基于贝叶斯决策的多网络切换算法

现有的垂直切换技术通常不支持多网络下切换.为此,提出了基于贝叶斯决策的改进算法.首先根据接入用户终端的信号强度、网络阻塞率和误码率以及不同用户业务对网络的实际需求建立多条件相关的切换概率分布,得出先验切换概率;然后利用贝叶斯垂直切换决策算法计算出后验概率;最后,根据后验概率的决策规则选出最优接入网络.仿真结果表明,该算法不仅有效地实现异构无线接入网之间的垂直切换,避免了不必要的切换,而且还能保持较高的网络平均负载,使用户获得更好的服务.     

基于故障分析模型的贝叶斯网络构建及应用

为快速、准确地构建具有较完备知识的贝叶斯网络诊断模型,提出了基于故障模式、影响(及危害性)分析知识模型的贝叶斯网络自动构建方法.在该方法中,借助影响(及危害性)知识模型中的产品结构层次关系,将产品各层零部件的故障模式加以关联,形成贝叶斯网络结构;并以影响(及危害性)知识模型中的概率知识为依据,确定贝叶斯网络中节点的先验概率和条件概率.以列车自动门为应用对象,实现贝叶斯网络诊断模型的自动构建,并开发了相应的诊断系统,解决了列车自动门的诊断系统开发、应用跟不上维护的难题.最后,通过列车自动门的故障诊断实例,证明了所构建的贝叶斯网络的有效性.     

基于贝叶斯网络的机械设备故障诊断方法研究

建立了一种基于贝叶斯网络的机械设备故障诊断模型,引入评分函数和蚁群算法对模型进行了优化,在模型建立过程中引入知识进行自我学习,减少了因检测对象造成的不确定信息,提高了机械设备故障检测的可信度,最后通过实例进行了验证。     

基于区域生长的生物图像分割方法

针对基于区域的分水岭算法中通常存在的严重过分割现象,采用两点措施来改进:其一是在分水岭分割之前采用迭代阈值分割算法对图像进行分割,从而有效地抑制了由图片表面的灰度变化引起的过分割,使边缘定位更加准确;其二是在分水岭分割之后以基于面积,对比度和深度控制的区域合并准则,有效抑制过分割现象,同时满足感兴趣区的分割要求,实验表明该方法简单有效,能够得到符合人类视觉系统特性的分割结果。     

An image processing pipeline to detect and segment nuclei in muscle fiber microscopic images

Muscle fiber images play an important role in the medical diagnosis and treatment of many muscular diseases. The number of nuclei in skeletal muscle fiber images is a key bio‐marker of the diagnosis of muscular dystrophy. In nuclei segmentation one primary challenge is to correctly separate the clustered nuclei. In this article, we developed an image processing pipeline to automatically detect, segment, and analyze nuclei in microscopic image of muscle fibers. The pipeline consists of image pre‐processing, identification of isolated nuclei, identification and segmentation of clustered nuclei, and quantitative analysis. Nuclei are initially extracted from background by using local Otsu's threshold. Based on analysis of morphological features of the isolated nuclei, including their areas, compactness, and major axis lengths, a Bayesian network is trained and applied to identify isolated nuclei from clustered nuclei and artifacts in all the images. Then a two‐step refined watershed algorithm is applied to segment clustered nuclei. After segmentation, the nuclei can be quantified for statistical analysis. Comparing the segmented results with those of manual analysis and an existing technique, we find that our proposed image processing pipeline achieves good performance with high accuracy and precision. The presented image processing pipeline can therefore help biologists increase their throughput and objectivity in analyzing large numbers of nuclei in muscle fiber images. Microsc. Res. Tech. 77:547–559, 2014. © 2014 Wiley Periodicals, Inc.     

基于贝叶斯网的制造工艺质量建模方法

针对多品种小批量制造模式下,工艺质量建模面临的模型维度高、数据稀疏的问题,提出了基于贝叶斯网的工艺质量建模方法.该方法以工艺机理知识为基础构建贝叶斯网结构,在构建时采用删除法保证结构的完备性与简洁性.设计实验获得均衡分布的实验数据,并通过实验数据的学习获得条件概率表.在应用中,模型利用生产线的数据更新条件概率表,来体现生产过程中不确定性因素的影响.以印刷线路板微小孔钻孔工艺为例进行了建模方法的应用与对比,结果验证了该方法对多品种小批量制造工艺的质量建模具有适用性,并且能够获得更高的模型精度.     

利用GSOM网络实现散乱点云的区域分割

提出了一种改进的动态自组织特征映射(GSOM)神经网络算法,实现逆向工程中点云的区域分割,以数据点的坐标、估算出的法矢量和曲率构成的8维向量作为神经网络的输入,在训练中动态生成网络结构,克服了现有SOFM网络需要预先给出分区数目的限制,网络生成的结点数少、聚类速度快.最后通过实例实现了数据点云的区域分割,验证了该方法的正确性.     

Dense nuclei segmentation based on graph cut and convexity–concavity analysis

With the rapid advancement of 3D confocal imaging technology, more and more 3D cellular images will be available. However, robust and automatic extraction of nuclei shape may be hindered by a highly cluttered environment, as for example, in fly eye tissues. In this paper, we present a novel and efficient nuclei segmentation algorithm based on the combination of graph cut and convex shape assumption. The main characteristic of the algorithm is that it segments nuclei foreground using a graph‐cut algorithm with our proposed new initialization method and splits overlapping or touching cell nuclei by simple convexity and concavity analysis. Experimental results show that the proposed algorithm can segment complicated nuclei clumps effectively in our fluorescent fruit fly eye images. Evaluation on a public hand‐labelled 2D benchmark demonstrates substantial quantitative improvement over other methods. For example, the proposed method achieves a 3.2 Hausdorff distance decrease and a 1.8 decrease in the merged nuclei error per slice.     

基于贝叶斯网络的多状态系统可靠性建模与评估

利用贝叶斯网络(Bayesian network, BN)的不确定性推理和图形化表达的优势,提出一种基于BN的多状态系统可靠性建模与评估的新方法,确定BN的结点及系统各元件的多个状态,并给出各状态的概率,进而用概率分布表(Conditional probability distributing, CPD)描述元件各状态之间的关系来表达关联结点的状态,建立多状态系统BN模型.该模型表达直观,能够清晰地表示系统和元件的多种状态以及状态概率,并能够根据元件多种状态概率直接计算系统可靠度,对多状态系统可靠性进行定性分析和定量评估.实例分析表明了应用BN方法进行多状态系统可靠性评估的有效性.     

Fault detection and classification in chemical processes based on neural networks with feature extraction

Feed forward neural networks are investigated here for fault diagnosis in chemical processes, especially batch processes. The use of the neural model prediction error as the residual for fault diagnosis of sensor and component is analyzed. To reduce the training time required for the neural process model, an input feature extraction process for the neural model is implemented. An additional radial basis function neural classifier is developed to isolate faults from the residual generated, and results are presented to demonstrate the satisfactory detection and isolation of faults using this approach.     

基于分水岭变换和图论的图像分割方法

提出了一种融合分水岭变换和图论的图像分割方法.利用图像的局部灰度信息进行分水岭变换后,将图像分割成多个小区域,再结合各小区域的灰度和空间信息从全局角度用Normalized Cut方法在区域之间进行分割,产生最终的分割结果.实验结果表明,该方法可以消除分水岭变换后所产生的过分割现象,是一种有效的图像自动分割方法.     

基于卷积神经网络的光学遥感图像检索

提出了一种基于深度卷积神经网络的光学遥感图像检索方法。首先,通过多层卷积神经网络对遥感图像进行卷积和池化处理,得到每幅图像的特征图,抽取高层特征构建图像特征库;在此过程中使用特征图完成网络模型参数和Softmax分类器的训练。然后,借助Softmax分类器在图像检索阶段对查询图像引入类别反馈,提高图像检索准确度,并根据查询图像特征和图像特征库中特征向量之间的距离,按相似程度由大到小进行排序,得到最终的检索结果。在高分辨率遥感图像数据库中进行了实验,结果显示:针对水体、植被、建筑、农田、裸地等5类图像的平均检索准确度约98.4%,增加飞机、舰船后7类遥感图像的平均检索准确度约95.9%;类别信息的引入有效提高了遥感图像的检索速度和准确度,检索时间减少了约17.6%;与颜色、纹理、词袋模型的对比实验表明,利用深度卷积神经网络抽取的高层信息能够更好地描述图像内容。实验表明该方法能够有效提高光学遥感图像的检索速度和准确度。     

基于SSDAE深度神经网络的钛板电涡流检测图像分类研究

钛板电涡流成像检测易受工业现场中的噪声影响,包含噪声的检测图像往往难以提取较好的特征,从而影响分类识别精度。针对以上问题,提出了一种基于栈式稀疏降噪自编码(SSDAE)深度神经网络的钛板缺陷电涡流检测图像分类方法。将稀疏性限制引入降噪自编码器并进行逐层无监督自学习,然后将自编码器栈式组合后添加逻辑识别(LR)层,构建出SSDAE深度神经网络,网络在有监督微调后可实现钛板缺陷电涡流图像特征自动提取与分类识别。稀疏性限制的引入提高了特征学习能力,降噪自编码器的栈式组合提高了深度网络的鲁棒性。实验结果表明,相比其他常规方法,所提出方法不仅在理想环境下有更高的分类准确率,且该方法能有效抵抗噪声,在复杂工况下能更有效地对钛板缺陷进行分类识别。     

基于PCA与贝叶斯决策的人脸识别算法

研究了主元分析与贝叶斯决策相结合的人脸识别方法。利用主元分析提取人脸图像训练集的特征子空间,将训练图像和测试图像投影到该子空间,提取特征向量及计算统计特性,利用最小错误率贝叶斯决策规则对测试图像进行分类,从而实现人脸识别。大量实验表明:主元分析能将人脸图像的特征信息有效地映射在特征子空间,同时采用贝叶斯决策规则能够快速准确地对人脸图像进行分类。     

基于贝叶斯复合分位数回归的参数估计及应用

针对传统最小二乘估计易受异常点干扰及稳健性较差的问题,建立了基于复合分位数回归估计的数据拟合预测模型。为了克服复合分位数回归在估计参数时忽视了参数的不确定性,致使估算出的参数精度不够高的缺点,将贝叶斯分析法与复合分位数回归相结合,提高了参数的估算精度。实证分析表明贝叶斯复合分位数回归估计优于复合分位数回归估计,而复合分位数回归估计优于传统最小二乘估计,值得工程技术人员借鉴。     

基于贝叶斯推论和自组织映射的轴承性能退化评估方法

为在线识别和评估轴承的动态运行状态,提出一种基于贝叶斯推论和自组织映射的轴承性能退化评估方法。首先运用独立成分分析算法从原始特征集提取表征轴承正常运行的特征集,建立描述轴承健康状态的基准自组织映射模型,进而提出基于负对数似然概率的设备性能量化评估指标和基于贝叶斯推论的失效概率计算方法,在线识别和评估轴承的动态运行状态。通过在轴承全寿命测试床的实验结果表明,与一些传统的特征值指标和基于支持向量数据描述的性能退化评估方法相比,提出的评估指标可有效地量化轴承的全寿命性能退化过程,为进一步制定维护计划提供重要的设备健康信息。     

基于测距定向的WSNs分步求精定位算法

针对现有算法无法满足在不同环境中对定位精度的要求,提出一种基于测距定向的分步求精定位算法(stepwise refine-ment localization algorithm based on ranging and orientation,SRLRO)。通过分析环境因素对RSSI(received signal strength indica-tion)测距的影响,算法首先建立RSSI测距定向模型,确定指向待定位节点所在较小区域的多条直线,通过质心算法求这些直线交点的质心。为了进一步提高算法精度,算法采取了一些优化规则。仿真和实验表明,在不同环境因素的影响下,算法都具有较高的定位精度。     

Robust cubature Kalman filter based on variational Bayesian and transformed posterior sigma points error

An improved robust cubature Kalman filter (RCKF) based on variational Bayesian (VB) and transformed posterior sigma points error is proposed in this paper, which not only retains the robustness of RCKF, but also exhibits adaptivity in the presence of time-varying noise. First, a novel sigma-point update framework with uncertainties reduction is developed by employing the transformed posterior sigma points error. Then the VB is used to estimate the time-varying measurement noise, where the state-dependent noise is addressed in the iteratively parameter estimation. The new filter not only reduces the uncertainty on sigma points generation but also accelerates the convergence of VB-based noise estimation. The effectiveness of the proposed filter is verified on integrated navigation, and numerical simulations demonstrate that VB-RCKF outperforms VB-CKF and RCKF.     

基于神经网络的测量模型的建立及检验

针对间接测量数学模型难于建立的问题,提出了基于径向基函数神经网络的非参数测量模型的建立方法.利用对训练样本的聚类结果来确定基函数的中心,使得神经网络在较少的训练样本条件下仍可获得较高的建模精度.应用实例验证了本方法的有效性.     

Bayesian approach for measuring EEPROM process capability based on the one-sided indices CPU and CPL

The purpose of process capability analysis is to provide numerical measures on whether a process is capable of reproducing items meeting the manufacturing specifications. Capability analyses have received considerable recent research attention and increased usage in process assessments and purchasing decisions. Most existing research works on capability analysis focus on estimating and testing process capability based on the traditional distribution frequency approach. In this paper, we propose a Bayesian approach based on the indices C_PU and C_PL to measure EEPROM process capability, in which the specifications are one-sided rather than two-sided. We obtain the credible intervals of C_PU and C_PL and develop a Bayesian procedure for capability testing. The posterior probability p, for which the process under investigation is capable, is derived. The credible interval is a Bayesian analog of the classical lower confidence interval. A process satisfies the manufacturing capability requirements if all the points in the credible interval are greater than the pre-specified capability level w. To make this Bayesian procedure practical for in-plant applications, a real example of an EEPROM manufacturing process is investigated, demonstrating how the Bayesian procedure can be applied to actual data collected in the factories.