基于免疫赦免机制的智能分布式入侵检测系统

入侵检测系统是在网络系统遭受攻击之前进行拦截和响应的一种积极主动的安全防护系统。分布式智能入侵检测系统DIIDS(Distributed Intelligent Intrusion Detection System)就是在分布式环境中将人工智能技术应用于入侵检测中,从而可以提高IDS(Intrusion Detection System)的检测的实时性、准确性和容错性。本文设计了一种基于免疫赦免机制的DIIDS。该方法以降低入侵检测系统的时延性与提高入侵检测系统的智能性、恢复能力为核心,改善入侵检测系统的实时性。为实现用户信息的安全转移和检测系统自身的免疫进化,构建了一种免疫赦免智能Agent植入机制(IPAT),从而提高了系统的可用性。     

A probabilistic reputation model based on transaction ratings

This work introduces a probabilistic model allowing to compute reputation scores as close as possible to their intrinsic value, according to the model. It is based on the following, natural, consumer-provider interaction model. Consumers are assumed to order items from providers, who each has some intrinsic, latent, “quality of service” score. In the basic model, the providers supply the items with a quality following a normal law, centered on their intrinsic “quality of service”. The consumers, after the reception and the inspection of the item, rate it according to a linear function of its quality - a standard regression model. This regression model accounts for the bias of the consumer in providing ratings as well as his reactivity towards changes in item quality. Moreover, the constancy of the provider in supplying an equal quality level when delivering the items is estimated by the standard deviation of his normal law of item quality generation. Symmetrically, the consistency of the consumer in providing similar ratings for a given quality is quantified by the standard deviation of his normal law of ratings generation. Two extensions of this basic model are considered as well: a model accounting for truncation of the ratings and a Bayesian model assuming a prior distribution on the parameters. Expectation-maximization algorithms, allowing to estimate the parameters based on the ratings, are developed for all the models. The experiments suggest that these models are able to extract useful information from the ratings, are robust towards adverse behaviors such as cheating, and are competitive in comparison with standard methods. Even if the suggested models do not show considerable improvements over other competing models (such as Brockhoff and Skovgaard’s model [12]), they, however, also permit to estimate interesting features over the raters - such as their reactivity, bias, consistency, reliability, or expectation.     

H.264解码器设计与算法优化

为了降低嵌入式平台下视频编解码的预测搜索算法复杂度,文章给出了基于达芬奇TMS320DM6446平台的H.264解码器设计,并对H.264帧内帧间预测模式做了分析,提出了一种对H.264帧内预测和帧间预测模式选择的算法,该算法通过计算并比较各种模式下的SAE(SumofAbsoluteError,绝对误差和)值,并选取SAE值最小的模式作为最佳预测模式的方法来达到优化算法的目的。实验结果表明,在峰值信噪比基本不变的条件下,可以有效避免重复帧内搜索,使预测搜索算法复杂度平均降低78%左右。     

基于QFD理论的洗衣机界面的设计与研究

质量功能展开(QFD),即质量屋的建造,是在整合产品生命周期内对产品功能质量进行分析、展开的理论方法。综合考虑客户要求、技术要求、市场状况以及其相互间的作用关系对产品质量、功能的影响。着重阐述质量屋的生成过程。并以洗衣机为例,建立分析、评价模型,构造相关要素矩阵,形成洗衣机的设计流程以及方法。     

无线传感器网络中基于RSSI的节点距离预测

无线传感器网络大量应用在环境监测、目标跟踪、安全监控等领域,因此网络的自身定位是大多数应用的基础。常用的定位方法必须测量节点间的距离。为了预测距离值,根据实验获取的RSSI值与对应的距离值,先对实验数据进行滤波处理,建立面向Matlab神经网络工具箱的神经网络预测模型,利用神经网络的特性和Matlab工具箱的强大功能,通过实测数据对网络进行训练。预测结果表明,距离精度达到1 m之内。     

海洋食品微生物生长智能通用预测平台

针对海洋食品对虾生产加工的特点,设计与开发了对虾生产加工中微生物生长智能通用预测平台,为海洋食品的安全生产与加工提供分析手段。     

Virtual worlds as knowledge management platform – a practice‐perspective

Virtual worlds, as electronic environments where individuals can interact in a realistic manner in form of avatars, are increasingly used by gamers, consumers and employees. Therefore, they provide opportunities for reinventing business processes. Especially, effective knowledge management (KM) requires the use of appropriate information and communication technology (ICT) as well as social interaction. Emerging virtual worlds enable new ways to support knowledge and knowing processes because these virtual environments consider social aspects that are necessary for knowledge creating and knowledge sharing processes. Thus, collaboration in virtual worlds resembles real‐life activities. In this paper, we shed light on the use of Second Life (SL) as a KM platform in a real‐life setting. To explore the potential and current usage of virtual worlds for knowledge and knowing activities, we conducted a qualitative study at IBM. We interviewed IBM employees belonging to a special workgroup called ‘Web 2.0/virtual worlds’ in order to gain experience in generating and exchanging knowledge by virtually collaborating and interacting. Our results show that virtual worlds – if they are able to overcome problems like platform stability, user interface or security issues – bear the potential to serve as a KM platform. They facilitate global and simultaneous interaction, create a common context for collaboration, combine different tools for communication and enhance knowledge and knowing processes.     

基于抗体选择策略的克隆挖掘算法

针对如何有效地利用大量的原始数据分析现状来预测未来的问题,基于抗体选择策略提出一种克隆选择挖掘算法。通过评估抗体的支持度、可信度和亲和度,求得有效的关联规则。实验结果表明,该算法能较快地获得可理解的规则,并且具有较高的准确率。     

基于RBF预估神经网络控制器的无线传感器网络拥塞算法

无线传感器网络中,汇聚节点是网络的瓶颈.由于传感器网络自身的特点,传统有线网络中的拥塞控制策略不再适用.已有的大多数拥塞控制策略和算法都没有充分考虑往返时延(RTT)对算法性能的影响.同时由于实际传感器网络运行中存在非线性、时间延迟和参数时变等干扰因素,若设计的控制器参数固定,不具有学习能力,则实际运行中收敛性差,收敛速度慢,无法达到控制队列长度的目标.针对以上问题,提出一种基于灰色预估神经网络控制队列的控制器,利用RBF神经网络的自学习能力解决网络实时变化时算法参数的在线整定问题,并利用灰色GM(1,1)预测器有效地解决了大时滞对网络性能的影响,最后通过仿真验证了这一算法的有效性.