检索结果-内蒙古大学图书馆

STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Haidong Li, Zhiyong Li, Yaping Nai, Ke Wen, Ming College of Computer Science Electronic Engineering of Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province Hunan Province Changsha410082 China State Grid Hunan Electric Power Company Limited Economical Technical Research Institute Hunan Key Laboratory of Energy Internet Supply-demand and Operation Hunan Province Changsha410000 China

Online multi-object tracking (MOT) is a longstanding task for computer vision and intelligent vehicle platform. At present, the main paradigm is tracking-by-detection, and the main difficulty of this paradigm is how to associate current candidate detections with historical tracklets. However, in the MOT scenarios, each historical tracklet is composed of an object sequence, while each candidate detection is just a flat image, which lacks temporal features of the object sequence. The feature difference between current candidate detections and historical tracklets makes the object association much harder. Therefore, we propose a Spatial-Temporal Mutual Representation Learning (STURE) approach which learns spatial-temporal representations between current candidate detections and historical sequences in a mutual representation space. For historical trackelets, the detection learning network is forced to match the representations of sequence learning network in a mutual representation space. The proposed approach is capable of extracting more distinguishing detection and sequence representations by using various designed losses in object association. As a result, spatial-temporal feature is learned mutually to reinforce the current detection features, and the feature difference can be relieved. To prove the robustness of the STURE, it is applied to the public MOT challenge benchmarks and performs well compared with various state-of-the-art online MOT trackers based on identity-preserving metrics. Copyright © 2022, The Authors. All rights reserved.

关键词： E-learning

Non-cooperative game approach for task offloading in edge clouds

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Bo. Li, Zhiyong Liu, Wenbin College of Information and Management Hunan University of Finance and Economics Changsha410205 China College of Computer Science and Electronic Engineering of Hunan University National Supercomputing Center in Changsha Key Laboratory for Embedded and Network Computing of Hunan Province Changsha410082 China

—Task offloading provides a promising way to enhance the capability of the mobile terminal (also called terminal user) that is distributed on network edge and communicates edge clouds with wireless. Generally, there are multiple edge cloud nodes with distinct processing capability in a geographic area, which can offer computing service for various terminal users. Furthermore, the terminal users are competitive and selfish, i.e., each user takes into account only maximizing her own profit, while conducting task offloading strategies. In this paper, we focus on the resource management optimization for edge clouds, and formulate the problem of resource competition among terminal users as a non-cooperative game, in which the terminal user who acts as the player always pursues the minimization of the expected response time for her tasks by optimizing allocation strategies. We present the utility function of the user with queuing theory, and then prove the existence of Nash equilibrium for the formulated game. Using the concept of Nash bargaining solution to calculate the optimal task offloading scheme for the user, we propose a distributed task offloading algorithm with low computation complexity. The results of simulated experiments demonstrate that our method can quickly reach the Nash equilibrium point, and deliver satisfying performance at the expected response time of the user’s tasks. Copyright © 2018, The Authors. All rights reserved.

关键词： Game theory

Dynamic negotiation strategy based parallel-offer in cloud computing

学校读者我要写书评

暂无评论

Journal of Computational Information Systems 2015年第10期11卷 3691-3699页

作者： Hu, Jun Xu, Ru Xiao, Deyu College of Computer Science and Electronics Engineering Hunan University Changsha China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Key Laboratory for Embedded and Network Computing of Hunan Province Changsha China

Cloud computing can dynamically provide service based on service level agreements that between cloud services and consumers. Establish a viable and efficient dynamic negotiation strategy is one of hot research in cloud negotiation. This paper proposes a dynamic negotiation strategy based on parallel-offer under cloud computing environment, which combines dynamic concession strategy with parallel-offer tradeoff mechanism. The strategy can adjust negotiation strategy according to the supply demand relationship and tradeoff strategy of multi-issue, to achieve flexible and efficient cloud computing negotiation. This work firstly, establishes predicting market supply-demand relationship model, to build the dynamic concession strategy. Then on the base of above, introduces a parallel offer multi-issue tradeoff strategy into negotiation strategy, to achieve the dynamic concession tradeoff strategy (DCT). Finally, DCT mechanism is implemented in CloudSim test bed, and empirical results show DCT negotiation mechanism reach faster agreements and achieve higher utilities than other related approaches in cloud computing environment. ©, 2015, Binary Information Press. All right reserved.

关键词： Cloud computing

Cyber-Physical Systems Design in An Uncertain Environment with Time Uncertainty Concern

学校读者我要写书评

暂无评论

Cyber-Physical Systems Design in An Uncertain Environment wi...

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Si Chen Lida Huang Xiongren Xiao Yan Liu Guoqi Xie Renfa Li College of Computer Science and Electronic Engineering Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Changsha China Center for Convergence of Automobile and Cyberspace Research Institute of Hunan University in Chongqing Chongqing China

Multiple processors system on chip (MPSoC) has been the trend in cyber-physical systems (CPSs), and reasonable partitioning for MPSoC resources is a critical step in CPSs design. The uncertainties of environment and time are both important factors that need to be considered in the design, but none of the previous work pays attention to two uncertainties at the same time. The state-of-the-art work presented a detailed process of applying uncertain programming to solve the partitioning problem, which provides a solution for designing in an uncertain environment. However, this work only considers the bipartition scenario which cannot be directly applied to MPSoC, and it does not focus specifically on time uncertainty. In this paper, we propose a method for modeling the MPSoC partitioning problem in an uncertain environment, with the time uncertainty concern. We present the uncertain model that can be applied to the multiple optional resources scenario. We build the optimization model with the objective of minimizing time, analyze two different cases of minimizing the uncertain time, and finally prove a unified deterministic model to solve. We come up with three algorithms, including the heuristic algorithm, the genetic algorithm, and the exact algorithm, and experiments show that the heuristic algorithm and the genetic algorithm can obtain good approximate solutions compared with the exact algorithm.

关键词：

Secret sharing based countermeasure for AES S-box

学校读者我要写书评

暂无评论

Secret sharing based countermeasure for AES S-box

International Symposium on Integrated Circuits (ISIC)

作者： Yi Wang Zheng Yuan Zhican Li Renfa Li Embedded Systems & Networking Laboratory Hunan Provincial Key Laboratory of Network and Information Security Hunan University Changsha China

Cryptographic devices are vulnerable to Differential Power Attack (DPA) in embedded systems. Masking methods are popularly used to defend against DPA by masking all intermediate data with random values. However, masking schemes on algorithm level are vulnerable to Higher-Order DPA (HODPA), while on gate level glitch attack is the biggest threaten attack. In this paper, we proposed a secret sharing based countermeasure for AES S-box, which can defend against both HODPA and glitch attack. The experimental results show that our proposed design takes up less hardware resources and achieves faster speed compared with the existing methods.

关键词： Logic gates Hardware Resistance Encryption Resists Algorithm design and analysis

CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent System

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guan, Qinghua Ouyang, Jinhui Wu, Di Yu, Weiren Zhu, Yi Yuan, Xiang The Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Hunan Changsha410082 China The Department of Computer Science University of Warwick CoventryCV4 7AL United Kingdom

The spatiotemporal data generated by massive sensors in the Internet of Things (IoT) is extremely dynamic, heterogeneous, large scale and time-dependent. It poses great challenges (e.g. accuracy, reliability, and stability) in real-time analysis and decision making for different IoT applications. The complexity of IoT data prevents the common people from gaining a deeper understanding of it. Agentized systems help address the lack of data insight for the common people. We propose a generic framework, namely CityGPT, to facilitate the learning and analysis of IoT time series with an end-to-end paradigm. CityGPT employs three agents to accomplish the spatiotemporal analysis of IoT data. The requirement agent facilitates user inputs based on natural language. Then, the analysis tasks are decomposed into temporal and spatial analysis processes, completed by corresponding data analysis agents (temporal and spatial agents). Finally, the spatiotemporal fusion agent visualizes the system’s analysis results by receiving analysis results from data analysis agents and invoking sub-visualization agents, and can provide corresponding textual descriptions based on user demands. To increase the insight for common people using our framework, we have agnentized the framework, facilitated by a large language model (LLM), to increase the data comprehensibility. Our evaluation results on real-world data with different time dependencies show that the CityGPT framework can guarantee robust performance in IoT computing. Copyright © 2024, The Authors. All rights reserved.

关键词： Internet of things

EBCRO: Hybrid chemical reaction with employed bee operator

学校读者我要写书评

暂无评论

EBCRO: Hybrid chemical reaction with employed bee operator

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Zhiyong Li Tingkun Yuan Bo Yang Shilong Jiang Yanmei Xie College of Computer Science and Electronic Engineering of Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province Changsha China PKU-HKUST Shenzhen-Hongkong Institution Shenzhen China Hunan Vocational College of Modern Logistics Changsha China

His article proposes a new hybrid algorithm EBCRO, which combines the local search operator of chemical reaction optimization algorithm (CRO) with modified employed bee operator (EB) main part of artificial bee colony algorithm (ABC), and the introduction of probability-based selection of molecular method. This algorithm creates new solutions not only by local search operation of CRO but also mechanisms of EB. CRO is a newly, effectively swarm intelligence optimization algorithm. However, owing to random characteristics of CRO and not make use of other solutions information, its search ability and convergence speed are inefficient. EB as a part of ABC has simplicity and efficiency global search ability, but the solution is updated only by other solutions information which leading to lack of local search ability. Therefore, this paper presents EBCRO, which can balance the exploitation and exploration of algorithm of numerical function optimization. In this study, EBCRO is tested on 23 benchmark numerical functions, and the simulation results of EBCRO, CRO, orthogonal chemical reaction optimization (OCRO), hybrid particle swarm and chemical reaction optimization (HP-CRO2), and ABC showed that EBCRO outperforms other algorithms in convergence performance.

关键词： Optimization Chemicals Convergence Particle swarm optimization Linear programming Kinetic energy

Fault Tolerance in Time-Sensitive networking with Mixed-Critical Traffic

学校读者我要写书评

暂无评论

Fault Tolerance in Time-Sensitive Networking with Mixed-Crit...

Design Automation Conference

作者： Wenhong Ma Xiangzhen Xiao Guoqi Xie Nan Guan Yu Jiang Wanli Chang Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University City University of Hong Kong Tsinghua University China

As an Ethernet-based communication protocol with timing determinism, TSN (time-sensitive networking) has become a well-recognized promising in-vehicle network solution for increasingly automated automobiles. To satisfy the reliability requirement of safety-critical applications, existing works towards fault-tolerant TSN trade too much bandwidth for redundancy, limiting their scope of applicability. Targeting mixed-critical traffic, which is widely found in practice, we define a shared fault-tolerant segment that is compatible with the TSN standard. It serves the critical flows when faults occur, to improve their reliability and serves the non-critical flows when otherwise, to improve their quality of service (QoS). On top of this, we propose a space-time redundancy scheduling algorithm, aiming to make the most efficient use of bandwidth, i.e., to fulfill both the reliability as well as hard real-time requirements, and maximize the QoS with the least bandwidth. In essence, we formulate a bi-objective design space exploration problem with hundreds of thousands of decision variables and solve it with customized heuristics. Experimental results show that compared to the state-of-the-art methods, our reported work increases the number of critical flows that can be accommodated on a resource-constrained network by 3 to 4 times, and achieve the highest QoS with an average reduction of 60.3% in bandwidth. As the first work along sharing of bandwidth between mixed-critical traffic in fault-tolerant TSN, this idea can be further pursued towards higher efficiency and may be applied in general autonomous systems.

关键词：

Software defined edge computing for distributed management and scalable control in IoT multinetworks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Di Nie, Xiang Deng, Hanhui Qin, Zhijin Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University China School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

Recently, edge computing has emerged as a promising paradigm to support mobile access in IoT multinetworks. However, coexistence of heterogeneous wireless communication schemes brings about new challenges to the mobility management and access control in such networks. To maintain its computing continuum, Software-Defined networking (SDN) architecture can be applied to the distributed edge networks, which provides consistent frameworks for mobility management and creates secure mechanisms for access control. In this paper, we first review the state-of-the-art SDN technology and its applications in edge computing. In particular, we highlight the prominent issues related to mobility management and access control for SDN in the edge computing environment. We also introduce a number of effective solutions to these issues by presenting real-world testbed experiments, prototypes and numerical analysis of adopting SDN based edge computing paradigms for IoT multinetworks. Copyright © 2021, The Authors. All rights reserved.

关键词： Edge computing