Investigation of Functional Hemispheric Asymmetry of Language in Tinnitus Sufferers.

The authors tested functional hemispheric asymmetry through word dichotic listening and lateralized lexical decision tasks in tinnitus patients and controls stimulated by a continuous tinnitus-like noise to test the influence of a tinnitus-like external stimulation. A classic right-ear advantage was shown in the auditory task for all but right-ear tinnitus patients, who performed as equally badly when the stimuli were presented to the right and left ears. Concerning the visual task, all participants demonstrated the expected right visual field advantage for word stimuli. Moreover, those who submitted to external stimulation demonstrated normal asymmetric patterns. These data suggest a specific effect of tinnitus on central processing and provide evidence for a functional reorganization induced by this auditory phantom perception. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

可重构片上系统设计流程中的动态重构问题研究

近年来,可重构片上系统已成为科学研究及嵌入式应用领域中应对复杂计算需求的有效技术解决方案.针对目前缺少一个从系统级设计到应用实现,统一、综合规划动态重构问题的系统设计流程,以及动态重构过程对系统设计人员不透明等问题,在系统设计层给出了一种过程级软硬件统一编程模型.在此框架内,设计人员通过调用已根据应用特性进行优化的软硬件协同函数,即可利用高级语言完成系统功能描述;在细节设计层提出了基于单位面积加速比的软硬件任务调度算法,实时管理动态可重构资源;在应用实现层,以可重构专用图形加速卡为原型系统,论述动态可重构系统实现中的关键技术.实验及测试结果验证了通过将动态重构问题置于整个系统设计流程中予以考虑,能够达到提升系统开发效率之目的.     

一种有效的动态任务分配方法

首先简单介绍了基于PVM的网络并行计算环境。接着重点讨论了任务分配方法和负载平衡问题。通过分析静态任务分配方法中存在的不足,提出了以计算能力的大小来动态分配任务的方法,避免了因个别计算机的低性能而影响了整个并行计算系统的加速比。实验表明这种策略实现简单,并且具有很好的并行效果。     

基于遗传算法的异构多核多帧任务分配*

讨论一组实时系统的任务在不同性质的处理器上的分配,使得所有任务得以完成并耗费更少的时间,是NP完全问题。建立了新的任务分析模型——异构多核多帧任务模型,并基于遗传算法给出解决方案。实验证明,该模型更为有效地表达了实时系统的性质,获得更高的分配成功率,算法拥有更低的时间复杂度,结果可信。     

Dynamic hinting: Collaborative real-time resource management for reactive embedded systems

The increasing complexity of today’s reactive embedded applications can rapidly result in reduced real-time capabilities of the underlying hard and software. As an example for this paper we’ll refer to the specific and growing demands on the severely resource constrained sensor nodes in sensor/actuator networks (SANet). While preemptive operating systems are one way to retain acceptable reactivity within highly dynamic environments, their concurrency paradigm commonly leads to severe resource management problems, caused by the coexistence of tasks with interfering and even varying requirements. To counteract these problems, we present the novel Dynamic Hinting approach for maintaining good reactivity in typically resource constrained sensor/actuator systems by efficient combination of preemptive task scheduling and collaborative resource allocation. With respect to task priorities, our technique significantly improves classical methods for handling priority inversions (and deadlocks where required) under both short- and long-term resource allocations. Furthermore, we facilitate compositional software design by providing independently developed tasks with runtime information for yet collaborative and reflective resource sharing – e.g. by means of time-utility-functions. In many cases this even allows to reduce blocking delays as otherwise imposed by bounded priority inversion.     

基于LVS和计算任务的实时集群负载均衡方法

对LVS(Linux virtual server)集群的体系结构和特点做了讨论,分析指出了LVS集群应用于军事测控系统时面临的传感器通信体制兼容和负载调度粒度过大等局限性.通过进行结构调整和功能改造,设计采用基于UDP协议、面向计算任务的应用层细粒度负载分配方法,提高了负载接入与分配调度、服务器并行计算的工作效率,实现了军事测控系统的强实时性要求.该负载均衡方案适用于实时领域的航空、航天测控集群系统,经实践应用证明是有效的.     

基于CUDA平台的规则LDPC码的译码实现研究

低密度奇偶校验(LDPC)码性能优越,允许全并行高速译码,已经在个人数字设备、移动无线通信等领域显示出了很大的应用价值,极可能取代Turbo码成为第四代移动通信的首选编码方案。NVIDIA公司的CUDA是一种新的用于GPU通用计算的软硬件架构。基于CUDA平台程序员可以写出C风格的代码来启动大量的GPU线程并行工作。基于CUDA平台提出和研究一种AWGN信道下的规则LDPC码的译码实现方案。仿真实验对LDPC码译码的CPU实现和CUDA实现的性能作了详细比较。研究表明CUDA能够带来明显的性能提升。     

从"5.12"地震看应急性非战争军事行动装备保障建设

应急性非战争军事行动装备保障的主要特点有：准备时间短,要求实施联合装备保障;任务多样化,保障内容具有复杂性;专业性强,被保障对象具有针对性。根据应急性非战争军事行动装备保障建设应贯彻的指导思想与基本原则,分析其基本对策,包括：加强非战争军事行动装备保障演练、健全军民一体社会化装备保障机制、加强特种装备的开发与研制等。     

Workforce planning and deployment for a hospital reservation call center with abandonment cost and multiple tasks

We consider a hospital reservation call center where operators handle multiple tasks. We take into account operator labor costs, caller waiting costs, and abandonment costs for lost calls. Instead of relying on the traditional method of queueing theory for call center management, we present a method that obtains expected caller waiting time and expected abandonment rate directly by introducing the inbound-load parameter. We develop a framework that combines workforce planning and operator deployment for a mixed call center in a single mathematical programming model. This paper also demonstrates how the proposed methodology can be applied in practice, with a case study based on actual operational data. Our primary conclusion is that the method presented in this research can significantly reduce both expected total cost (by 55.1% in our case study) and abandonment rate (from 15% to 2.1% in our case study). In addition, we demonstrate, using a sensitivity analysis, that our methodology will be more effective in an environment where the unit penalty cost of an abandoned call is relatively high among competitive hospitals.     

基于混合蚁群优化的边缘计算细粒度任务调度方法

为缓解中心服务器的压力,制定合理的调度方案,基于混合蚁群优化算法提出了边缘计算细粒度任务调度方法。描述边缘计算任务调度问题,并设置假设条件,简化调度求解难度。通过计算任务的优先指数,按照从大到小的顺序排列后组成任务队列。分析边缘服务器性能特征,明确边缘服务器处理能力。构建能耗以及时延多目标函数,并设置约束条件,利用混合蚁群优化算法求解多目标函数,完成边缘计算细粒度任务调度方案设计。结果表明：该方法应用下的任务调度能耗和时延更小,说明所提方法性能更优,所获得的调度方案更合理。