduate School Peking University China

ISBN: (纸本)9781728120584

Variable-length hierarchical names of Named data networking (NDN) content bring about intuitive issues for both content routing and large-scale forwarding. Bloom filters can accelerate hash-based NDN content discovery with a false positive probability. In this paper, we propose ECBF, a component-based bloom filter scheme to enhance the reliability of bloom filters. We exploit the hierarchical characteristics of NDN content names and store them into different bloom filters in a component-based way, and then we present a correlation validation policy to check whether the names exist. Finally, we introduce an ECBF-based content discovery scheme BCD. ECBF and the correlation validation value are stored in a fast on-chip memory, and cryptographic check values of content names and related information are respectively stored in an off-chip memory of intermediate routers. This design not only improves the effectiveness of content discovery, but also reduces the additional memory throughput. We experimentally demonstrate that BCD can provide a more than twice reduction of false probability compared with the primary bloom filter methods. Besides, BCD can economize about 40% memory consumption. © 2019 IEEE.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of a Flexible CPW–Fed Slotted Planar Monopole for WLAN/WBAN and 5G

Design and Optimization of a Flexible CPW–Fed Slotted Plana...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Bashar Bahaa Qas Elias Ping Jack Soh Mohamad Kamal A. Rahim Azremi Abdullah Al-Hadi Hadi Aliakbarian Sen Yan School of Computer and Communication Engineering Universiti Malaysia Perlis (UniMAP) Perlis Malaysia Advanced Microwave & RF Research Group School of Electrical Engineering Universiti Teknologi Malaysia Johor Malaysia The Wireless Terminals Measurement Lab K.N.Toosi Uiversity of Technology Iran Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an China

ISBN: (数字)9788831299008

ISBN: (纸本)9781728137124

A flexible Kapton-based coplanar waveguide-fed (CPW) patch antenna has been designed in this work to operate in different wireless applications. The wideband operation and compact size of the antenna is enabled using a simple rhombic-shaped integrated onto the monopole which was designed using a rectangular patch. The proposed broadband antenna model operated below -10dB at 2.45 GHz and 3.5 GHz for the WLAN/WBAN and 5G band, respectively. The antenna optimization process is explained when varying the ground structure, patch dimensions, feed width, and substrate thickness using FEKO software. The performance of the antenna is studied in terms of radiation efficiency, gain, bandwidth and current distributions. Results indicate that the proposed antenna operates throughout the 2.45 and 3.5 GHz bands, with a bandwidth of 1710 MHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible PDMS-based triboelectric nanogenerator for instantaneous force sensing and human joint movement monitoring

引用

Science China Materials 2019年第10期62卷 1423-1432页

作者： Junbin Yu Xiaojuan Hou Min Cui Shuzheng Shi Jian He Yawei Sun Chao Wang Xiujian Chou Science and Technology on Electronic Test and Measurement Laboratory School of Instrument and ElectronicsNorth University of ChinaTaiyuan 030051China School of Mechanical Engineering Hebei University of ArchitectureZhangjiakou 075000China North Information Control Research Academy Group Co. LtdNanjing 211100China

Flexible wearable sensors with excellent electric response and self-powered capability have become an appealing hotspot for personal healthcare and human-machine ***,based on triboelectric nanogenerator(TENG),a flexible self-powered tactile sensor composed of micro-frustum-arrays-structured polydimethylsiloxane(PDMS)film/copper(Cu)electrodes,and poly(vinylidenefluoride-trifluoroethylene)(P(VDF-TrFE))nanofibers has been *** TENG-based self-powered tactile sensor can generate electrical signals through the contact-separation process of two triboelectric layers under external mechanical *** to the uniform and controllable micro-frustum-arrays structure fabricated by micro-electro-mechanical system(MEMS)process and the P(VDF-TrFE)nanofibers fabricated by electrostatic spinning,the flexible PDMS-based sensor presents high sensitivity of 2.97 V kPa^-1,stability of 40,000 cycles(no significant decay),response time of 60 ms at 1 Hz,low detection pressure of a water drop(~4 Pa,35 mg)and good linearity of 0.99231 in low pressure *** the PDMS film presents ultra-flexibility and excellent-biocompatibility,the sensor can be comfortably attached on human ***,the tactile sensor can recognize various types of human body movements by the corresponding electrical ***,the as-prepared TENGs are potential on the prospects of gesture detection,health assessment,human-machine interfaces and so on.

关键词： self-powered triboelectric nanogenerator wearable sensor MEMS process personal healthcare

来源：评论

学校读者我要写书评

暂无评论

Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification

arXiv

引用

arXiv 2020年

作者： Qu, Ying Baghbaderani, Razieh Kaviani Li, Wei Gao, Lianru Zhang, Yuxiang Qi, Hairong The Advanced Imaging and Collaborative Information Processing Group Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN37996 United States The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Hyperspectral image (HSI) classification is one of the most active research topics and has achieved promising results boosted by the recent development of deep learning. However, most state-of-the-art approaches tend to perform poorly when the training and testing images are on different domains, e.g., source domain and target domain, respectively, due to the spectral variability caused by different acquisition conditions. Transfer learning-based methods address this problem by pre-training in the source domain and fine-tuning on the target domain. Nonetheless, a considerable amount of data on the target domain has to be labeled and non-negligible computational resources are required to retrain the whole network. In this paper, we propose a new transfer learning scheme to bridge the gap between the source and target domains by projecting the HSI data from the source and target domains into a shared abundance space based on their own physical characteristics. In this way, the domain discrepancy would be largely reduced such that the model trained on the source domain could be applied on the target domain without extra efforts for data labeling or network retraining. The proposed method is referred to as physically-constrained transfer learning through shared abundance space (PCTL-SAS). Extensive experimental results demonstrate the superiority of the proposed method as compared to the state-of-the-art. The success of this endeavor would largely facilitate the deployment of HSI classification for real-world sensing scenarios. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

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：