CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis

As a representative deep learning network, Convolutional Neural Network (CNN) has been extensively used in bearing fault diagnosis and many good results have been reported. In Prognostics and Health Management (PHM) field, the CNN’s input size is usually designed as a 1D vector or 2D square matrix, and the convolution kernel size is also defined as a square shape like 3 × 3 and 5 × 5, which are directly adopted from the image recognition. Though satisfying results can be obtained, CNN with such parameter specifications is not optimal and efficient. To this end, this paper elaborated the physical characteristics of bearing acceleration signals to guide the CNN design. First, the fault period under different fault types and shaft rotation frequency were used to determine the size of CNN’s input. Next, an exponential function was involved in fitting the envelope of decaying acceleration signal during each fault period, and signal length within different decaying ratios was used to define the CNN’s kernel size. Finally, the designed CNN was validated with the Case Western Reserve University bearing dataset and Paderborn University bearing dataset. Results confirm that the physics-guided CNN (PGCNN) with rectangular input shape and rectangular convolution kernel works better than the baseline CNN with higher accuracy and smaller uncertainty. The feasibility of designing CNN parameters with physics-guided rules derived from bearing fault signal analysis has also been verified.     

基于系统调用序列学习的内核模糊测试

操作系统内核是计算机系统中最基本的软件组件, 它控制和管理计算机硬件资源, 并提供访问和管理其他应用程序所需的接口和服务. 操作系统内核的安全性直接影响整个计算机系统的稳定性和可靠性. 内核模糊测试是一种高效、准确的安全漏洞检测方法. 然而目前内核模糊测试工作中, 存在系统调用间关系的计算开销过大且容易误判, 以及系统调用序列构造方式缺乏合理能量分配以至于很难探索低频系统调用的问题. 本文提出以N-gram模型学习系统调用间关系, 根据系统调用的出现频次信息和TF-IDF信息优先探索出现频次低或者TF-IDF值高的系统调用. 我们以极低的开销, 在Linux 4.19和5.19版本的24 h实验中分别提升了15.8%、14.7%的覆盖率. 此外, 我们挖掘到了一个已知CVE (CVE-2022-3524)、8个新崩溃, 其中一个获得了CNNVD编号(CNNVD-2023-84723975).     

A new method using feature extraction for identifying paddy rice species for quality seed selection

The purpose of this work was to explore a new feature extraction method for classifying paddy seeds using a feature extraction algorithm to achieve the area ratio, horizontal–slant and front–rear angles and find whether the proposed features have high discriminating power. Another objective was to find the smallest feature set that can ensure highly accurate recognition of seeds. A total of a 100 image features were extracted, and features having significant discriminating power were identified based on the analysis of variance (ANOVA). From the 100 features, 14 features were found to have high discriminating power and from these features, six were selected as the proposed features. Experimental results show that the proposed features and removal of redundant features enhanced the discriminating power of the feature set, and that the proposed features have an excellent discriminating property for seeds. The presented features resulted in the highest classification accuracy (98.8%) when compared to other methods.     

Betweenness parameterized above tight lower bound

We study ordinal embedding relaxations in the realm of parameterized complexity. We prove the existence of a quadratic kernel for the Betweenness problem parameterized above its tight lower bound, which is stated as follows. For a set V of variables and set C of constraints “vi is between vj and vk”, decide whether there is a bijection from V to the set {1,…,|V|} satisfying at least |C|/3+κ of the constraints in C. Our result solves an open problem attributed to Benny Chor in Niedermeier's monograph “Invitation to Fixed-Parameter Algorithms”. The betweenness problem is of interest in molecular biology. An approach developed in this paper can be used to determine parameterized complexity of a number of other optimization problems on permutations parameterized above or below tight bounds.     

Local normalized linear summation kernel for fast and robust recognition

Kernel-based methods are effective for object detection and recognition. However, the computational cost when using kernel functions is high, except when using linear kernels. To realize fast and robust recognition, we apply normalized linear kernels to local regions of a recognition target, and the kernel outputs are integrated by summation. This kernel is referred to as a local normalized linear summation kernel. Here, we show that kernel-based methods that employ local normalized linear summation kernels can be computed by a linear kernel of local normalized features. Thus, the computational cost of the kernel is nearly the same as that of a linear kernel and much lower than that of radial basis function (RBF) and polynomial kernels. The effectiveness of the proposed method is evaluated in face detection and recognition problems, and we confirm that our kernel provides higher accuracy with lower computational cost than RBF and polynomial kernels. In addition, our kernel is also robust to partial occlusion and shadows on faces since it is based on the summation of local kernels.     

Learning state machine-based string edit kernels

During the past few years, several works have been done to derive string kernels from probability distributions. For instance, the Fisher kernel uses a generative model M (e.g. a hidden Markov model) and compares two strings according to how they are generated by M. On the other hand, the marginalized kernels allow the computation of the joint similarity between two instances by summing conditional probabilities. In this paper, we adapt this approach to edit distance-based conditional distributions and we present a way to learn a new string edit kernel. We show that the practical computation of such a kernel between two strings x and x^′ built from an alphabet Σ requires (i) to learn edit probabilities in the form of the parameters of a stochastic state machine and (ii) to calculate an infinite sum over Σ^* by resorting to the intersection of probabilistic automata as done for rational kernels. We show on a handwritten character recognition task that our new kernel outperforms not only the state of the art string kernels and string edit kernels but also the standard edit distance used by a neighborhood-based classifier.     

基于S3C2440的嵌入式Linux内核设计

该文介绍了三星公司的基于ARM9内核S3C2440芯片嵌入式Linux系统设计。在确认已经移植好的U-boot的基础上,进行控制模块基于ARM9的Linux嵌入式系统设计方案,裁剪并移植Linux内核。     

基于自适应阈值设置的运动目标检测算法

提出一种基于自适应阈值设置的运动目标检测算法,该算法不同干传统的全局阈值设置方法,而是利用核密度对背景像素点进行密度估计,给出一种新的全局和局部阈值相结合的自适应阈值设置方法。该方法考虑不同位置的像素颜色分布复杂度不同,针对每个像素点自适应设置局部阈值,能克服全局阈值的不足,提高检测的精度。对多个标准视频进行实验,实验结果证明了该算法的有效性。     

基于确定模式的伪单跳变测试矢量生成技术

提出了一种基于确定模式的伪单跳变测试矢量生成方法,它是在折叠计数器确定模式的基础上,采用LFSR编码折叠计数器种子,通过选定的存储折叠距离来控制测试模式,使得产生的测试矢量之间实现伪单跳变。由于是在确定模式基础上进行的研究,没有改变原来的测试矢量,所以故障覆盖率不会改变,却大大降低了测试功耗。这样既保证了高故障覆盖率,又解决了不同种子所生成的测试矢量之间的重叠冗余。研究结果不仅表明该方案具有很好的数据压缩率,而且证明了该方案的有效性。     

基于KISOMAP-LDA-KNN算法TE过程故障诊断研究

针对化工连续生产过程的时序性及非线性等特征,文章提出了一种基于KISOMAP-LDA-KNN的非线性故障辨识方法。首先采用核等距映射（KISOMAP）算法在保持训练数据内在几何结构下进行非线性降维,然后使用线性判别（LDA）算法保持数据的最佳分类效果下进行降维,完成过程的特征提取,最后用K近邻（KNN）算法进行模式分类。将上述方法应用到TE过程,仿真结果验证了该故障诊断方法有较高的辨识能力。