检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Xiao, Jiangtao Lin, Yang Zhou, Wangming Qiao, Zeyu Chang, Yu Yu, Xinran Li, Yuanyuan Ren, Ping Fang, Lei Key Lab of Land Resources Evaluation and Monitoring in Southwest China Ministry of Education Sichuan Normal University Chengdu610066 China School of Geography and Resources Sciences Sichuan Normal University Chengdu610066 China CAS Key Laboratory of Forest and Ecology Management Institute of Applied Ecology Chinese Academy of Sciences Shenyang110016 China School of Land and Resources Surveying and Mapping Engineering Shandong Agriculture and Engineering University Jinan250100 China Big Data Research Center for Ecology and Environment Shandong University Qingdao266237 China Environment Research Institute Shandong University Qingdao266237 China

Wildland fire is an important disturbance agent that can drastically alter forest structures and erode forest ecosystem services. Forests in the wildland-urban interface (WUI) are of high value but vulnerable to fires due to abundant fire ignitions and flammable forest fuels. It is critically important to quickly restore the post-fire WUI forest landscape to maintain ecosystem service provision following near-natural restoration strategies. To evaluate the long-term effects of near-natural restoration on the WUI forest landscape, which are largely unclear, we used a wildfire near Shenyang City in northeast China as an example and investigated the post-fire forest dynamics under two different scenarios (i.e., natural succession and near-natural restoration) based on the forest landscape model. The results demonstrated that artificial plantations can significantly accelerate the restoration process in terms of forest biomass, species biodiversity, and age structure. Under the near-natural restoration scenario, the biomass of the burned area can be quickly restored, but biomass under both scenarios tended to equal out at the end of the simulation. At the species level, the biomass of pioneer tree species such as Chinese pine and Black locust decreased under the near-natural restoration scenario, while the biomass of other species started to increase, not only in terms of biomass, but the results also showed that post-fire planting accelerated the restoration of forest biodiversity and increased biodiversity. By 2070, the Shannon‒Wiener index was predicted to be 1.49 under natural succession and remained at 2.02 under near-natural restoration. In terms of age structure, near-natural restoration shortens the evolution time of fire trails to mature forests. In summary, near-natural restoration accelerates forest recovery in post-fire WUI areas. Our results highlighted the impact of near-natural restoration on forest restoration to inform post-fire forest management practi

关键词： Biomass

来源：评论

学校读者我要写书评

暂无评论

FABind: fast and accurate protein-ligand binding 23

FABind: fast and accurate protein-ligand binding

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qizhi Pei Kaiyuan Gao Lijun Wu Jinhua Zhu Yingce Xia Shufang Xie Tao Qin Kun He Tie-Yan Liu Rui Yan Gaoling School of Artificial Intelligence Renmin University of China and Engineering Research Center of Next-Generation Intelligent Search and Recommendation Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Microsoft Research AI4Science School of Information Science and Technology University of Science and Technology of China Gaoling School of Artificial Intelligence Renmin University of China Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods

Modeling the interaction between proteins and ligands and accurately predicting their binding structures is a critical yet challenging task in drug discovery. Recent advancements in deep learning have shown promise in addressing this challenge, with sampling-based and regression-based methods emerging as two prominent approaches. However, these methods have notable limitations. Sampling-based methods often suffer from low efficiency due to the need for generating multiple candidate structures for selection. On the other hand, regression-based methods offer fast predictions but may experience decreased accuracy. Additionally, the variation in protein sizes often requires external modules for selecting suitable binding pockets, further impacting efficiency. In this work, we propose FABind, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding. FABind incorporates a unique ligand-informed pocket prediction module, which is also leveraged for docking pose estimation. The model further enhances the docking process by incrementally integrating the predicted pocket to optimize protein-ligand binding, reducing discrepancies between training and inference. Through extensive experiments on benchmark datasets, our proposed FABind demonstrates strong advantages in terms of effectiveness and efficiency compared to existing methods. Our code is available at Github https://***/QizhiPei/FABind.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An approach of on-barn pig weight estimation via 3D computer vision by kinect V2

An approach of on-barn pig weight estimation via 3D computer...

引用

2020 ASABE Annual International Meeting

作者： Ma, Yafang Chen, Xin Zhang, Wenxin Zheng, Lihua Gao, Wanlin Wang, Minjuan Key Laboratory of Agricultural Informatization Standardization Ministry of Agriculture and Rural Affairs China Agricultural University Beijing100083 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China Key Laboratory of Modern Precision Agriculture System Integration Research Ministry of Education China Agricultural University Beijing100083 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University Beijing100048 China

Monitoring the individual body weight is of great importance for pig health management and pig production systems. The objective of this paper was to achieve the estimation of live body weight without contact and stress on animals. The proposed approach was based on 3D data provided by the Microsoft Kinect V2. The camera was placed over the pen in which the pigs lived freely, rather than as a single-row channel or limit fence. Top-view images of Landrace gilts and Yorkshire shoats in group-housed were processed to extract body features. The SVR models using leave one out cross-validation developed with data including gilts and shoats presented an R2 ranging from 0.95 to 0.98. While using the merged data sets, the R2 was ranged from 0.97 to 0.98. The RMSE and MAE values of ultimately selected VA-Q-SVR model were 5.5969, 4.299%. These results revealed the approach has the potential for 3D computer vision to estimate body weight in the pig breeding industry. © ASABE 2020 Annual International Meeting.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Net cage acoustic monitoring system sampling and classification using compressed sensing

Net cage acoustic monitoring system sampling and classificat...

引用

2020 ASABE Annual International Meeting

作者： Zhang, Wenxin Wang, Ying Ma, Yafang Zheng, Lihua Yang, Zhenghong Gao, Wanlin Wang, Minjuan Key Laboratory of Agricultural Informatization Standardization Ministry of Agriculture and Rural Affairs China Agricultural University Beijing100083 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China Key Laboratory of Modern Precision Agriculture System Integration Research Ministry of Education China Agricultural University Beijing100083 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University Beijing100048 China

Efficient sampling and recovering of acoustic signals and classifying them to determine whether the signal belongs to specific fish is crucial for the refinement cage aquaculture in modern fisheries. However, traditional acoustic signal acquisition follows the Shannon-Nyquist sampling theorem, but it takes a lot of time and space to get all the information about the signal. This paper presents a cage acoustic monitoring system based on compressed sensing (CS) technology, which can sample and recover the sound signal of fish within the control range of the cage scanning, and judge whether the recovered signal is the large yellow croaker. Firstly, the monitoring system samples the signal when the large yellow croaker swims within control, it will reflect the sound signal emitted by the transmitter and implements the sparse transformation. Secondly, the Gaussian random observation matrix measures the sparse signal, which is reconstructed and restored by the Orthogonal Matching Pursuit (OMP) algorithm. Experimental results show that the reconstructed signal compared to the original signal error is small, so this method can be used to sample of large yellow croaker returned acoustic signals. Lastly, we used the mean of the acoustic signals returned by the large yellow croaker at 49-time points as the characteristic signal, which were fitted by polynomial regression for construct a classification model that can represent the large yellow croaker. Experiments show that the sampling method based on CS can restore the original signal with less sampling points to achieve the refinement of fish farming. © ASABE 2020 Annual International Meeting.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Time persistence of climate and carbon flux networks

arXiv

引用

arXiv 2024年

作者： Qing, Ting Wang, Fan Li, Qiuyue Dong, Gaogao Tian, Lixin Havlin, Shlomo School of Mathematical Sciences Jiangsu University Jiangsu Zhenjiang212013 China Department of Physics Bar-Ilan University Ramat-Gan52900 Israel Research Institute of Carbon Neutralization Development School of Mathematical Sciences Jiangsu University Zhenjiang212013 China Jiangsu Province Engineering Research Center of Industrial Carbon System Analysis School of Mathematical Sciences Jiangsu University Zhenjiang212013 China Jiangsu Province Engineering Research Center of Spatial Big Data School of Mathematical Sciences Nanjing Normal University Nanjing210023 China Key Laboratory for NSLSCS Ministry of Education School of Mathematical Sciences Nanjing Normal University Nanjing210023 China

The persistence of the global climate system is critical for assuring the sustainability of the natural ecosystem and the further development of the prosperity of socio-economics. In this paper, we develop a framework and analyze the time persistence of the yearly networks of climate and carbon flux, based on cross-correlations between sites, using daily data from China (East Asia), the contiguous United States (North America), and the Europe land region during 2000-2019. There are many studies on time persistence of single nodes, e.g., climate variables at a given location, however persistence at a network level has been rarely discussed. Here we develop a framework to study time persistence of network and we apply it to climate and carbon flux. Our framework for determining the persistence is based on analyzing the similarity between the network structures, i.e., the links of climate and carbon flux in different years of systems using the Jaccard index. Our Jaccard results reveal that the similarity of climate and carbon flux networks in different years are within the range of 0.51 ± 0.09 (p − value Copyright © 2024, The Authors. All rights reserved.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Event-triggering-based H_∞ load frequency control for multi-area cyber–physical power system under DoS attacks

Franklin Open

引用

Franklin Open 2023年 3卷

作者： Liu, Xingyue Shi, Kaibo Zhou, Kun Wen, Shiping Tang, Yiqian Tang, Lin School of Electronic Information and Electrical Engineering Chengdu University Chengdu 610106 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou 310018 China Australian AI Institute Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 NSW Australia Engineering Research Center of Power Quality of Ministry of Education Anhui University Hefei 230601 China Institute of Electronic and Information Engineering of University of Electronic Science and Technology of China in Guangdong 523808 China

In this work, the event-triggering-based resilient H∞ load frequency control (LFC) scheme under denial-of-service (DoS) attacks is developed for multi-area cyber–physical power system (MA-CPPS) with electric vehicle... 详细信息

In this work, the event-triggering-based resilient H_∞ load frequency control (LFC) scheme under denial-of-service (DoS) attacks is developed for multi-area cyber–physical power system (MA-CPPS) with electric vehicles (EVs). In MA-CPPS, the sampled measurements are transmitted through the communication network, which may be subjected to the energy-limited DoS attack with a resilient index of maximum allowable continuous data losses. Meanwhile, a novel adaptive event-triggering mechanism (AETM) characterized by parameters disturbances and dynamic adjustment mechanism of triggering threshold can effectively reduce the occupation of network bandwidth and computational burden in practical operation of sampled-data LFC in MA-CPPS. Hence a sampled-data LFC model of considering energy-limited DoS attack and AETM is established firstly. Then based on a novel AETM transmission interval-dependent loop functional approach, a resilient H_∞ state-feedback controller is designed with guaranteed H_∞ performance and resilient index of energy-limited DoS attack. Finally, the effectiveness and superiority of our proposed scheme are verified by one-area and three-areas LFC CPPS. © 2023 The Authors

关键词： Adaptive event-triggering mechanism Cyber–physical power system Denial-of-service attacks Resilient H∞ load frequency control scheme Transmission interval-dependent loop functional approach

来源：评论

学校读者我要写书评

暂无评论

data-Driven Single Image Deraining: A Comprehensive Review and New Perspectives

TechRxiv

引用

TechRxiv 2021年

作者： Zhang, Zhao Wei, Yanyan Zhang, Haijun Yang, Yi Yan, Shuicheng Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China Shenzhen China Centre for Artificial Intelligence University of Technology Sydney SydneyNSW Australia Department of Electrical and Computer Engineering National University of Singapore Singapore Hefei University of Technology China

Single Image Deraining task aims at recovering the rain-free background from an image degraded by rain streaks and rain accumulation. For the powerful fitting ability of deep neural networks and massive training data, data-driven deep SID methods obtained significant improvement over traditional ones. Current SID methods usually focus on improving the deraining performance by proposing different kinds of deraining networks, while neglecting the interpretation of the solving process. As a result, the generalization ability may still be limited in real-world scenarios, and the deraining results also cannot effectively improve the performance of subsequent high-level tasks (e.g., object detection). To explore these issues, we in this paper re-examine the three important factors (i.e., data, rain model and network architecture) for the SID problem, and specifically analyze them by proposing new and more reasonable criteria (i.e., general vs. specific, synthetical vs. mathematical, black-box vs. white-box). We also study the relationship of the three factors from a new perspective of data, and reveal two different solving paradigms (explicit vs. implicit) for the SID task. We further discuss the current mainstream data-driven SID methods from five aspects, i.e., training strategy, network pipeline, domain knowledge, data preprocessing, and objective function, and some useful conclusions are summarized by statistics. Besides, we profoundly studied one of the three factors, i.e., data, and measured the performance of current methods on different datasets through extensive experiments to reveal the effectiveness of SID data. Finally, with the comprehensive review and in-depth analysis, we draw some valuable conclusions and suggestions for future research. © 2021, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Achieving Enhanced Bi-Linear Attention Network for Teaching Manner Analysis over Edge Cloud-assisted AIoT: Voice-Body Coordination Perspective

引用

IEEE Transactions on Cloud Computing 2025年

作者： Zhou, Yu Zou, Sai Wu, Bochun Ni, Wei Du, Xiaojiang Guizhou University Micro-nano and Intelligent Manufacturing Engineering Research Centre of Ministry of Education College of Big Data and Information Engineering China Fudan University State Key Laboratory of Integrated Chips and Systems Shanghai200433 China Data61 CSIRO Australia Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ07030 United States

Edge computing, an advanced extension of cloud computing, provides superior computational capabilities and lowlatency processing at the network edge, facilitating its availability for real-time data analysis in resource-limited settings. When applied to the analysis of teaching methodologies, edge computing enables the seamless integration of vocal and physical cues, facilitating collaborative, dynamic, and real-time evaluations of teaching quality. However, the inherent complexity of human perception and multimodal interactions impose great challenges to the analysis of these aspects in Artificial Intelligence of Things (AIoT). This paper introduces an innovative mathematical model and a measurement index specifically designed to assess changes in voice-body coordination over time. To achieve this, we propose a cloud-enabled enhanced Bi-Linear Attention Network incorporating entropy and Fourier transforms (BAN-E-FT), which leverages both temporal and frequencydomain features. Specifically, by harnessing the computational and storage capabilities of edge computing, BAN-E-FT facilitates distributed training, expedites large-scale data processing, and enhances model scalability, where entropy measures and Fourier transforms capture modality dynamics, enhancing BAN's fusion capabilities. Moreover, a conditional domain adversarial network is embedded to address regional teaching variations, improving model generalizability. We also verify the robustness of BAN-EFT with accuracy and convergence through convex optimization analysis. Experiments on the eNTERFACE'05 dataset demonstrate 81% accuracy in assessing teaching adaptability, while real-world test at Guizhou University confirms 78% accuracy when using BAN-E-FT, matching human expert assessments. © 2013 IEEE.

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

Neural mechanisms of top-down divided and selective spatial attention in visual and auditory perception

引用

Brain Science Advances 2023年第2期9卷 95-113页

作者： Zhongtian Guan Meng Lin Qiong Wu Jinglong Wu Kewei Chen Hongbin Han Dehua Chui Xu Zhang Chunlin Li School of Biomedical Engineering Capital Medical UniversityBeijing 100069China Beijing Advanced Innovation Center for Big Data-based Precision Medicine Capital Medical UniversityBeijing 100069China Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application Capital Medical UniversityBeijing 100069China Peking University First Hospital Beijing 100034China Biomedical Engineering Laboratory Graduate School of Natural Science and TechnologyOkayama University3-1-1 Tsushima-nakaOkayamaJapan Key Laboratory of Biomimetic Robots and Systems Ministry of EducationBeijing Institute of TechnologyBeijing 100081China Computational Image Analysis Banner Alzheimer’s Institute and Banner Good Samaritan Medical CentrePET CentrePhoenixAZ 85006USA Radiology Peking University Third HospitalBeijing 100191China Neuroscience Research Institute/Peking University Third Hospital Beijing 100191China

Top-down attention mechanisms require the selection of specificobjects or locations;however,the brain mechanism involved when attention is allocated across different modalities is not well *** aim of this study was to use functional magnetic resonance imaging to define the neural mechanisms underlyingdivided and selective spatial attention.A concurrent audiovisual stimulus was used,and subjects were prompted to focus on a visual,auditory and audiovisual stimulus in a Posner *** results confirmed the better performance of selectiveattention compared to devided *** found differences in the activation level of the frontoparietal network,visual/auditorycortex,the putamen and the salience network under differentattention *** further used Granger causality(GC)toexplore effective connectivity differences between *** in GC connectivity between visual and auditory selective tasksreflected the visual dominance effect under spatial *** addition,our results supported the role of the putamen inredistributing attention and the functional separation of the *** summary,we explored the audiovisual top-down allocation of attention and observed the differences in neuralmechanisms under endogenous attention modes,which revealedthe differences in cross-modal expression in visual and auditory attention under attentional modulation.

关键词： top-down mechanism divided spatial attention selective spatial attention fMRI Granger causality

来源：评论

学校读者我要写书评

暂无评论

Secure Cross-Domain Authentication and data Sharing Scheme for IIoT in Cloud-Fog Automation Architecture

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Chen, Xi Hu, Chunqiang Cai, Bin Hu, Pengfei Yu, Jiguo Ministry of Education of China Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Chongqing University School of Big Data and Software Engineering Chongqing China Shandong University School of Computer Science and Technology Shandong China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Qilu University of Technology Big Data Institute Jinan China

Cloud-fog automation architecture has propelled the advancement of the Industrial Internet of Things (IIoT), significantly enhancing production efficiency and intelligence through extensive data collection and connectivity. Simultaneously, industrial cyber-physical system leverages this data to achieve intelligent control and optimization of production processes. As industrial production becomes increasingly specialized and complex, independent operations within a single domain are no longer sufficient to meet demands, making cross-domain collaborative production inevitable. Consequently, ensuring the security of cross-domain communication and data sharing has become a critical issue for IIoT under the cloud-fog automation architecture. Existing solutions encounter substantial management and computational burdens in cross-domain communication and data sharing, and they are vulnerable to privacy leakage risks. To address these challenges and enhance industrial production efficiency, this paper uses consortium blockchain to co-design a cross-domain authentication and data sharing scheme. The scheme ensures secure and private cross-domain communications with minimal computational, communication, and storage overhead. And, the proposed time-specific plaintext checkable encryption protocol can secure data during cross-domain sharing. Security and performance analyses show that the proposed scheme effectively reduces computational and communication resource demands while maintaining communication and data security. © 1983-2012 IEEE.

关键词： Sensitive data

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：