Rakeness with block sparse Bayesian learning for efficient ZigBee‐based EEG telemonitoring

Future healthcare systems are shifted toward long‐term patient monitoring using embedded ultra‐low power devices. In this paper, the strengths of both rakeness‐based compressive sensing (CS) and block sparse Bayesian learning (BSBL) are exploited for efficient electroencephalogram (EEG) transmission/reception over wireless body area networks. A binary sensing matrix based on the rakeness concept is used to find the most energetic signal directions. A balance is achieved between collecting energy and enforcing restricted isometry property to capture the underlying signal structure. Correct presentation of the EEG oscillatory activity, EEG wave shape, and main signal characteristics is provided using the discrete cosine transform based BSBL, which models the intra‐block correlation. The IEEE 802.15.4 wireless communication technology (ZigBee) is employed, since it targets low data rate communications in an energy efficient manner. To alleviate noise and channel multipath effects, a recursive least square based equalizer is used, with an adaptation algorithm that continually updates the filter weights using successive input samples. For the same compression ratio (CR), results indicate that the proposed system permits a higher reconstruction quality compared with the standard CS algorithm. For higher CRs, lower dimensional projections are allowed, meanwhile guaranteeing a correct reconstruction. Thus, low computational high quality data compression/reconstruction are achieved with minimal energy expenditure at the sensors nodes.     

Service configuration and user profiling in 4G terminals

This paper presents a middleware platform for managing devices that operate in heterogeneous environments. The proposed management framework supports terminal-controlled, preference-based access network selection. Two separate problems are identified in this domain: one involving the computation of optimal allocations of services to access networks and quality levels (service configuration), and one concerning the dynamic inference of the user’s preferences, according to the usage context (user profiling). This paper includes an approach to the definition, mathematical formulation and solution of both these problems. Indicative results of the proposed solution methods are presented in the context of a real-life scenario simulating a day in the life of an ordinary user.     

高速公路车辆行驶路径模糊匹配分析

高速公路车辆行驶路径在省界站处被自然分隔为两段,不能真实反映行驶车辆在高速公路上的路径信息.本文选取收费系统中车牌号、出入口时间、轴型、车货总重等字段信息,利用贝叶斯方法对分隔路径进行模糊匹配,从而得出行驶车辆在高速公路的全路径信息.     

一种基于贝叶斯网络的雷达重频模式识别方法

雷达重频模式指雷达脉冲重复间隔（PRI）的调制样式，重频模式识别对于雷达型号、类别识别具有重要支持作用，但这是一个较困难的过程，一般难以通过单一重频特征完成多种复杂重频模式的自动识别。本文为解决雷达多重频模式自动识别及识别抗噪声干扰问题，针对多种重频模式提取了几种PRI序列特征量（重频特征），然后引入了贝叶斯多网络分类器（BMNClassifier），利用所提取的特征量作为贝叶斯多网络分类器输入节点，通过贝叶斯多网络分类器的概率推理能力来实现雷达重频模式识别。     

基于可信度的Bayes融合方法在可靠性评估中的应用

在工程实践中,验前信息往往具有多源性的特点.如何把各类先验信息融合成为现场试验的验前信息就成为一个不可回避的问题.本文针对指数寿命型产品,在考虑其失效率的验前信息可信度时,给出其失效率的Bayes估计方法.通过具体实例说明考虑验前信息可信度时Bayes估计有明显改善.     

基于贝叶斯网络的串行译码方法

多维并行级联码的译码普遍采用并行译码方法。给出了一种新颖的译码方法－串行译码方法。串行译码方法不仅计算简单,而且所达到的性能与并行译码方法相近。采用人工智能中的贝叶斯网络概率传播算法对串行译码方法的合理性给出了证明。     

复合高斯杂波条件下存在干扰时的反对称贝叶斯检测器

该文对复合高斯杂波条件下存在干扰时的目标检测问题进行研究。针对自适应检测器需要一定数目独立同分布训练样本才能保证较好的检测性能,利用接收天线的反对称结构以及引入杂波协方差矩阵的先验信息的方法,利用两步广义似然比检验准则提出了该背景下的贝叶斯检测器。仿真结果表明,该文提出的检测器在训练样本数较少时具有较好的目标检测性能。     

基于验前信息可信度的鱼雷实航工作可靠度Bayes融合评估方法

针对火箭助飞鱼雷作战效能中实航工作可靠度这一指标的考核,存在着试验样本数少、风险高等缺陷,不利于对该指标作出正确的评估。为此,借鉴战术导弹鉴定试验技术,使用验前信息进行指标融合评估,但为防止大量的验前信息＂淹没＂现场试验信息的可能性,提出了基于验前信息可信度的后验加权Bayes融合评估的鱼雷实航工作可靠度指标考核方法,该方法能够较真实地评估出鱼雷实航工作可靠度指标。     

基于贝叶斯网络的复杂系统FMEA模型

贝叶斯网络用因果关系图的形式表达变量间相互关系,实现复杂系统的故障模式和效应分析.贝叶斯网络建模先确定模型变量,根据变量间因果关系确定网络的拓扑结构.再为贝叶斯网络赋值,确定先验概率和条件概率.并通过融合新的试验信息与专家信息,改进网络结构,作最后的统计推断.     

联合人体模型与块生长的人群目标分割

人群目标的准确分割,是进行多相机联合目标跟踪与识别的关键。该文首先构造包含位置、尺寸、姿态信息的人体粗略姿态模型,并利用贝叶斯模型获得对应的目标模型。然后将前景区域利用分水岭算法划分为颜色分布一致的子块,通过位置和颜色约束解决遮挡目标的种子块选取问题。最后通过块生长获得每个目标区域。对于颜色相似子块,通过比较其产生的边缘能量确定其所属目标。实验结果表明,本文能够实现对人群目标较精确分割,且对背景噪声具有一定的抗干扰能力。