检索结果-内蒙古大学图书馆

A Multiscale Superpixel-Level Salient Object Detection Model Using Local-Global Contrast Cue

Journal of Shanghai Jiaotong university(science) 2017年第1期22卷 121-128页

作者：穆楠徐新王英林张晓龙 School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology School of Information Management and Engineering Shanghai University of Finance and Economics

The goal of salient object detection is to estimate the regions which are most likely to attract human's visual attention. As an important image preprocessing procedure to reduce the computational complexity, salient object detection is still a challenging problem in computer vision. In this paper, we proposed a salient object detection model by integrating local and global superpixel contrast at multiple scales. Three features are computed to estimate the saliency of superpixel. Two optimization measures are utilized to refine the resulting saliency map. Extensive experiments with the state-of-the-art saliency models on four public datasets demonstrate the effectiveness of the proposed model.

关键词： salient object detection superpixel multiple scales local contrast global contrast TP 391.4 A

来源：评论

学校读者我要写书评

暂无评论

Exploiting Local and Global Characteristics for Contrast Based Visual Saliency Detection

引用

Journal of Shanghai Jiaotong university(science) 2015年第1期20卷 14-20页

作者：徐新王英林张晓龙 School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology School of Information Management and Engineering Shanghai University of Finance and Economics

Visual saliency is an important cue in human visual system to identify salient region in the image;it can be useful in many applications including image retrieval,object recognition,image segmentation,*** contrast has been used as an effective feature to detect visual salient ***,the conventional contrast measures either in spectral domain or in spatial domain fail to give sufficient consideration towards the local and global characteristics of the *** paper presents a visual saliency detection algorithm based on a novel contrast *** measurement extracts the spectral information of image block using the 2D discrete Fourier transform(DFT),and combines with the total variation(TV)of image block in spatial *** proposed algorithm is used to perform salient region detection in the image,and compared with state-of-the-art *** experimental results from the MSRA dataset validate the effectiveness of the proposed algorithm.

关键词： visual saliency contrast measure multi-scale local contrast global contrast

来源：评论

学校读者我要写书评

暂无评论

Potential Challenges and Food Security Responses to Climate Change in China and Mongolia in the Post-COP28 Era

引用

Journal of Resources and Ecology 2025年第1期16卷 22-35页

作者： CHEN Jiannan Faith Ka Shun CHAN WANG Jiayu FENG Meili WANG Zilin Ochir ALTANSUKH SHAO Yating LI Pengfei WANG School of Human Settlements and Civil Engineering Xi’an Eurasia UniversityXi’an 710054China College of Geomatics Xi’an University of Science and TechnologyXi’an 710054China School of Geographical Sciences University of Nottingham Ningbo ChinaNingboZhejiang 315100China Water@Leeds Research Institute and School of Geography University of LeedsLeeds LS29JTUK Research Centre for Intelligent Management&Innovation Development/Research Base for Shenzhen Municipal Policy&Development Southern University of Science and TechnologyShenzhenGuangdong 518000China Key Laboratory of Urban Environment and Health Institute of Urban EnvironmentChinese Academy of SciencesXiamenFujian 361021China Department of Environment and Forest Engineering School of Engineering and Technology and Environmental Engineering LaboratoryNational University of MongoliaUlaanbaatar 14201Mongolia State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China

After the COP28 Conference,many countries are increasingly concerned about their future practices regarding food *** North Asia,the Northeast China is the major food production base for the *** the border,the economy of Mongolia is heavily reliant on agricultural production and animal *** recent years,climatic extremes such as droughts and floods,combined with human-induced overgrazing,have posed alarming threats to food *** review illustrates the challenges and constraints these two countries are facing due to climate changes and summarizes the existing measures and established programs in both ***,we develop the“climate resilient agriculture”(CRA)framework for improving agricultural *** framework emphasizes the importance of international institutions,such as the World Bank,and developed countries to provide more financial and technological support to bolster climate resilience in Northern ***,we conclude by encouraging cross-border co-production and collaborations among governments to implement the CRA framework to tackle future climatic challenges.

关键词： agricultural sensitivity climatic extremes climate resilient agriculture(CRA) food security China and Mongolia

来源：评论

学校读者我要写书评

暂无评论

Ozone pollution induced-yield loss of major staple crops in China and effects from COVID-19

引用

Journal of Environmental sciences 2025年 157卷 804-820页

作者： Haiyang Liu Siyuan Wang Guangsheng Chen Zhaozhong Feng Di Liu Wenxiu Zhang Shufen Pan Hanqin Tian State Key Laboratory For Ecological Security of Regions and Cities Research Center for Eco-Environmental Sciences Chinese Academy of Sciences Beijing 100085 China University of Chinese Academy of Sciences Beijing 100049 China College of Environmental and Resource Sciences Zhejiang A&F University Hangzhou 311300 China School of Ecology and Applied Meteorology Nanjing University of Information Science and Technology Nanjing 210044 China Department of Engineering and Environmental Studies Program Boston College Chestnut Hill MA 02467-9991 USA Center for Earth System Science and Global Sustainability Schiller Institute for Integrated Science and Society Boston College Chestnut Hill MA 02467-9991 USA Department of Earth and Environmental Sciences Boston College Chestnut Hill MA 02467-9991 USA

Surface ozone (O 3 ) pollution showed a continuous increasing trend during the recent decades in China, posing an increasing threat to food security. A wide range of yield reductions have been reported and thus more studies are needed to narrow down the uncertainty resulting from spatiotemporal accuracy of O 3 metrics and extrapolation methods. Based on a high spatial resolution (0.1°) hourly surface O 3 data, here we analyzed the spatiotemporal O 3 pollution patterns and impacts on yield, production and economic losses for wheat, rice, and maize in China during 2005–2020. The accumulated O 3 exposure over a threshold of 40 ppb (AOT40) increased by 10 % during 2005–2019, and a decrease of 5.56 % was observed in 2020 due to the COVID-19 lockdowns. Rising O 3 pollution reduced national level wheat, rice and maize yields by 14.51 % ± 0.43 %, 11.10 % ± 0.6 %, and 3.99 % ± 0.11 %, respectively. A Business-As-Usual projection suggested that the relative yield loss (RYL) would potentially reach 8 %–18 % at the national scale by 2050 if no emission control is implemented. COVID-19 lockdowns in 2020 led to significantly reduced RYL for maize (0.52 %) and rice (2.17 %) but not for wheat (0.11 %), with the largest reduction (1.88 %–9.4 %) in North China Plain, highlighting the potential benefits of emission control. Our findings provided robust evidence that rising O 3 pollution has significantly affected China's crop yields, production and economic losses, underscoring the urgent need to curb O 3 pollution to safeguard food security, particularly in densely populated and industrialized regions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large language models for diabetes training:a prospective study

引用

science Bulletin 2025年第6期70卷 934-942页

作者： Haoxuan Li Zehua Jiang Zhouyu Guan Yuqian Bao Yuexing Liu Tingting Hu Jiajia Li Ruhan Liu Liang Wu Di Cheng Hongwei Ji Yong Wang Ya-Xing Wang Carol Y.Cheung Yingfeng Zheng Jihong Wang Zhen Li Weibing Wu Cynthia Ciwei Lim Yong Mong Bee Hong Chang Tan Elif I.Ekinci David C.Klonoff Justin B.Echouffo-Tcheugui Nestoras Mathioudakis Leonor Corsino Rafael Simó Charumathi Sabanayagam Gavin Siew Wei Tan Ching-Yu Cheng Tien Yin Wong Huating Li Chun Cai Lijuan Mao Lee-Ling Lim Yih-Chung Tham Bin Sheng Weiping Jia Shanghai University of Sport Shanghai 200438China School of Clinical Medicine Beijing Tsinghua Changgung HospitalTsinghua MedicineTsinghua UniversityBeijing 100084China Beijing Visual Science and Translational Eye Research Institute(BERI) Tsinghua MedicineTsinghua UniversityBeijing 100084China Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and EngineeringSchool of ElectronicInformationand Electrical EngineeringShanghai Jiao Tong UniversityDepartment of Endocrinology and MetabolismShanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghai Diabetes InstituteShanghai Clinical Center for DiabetesShanghai 200240China MoE Key Lab of Artificial Intelligence Artificial Intelligence InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Cardiology the Affiliated Hospital of Qingdao UniversityQingdao 266011China CEMS NCMISHCMSMADISAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematics University of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100049China Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China Beijing Institute of Ophthalmology Beijing Tongren HospitalCapital Medical UniversityBeijing Ophthalmology and Visual Sciences Key LaboratoryBeijing 100730China k.Department of Ophthalmology and Visual Sciences The Chinese University of Hong KongHong Kong 999077China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityGuangdong Provincial Key Laboratory of Ophthalmology and Visual ScienceGuangdong Provincial Clinical Research Center for Ocular DiseasesGuangzhou 510060China Department of Renal Medicine Singapore General HospitalSingHealth-Duke Academic Medical CentreSingapore169

Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes *** Language Models(LLMs)provide new insights into diabetes training,but their performance in diabetes-related queries remains uncertain,especially outside the English language like *** first evaluated the performance of ten LLMs:ChatGPT-3.5,ChatGPT-4.0,Google Bard,LlaMA-7B,LlaMA2-7B,Baidu ERNIE Bot,Ali Tongyi Qianwen,MedGPT,HuatuoGPT,and Chinese LlaMA2-7B on diabetes-related queries,based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC)and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United ***,we assessed the training of primary care physicians(PCPs)without and with the assistance of ChatGPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical *** found that ChatGPT-4.0 outperformed other LLMs in the English examination,achieving a passing accuracy of 62.50%,which was significantly higher than that of Google Bard,LlaMA-7B,and *** the NCE-CPFC examination,ChatGPT-4.0,Ali Tongyi Qianwen,Baidu ERNIE Bot,Google Bard,MedGPT,and ChatGPT-3.5 successfully passed,whereas LlaMA2-7B,HuatuoGPT,Chinese LLaMA2-7B,and LlaMA-7B ***-4.0(84.82%)surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%).In summary,LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language,and hold great potential to assist future diabetes training for physicians globally.

关键词： Diabetes Diabetestraining Largelanguagemodels Primarydiabetescare Prospectivestudy

来源：评论

学校读者我要写书评

暂无评论

Multi-time Scale Dispatching Strategy for EV Charging Considering Wind Power 36

Multi-time Scale Dispatching Strategy for EV Charging Consid...

引用

第36届中国控制会议

作者： Yueshuang Bao Qilong Huang Zhifeng Qiu Chunsheng Wang Weihua Gui School of Information Science and Engineering Central South University Intelligent and Network System Research Center Tsinghua University

ISBN: (纸本)9781538629185

This paper investigates the double randomness matching mechanism between electric vehicle（EV） charging and wind power in a distribution network. The Markov Decision Process is employed to model the uncertainties of both EV and wind power. The optimized dispatching models and strategies for EV charging under multi-time scale are developed to achieve the objective *** goal of this function is to maximize matching degree between EV charging and wind power as well as minimize the power losses fully taking the physical constraints of distribution network into account. This actualizes dynamic control of EV charging. The simulation results on IEEE 5 node system and IEEE 30 node system demonstrate that the optimal dispatching method can reduce the network power losses and improve the matching degree between the EV charging and wind power.

关键词： Electric vehicle optimal dispatching wind power randomness Markov decision process matching degree network losses

来源：评论

学校读者我要写书评

暂无评论

An Inverse Power Generation Mechanism Based Fruit Fly Algorithm for Function Optimization

引用

Journal of systems science & Complexity 2019年第2期32卷 634-656页

作者： LIU Ao DENG Xudong REN Liang LIU Ying LIU Bo School of Management Wuhan University of Science and Technology Center for Service Science and Engineering Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Economics and Management Beihang University Academy of Mathematics and Systems Science Chinese Academy of Sciences

As a novel population-based optimization algorithm, fruit fly optimization(FFO) algorithm is inspired by the foraging behavior of fruit flies and possesses the advantages of simple search operations and easy implementation. Just like most population-based evolutionary algorithms, the basic FFO also suffers from being trapped in local optima for function optimization due to premature *** this paper, an improved FFO, named IPGS-FFO, is proposed in which two novel strategies are incorporated into the conventional FFO. Specifically, a smell sensitivity parameter together with an inverse power generation mechanism(IPGS) is introduced to enhance local exploitation. Moreover,a dynamic shrinking search radius strategy is incorporated so as to enhance the global exploration over search space by adaptively adjusting the searching area in the problem domain. The statistical performance of FFO, the proposed IPGS-FFO, three state-of-the-art FFO variants, and six metaheuristics are tested on twenty-six well-known unimodal and multimodal benchmark functions with dimension 30, respectively. Experimental results and comparisons show that the proposed IPGS-FFO achieves better performance than three FFO variants and competitive performance against six other meta-heuristics in terms of the solution accuracy and convergence rate.

关键词： Evolutionary algorithms fruit fly optimization function optimization meta-heuristics

来源：评论

学校读者我要写书评

暂无评论

Polarized Modulation for RIS-Aided Vehicular Communication Networks

引用

IEEE Internet of Things Journal 2025年

作者： Shang, Pingping Xie, Longhui Li, Jun Feng, Li Hai, Han Xu, Binbin Li, Jie Yu, Ling Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China Hubei University of Technology Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Wuhan430068 China Guangzhou University Research Center of Intelligent Communication Engineering School of Electronics and Communication Engineering Guangzhou510006 China Key Laboratory of On-Chip Communication and Sensor Chip of Guangdong Higher Education Institutes Guangzhou510006 China Donghua University School of Information Science and Technology Shanghai201620 China Maritime Communication Research Institute Wuhan430068 China Guangdong Provincial Hospital of Chinese Medicine Guangzhou510120 China State Key Laboratory of Traditional Chinese Medicine Syndrome Guangzhou510120 China

The reconfigurable intelligent surface (RIS) stands as an emergent technique poised to revolutionize future vehicular communication. In order to facilitate the application of RIS in vehicular communication, this paper proposes two effective RIS-aided schemes tailored for polarization modulation (PM) aiming to achieve remarkable spectral efficiency. Specifically, Scheme I proposes a novel index modulation (IM) aided PM-RIS framework that innovatively encodes information across three distinct dimensions, the indices of dual-polarized antennas (DP-AEs), PM symbols and the reflecting surface indices of the RIS. Scheme II employs a deep neural network method to analyze the channel state information (CSI) for transmit antenna selection, that enhances the reliability and interference immunity in dynamic conditions while reducing computational complexity. Furthermore, a stepwise estimation (SE) method is introduced at the detection stage, which significantly reduces the complexity associated with information decoding. The simulation results highlight the superiority of the proposed system. Compared with traditional PM systems, it demonstrates enhanced performance in terms of spectral efficiency, channel stability, and bit error rate (BER). © 2014 IEEE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

Video Quality Indicators for Video-Based Learning system in Higher Education 23

Video Quality Indicators for Video-Based Learning System in ...

引用

9th International Conference on Frontiers of Educational Technologies, ICFET 2023

作者： Zulkarnain, Novan Prabowo, Harjanto Gaol, Ford Lumban Isa, Sani Muhamad Computer Science Department BINUS Graduate Program Computer Science Information System Bina Nusantara University Indonesia Department School of Information System Bina Nusantara University Indonesia Management Department BINUS Business School Undergraduate Program Information System Department School of Information System Bina Nusantara University Indonesia

ISBN: (纸本)9798400707353

Higher education worldwide has adopted Video-Based Learning (VBL) over the past decade. They have tried to build a VBL system to improve services to students. However, the researcher's topic was not fully explored, especially in making the video itself. What features are mandatory and must be considered in making a video lecture to increase student engagement. A systematic review of the literature (SLR) is a way to identify these features. This study provides a critical analysis of the current research in VBL over the last five years (2017 - 2021). It presents a general trend examining 1336 journals and many literary works related to VBL design in Higher Education, selected through a stepwise process based on PRISMA Framework guidelines, using pre-defined selection criteria. We carefully selected 32 journals and found 22 features referring to the Lecture Video Design succession. © 2023 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Adaptive Multitask Autoencoder-Based Hyperspectral Unmixing Exploiting Auxiliary Data via Graph Associations”

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Jia Chen Jun Li Paolo Gamba School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China School of Computer Science China University of Geosciences (Wuhan) Wuhan China Telecommunications and Remote Sensing Laboratory University of Pavia Pavia Italy

Presents corrections to the paper, (Corrections to “Adaptive Multitask Autoencoder-Based Hyperspectral Unmixing Exploiting Auxiliary Data via Graph Associations”).

关键词： Autoencoders Geoscience and remote sensing Hyperspectral imaging

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：