检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Hongting Ye Yalu Zheng Yueying Li Ke Zhang Youyong Kong Yonggui Yuan Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Ministry of Education China Department of Psychosomatics and Psychiatry Zhongda Hospital School of Medicine Southeast University

Multimodal fusion has become an important research technique in neuroscience that completes downstream tasks by extracting complementary information from multiple modalities. Existing multimodal research on brain networks mainly focuses on two modalities, structural connectivity (SC) and functional connectivity (FC). Recently, extensive literature has shown that the relationship between SC and FC is complex and not a simple one-to-one mapping. The coupling of structure and function at the regional level is heterogeneous. However, all previous studies have neglected the modal regional heterogeneity between SC and FC and fused their representations via "simple patterns", which are inefficient ways of multimodal fusion and affect the overall performance of the model. In this paper, to alleviate the issue of regional heterogeneity of multimodal brain networks, we propose a novel Regional Heterogeneous multimodal Brain networks Fusion Strategy (RH-BrainFS). Briefly, we introduce a brain subgraph networks module to extract regional characteristics of brain networks, and further use a new transformer-based fusion bottleneck module to alleviate the issue of regional heterogeneity between SC and FC. To the best of our knowledge, this is the first paper to explicitly state the issue of structural-functional modal regional heterogeneity and to propose a solution. Extensive experiments demonstrate that the proposed method outperforms several state-of-the-art methods in a variety of neuroscience tasks. The codes are available at https://***/Yedaxia1/RH-BrainFS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on User Authentication for Grid Computing Security

Research on User Authentication for Grid Computing Security

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Ronghui Wu Ronghui Wu Renfa Li Renfa Li Fei Yu Fei Yu Guangxue Yue Guangxue Yue Cheng Xu Cheng Xu State Key Laboratory of Information Security Graduate School of Chinese Academy of Sciences Beijing China School of Computer & Communication Hunan University Changsha China Provincial Key Laboratory of Computer Information Processing Technology Suzhou University Suzhou Jiangsu Province China College of Informationg Engineering JiaXing University JiaXing China

Recently, Authentication protocol has been recognized as an important factor for grid computing security. This paper described a new simple and efficient Grid authentication system providing user anonymity. Our system is based on hash function, and mobile users only do symmetric encryption and decryption. In our system, it takes only one round of messages exchange between the mobile user and the visited network, and one round of message exchange between the visited network and the corresponding home network. The proposed architecture possesses several desirable emerging properties that enable it to provide an improved level of security for grid computing systems..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Code Generation Based on Quality-Aware Reordering

Code Generation Based on Quality-Aware Reordering

引用

6th International Conference on Intelligent Computing and Signal processing (ICSP)

作者： Yuan Song Luo Yu College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Translation efforts from natural language to code generation have achieved great success with large pre-trained language models. However, selecting the correct code output for the problem posed by the generated set of candidate codes is still challenging. In this paper, we address this problem by proposing an outcome-based quality-aware reordering method for code selection. This method scores each code by whether the set of candidate codes passes the test cases or not as a reference to select the top k best code outputs. In addition, this method depends on the quality and number of test cases. However, it is impractical to manually create a large number of test cases for each problem, so this paper adopts an automated approach that utilizes the current model to generate test cases for each problem. The experimental results show that the approach proposed in this paper obtains a significant improvement in the pass@k benchmark for each model, and the correctness and quality of test cases generated automatically using the model are discussed experimentally. Summarizing the experimental results and discussions, the result-based quality-aware reordering method proposed in this paper achieves a significant improvement in solving the problem of selecting the correct output from natural language to code generation, effectively improves the accuracy of evaluation by automating the generation of test cases, and provides an effective solution to improving the correctness of code generation.

关键词： Codes Accuracy Computational modeling Estimation Signal processing Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Sample efficient imitation learning via reward function trained in advance

arXiv

引用

arXiv 2021年

作者： Zhang, LiHua Liu, Quan School of Computer Science and Technology Soochow University Soochow China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University Jilin China

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms of environment interaction, which severely limits their application to simulated domains. In industrial applications, learner usually have a high interaction cost, the more interactions with environment, the more damage it causes to the environment and the learner itself. In this article, we make an effort to improve sample efficiency by introducing a novel scheme of inverse reinforcement learning. Our method, which we call Model Reward Function Based Imitation Learning (MRFIL), uses an ensemble dynamic model as a reward function, what is trained with expert demonstrations. The key idea is to provide the agent with an incentive to match the demonstrations over a long horizon, by providing a positive reward upon encountering states in line with the expert demonstration distribution. In addition, we demonstrate the convergence guarantee for new objective function. Experimental results show that our algorithm reaches the competitive performance and significantly reducing the environment interactions compared to IL methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Leakage-resilient identity-based encryption scheme

Leakage-resilient identity-based encryption scheme

引用

International Conference on Networked Computing and Advanced information Management (NCM)

作者： Xizhao Luo Peide Qian Yanqin Zhu Shangping Wang School of Computer Science and Technology Soochow University Suzhou China Provincial Key Laboratory of Computer Information Processing Technology Soochow University Suzhou China School of Science Xi'an University of Technology Xi'an Shaanxi China

ISBN: (纸本)9781424476718

We present an identity-based encryption in the relative-leakage model. In our construction, we firstly make use of a notion of new cryptographic primitive, identity-based hash proof system(IB-HPS), to construct a leakage-resilient IB-HPS based on a simple assumption and also prove its security by the variant of dual system encryption. Then, based on our IB-HPS scheme, we construct directly an efficient leakage-resilient identity-based encryption(IBE) scheme in the model.

关键词： Zinc Erbium Cryptography

来源：评论

学校读者我要写书评

暂无评论

Node-based sampling P2P bot detection

引用

Telkomnika 2012年第5期10卷 1117-1122页

作者： Yin, Chunyong Sun, Ruxia Yang, Lei Dariuslko School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China Jiangsu Key Laboratory of Meteorological Observation Information Processing Nanjing University of Information Science and Technology Nanjing 210044 China

The concept of using node-based sampling for the treatment of packet capture mechanism based on Libpcap of network-based detecting Peer-to-Peer botnet process was tested, and its effect on the time window of feature extracting and sampling time interval was explored. Node-based sampling treatment resulted in significant increase in the detection performance due to node profile of the novel behaviors to the detected computer in Peer-to-Peer bot detection, and the degradation of false positive. At relatively right time window (e.g., about 180s), precision was completely maximized, while the false positive decreased by 10% to 15%. The detection rate can be significantly increased due to the false positive degradation. A new performance index called Comprehensive Evaluation Index is proposed for more clearly represent the effectiveness. Sampling can reduce more than 60% input raw packet traces and achieve a high detection rate (about 99%) and a low false positive rates (0-2%). © 2012 Universitas Ahmad Dahlan.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Target Detection and Classification Based on Improved Candidate Regions 11th

Large-Scale Target Detection and Classification Based on Imp...

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Xi, Runping Han, Qianqian Jia, Gaoyun Kou, Xuefeng School of Computer Science and Techology Northwest Polytechnical University Xi’an710072 China National Engineering Laboratory of Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Xi’an710129 China Shaanxi Baocheng Aviation instrument Co. Ltd. Baoji China

ISBN: (纸本)9783030873578

Target detection of aerial images has become a frontier subject of concern in the image processing field. Using existing method to detect and classify large-scale building objects in aerial images, the accuracy is still a little low. This is mainly because the current method does not make full use of the prior information of the target to be detected, so there are too much redundant information in the candidate box. In this paper, our own dataset were built and then utilize the Hough transform to filter out the images that may exist in the sequence image. For images with dense lines or circles, it is possible that there is an artificial building target which will be detected, otherwise it is excluded directly. Besides, this paper exploits significance analysis from the filtered image and then extract the area of interest where the potential target is located. The results of the above-mentioned processing lay a good foundation for the subsequent detection and classification which can help improve the accuracy. © 2021, Springer Nature Switzerland AG.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Robust monocular visual odometry using optical flows for mobile robots

Robust monocular visual odometry using optical flows for mob...

引用

Chinese Control Conference (CCC)

作者： Haifeng Li Zunhe Hu Xinwei Chen College of Computer Science and Technology Civil Aviation University of China Tianjin Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou Department of Computer Science Minjiang University Fuzhou

A robust optical flow-based visual odometry method using a single onboard camera is proposed in this paper. To improve the quality of the noisy optical flows, a correction method across multiple frames is developed. Furthermore, the optical flows in the plane at infinity are detected and removed as these optical flows have very low signal to noise ratio for robot translation estimation. Finally, a RANSAC approach for robot ego-motion estimation is proposed. Physical experiments are carried out and the results show that the proposed method is able to estimate the camera trajectory robustly with reasonable accuracy.

关键词： Adaptive optics Image motion analysis computer vision Optical imaging Optical sensors Cameras Optical noise

来源：评论

学校读者我要写书评

暂无评论

A Reliable Broadcasting Algorithm in Locally Twisted Cubes

A Reliable Broadcasting Algorithm in Locally Twisted Cubes

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Baolei Cheng Jianxi Fan Dajin Wang Jiwen Yang Provincial Key Laboratory for Computer Information Processing Technology Soochow University China School of Computer Science and Technology Soochow University Suzhou China Department of Computer Science Montclair State University Upper Montclair NJ USA

ISBN: (纸本)9781467393010

Reliable broadcasting for a network can be obtained by using completely independent spanning trees(CISTs). Locally twisted cubes are popular networks which have been studied widely in the literature. In this paper, we study the problem of using CISTs to establish reliable broadcasting in locally twisted cubes. We first propose an algorithm, named LTQCIST, to construct two CISTs in locally twisted cubes, then exemplify the construction procedures to construct CISTs. Finally, we prove the correctness of Algorithm LTQCIST and simulate CISTs with JUNG.

关键词： Broadcasting Hypercubes Reliability computer science Conferences computer security

来源：评论

学校读者我要写书评

暂无评论

Design and realization of evaluation environment in the performance analysis of intrusion detection system

Design and realization of evaluation environment in the perf...

引用

26th Chinese Control Conference, CCC 2007

作者： Liao, Guiping Yu, Fei Shen, Yue Zhang, Linfeng Xu, Cheng School of Computer and Information Engineering Hunan Agricultural University Changsha 410128 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou University Suzhou 2150063 China Guangdong Province Key Lab of Electronic Commerce Market Application Technology Guangdong University of Business Studies Guangzhou510320 China

ISBN: (纸本)7900719229

With the deeply research on intrusion detection techniques and the widely use of intrusion detection products, the study of evaluation techniques of intrusion detection systems became important. In the paper, relative works of the evaluation of intrusion detection systems was introduced. The primary aspects of intrusion detection systems in an evaluation were discussed. An evaluation system for intrusion detection systems was proposed. In the system, a supervisor module controls the whole system. The supervisor module schedules the traffic control module and the attack emulation module. The data in the evaluation environment are recorded and input to the evaluation module. The functions such as emulation of network traffic and host usage, emulation of attacks and evaluation report generation are implemented.

关键词： Control system analysis

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：