基于频繁项挖掘的未知P2P流量识别方法

提出一种基于多维聚类的频繁项挖掘算法,利用聚类思想自动挖掘网络中的显著流量及其规则,并在此基础上,对显著流量进行P2P疑似性判别,同时结合应用层特征识别技术,对高度疑似的P2P显著流量类进行过滤,实现未知P2P流量检测。实验结果表明,该方法是有效的。     

有效的WebGIS地图服务器场负载均衡算法

针对现有网络地理信息系统（WebGIS）负载均衡技术的缺陷,分析利用集群技术解决WebGIS负载均衡的必要性和可行性,提出基于地图服务器场的WebGIS分布式负载均衡模型,研究地图服务器场分布式动态均衡调度算法,建立试验床,通过一系列的试验结果验证了该算法良好的全局网络负载性。     

基于Web Service的虚拟研究中心KMS构建

针对虚拟研究中心知识管理敏捷化、柔性化和分布式的需求特性,结合Web Service技术搭建了虚拟研究中心知识管理系统网络体系架构,提出一种基于Web Service的虚拟研究中心知识管理系统模型。依据模型框架,构建雅砻江水电开发虚拟研究中心知识管理系统。研究表明,依据模型构建的虚拟研究中心知识管理系统能有效地实现基于Web的知识共享、交流和创新,模型具有较好的可靠性和可行性。     

网格环境下的分布仿真事件调度研究

针对网格仿真中的事件调度问题,提出一种新的时序管理方法。该方法同时考虑网格仿真成员的按需模型服务调用与成员间的交互,对仿真中具体存在的事件进行分类,建立成员的相关局部事件触发矩阵和时序关系矩阵,并应用Mutli-AWS算法求解每个事件的开始时间。实验结果证明,该方法可以确保成员之间事件的时序关系,有效解决成员按需模型服务调用问题。     

UML状态图在回归测试中的应用

基于UML状态图的测试是一种系统测试技术,也是基于需求的回归测试方法的扩展。该文通过依赖性分析,生成基于依赖性分析的UML状态图和依赖图,将修改前和修改后的UML状态图进行比较,为回归测试中待测试的程序的理解、发现和修改错误提供一种方法,并运用SATM实例讨论该技术在回归测试中的应用。     

Predictive capability of cognitive ability and cognitive style for spaceflight emergency operation performance

This study explores the effects of cognitive ability (information seeking, inference, spatial recognition, attention span, and attention allocation) and cognitive style (active-reflective, sensing-intuitive, visual-verbal, and sequential-global) on task performance of simulated spaceflight emergency operations that require judgment and operation on a Chinese spaceflight instrument board and the possible interaction effect with training experience. The performance criteria included task completion time and number of human errors. It was found that inference ability, spatial recognition ability, and attention span had significant effects on task completion time, while attention allocation ability had significant effect on the number of error. The participants with a sequential cognitive style made significantly fewer errors than those with a global cognitive style. Training experience significantly decreased task completion time. The participants with sequential cognitive style learnt faster than those with global cognitive style in the spaceflight instrument operations. With increasing training experience, the predictive capability of cognitive ability on performance decreased, whereas the predictive capability of the sequential-global cognitive style on performance increased.     

功能性电刺激下的关节自适应运动控制研究

针对功能性电刺激（Functional electrical stimulation,FES）下外部干扰和肌肉疲劳对关节运动的影响,提出了一种神经网络自适应滑模控制方法以获得更加精确的关节运动.本文建立了电刺激下的关节运动模型,在此模型的基础上设计了滑模控制律,利用径向基神经网络在线逼近系统不确定特性,并通过Lyapunov方法设计了径向基神经网络的自适应律,以电刺激所产生的膝关节运动控制为例,通过仿真和实验研究验证了该神经网络滑模控制方法相对于传统的滑模控制来说,不仅可以准确地控制电刺激而获得期望的关节运动,而且当关节运动受到外部干扰和肌肉疲劳的影响时,还可自适应地对此进行补偿,有效地调节电刺激强度以获得准确的关节运动.     

A rapid-prototyping framework for extracting small-scale incident-related information in microblogs: Application of multi-label classification on tweets

Small scale-incidents such as car crashes or fires occur with high frequency and in sum involve more people and consume more money than large and infrequent incidents. Therefore, the support of small-scale incident management is of high importance.Microblogs are an important source of information to support incident management as important situational information is shared, both by citizens and official sources. While microblogs are already used to address large-scale incidents detecting small-scale incident-related information was not satisfyingly possible so far.In this paper we investigate small-scale incident reporting behavior with microblogs. Based on our findings, we present an easily extensible rapid prototyping framework for information extraction of incident-related tweets. The framework enables the precise identification and extraction of information relevant for emergency management. We evaluate the rapid prototyping capabilities and usefulness of the framework by implementing the multi-label classification of tweets related to small-scale incidents. An evaluation shows that our approach is applicable for detecting multiple labels with an match rate of 84.35%.     

不确定层次任务网络规划研究综述

层次任务网络(Hierarchical task network, HTN)规划作为一项重要的智能规划技术被广泛应用于实际规划问题中, 传统的HTN规划无法处理不确定规划问题.然而, 现实世界不可避免地存在无法确定或无法预测的信息, 这使许多学者开始关注不确定规划问题, 不确定HTN规划研究也成为HTN规划研究的前沿.本文从HTN规划过程出发分析了不确定HTN规划问题中涉及的三类不确定, 即状态不确定、动作效果不确定和任务分解不确定; 总结了系统状态、动作效果和任务分解等不确定需要扩展确定性HTN规划模型的工作, 以此对现有不确定HTN规划的研究工作加以梳理和归类; 最后,对不确定HTN规划研究中仍需要解决的问题和未来的研究方向作了进一步展望.