检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2021

作者： Du, Feilong Ban, Xiaojuan Zhang, Yalan Dong, Zirui Duan, Haojian University of Science and Technology Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China

ISBN: (纸本)9781665432085

To solve the problems of low accuracy in long time series prediction and low generality of network parameter model in the existing data-driven Lagrangian fluid simulation, a light neural network prediction model which is physics-based multi-layer shared perceptron was proposed. Each fluid particle is standardized by searching neighbor particles through the optimized parallel processing module. The neural network is used to predict the effect of each neighbor particle on the central particle. The solid-liquid two-state differentiated aggregation operation is used to predict the acceleration of each fluid particle. The experimental results show that, compared with the existing methods, the method proposed in this paper greatly improves the prediction accuracy with less time overhead, and at the same time maintains more fluid motion details. In addition, we can enables more accurate long-term fluid motion prediction. Compared with PointRNN, PointNet++ and other single-channel data-driven methods, we can better deal with the fluid-solid coupling problem, and has wider network versatility. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery

arXiv

引用

arXiv 2024年

作者： Wang, Jiaxin Zhang, Lingling Liu, Jun Guo, Tianlin Wu, Wenjun The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an710049 China

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to clusters as well as providing specific meanings for these clusters. The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances. We then propose a novel framework, SFGRD, for this task to solve the above issues by learning from semi-factuals in two stages. The first stage is semi-factual generation implemented by a tri-view debiased relation representation module, in which we take each original sentence as the main view and design two debiased views to generate semi-factual examples for this sentence. The second stage is semi-factual thinking executed by a dual-space tri-view collaborative relation learning module, where we design a cluster-semantic space and a class-index space to learn relational semantics and relation label indices, respectively. In addition, we devise alignment and selection strategies to integrate two spaces and establish a self-supervised learning loop for unlabeled data by doing semi-factual thinking across three views. Extensive experimental results show that SFGRD surpasses state-of-the-art models in terms of accuracy by 2.36% ∼5.78% and cosine similarity by 32.19%∼ 84.45% for relation label index and relation semantic quality, respectively. To the best of our knowledge, we are the first to exploit the efficacy of semi-factuals in relation extraction. Copyright © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A power optimization approach for mixed polarity Reed–Muller logic circuits based on multi-strategy fusion memetic algorithm

引用

Frontiers of Information Technology & Electronic engineering 2025年第3期26卷 415-426页

作者： Mengyu ZHANG Zhenxue HE Yijin WANG Xiaojun ZHAO Xiaodan ZHANG Limin XIAO Xiang WANG Intelligent Agricultural Equipment Research Institute Hebei Agricultural UniversityBaoding 071001China Key Laboratory of Agricultural Big Data of Hebei Province Hebei Agricultural UniversityBaoding 071001China School of Computer Science and Engineering Beihang UniversityBeijing 100191China School of Electronic Information Engineering Beihang UniversityBeijing 100191China

The power optimization of mixed polarity Reed–Muller(MPRM)logic circuits is a classic combinatorial optimization *** optimization approaches often suffer from slow convergence and a propensity to converge to local optima,limiting their effectiveness in achieving optimal power ***,we propose a novel multi-strategy fusion memetic algorithm(MFMA).MFMA integrates global exploration via the chimp optimization algorithm with local exploration using the coati optimization algorithm based on the optimal position learning and adaptive weight factor(COA-OLA),complemented by population management through truncation ***,leveraging MFMA,we propose a power optimization approach for MPRM logic circuits that searches for the best polarity configuration to minimize circuit *** results based on Microelectronics Center of North Carolina(MCNC)benchmark circuits demonstrate significant improvements over existing power optimization *** achieves a maximum power saving rate of 72.30%and an average optimization rate of 43.37%;it searches for solutions faster and with higher quality,validating its effectiveness and superiority in power optimization.

关键词： Power optimization Multi-strategy fusion memetic algorithm(MFMA) Mixed polarity Reed-Muller(MPRM) Combinatorial optimization problem

来源：评论

学校读者我要写书评

暂无评论

MedX-Net: Hierarchical Transformer with Large Kernel Convolutions for 3D Medical Image Segmentation

MedX-Net: Hierarchical Transformer with Large Kernel Convolu...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Lin Zou, Qingzhi Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Due to the exceptional performance of Transform-ers in 2D medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Prompt-Based Representation Individual Enhancement Method for Chinese Idiom Reading Comprehension 28th

A Prompt-Based Representation Individual Enhancement Method ...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Sha, Ying Wu, Mingmin Zeng, Zhi Ge, Xing Huang, Zhongqiang Wang, Huan College of Informatics Huazhong Agricultural University Wuhan China Key Laboratory of Smart Farming for Agricultural Animals Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China

ISBN: (纸本)9783031306747

Chinese idiom is a distinctive language phenomenon, which usually consists of four Chinese characters and expresses a non-compositional and metaphorical meaning. Therefore, Chinese idioms pose unique challenges for Chinese machine reading comprehension. To address this issue, researchers proposed a Chinese idiom cloze task and a large-scale Chinese idioms dataset ChID. Existing methods have proposed a number of models and achieved reasonable performance on ChID. However, they fall short of fully exploring the precise representations and distinctions of the meanings of idioms, especially idioms with similar meanings. In this paper, we propose a prompt-based representation individual enhancement method (PRIEM). This method fuses the context-specific representation and the generic definition representation of the idioms, and uses the prompt method to guide the model in learning the metaphorical meanings of idioms purposefully. To further improve the distinction representations of idioms with similar meanings, PRIEM adopts a method of idiom representation mapping and decomposing based on orthogonal projection to obtain the common and individual representations of idioms respectively. Experimental results on ChID show that our model outperforms state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

System Reliability Analysis of Planar Rock Slope Based on the Modified Pseudo-Dynamic Method and the Nonlinear Barton-Bandis Criterion

引用

Iranian Journal of Science and Technology, Transactions of Civil engineering 2025年 1-16页

作者： Zuo, Shi Liu, Wensheng Zhao, Lianheng Yu, Chenghao Liu, Le Xin, Yue Zhu, Jincheng School of Civil Engineering Changsha University Changsha China Hunan Provincial Key Laboratory for Big Data Smart Application of Natural Disaster Risks Survey of Highway Engineering Changsha University Changsha China The Second Engineering Co LTD. Of CTCE Group Suzhou China College of Civil Engineering Central South University Changsha China Key Laboratory of Heavy-Haul Railway Engineering Structure Ministry of Education Central South University Changsha China Hunan Provincial Key Laboratory for Disaster Prevention and Mitigation of Rail Transit Engineering Structure Central South University Changsha China

The stability analysis of jointed rock slopes under seismic activity is a crucial and challenging task. To assess the various potential damage modes of rock slopes featuring tension fracture planes, it is necessary to take into consideration the nonlinear properties of shear strength and the dynamic features of seismic activity. A modified pseudo-dynamic technique has been used to represent the slope safety coefficient under seismic action by utilizing the nonlinear Barton-Bandis failure criterion. Furthermore, a system reliability analysis of slope stability is carried out using a Monte Carlo simulation method. The findings indicate that the slope safety coefficient exhibits periodic variations over time when considering seismic action in dynamic conditions. Additionally, the interaction force between the blocks significantly influences the factor of safety. The slope system stability is notably affected by the horizontal seismic coefficient, while the vertical seismic coefficient has a less effect. Among the various potential failure modes, failure modes 2 and 4 are identified as the primary failure modes. The likelihood of failure mode 1 occurrence gradually increases with an increase in the nodal strength parameter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KAN v.s. MLP for Offline Reinforcement Learning

KAN v.s. MLP for Offline Reinforcement Learning

引用

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

作者： Haihong Guo Fengxin Li Jiao Li Hongyan Liu School of Information Renmin University of China China Institute of Medical Information / Medical Library Chinese Academy of Medical Sciences / Peking Union Medical College China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements.

关键词： Training Performance evaluation Hands Q-learning Neural networks Memory management Signal processing Benchmark testing Splines (mathematics) Speech processing

来源：评论

学校读者我要写书评

暂无评论

WOBTree:a write-optimized B+-tree for non-volatile memory

引用

Frontiers of Computer Science 2021年第5期15卷 37-51页

作者： Haitao WANG Zhanhuai LI Xiao ZHANG Xiaonan ZHAO Song JIANG School of Computer Science and Engineering Northwestern Polytechnical UniversityXi'An 710072China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical UniversityMinistry of Industry and Information TechnologyXi'An 710072China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’An 710072China Department of Computer Science and Engineering University of Texas at ArlingtonArlingtonTX 76010USA

The emergence of non-volatile memory(NVM)has introduced new opportunities for performance optimizations in existing storage *** better utilize its byte-addressability and near-DRAM performance,NVM can be attached on the memory bus and accessed via load/store memory instructions rather than the conventional block *** this scenario,a cache line(usually 64 bytes)becomes the data transfer unit between volatile and non-volatile ***,the failure-atomicity of write on NVM is the memory bit width(usually 8 bytes).This mismatch between the data transfer unit and the atomicity unit may introduce write amplification and compromise data consistency of node-based data structures such as B+-*** this paper,we propose WOBTree,a Write-Optimized B+-Tree for NVM to address the mismatch problem without expensive *** minimizes the update granularity from a tree node to a much smaller subnode and carefully arranges the write operations in it to ensure crash consistency and reduce write *** results show that compared with previous persistent B+-tree solutions,WOBTree reduces the write amplification by up to 86× and improves write performance by up to 61× while maintaining similar search performance.

关键词： non-volatile memory B+-tree atomic granularity mismatch write amplification performance optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization analysis of an electric vehicle air-conditioning system based on AMEsim and HEEDS 10

Multi-objective optimization analysis of an electric vehicle...

引用

10th International Conference on Energy Materials and Electrical engineering, ICEMEE 2024

作者： Yao, Mengliang Zeng, Zhixin Ruan, Xianzhen Peng, Changbo Zhu, Liang Li, Siwang Feng, Bo Xu, Zichen Xie, Peng Wang, Chaoqian Automotive Engineering Institute Guangzhou Automobile Group Co. LTD Guangzhou511434 China School of Mechanical and Automotive Engineering South China University of Technology Guangzhou510641 China Guangdong Provincial Key Laboratory of Fuel Cell Technology School of Chemistry and Chemical Engineering South China University of Technology Guangzhou510640 China Automotive Data of China co. Ltd Tianjin300300 China

ISBN: (纸本)9781510686243

The air conditioning system of electric vehicles is crucial to ensure the comfort of passengers and reduce energy consumption. This paper establishes a multi-objective optimization co-simulation model of an electric vehicle air conditioning system based on AMEsim and HEEDS. With the system cooling capacity, compressor energy consumption, performance of coefficient, and temperature drop time as the optimization objectives and the evaporator outlet air temperature, operating pressure, and pressure ratio as the constraints, the NSGA-Ⅲ algorithm is used to select the system operating parameters that meet the optimization objectives and constraint conditions. The effects of different operating parameters on the optimization objectives are analyzed. The results show that the research method can effectively locate a reasonable range of different operating parameters, compressor speed is the most important factor affecting the optimization objectives, and parameter sensitivity analysis results help formulate more effective operation control strategies. © 2024 SPIE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Summer Atmospheric Water Cycle under the Transition Influence of the Westerly and Summer Monsoon over the Yarlung Zangbo River Basin in the Southern Tibetan Plateau

引用

Advances in Atmospheric Sciences 2024年第5期41卷 830-846页

作者： Qianhui MA Chunyan ZHANG Donghai WANG Zihao PANG School of Atmospheric Sciences Sun Yat-sen UniversityGuangdong Province Key Laboratory for Climate Change and Natural Disaster StudiesKey Laboratory of Tropical Atmosphere-Ocean SystemMinistry of EducationZhuhai 519082China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519082China Guangdong Meteorological Data Center Guangdong Meteorological ServiceGuangzhou 510080China National Observation and Research Station of Coastal Ecological Environments in Macao Macao Environmental Research InstituteMacao University of Science and TechnologyMacao SAR 999078China National Meteorological Information Center China Meteorological AdministrationBeijing 100081China

This study compares the summer atmospheric water cycle,including moisture sources and consumption,in the upstream,midstream,and downstream regions of the Yarlung Zangbo River Basin in the southern Tibetan *** evolutions of moisture properties under the influence of the westerly and summer southerly monsoon are examined using 5-yr multi-source measurements and ERA5 reanalysis *** that moisture consumption in this study is associated with clouds,precipitation,and diabatic *** to the midstream and downstream regions,the upstream region has less moisture,clouds,and precipitation,where the moisture is brought by the *** early August,the vertical wet advection over this region becomes enhanced and generates more high clouds and *** midstream region has moisture carried by the westerly in June and by the southerly monsoon from July to *** higher vertical wet advection maximum here forms more high clouds,with a precipitation peak in early *** downstream region is mainly affected by the southerly-driven wet *** rich moisture and strong vertical wet advection here produce the most clouds and precipitation among the three regions,with a precipitation peak in late *** height of the maximum moisture condensation is different between the midstream region(325 hPa)and the other two regions(375 hPa),due to the higher upward motion maximum in the midstream *** diabatic heating structures show that stratiform clouds dominate the upstream region,stratiform clouds and deep convection co-exist in the midstream region,and deep convection systems characterize the downstream region.

关键词： Yarlung Zangbo River Basin atmospheric water cycle constrained variational analysis moisture source and consumption

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：