检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Yepeng Shi Guijuan Zhang Dianjie Lu Lei Lv Hong Liu Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (纸本)9781728165981

Negative emotion will spread among the crowd, and make people irrational. Intervention can reduce crowd panic by isolating the source of transmission or spreading positive emotions, which is an effective measure to ensure the safety of the crowd. However, it is still a very challenging problem that how to use appropriate intervention to maximize the influence to infected individuals while minimizing the cost of the intervention. To this end, we present an intervention optimization method for crowd emotional contagion (IO-CEC) to adaptively intervene in negative emotional contagion. First, we build a stochastic events based emotional contagion model (SEEC) to capture the dynamic evolution characteristics of crowd emotional contagion. In this model, we combine the SIS infection model and the Markov stochastic process to study the dynamic change of the number of infected individuals. Second, we propose a Hawkes process based intervention model (HIM) to describe the intensity of intervention. By using the Hawkes stochastic point process, two intervention intensity functions are defined to quantify the infection rate and recovery rate. Then, in order to improve the efficiency of intervention, we formulate the intervention optimization as a problem of maximizing the utility and use a heuristic algorithm to solve it. Finally, we implement a crowd emotional contagion simulation system to visualize the results of emotional intervention. Experimental results show that our method is effective and has great significance for guiding realistic emotional intervention.

关键词： Adaptation models Visualization Computational modeling Heuristic algorithms Stochastic processes Optimization methods Manuals

来源：评论

学校读者我要写书评

暂无评论

Distribution-restrained Softmax Loss for the Model Robustness

arXiv

引用

arXiv 2023年

作者： Wang, Hao Li, Chen Jiang, Jinzhe Zhang, Xin Zhao, Yaqian Gong, Weifeng School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Inspur Electronic Information Industry Co. Ltd Jinan China State Key Laboratory of High-End Server & Storage Technology Jinan China Shandong Hailiang Information Technology Institutes Jinan China Zhengzhou Yunhai Information Technology Co. Ltd Zhengzhou China

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on. However, the principle of the robustness to attacks is still not fully understood, also the related research is still not sufficient. Here, we have identified a significant factor that affects the robustness of models: the distribution characteristics of softmax values for non-real label samples. We found that the results after an attack are highly correlated with the distribution characteristics, and thus we proposed a loss function to suppress the distribution diversity of softmax. A large number of experiments have shown that our method can improve robustness without significant time *** Codes 68T45 © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DTNet: Dual-encoder generative adversarial network for generating breast cancer immunohistochemical images

DTNet: Dual-encoder generative adversarial network for gener...

引用

Computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Yifan Jia Guanhua Duan Yanyun Song Lan Ye Zhi Liu The School of Information Science and Engineering Shandong University Qingdao China Shandong sports rehabilitation research center Jinan China The Cancer center the Second Hospital of Shandong University Jinan China State Key Laboratory of High Performance Server and Storage Technology Jinan China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

In order to address the coloring problem in breast cancer, we propose an innovative generator network architecture paradigm and a pooling-based loss function to tackle the challenge of strict alignment between image pairs. Our network architecture primarily consists of a content encoder, a style encoder, a decoder, and a TSA skip-connection module. The content encoder ensures that content features are preserved during coloring, while the style encoder guarantees the accuracy of coloring styles. The TSS skipconnection layer based on a transformer architecture is employed to facilitate the flow of feature information. Experimental evaluations on four coloring datasets demonstrate that our model exhibits superior performance and robustness compared to existing models.

关键词： Training Image registration Network architecture Feature extraction Transformers Generative adversarial networks Breast cancer

来源：评论

学校读者我要写书评

暂无评论

SGED: A Benchmark dataset for Performance Evaluation of Spiking Gesture Emotion Recognition

arXiv

引用

arXiv 2023年

作者： Wang, Binqiang Dong, Gang Zhao, Yaqian Li, Rengang Cao, Lu Lu, Lihua Shandong Massive Information Technology Research Institute Jinan China State Key Laboratory of High-end Server & Storage Technology Beijing China Electronic Information Industry Co. Ltd. Beijing China Inspur Electronic Information Industry Co. Ltd. Jinan China Intel Labs China Beijing China

In the field of affective computing, researchers in the community have promoted the performance of models and algorithms by using the complementarity of multimodal information. However, the emergence of more and more modal information makes the development of datasets unable to keep up with the progress of existing modal sensing equipment. Collecting and studying multimodal data is a complex and significant work. To supplement the challenge of partial missing of community data, we collected and labeled a new homogeneous multimodal gesture emotion recognition dataset based on the analysis of the existing data sets. This data set complements the defects of homogeneous multimodal data and provides a new research direction for emotion recognition. Moreover, we propose a pseudo dual-flow network based on this dataset, and verify the application potential of this dataset in the affective computing community. The experimental results demonstrate that it is feasible to use the traditional visual information and spiking visual information based on homogeneous multimodal data for visual emotion recognition. The dataset is available at https://***/201528014227051/SGED. Copyright © 2023, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Probing the Underlying Implementation Mechanisms of SW26010 22

Probing the Underlying Implementation Mechanisms of SW26010

引用

22nd IEEE International Conference on high Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020

作者： Zhu, Xiaomin Zhao, Yaqian Balaji, Pavan State Key Laboratory of High-End Server Storage Technology Jinan China Inspur Electronic Information Industry Co. Ltd Jinan China Argonne National Laboratory Usa

ISBN: (纸本)9781728176499

SW26010 is a heterogeneous many-core CPU equipped in the Sunway TaihuLight Supercomputer, which ranks fourth in June 2020 Top500 list. Large varieties of applications have been tuned on SW26010, but only a few researches focus on system-level modeling, benchmarking. In this paper, we evaluated the threading performance on SW26010, concentrating on the underlying implementations of systematic threading and data transmission operations inside a thread, which are the two main overheads deteriorating the overall performance of heterogeneous computing. We design several benchmarks to test and verify the underlying implementation mechanisms, and present thorough analysis of the experimental results. We find that threading overhead is related to the active slave core number and is nontrivial when the data volume and flops/byte ratio are relatively low;data transmission requests are serially handled, while data is transferred in parallel with four buses, each of which is shared by two rows of 16 slave cores. In addition, given that not all slave cores are used, the interleave mode performs better than the continuous mode in both request response and data transmission. At last, several programming methods and optimization principles for SW26010 are proposed. © 2020 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Research on Application of Genetic Algorithms in Corporal Portal Search Engines

Research on Application of Genetic Algorithms in Corporal Po...

引用

IEEE Advanced Information technology, Electronic and Automation Control Conference (IAEAC)

作者： Ye Qiu Dechao Wang Hongli Yan Jinan Rail Transit Group Co. LTD Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

This paper introduces the genetic algorithm followed by implementation steps of it. We began our work with researching and summarizing the application of genetic algorithm in Search Engine Optimization (SEO) of enterprise portal, which shows the effectiveness of genetic algorithm deployed in solving the query optimization problem. Later on, we gave the implementation steps and system framework of the query optimization method based on genetic algorithm. Related studies have proved that genetic algorithm applied in SEO have the potential to optimize the search engine of enterprise portal and achieve fair results.

关键词： Query processing Natural languages Search engines Information technology Portals Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Low-power 25Gb/s 16:1 Multiplexer for 400Gb/s Ethernet PHY 2

Low-power 25Gb/s 16:1 Multiplexer for 400Gb/s Ethernet PHY

引用

2021 2nd International Conference on Applied Physics and Computing, ICAPC 2021

作者： Zhan, Yongzheng Li, Tuo Yue, Yuqiu Liu, Tongqiang Zhou, Yulong Zou, Xiaofeng State Key Laboratory of High-end Server and Storage Technology Jinan China Inspur Electronic Information Industry Co. Ltd. Jinan China Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co. Ltd. Jinan China School of DingLi Shandong University of Engineering and Vocational Technology Jinan China

A lower power 25Gb/s 16:1 multiplexer using 65nm CMOS technology for 400Gb/s Ethernet (400GbE) physical layer (PHY) interface was presented. CMOS+CML mixed logic is adopted to achieve hierarchical architecture, avoiding the high clock requirement of one-step structure and improving the transmission speed. In order to reduce power while achieving high data rate, multiplexing structure is also optimized by utilizing multi-frequency multi-phase technology which not only ensures the requirement of the phase stabilization, but also leaves out some flip-flops. For CMOS-CML conversion circuit, transmission gate and cross-coupled CMOS inverter are used to match the delay of CMOS inverter, suppressing the effect of common-mode noise. Simulation results show that the multiplexer works correctly and jitter of output signal is less than 0.1UI. When voltage is 1.2V, the total power is 32.7mW at 25Gb/s. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Ethernet

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Knowledge Graph Completion Based On Gated Attention Unit

Sequence-to-Sequence Knowledge Graph Completion Based On Gat...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Fengge Yi Xiumei Wei Xiaojing Liu Xuesong Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5’s proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HMEH: write-optimal extendible hashing for hybrid DRAM-NVM memory 36

HMEH: write-optimal extendible hashing for hybrid DRAM-NVM m...

引用

36th International Conference on Massive storage Systems and technology, MSST 2020

作者： Zou, Xiaomin Wang, Fang Feng, Dan Chen, Janxi Liu, Chaojie Li, Fan Su, Nan Wuhan National Laboratory for Optoelectronics School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory of High-end Server & Storage Technology Shandong Massive Information Technology Research Institute China

Emerging non-volatile memory (NVM) is expected to coexist with DRAM as a hybrid memory to fully exploit the complementary strengths of DRAM’s low read-write latency and NVM’s high density, persistence, and low standby power. However, existing hashing schemes cannot efficiently reap the benefits of such a hybrid memory. In this paper, we present a hybrid DRAM-NVM write-optimal and high-performance dynamic hashing scheme, named HMEH (Hybrid Memory Extendible Hashing). In our design, key-value items are persisted in NVM while the directory is placed in DRAM for faster access. To rebuild the directory upon recovery, HMEH also keeps a radix-tree-structured directory in NVM with negligible overhead. Furthermore, HMEH proposes a cross-KV strategy to write back items through natural eviction, which can ensure data consistency with no performance degradation from persist barriers. Experimental results show that HMEH outperforms the state-of-the-art NVM-based hashing structures by up to 2.47×. And concurrent HMEH also delivers superior performance and high scalability under YCSB workloads with different search/insertion ratios. © 2020 36th International Conference on Massive storage Systems and technology, MSST 2020. All Rights Reserved.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

A Parallelizable Counterfactual Generation Method Based on Gradient Optimization

A Parallelizable Counterfactual Generation Method Based on G...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Haorun Ding Xuesong Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

Post-hoc explanations are important for people to understand the predictions of explanation models. One class of methods in post-hoc explanation is the generation of counterfactuals, where a hypothetical example is obtained by perturbing the inputs to show how one could obtain a different prediction from the decision model. Counter-factual explanations should satisfy several properties: One is that counterfactuals generated under specific scenarios and constraints should be feasible for users, i.e., they should accommodate different causal constraints. The other is that it is more desirable for users to have a wider variety of viable examples, i.e., counterfactual diversity. To this end, we propose a parallelizable method based on gradient optimization. We partition the input feasible domains, perform counterfactual generation independently for each feasible domain, and then parallelize the counterfactual generation process for each feasible domain. Experimental results show that our approach effectively improves the diversity, sparsity, and proximity of the generated counterfactual instances on the public datasets Adult-Income, Lending-Club, German-Credit, and COMPAS compared to other models.

关键词：

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：