检索结果-内蒙古大学图书馆

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Xuyi Lu Guan Li Ya Wang Yu Dong Dong Tian Guihua Shan Computer Network Information Center Chinese Academy of Sciences University of Chinese Academy of Sciences National Key Laboratory of Earth System Numerical Modeling and Application Institute of Atmospheric Physics Chinese Academy of Sciences Earth System Numerical Simulation Science Center Institute of Atmospheric Physics Chinese Academy of Sciences Computer Network Information Center Chinese Academy of Sciences Computer Network Information Center Chinese Academy of Sciences University of Chinese Academy of Sciences Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences

ISBN: (数字)9798331505813

ISBN: (纸本)9798331505820

Meteorological experts achieved promising results in improving the effectiveness of neural weather networks in precipitation forecasting by incorporating precipitation-optimized objectives into the loss function. However, since neural networks are not based on explicit physical processes, meteorological experts may lack understanding and trust in the model’s predictions, and they cannot perform bias correction by adjusting physical parameters. Additionally, precipitation events are highly imbalanced, with heavy rainfall events being relatively rare but of greater importance. Therefore, traditional metrics for evaluating deep models are insufficient to fully assess precipitation forecasting performance. In this paper, we present a neural weather network visual analysis system designed to help domain experts understand and comprehensively compare the impact of different loss functions on neural networks. We customize the model evaluation process based on the characteristics of precipitation forecasting tasks and provide a reference for bias correction using historically similar data. To validate our approach, we perform two case studies using real-world reanalysis datasets, with feedback from domain experts further confirming its effectiveness.

关键词： Precipitation Rain Visual analytics Neural networks Weather forecasting Predictive models Network architecture Prediction algorithms Reliability Forecasting

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs 29

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Duan, Huijuan Wang, Danghui Zhao, Xingting Mei, Kuizhi Wang, Jihe Polytechnical University School of Computer Science Northwestern Xi'an China Northwestern Polytechnical University Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Xi'An Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an China Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China

ISBN: (纸本)9798350330717

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies. © 2023 IEEE.

关键词： heterogeneous systems NAS pipeline mapping search space reduction

来源：评论

学校读者我要写书评

暂无评论

A homogenization method for nonlinear inhomogeneous elastic materials

引用

Virtual Reality & Intelligent Hardware 2021年第2期3卷 156-170页

作者： Jing ZHAO Fei ZHU Liyou XU Yong TANG Sheng LI College of Information Science and Engineering Yanshan UniversityQinhuangdaoHebei 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei 066004China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Beijing Engineering Research Center for Virtual Simulation and Visualization Beijing 100871China

Background Fast simulation techniques are strongly favored in computer graphics,especially for the nonlinear inhomogeneous elastic *** homogenization theory is a perfect match to simulate inhomogeneous deformable objects with its coarse discretization,as it reveals how to extract information at a fine scale and to perform efficient computation with much less *** existing homogenization method is not applicable for ubiquitous nonlinear materials with the limited input deformation *** In this paper,we have proposed a homogenization method for the efficient simulation of nonlinear inhomogeneous elastic *** approach allows for a faithful approximation of fine,heterogeneous nonlinear materials with very coarse *** analysis provides the basis of a linear deformation space and modal derivatives extend the space to a nonlinear regime;based on this,we exploited modal derivatives as the input characteristic deformations for *** also present a simple elastic material model that is nonlinear and anisotropic to represent the homogenized *** nonlinearity of material deformations can be represented properly with this *** material properties for the coarsened model were solved via a constrained optimization that minimizes the weighted sum of the strain energy deviations for all input deformation *** arbitrary number of bases can be used as inputs for homogenization,and greater weights are placed on the more important low-frequency *** Based on the experimental results,this study illustrates that the homogenized material properties obtained from our method approximate the original nonlinear material behavior much better than the existing homogenization method with linear displacements,and saves orders of magnitude of computational *** The proposed homogenization method for nonlinear inhomogeneous elastic materials is capable of capturing the nonlinear dynamics of the

关键词： Physical-based simulation Homogenization theory Heterogeneous material Modal basis

来源：评论

学校读者我要写书评

暂无评论

Substation Safety Operation Monitoring system Based on Internet of Things Technology

Substation Safety Operation Monitoring System Based on Inter...

引用

Electronics, Data Processing and Informatics (ACEDPI), Asia-Europe Conference on

作者： Chaoyu Yu Junfei Han Yifan Zhang Hongbin Hu Yuqiang Wang Baoquan Zhang Ningping Yuan Inner Mongolia Enterprise Key Laboratory of Smart Grid Simulation of Electrical Power System Inner Mongolia Power Research Institute Hohhot China School of Computer Information Inner Mongolia Medical University Hohhot China

The existing wireless technologies for substation operation safety monitoring include WiFi, RFID, ZigBee, CSS and other wireless positioning technologies, but due to poor positioning accuracy, it is difficult to meet the needs of applications. IoT technology has a variety of information sensors, powerful information collection and communication functions, and can provide advantages such as precise positioning. For a high-risk industry such as substations, it is also essential to monitor the safe operation of substations. Therefore, IoT technology is safe in substations. The application of operation monitoring has also become a research hotspot. In this paper, three positioning algorithms such as TOA, TDOA and AOA are proposed, and the positioning accuracy of TDOA is determined by the positioning accuracy measurement experiment. Therefore, TDOA can be selected for the positioning of the operator’s position by the monitoring system. The information transmission function transmits the location information of the operator to the monitoring background. When the operator exceeds the safe area, the system will alarm and remind to ensure the safety of the personnel.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Microgrid Self-healing Control of Distributed Power Supply Combining Particle Swarm Optimization Algorithm 3

Microgrid Self-healing Control of Distributed Power Supply C...

引用

3rd International Symposium on Advances in Informatics, Electronics and Education, ISAIEE 2022

作者： Han, Junfei Han, Rulei Yu, Chaoyu Wang, Yuqiang Zhang, Yifan Zhang, Longlong Yuan, Ningping Inner Mongolia Power Research Institute Inner Mongolia Enterprise Key Laboratory of Smart Grid Simulation of Electrical Power System Hohhot China Inner Mongolia Tianda Tiancai Information Technology Co. Ltd. Hohhot China School of Computer Information Inner Mongolia Medical University Hohhot China

ISBN: (纸本)9781665463577

Microgrid is an important part of smart grid, and self-healing is a key feature of smart grid. The purpose of this paper is to combine the particle swarm optimization algorithm and the binary particle swarm optimization algorithm to study the self-healing control of the distributed power supply in the microgrid. Can be used to solve nonlinear multi-objective optimization problems with continuous and discrete variables. At the same time, considering the load shedding effects of fault recovery, switch opening and closing times, active and reactive power losses, node voltage drift, distributed generator performance, etc., it becomes a nonlinear, multi-objective function involving continuous or discrete variables.. After the optimal operation of the traditional microgrid system, the power factor and line loss cannot reach the optimal state. The line loss of microgrid 1 is 0.71, the power factor is 0.88, the line loss of microgrid 1 is 0.72, and the power factor is 0.88. In the plan, plan 1 operates the switch 2 times, plan 2 operates 5 times, and finally choose plan 1 with fewer operations. © 2022 IEEE.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

A Novel Cascade Instruction Tuning Method for Biomedical NER

A Novel Cascade Instruction Tuning Method for Biomedical NER

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jin Zhao Chao Liu Jiaqing Liang Zhixu Li Yanghua Xiao Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Zhengzhou Zhongke Institute of Integrated Circuit and System Application School of Data Science Fudan University China Fudan-Aishu Cognitive Intelligence Joint Research Center Shanghai China

Large language models(LLMs) have achieved remarkable performance on various tasks. However, LLMs suffer from severe limitations in domain generalisation, primarily due to inherent limitations. Closed-source LLMs face constraints in fine-tuning, while open-source LLMs contend with the scarcity of domain-specific data. Moreover, LLMs often prioritize addressing standard patterns, inadvertently neglecting intricate and domain-specific patterns. This preference hampers effective domain generalization. In this paper, inspired by curriculum learning, we explore a cascade instruction tuning method to train a domain-specific LLMs that can excel in a broad application such as information extraction. Taking biomedical name entity recognition(BioNER) as a case study, we show how to cultivate general LLMs into domain-specific LLMs with limited domain data and address the complex pattern for BioNER. To validate our method, we construct NER INSTRUCTIONS, the largest and broadest benchmark sourced from 55 publicly available NER datasets across 17 domains. We conduct extensive experiments on the dataset, and the results demonstrate the effectiveness of our proposed framework in downstream task generalisation and its ability to tackle intricate patterns.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence and mechanism of solar radiation intensity on the interdecadal variability of strong Meiyu events during historical periods

引用

Science China Earth Sciences 2023年第2期66卷 408-416页

作者： Liulin WANG Liang NING Kefan CHEN Mi YAN Jian LIU Zhengyu LIU Yanmin QIN Jiao XUE Chuxin LI Key Laboratory for Virtual Geographic Environment Ministry of Education/State Key Laboratory Cultivation Base of Geographical Environment Evolution of Jiangsu Province/Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application/School of GeographyNanjing Normal UniversityNanjing210023China Open Studio for the Simulation of Ocean-Climate-Isotope Pilot National Laboratory for Marine Science and Technology(Qingdao)Qingdao266237China Climate System Research Center Department of GeosciencesUniversity of MassachusettsAmherst01003USA State Key Laboratory of Loess and Quaternary Geology Institute of Earth EnvironmentChinese Academy of SciencesXi’an710061China Department of Geography The Ohio State UniversityColumbusOH43210USA

Most recent studies on Meiyu over the middle and lower reaches of the Yangtze River(MLRYR)have focused on its interannual variability or the mechanism of certain abnormal *** influence and physical mechanism of solar radiation intensity on the interdecadal frequency of strong Meiyu events over the MLRYR during historical periods were investigated using reconstructed precipitation data,reconstructed solar radiation data,and model simulation ***,according to the solar radiation intensity,the Ming and Qing Dynasties(1470-1850)were divided into three periods of strong solar radiation and three periods of weak solar *** was found that during the periods of strong solar radiation,the frequency of strong Meiyu events was significantly higher than that during the periods of weak solar radiation in the reconstructed precipitation data and model *** analyses show that during the periods of strong solar radiation,the Western Pacific Subtropical High(WPSH)is stronger,and the blocking highs over the middle-high-latitudes are also stronger,which is conducive to the continuous convergence of the southward cold air and the northward warm and humid air flow at the ***,a circulation spatial pattern conducive to the occurrence of strong Meiyu events is then *** probability distributions of precipitation also show that,during periods of strong solar radiation,changes in circulation patterns cause the probability distribution of precipitation to shift significantly to the right,increasing the probability of strong Meiyu events occurring on the right side of the probability distribution.

关键词： Ming Dynasty Historical flood Strong Meiyu events Solar radiation CESM-LME

来源：评论

学校读者我要写书评

暂无评论

Chaotic Neural Network with Legendre Function Self-feedback and applications

Chaotic Neural Network with Legendre Function Self-feedback ...

引用

作者： Zhang, Yu Wei, SiFan Wang, Yu Xu, Yaoqun School of Computer and Information Engineering Harbin University of Commerce Harbin150028 China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin150028 China Heilongjiang Cultural Big Data Theory Application Research Center Harbin150028 China Institute of System Engineering Harbin University of Commerce Harbin150028 China

A new transient chaotic neuron model which introduces Legendre function into the self-feedback term is constructed. The dynamic characteristics of the single neuron are analyzed by the time evolution graph and the inverted bifurcation graph of the largest Lyapunov exponent. The network parameters are set for settling the combinatorial optimization problem. The effectiveness of this model has been verified by the simulation results in nonlinear function optimization, traveling salesman problem (TSP). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

PseudoSC: A Binary Approximation to Stochastic Computing within Latent Operation-Space for Ultra-Lightweight on-Edge DNNs 23

PseudoSC: A Binary Approximation to Stochastic Computing wit...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jihe Wang Zhaoqing Wang Danghui Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350323481

Recently, stochastic computing (SC) is increasingly popular in constructing MAC for on-edge DNNs benefiting from its outstanding energy-efficiency, including its adequate precision and gatelevel operation. However, current SC-DNN systems always include a lot of costly SNGs/APCs for inevitably switches between binary and stochastic domains, which mortgages incongruous resources to pay the "bill" of the domain-switches and impedes highly-concurrent deployments. In this work, PseudoSC, a binary approximation to low-discrepancy SC, is proposed to totally remove the domain-switch for SNG/APC-free SC-DNNs. Its basic idea is to virtually re-arrange a couple of stochastic operands into a 2-D latent op-space, in which, original Monte Carlo sampling can be partitioned into three sub-ops, i.e., two fixed binary-ops and a fractal recursion. In theory, the recursion forms an isomorphic partition of the sampling repeated in smaller scales until the binary base-case achieved, as a result, a SC-op is well approximated only with binary-ops. Based on above theory, a multi-lane micro-architecture is designed to unroll the recursion within a few cycles and its advantages on hardware saving is verified under popular DNNs. The evaluation shows that the DNN-models with our schemes achieve 98.7% accuracy of the fixed-point implementations, which significantly outperform other SOTA methods. In addition, its reduced structure improves the power efficiency by 3.67 times on average.

关键词： stochastic computing

来源：评论

学校读者我要写书评

暂无评论

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded ...

引用

2022 International Conference on Radar systems, RADAR 2022

作者： Wang, Muhan Zhang, Zhe Wang, Yue Gao, Silin Qiu, Xiaolan Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Electrical and Computer Engineering Department George Mason University FairfaxVA22030 United States

ISBN: (纸本)9781839537776

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Compressed sensing

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：