检索结果-内蒙古大学图书馆

第35届中国控制与决策会议

作者： Shun Wang Hongyan Ma Shengyan Li Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big DataBeijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

University library is an important building for teaching and *** atrium library has the characteristics of good lighting and flexible use,and the atrium structure was extensively ***,the fire in the atrium library will cause more serious *** this paper,we build a fire and evacuation model of a university atrium library and conduct a simulation *** with BIM technology,we restored the physical information of a university library and establish a fire *** was used to simulate the fire somke diffusion,and the smoke factors were analyzed to derive the available safe evacuation time(ASET).Pathfinder was used to simulate personnel evacuation,which determines the required safe evacuation time(REST).The simulation results show that the visibility of the smoke is the most important factor affecting personnel evacuation,and the personnel needs 108 s to evacuate the fire area and 291 s to enter the stairwell to *** the personnel in the library by area can shorten the evacuation time by about 74 *** study is expected to provide support for the fire simulation and personnel evacuation in atrium building.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neighbor Importance-Aware Graph Collaborative Filtering for Item Recommendation

SSRN

引用

SSRN 2022年

作者： Wang, Qingxian Liu, Xinyu Bai, Yanan Chen, Bo Shi, Xiaoyu Chengdu610054 China Chongqing University of Technology Chongqing401135 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China Intelligent Terminal Key Laboratory of SiChuan Province Yibin644000 China

The emerging topic of Graph Neural Network (GNN) has attracted increasing attention and achieved state-of-the-art (SOTA) performance in many recommendation problems, due to its strong ability in node representation with exploring high-order information. To learn a node’s representation, most previous methods usually linearly combine the embeddings of node features, amusing the equal importance of neighbors. However, due to the intrinsic differences (i.e., degree, create time) over neighbors, we argue that these differences carry important signals for node representation. Ignoring them will lead to a sub-optimal in node representation and thus weaken the effectiveness of the follow-up graphbased operations. To address it, we propose big-SAGE@ for item recommendation with rating prediction task, which is a neighbor importance-aware graph neural network. Specifically, its main idea is two-fold: 1) A rating-confidencebased neighborhood sampling method is introduced, making the sampling process biased to those more valuable nodes. 2) An attention network is integrated to achieve the rating prediction task, by flexibly incorporating information from user and item embedding features. Finally, we verified the effectiveness of the proposed model on six public data sets. Extensive experimental results demonstrate the superior performance of big-SAGE@ in the rating prediction task, compared to the SOTA methods. © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Projection methods with linesearch technique for pseudomonotone equilibrium problems and fixed point problems

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第1期83卷 3-14页

作者： Zhu, Li-Jun Yao, Yonghong Postolache, Mihai The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China School of Mathematical Sciences Tiangong Uni-versity Tianjin300387 China Center for General Education China Medical University Taichung40402 Taiwan Department of Interior Design Asia University Taichung Taiwan Romanian Academy Gh. Mihoc-C. Iacob Institute of Mathematical Statistics and Applied Mathematics Bucharest050711 Romania University "Politehnica" of Bucharest Department of Mathematics and Informatics Bucharest060042 Romania

In this paper, we discuss pseudomonotone equilibrium problems and fixed point problems in real Hilbert spaces. With the help of linesearch technique, we propose a projection algorithm without any Lipschitz-type condition for solving equilibrium problems and fixed point problems. We show that the constructed algorithm converges strongly to a common element of the investigated problems. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

A pruning method based on the dissimilarity of angle among channels and filters

arXiv

引用

arXiv 2022年

作者： Yao, Jiayi Li, Ping Kang, Xiatao Wang, Yuzhe Changsha University of Science and Technology China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp China

Convolutional Neural Network (CNN) is more and more widely used in various fileds, and its computation and memory-demand are also increasing significantly. In order to make it applicable to limited conditions such as embedded application, network compression comes out. Among them, researchers pay more attention to network pruning. In this paper, we encode the convolution network to obtain the similarity of different encoding nodes, and evaluate the connectivity-power among convolutional kernels on the basis of the similarity. Then impose different level of penalty according to different connectivity-power. Meanwhile, we propose Channel Pruning base on the Dissimilarity of Angle (DACP). Firstly, we train a sparse model by GL penalty, and impose an angle dissimilarity (AD) constraint on the channels and filters of convolutional network to obtain a more sparse structure. Eventually, the effectiveness of our method is demonstrated in the section of experiment. On CIFAR-10, we reduce 66.86% FLOPs on VGG-16 with 93.31% accuracy after pruning, where FLOPs represents the number of floating-point operations per second of the model. Moreover, on ResNet-32, we reduce FLOPs by 58.46%, which makes the accuracy after pruning reach 91.76%. Our code is made public at: https://***/kangxiatao/prune_tf2_master. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

arXiv

引用

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Asymmetrical Interactions Driven by Strategic Persistence Effectively Alleviates Social Dilemmas in Spatial Games

SSRN

引用

SSRN 2024年

作者： Li, Xiaopeng Wang, Zhonglin Xu, Yan Zhang, Hui Yu, Guihai College of Big Data Statistics Guizhou University of Finance and Economics Guizhou Guiyang550025 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China School of Information Guizhou University of Finance and Economics Guizhou Guiyang550025 China Guangxi Key Laboratory of Big Data in Finance and Economics Guangxi University of Finance and Ecomonics Nanning530003 China

Asymmetry is a common phenomenon in real life due to constraints such as status, age, information, reputation, and so on. Yet it is still unclear how asymmetric interactions driven by adaptive feedback affect the evolution of cooperation. To this end, we creatively propose a novel asymmetric interaction model driven by strategy persistence to unravel this mystery. In particular, players whose strategy persistence is beyond the threshold β are the pearls for being able to interact with all of the neighbors. Otherwise, they can only interact with half of their neighbors as the layfolks. As the strategy persistence is always updated, leading to the fact that the pearls and the layfolks maybe switch at any time, which adds uncertainty to the evolution of cooperation. Simulation results show that the asymmetric interaction of adaptive feedback effectively alleviates social dilemmas, thus opening up a path for cooperators to survive. Moreover, with the increase of β, there is an appropriate interval resulting in the optimal evolution of cooperation. Micro analysis further indicates that the pearl cooperators play an irreplaceable pivotal role in promoting the evolution of cooperation. At last, we verify and extend the applicability and robustness of the designed model through other social dilemmas, network topologies, and strategy update patterns © 2024, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Visualization Study on the Dynamic Behavior of Shear Thinning Droplets Impacting Superhydrophobic Spheres

SSRN

引用

SSRN 2024年

作者： Qian, Lijuan Xu, Liujun Sun, Chengbin Lv, Li College of Mechanical and Electrical Engineering China Jiliang University Hangzhou310018 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China jiliang University Hangzhou310018 China

The surface characteristics and droplet characteristics significantly affect the dynamic behavior of droplet impact on solid surfaces. A visualization platform is utilized in this work to experimentally study the dynamic behavior of shear thinning fluid droplets impacting superhydrophobic spheres. By calculating the diffusion arc angle and diffusion coefficient corresponding to the two-dimensional wetting arc in the maximum diffusion state, the effects of different concentrations, We numbers, particle size ratios on droplets impact are studied. The results show that on the superhydrophobic sphere, as the shear thinning droplet concentration increases, the diffusion diameter increases, and the contact time decreases. Under the same curvature, the contact time between the droplet and the sphere decreases with the increase of We number. After the We number reaches a specific value, the contact time remains unchanged with the increase of We number. Then under different curvature conditions, the contact time increases with the increase of curvature. When the diameter ratio of the sphere to the droplet is D*≥6, the maximum diffusion coefficient remains almost unchanged. However, when D*＜6, the maximum diffusion dimensionless diameter significantly increases as the particle size ratio decreases. Importantly, a theoretical model considering gravity effect is established to predict the maximum dimensionless diameter of shear thinning droplets on superhydrophobic spheres on the basis of energy conservation. The deviation between the maximum dimensionless diameter obtained by this theoretical model and the experimental results is within ± 10%. © 2024, The Authors. All rights reserved.

关键词： Shear thinning

来源：评论

学校读者我要写书评

暂无评论

Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning (Extended Abstract)

Cost-Sensitive Portfolio Selection via Deep Reinforcement Le...

引用

International Conference on data Engineering

作者： Yifan Zhang Peilin Zhao Qingyao Wu Bin Li Junzhou Huang Mingkui Tan National University of Singapore Tencent AI Lab South China University of Technology Wuhan University University of Texas at Arlington Key Laboratory of Big Data and Intelligent Robot Ministry of Education Pazhou Laboratory

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Adaptive Compression for Efficient Communication in Heterogeneous Federated Learning

Dual Adaptive Compression for Efficient Communication in Het...

引用

IEEE/ACM International Symposium on Cluster computing and the Grid (CCGRID)

作者： Yingchi Mao Zibo Wang Chenxin Li Jiakai Zhang Shufang Xu Jie Wu Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer and Information Hohai University Nanjing China Center for Networked Computing Temple University Philadelphia USA

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

In federated learning, multiple rounds of communication are involved between clients and the server to train a global model. The extensive model updates transmitted during the training lead to significant communication costs. Previous methods usually employ quantization or sparsification to compress model updates. However, the lossy compression leads to a decline in accuracy, it is challenging to strike a balance between communication efficiency and model accuracy. Meanwhile, due to the data heterogeneity, local updates among different clients are biased towards each other. Employing the same compression ratios for each local updates will further degrade the model accuracy. To achieve the trade-off between communication efficiency and model accuracy, we propose FedDAC, a Dual Adaptive Compression method in heterogeneous federated learning. In the local computation phase, the loss queue is adopted to detect the convergence trends within each client. FedDAC can then dynamically quantify model updates and allow for various compression ratios among heterogeneous clients. In the global aggregation phase, FedDAC can determine the fluctuations in training based on the similarity between clients and the server, thereby adjusting the sparsity ratio flexibly. To alleviate the reduction in model accuracy caused by lossy compression, we introduce residual updates in the local computation and global aggregation phases to maintain model accuracy. Experiment results show that compared with one-way compression methods NAGC and AdaQuantFL, FedDAC can maintain comparable accuracy while the accumulated communication volume is reduced by about 29.6 times, and 22.8 times, respectively. Moreover, the global model accuracy of FedDAC surpasses the two-way compression method T-FedAvg by about 2.4%, and the accumulated communication volume is about 2.5 times lower than T-FedAvg.

关键词： Training Adaptation models Solid modeling Accuracy Quantization (signal) Fluctuations Federated learning Computational modeling Market research Servers

来源：评论

学校读者我要写书评

暂无评论

3D-GRES: Generalized 3D Referring Expression Segmentation

arXiv

引用

arXiv 2024年

作者： Wu, Changli Liu, Yihang Ji, Jiayi Ma, Yiwei Ding, Henghui Wang, Haowei Sun, Xiaoshuai Luo, Gen Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China Institute of Big Data Fudan University Shanghai China Youtu Lab Tencent Shanghai China

3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-object segmentation tasks into simpler, individual segmentations. MDIN comprises two fundamental components: Text-driven Sparse Queries (TSQ) and Multi-object Decoupling Optimization (MDO). TSQ generates sparse point cloud features distributed over key targets as the initialization for queries. Meanwhile, MDO is tasked with assigning each target in multi-object scenarios to different queries while maintaining their semantic consistency. To adapt to this new task, we build a new dataset, namely Multi3DRes. Our comprehensive evaluations on this dataset demonstrate substantial enhancements over existing models, thus charting a new path for intricate multi-object 3D scene comprehension. The benchmark and code are available at https://***/sosppxo/MDIN. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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：