检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ouyang, Jinhui Zhu, Yijie Yuan, Xiang Wu, Di Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Changsha Hunan410082 China

The precise prediction of multi-scale traffic is a ubiquitous challenge in the urbanization process for car owners, road administrators, and governments. In the case of complex road networks, current and past traffic information from both upstream and downstream roads are crucial since various road networks have different semantic information about traffic. Rationalizing the utilization of semantic information can realize short-term, long-term, and unseen road traffic prediction. As the demands of multi-scale traffic analysis increase, on-demand interactions and visualizations are expected to be available for transportation participants. We have designed a multi-scale traffic generation system, namely TrafficGPT, using three AI agents to process multi-scale traffic data, conduct multi-scale traffic analysis, and present multi-scale visualization results. TrafficGPT consists of three essential AI agents: 1) a text-todemand agent that is employed with Question & Answer AI to interact with users and extract prediction tasks through texts;2) a traffic prediction agent that leverages multi-scale traffic data to generate temporal features and similarity, and fuse them with limited spatial features and similarity, to achieve accurate prediction of three tasks;and 3) a suggestion and visualization agent that uses the prediction results to generate suggestions and visualizations, providing users with a comprehensive understanding of traffic conditions. Our TrafficGPT system focuses on addressing concerns about traffic prediction from transportation participants, and conducted extensive experiments on five realworld road datasets to demonstrate its superior predictive and interactive performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Sensor data fusion based on an improved dempaster-shafer evidence theory in vehicular cyber-physical systems

Sensor data fusion based on an improved dempaster-shafer evi...

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： Mengmeng Ma Jiyao An Zhong Huang Zhangbao Cao Key Laboratory of Embedded and Network Computing of Hunan Province Hunan University Changsha PR China

ISBN: (纸本)9781479977895

In Vehicular Cyber-Physical Systems (VCPS), the collected sensor data are always uncertain and conflicting. Dempster-Shafer (DS) evidence theory can effectively deal with uncertain information, but the Dempster's rule may produce counter-intuitive results when the information is conflicting. This paper proposed an improved approach for combining conflicting evidence with different weighting factors based on a novel dissimilarity measure. Firstly, a new dissimilarity measure mixing fuzzy nearness with the introduced correlation coefficient is proposed to characterize the divergence degree between two basic probability assignments (BPAs). Then, the weighting factors are developed by using the proposed dissimilarity measure. Finally, the Dempster's rule is chose to combine the revised sources. Simulation experiment shows that the improved method can effectively solve the problem of sensor data fusion in VCPS with better convergence performance.

关键词： Cyber-physical systems Yttrium Real-time systems Weight measurement Data integration Correlation coefficient Reliability

来源：评论

学校读者我要写书评

暂无评论

Schedule length minimization of parallel applications with energy consumption constraints using heuristics on heterogeneous distributed systems

Schedule length minimization of parallel applications with e...

引用

作者： Xie, Guoqi Xiao, Xiongren Li, Renfa Li, Keqin College of Computer Science and Electronic Engineering Hunan University Changsha China Key Laboratory for Embedded and Network Computing of Hunan Province Changsha China Department of Computer Science State University of New York AlbanyNY United States

Energy consumption is one of the primary design constraints in heterogeneous parallel and distributed systems ranging from small embedded devices to large-scale data centers. The problem of minimizing the schedule length of an energy consumption-constrained parallel application has been studied recently in homogeneous systems with a shared memory. To adopt the heterogeneity and distribution of high-performance computing systems, this study solves the problem of minimizing the schedule length of an energy consumption-constrained parallel application in heterogeneous distributed systems based on a dynamic voltage and frequency scaling energy-efficient design technique. The aforementioned problem is divided into 2 subproblems in this study, namely, satisfying energy consumption constraint and minimizing schedule length. The first subproblem is solved by transferring the energy consumption constraint of the application to that of each task, whereas the second subproblem is solved by heuristically scheduling each task with low time complexity. Experiments using both fast Fourier transform and Gaussian elimination parallel applications show that the actual energy consumption values do not always exceed but are close to the given energy consumption constraints. In addition, the minimum schedule lengths are generated using the proposed algorithm. Copyright © 2016 John Wiley & Sons, Ltd.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Online object tracking based on local sparse representation in a Bayesian inference framewo

引用

Journal of Computational Information Systems 2015年第11期11卷 3919-3928页

作者： Liu, Zekun Xu, Cheng Key Laboratory for Embedded Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Changsha China

Significant research has been devoted to object tracking. Most existing algorithms can track the object well in the controlled environment. However, they may fail in the presence of drastic appearance changes or complex environment variation. In the paper, for robustness object tracking, we proposed an algorithm based on the local sparse representation. Different from most of the traditional object representation which only consider the holistic representation, in our proposed algorithm, the image patch of the object is represented sparsely in the form of a linear combination of dictionary elements constructed online to deal with the target appearance changes. And the aim of the object tracking is posed as a binary classification problem. A linear classifier is learned for discriminate the object target from the background. Furthermore, we combine them in a Bayesian inference framework. To alleviate the tracking drift, we proposed a two-stage particle filtering method. Experiments on several benchmark video sequences has demonstrate that our proposed algorithm performs favorably contrasted with other several state-of-art algorithms. ©, 2015, Binary Information Press. All right reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

On Efficient Feature Ranking Methods for High-Throughput Data Analysis

On Efficient Feature Ranking Methods for High-Throughput Dat...

引用

作者： Liao, Bo Jiang, Yan Liang, Wei Peng, Lihong Peng, Li Hanyurwimfura, Damien Li, Zejun Chen, Min Key Laboratory for Embedded and Network Computing of Hunan Province College of Information Science and Engineering Hunan University Changsha Hunan410082 China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Department of Computer Science and Engineering Changsha Medical University Changsha Hunan410219 China

Efficient mining of high-throughput data has become one of the popular themes in the big data era. Existing biology-related feature ranking methods mainly focus on statistical and annotation information. In this study, two efficient feature ranking methods are presented. Multi-target regression and graph embedding are incorporated in an optimization framework, and feature ranking is achieved by introducing structured sparsity norm. Unlike existing methods, the presented methods have two advantages: (1) the feature subset simultaneously account for global margin information as well as locality manifold information. Consequently, both global and locality information are considered. (2) Features are selected by batch rather than individually in the algorithm framework. Thus, the interactions between features are considered and the optimal feature subset can be guaranteed. In addition, this study presents a theoretical justification. Empirical experiments demonstrate the effectiveness and efficiency of the two algorithms in comparison with some state-of-the-art feature ranking methods through a set of real-world gene expression data sets. © 2015 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A unified architecture for DPA-resistant PRESENT

A unified architecture for DPA-resistant PRESENT

引用

2012 International Conference on Innovations in Information Technology, IIT 2012

作者： Zhao, Wei Wang, Yi Li, Renfa Embedded System and Network Laboratory Hunan University Changsha Hunan 410082 China Hunan Province Key Laboratory of Network and Information Security Hunan University Changsha Hunan 410082 China College of Information Science and Engineering Hunan University Changsha Hunan 410082 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore

ISBN: (纸本)9781467311014

Recently, there is a new kinds of cryptographic algorithms are proposed to meet the requirements of "lightweight" applications. PRESENT is one of them, which is built based on 4-bit substitution transformation (S-box) and suitable for low cost hardware implementations. Usually, there needs two 4-bit S-boxes, Sp, ISp, for PRESENT encryption and decryption, in which ISp can be computed from Sp. Therefore, we proposed a unified architecture to supporting the operations of PRESENT encryption and decryption. There also exists a kind of power analysis attacks pose a serious threat on hardware based PRESENT. In order to resist against DPA, we proposed a new masking scheme for PRESENT, in which the nonlinear substitution needs to be carefully masked. In order to reduce the hardware resources for the proposed masking scheme, we reuse the masked Sp to generate masked ISp. The experimental results show that our proposed unified masked PRESENT takes up only one time larger than the unmasked existing design. But, it is obvious that our proposed design has the ability to defend against DPA. © 2012 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Improvement on masked S-box hardware implementation

Improvement on masked S-box hardware implementation

引用

2012 International Conference on Innovations in Information Technology, IIT 2012

作者： Zeng, Juanli Wang, Yi Xu, Cheng Li, Renfa Embedded System and Network Laboratory Hunan University Changsha Hunan 410082 China Hunan Province Key Laboratory of Network and Information Security Hunan University Changsha Hunan 410082 China College of Information Science and Engineering Hunan University Changsha Hunan 410082 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore

ISBN: (纸本)9781467311014

Masking in gate level could efficiently protect AES S-box out of power analysis attack. But there still exists a kind of attack, called glitch attack, to achieve the sensitive information from gate cell leakage. Some works had been done to resist against glitch attack, which carefully masked AND gate or used Wave Dynamic Differential Logic (WDDL) cell. In this paper, we propose an improved masked AND gate, in which the relationship between input masked values and masks is nonlinear. Usually, when converting S-box operations from GF(2 8) to GF(((22)2)2), all the necessary computations become XOR and AND operations. Therefore, to fully mask AES S-box is to substitute the unmasked XOR and AND operations with the proposed masked AND gate and protected XOR gate. Although the proposed masked AND gate take up one extra XOR gate than Trichina's design and Baek's design, it can resist against glitch attack without using specific gate cell, such as WDDL. © 2012 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

The Impact of Word Segmentation on CCG-based Arabic-English SMT

The Impact of Word Segmentation on CCG-based Arabic-English ...

引用

2017 2nd International Conference on Artificial Intelligence: Techniques and Applications (AITA 2017)

作者： Hamdi Ahmed Rajeh Zhi-yong LI Al-Ghaili Mohammed College of Computer Science and Electronic Engineering Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province

This paper presents a comparative study of two approaches to statistical machine translation(SMT).We present a study on Factored Machine Translation for the Arabic–English pair of *** illustrate pre-processing step for the Arabic source language and the new factors which added to the English target *** experiments that injected English side by part-ofspeech(POS) tags,Combinatory Categorical Grammar(CCG) supertags and segmented Arabic sentences displayed a considerable progress in terms of the BLEU *** experiments gained the premier examine of the Baseline phrase-based models during two approaches,Segmented(#S1) and non-segmented(#S2).In both approaches,CCG models acquired the greatest BLEU *** results show that the segmented approach which consists of CCG produce the highest accuracy at 30.91%(1.84% superior than baseline).As shown,the results presented considerable improvement in translating the segmented Arabic rather than the non-segmented into English language.

关键词： Phrase-based translation model Combinatory Categorial Grammar Part-of-speech Factored translation model Word segmentation

来源：评论

学校读者我要写书评

暂无评论

Activity-specific caloric expenditure estimation from kinetic energy harvesting in wearable devices

引用

Pervasive and Mobile computing 2020年 67卷 101185-101185页

作者： Xiao, Ling Wu, Kai Tian, Xiaobing Luo, Juan College of Computer Science and Electronic Engineering Hunan University Changsha0731 China Key Laboratory for Embedded and Network Computing of Hunan Province China

Accurate and efficient estimation of caloric expenditure during daily activities is desirable in tracking personal activity and health. Kinetic energy harvesting (KEH) has created an opportunity for wearable devices with limited battery power to realize long-term human health monitoring. We postulate to utilize KEH device for calorie estimation instead of accelerometer considering that the kinetic energy is produced when the user expends some calories by doing the bodily movement. In this paper, we propose to use the output voltage of KEH for activity intensity classification and develop activity-specific regression models combined with anthropometric characteristics for caloric expenditure estimation by random forest. To validate our approach, we build a KEH hardware platform and collect the dataset of seven different activities in free-living conditions from ten participants. Experiment results show that our approach achieves an accuracy of 95. 7% to classify intensity of activity and yields a R2 coefficient of 0.93 for regression model and a root mean square error (RMSE) of 1.09 kcal/min to estimate calorie expenditure by only using the output voltage of KEH. The comparison experiments validate the effectiveness of KEH device for caloric expenditure estimation act as a substitute for accelerometer in terms of estimation accuracy and energy saving. © 2020 Elsevier B.V.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Brief Industry Paper: Response Time Evaluation of Cross-Domain Communication in CAN-FD and TSN

Brief Industry Paper: Response Time Evaluation of Cross-Doma...

引用

Real-Time Systems Symposium (RTSS)

作者： Wenhong Ma Xiaoyi Huang Dongsheng Wei Renfa Li Yunfei Zhang Guoqi Xie Wanli Chang Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University China Tencent Future Network Lab Tencent Corporation China

With the advancement of intelligence and networked automotive, the domain-centralized architecture, which employs time sensitive networking (TSN) as the inter-domain backbone network and control area network with flexible data rate (CAN-FD) as the intra-domain network, has garnered significant attention. However, cross-domain end-to-end communication involves multiple components, and significant disparities between TSN and CAN-FD render response time analysis within domain-centralized architecture for mixed-critical traffic exceptionally complex. In this paper, we develop a cross-domain with TSN and CAN-FD end-to-end response time evaluation tool, which analyzes the response time of mixed-critical traffic under different design options segment by segment. We specifically analyze the waiting times of different messages in the domain control unit when faced with the design options of one-to-one and multi-to-one conversion of CAN-FD and TSN frames. The proposed evaluation tool can be easily extended to different design options to support more application scenarios. Theoretical computational analysis and real hardware measurements show the effectiveness of our tool.

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：