多用户存储中自适应动态预取策略

通过分析多用户数据请求规律以及实时分解随机请求序列来获取顺序请求序列。基于对多用户顺序请求进行命令预分解和命中率统计,实现读预取长度自我学习。分析多用户预取率及系统负载与预取失效代价之间的关系,对常规自适应Cache策略进行优化,选择合适预取阈值等参数。与常规自适应预取策略相比,动态调整Cache策略的预取命中率提高了30%。有效解决了多用户访问共享存储系统的预取失效率高问题。     

一种基于主动视觉的摄像机内参数自定标方法

摄像机定标是计算机视觉的一项基本任务．本文提出了一种基于主动视觉的摄像机内参数自定标方法．该方法和文献［1］提出的方法相比最大的优点在于不要求摄像机在三维空间作任意方向的平移运动，只需要控制摄像机在同一平面作四组运动，其中每组包括两次相互正交的平移运动，同时适当调整摄像机平移运动的姿态，可以线性求解摄像机内参数．理论上证明了如果摄像机作三次俯仰或者作两次俯仰一次扫视来调整摄像机平移运动的姿态，则解存在而且唯一．通过稳定性分析证明前一种方法对误差很敏感，后者则是稳定的．最后给出了采用真实图像的实验结果．     

基于自适应粒子滤波的摄像机位姿估计方法

提出一种基于自适应粒子滤波的摄像机位姿估计方法。该方法首先利用相邻两帧传递模型的噪声方差动态调整传递模型,接着利用内点统计方法计算粒子权值,在对权值作归一化运算之后,利用粒子加权和计算摄像机位置和姿态。实验结果表明该方法很大程度上提高了基于标识的摄像机位姿估计系统的健壮性与稳定性。     

基于单轴气浮台的空间跟瞄地面试验的设计与实现

为验证通过调整卫星本体姿态而实现精确跟瞄的可行性,设计出基于单轴气浮转台,以反作用轮和精密轮为执行机构,CCD摄像机与DSP图像处理器为光学系统,以PID算法为跟踪控制器算法的跟瞄地面实验系统,提出了跟踪控制方案;并以一个典型工况为例,测试出了跟瞄实验系统的精度;实验结果表明,当摄像机距离目标2.5m,而目标视线以1mrad/s的速度转动时,跟瞄实验系统的跟踪误差小于0.051mrad,从而验证了通过调整卫星本体姿态实现精跟瞄的可行性。     

引入PnP问题的多姿态人脸旋转角度计算方法研究

在多姿态人脸识别中,人脸的旋转也可以看作是双目成像系统中摄像机的旋转,由此我们引入PnP问题的求解得出双目成像系统中的摄像机的旋转矩阵,求解即得人脸旋转角度.引入PnP问题进行多姿态人脸旋转角度的计算的方法还没被用在多姿态人脸识别中.     

引入PnP问题的多姿态人脸旋转角度计算方法研究

在多姿态人脸识别中,人脸的旋转也可以看作是双目成像系统中摄像机的旋转,由此我们引入PnP问题的求解得出双目成像系统中的摄像机的旋转矩阵,求解即得人脸旋转角度。引入PnP问题进行多姿态人脸旋转角度的计算的方法还没被用在多姿态人脸识别中。     

基于EKF的摄像机-IMU相对姿态标定方法

摄像机与惯性传感器之间的相对姿态标定是视觉-惯性混合跟踪器的关键技术之一,是混合跟踪器进行数据融合获得鲁棒姿态输出的前提。提出一种新颖的基于扩展卡尔曼滤波器EKF(Extended Kalman Filter)的摄像机-惯性测量单元IMU(Internal Measurement Unit)相对姿态标定方法。该方法通过构建基于刚体运动学的过程模型和基于摄像机外参数的测量模型,估计摄像机与惯性传感器的相对位置和方向。初步实验结果显示,所提出的标定方法不仅能够标定6 DOF相对姿态,标定操作更简易快速,而且在系统初始误差较大和非线性噪声较大的条件下,该方法仍然能够精确地获得摄像机与IMU之间的相对姿态。     

基于WLAN的智能监控系统设计

智能监控系统由现场设备、嵌入式WEB服务器、无线传输网络和监控中心组成。嵌入式WEB服务器是系统的核心，主要由嵌入式微处理器MPC8250、无线数据传输模块、MPEG-4视音频编码模块、云台控制模块、无线网卡、大容量硬盘等组成。监控中心的用户无需使用专用软件，通过浏览器便可直接观看Web服务器上的摄像机图像和报警信息，并可根据需要向服务器发送视频请求以及对摄像机的控制信号。     

MIMO系统中的自适应比例公平调度算法研究

在MIMO系统中,通过在每个时隙选择信道条件最好的用户进行通信,可以利用无线通信系统的多用户分集大大提高系统吞吐量,但该方法存在公平性差的缺点。主要关注应用机会波束形成的MIMO系统的公平性。提出了一种自适应比例公平调度算法来提高长时间处于较差信道条件下的用户的吞吐量,从而提高系统的公平性。在每个时隙,基站监测每个用户的实时请求速率和过去一段时间内的平均请求速率,并根据这两个速率来调整算法中的自适应参数。提出的算法较好地获得了系统吞吐量和公平性的折中,仿真实验结果也表明了算法的有效性。     

一种连续LBS请求下的位置匿名方法

为避免不同时刻来自同一用户的连续位置服务(LBS)请求之间的相关攻击,提出一种改进的k-匿名模型,设计一种连续LBS请求下的位置匿名方法。在满足用户隐私要求的前提下,利用位置采样寻找最优的匿名集,使用户平均匿名区域最小。分析结果表明,该方法能合理利用系统计算资源,提高在多用户请求下系统的响应速度。     

RAID控制器中I/O调度算法研究

介绍应用于RAID控制器的I/O调度算法的设计与实现.主要目标是把来自RAID模块针对每个磁盘的具体读写请求按照响应的策略放入对应磁盘的读写I/O队列.然后根据具体请求的优先级和读写特性,对响应请求在队列中的次序进行调整或者对前后项进行合并,实现I/O请求的调度策略.     

一种基于度量的Web服务质量机制

提出了一种简单、准确和高效的带宽调节算法，该算法对每一个服务请求设置一个带宽标准，同时根据对服务请求的分类和Web服务器系统的有效带宽，来分配及调节每一个服务请求的实际带宽，构成一种基于度量的Web服务质量机制，使Web服务器系统能为不同类型的客户请求提供有区分的和有服务质量的Web服务。     

Dynamic quota-based admission control with sub-rating in multimedia servers

An admission control algorithm for a multimedia server is responsible for determining if a new request can be accepted without violating the Quality of Service (QoS) requirements of the existing requests in the system. A novel quota-based admission control algorithm with sub-rating for two priority classes of requests is proposed in this study. The server capacity is divided into three partitions based on the quota values: one for each class of requests and one common pool shared by two classes of requests. Reward and penalty are adopted in the proposed system model. High-priority requests are associated with higher values of reward as well as penalty than low-priority ones. Given the characteristics of the system workload, the proposed algorithm finds the best partitions, optimizing the system performance based on the objective function of the total reward minus the total penalty. The sub-rating mechanism will reduce the QoS requirements of several low- priority clients, by cutting out a small fraction of the assigned server capacity, to accept a new high- priority client and to achieve a higher net earning value. A stochastic Petri-Net model is used to find the optimal quota values and two approximation approaches are developed to find sub-optimal settings. The experiment results show that the proposed algorithm performs better than one without sub-rating mechanism, and that the sub-optimal solutions found by the proposed approximation approaches are very close to optimal ones. The approximation approaches enable the algorithm to dynamically adjust the quota values, based on the characteristics of the system workload, to achieve higher system performance.     

基于QoS的磁盘调度策略

随着视频点播、视频会议、视频监控、数字图书馆等流媒体应用的普及，流媒体服务器存储资源管理成为制约服务质量的瓶颈之一。根据多媒体服务器的性能要求，提出了一种支持QoS的磁盘调度策略。它由三个主要部分组成：探测模块、负载监测模块和自适应管理模块。探测模块，负责判断当前的资源情况能否满足服务请求；自适应模块，根据负载监删模块检测到的负载变化情况，动态调整服务周期在实时请求和尽力服务请求之间的分配。实验表明此磁盘调度策略能在保证实时请求无抖动执行的同时，明显减少了非实时请求的响应时间。     

An MMAP/G/1 queueing system with repeated calls and with absolute priority

In this paper, a single-channel queueing system without an input buffer and with two types of requests is considered. At the input of the system, a marked Markov flow of requests arrives. Requests of the first type have absolute priority over requests of the second type; i.e., if a server is busy with servicing a request of the second type, an incoming request of the first type interrupts this servicing. Interrupted requests of the second type, as well as requests of this type that find the server busy on their arrival, become repeated requests and retry to get servicing later. An incoming first type request that finds the server busy with servicing a request of the same type is lost. The time of servicing requests has an arbitrary distribution dependent on the type of request. A nontrivial existence condition of the stationary operation of the system is obtained. A stationary probability distribution of system’s states at nested and random instants is found. Formulas for the main performance characteristics are obtained. The result of the numerical experiment is presented.     

基于Ajax请求会话超时处理的研究

B／S架构下,来自于浏览器的同步请求如果发生了会话超时,可以很容易的让页面跳转到超时页面,但现在的Web系统为了提高用户体验,大量使用了Ajax技术,请求变成了异步请求,使用原有的方法,页面无法去处理跳转。本文在JQuery和Ext框架下,提出一种处理异步请求会话超时的方法。     

A Queueing System MN |GN |1|1 with Loss of Interrupted Requests

Formulas of stationary probabilities of states are obtained for a queueing system with one waiting space and Poisson flows of arrived requests of different types. It is assumed that the request being serviced can be interrupted by an arrived request. Such an interruption is realized with probability depending on the types of these two requests.     

On the performance of real-time multi-item request scheduling in data broadcast environments

On-demand broadcast is an effective wireless data dissemination technique to enhance system scalability and capability to handle dynamic data access patterns. Previous studies on time-critical on-demand data broadcast were conducted under the assumption that each client requests only one data item at a time. With the rapid growth of time-critical information dissemination services in emerging applications, there is an increasing need for systems to support efficient processing of real-time multi-item requests. Little work, however, has been done. In this paper, we study the behavior of six representative single-item request based scheduling algorithms in time-critical multi-item request environments. The results show that the performance of all algorithms deteriorates when dealing with multi-item requests. We observe that data popularity, which is an effective factor to save bandwidth and improve performance in scheduling single-item requests, becomes a hindrance to performance in multi-item request environments. Most multi-item requests scheduled by these algorithms suffer from a starvation problem, which is the root of performance deterioration. Based on our analysis, a novel algorithm that considers both request popularity and request timing requirement is proposed. The performance results of our simulation study show that the proposed algorithm is superior to other classical algorithms under a variety of circumstances.     

基于微服务架构FPGA云平台的并发请求调度机制

基于微服务架构的现场可编程门阵列（FPGA）云平台在被大规模推广后积累了许多用户。针对FPGA云平台存在大量用户并发请求的问题,建立一种基于优先级调度的自定义参数响应指数计算模型。将5个请求关键影响因素作为自定义参数,采用层次分析法确定各参数权重,根据响应指数函数计算各请求的响应指数。在该模型的基础上,设计一种高并发请求调度（HCRS）算法,通过响应指数阈值对请求类别进行划分,使得高优先级请求优先得到处理,次优先级请求加入先进先出队列等待,低优先级请求暂时挂起,从而缩短请求响应时间以及请求响应延时,缓解由高并发请求带来的硬件节点资源分配压力。在真实运营的FPGA云平台中实现该算法并在实际环境中进行测试,结果表明,在并发请求量相同时,与先来先服务调度算法相比,HCRS算法的平均响应延时降低29 074 ms,平均请求响应时间缩短12 605 ms,其在提升系统吞吐量与并发度的同时可以有效优化硬件节点资源利用率。     

An On-line Multi-CBR Agent Dispatching Algorithm

Case-based reasoning (CBR) is an effective and fast problem-solving methodology, which solves new problems by remembering and adaptation of past cases. With the increasing requests for useful references for all kinds of problems and from different locations, keeping a single CBR system seems to be outdated and not practical. Multi-CBR agents located in different places are of great support to fast meet these requests. In this paper, the architecture of a multi-CBR agent system is proposed, where the CBR agents locate at different places, and are assumed to have the same ability to deal with new problem independently. When the requests in a request queue from different places are coming one by one, we propose a new policy of dispatching which agent to satisfy the request queue. Throughout the paper, we assume that the system must solve the coming request by considering only past requests. In this context, the performance of traditional greedy algorithms is not satisfactory. We apply a new but simple approach – competitive algorithm for on-line problem (called On-line multi-CBR agent dispatching algorithm) to determine the dispatching policy to keep comparative low cost. The corresponding on-line dispatching algorithm is proposed and the competitive ratio is given. Based on the competitive algorithm, the dispatching of multi-CBR agents is optimized.