关键词： Fast matching algorithm   partial discharge (PD)   pattern recognition   vector quantization (VQ)  

摘要： The apparent charge sequence of cable joint samples with typical defects at different test voltages is utilized as a feature for pattern recognition of partial discharge (PD). The vector quantization and fast matching algorithm are introduced to realize PD pattern recognition of the cable. First, the codebook design makes use of Linde-Buzo-Gray encoding technology. Second, the code matrices of PD training samples and testing samples under different defects of cable joints are obtained, and the code occurrence frequency matrix is calculated. Finally, a fast matching algorithm is used to match the code occurrence frequency matrices of training and testing samples. The defect type with the highest matching degree is chosen as the recognition result. The recognition results of 100 samples of cable joints with four defect types demonstrate that the recognition algorithm has the advantages of high execution efficiency and high-recognition rate.

关键词： Cow's milk allergy (CMA)   anaphylaxis   sensitization pattern   cow's milk allergens   CAP-FEIA (Fluorescence Enzyme Immunoassay)   multiplex dot test   basophil activation test (BAT)   human breast milk  

摘要： Cow's milk allergy (CMA) belongs to one of the most common food allergies in early childhood affecting 2-3% of children under 3 years of age. However, approximately 1% of adults remain allergic to cow's milk, often showing severe reactions even to traces of milk. In our study, we recruited patients with different clinical manifestations of CMA, including patients with anaphylaxis and less severe symptoms. We assessed the sensitization patterns and allergic responses of these subgroups through different immunological and cell-based methods. Sera of patients were investigated for IgE against whole cow's milk and its single allergens by CAP- FEIA. In a newly developed in-house multiplex dot assay and a basophil activation test (BAT), cow's milk allergens, in addition to human breast milk and single allergens from cow's and human milk were analyzed for IgE recognition and severity of CMA in the included patients. Both the CAP-FEIA routine diagnostic and the multiplex dot test could differentiate CMA with severe from milder allergic reactions by means of the patients' casein sensitization. The BAT, which mirrors the clinical response in vitro, confirmed that basophils from patients with severe reactions were more reactive to caseins in contrast to the basophils from more moderate CMA patients. By means of this improved component-resolved diagnosis of CMA, individual sensitization patterns could be assessed, also taking sensitization against human milk into consideration.

关键词： Time difference of arrival  

摘要： A GNSS in-car-jammer poses a great threat to the security of navigation satellite signals for civilian applications. Traditional interference localization methods such as received signal strength (RSS), signal arrival angle (AOA), and signal arrival time difference (TDOA) have poor performance in urban environments due to line-of-sight (LoS) path obstruction and reflection. In this paper, a new interference localization method, which works on monitoring networks and follows the pattern recognition principle is proposed. The algorithm locates the jammer by learning the carrier-to-noise density ratio features that are extracted from the data of all monitoring nodes of the network with the means of binary tree support vector machine (SVM) classification technology. Its performance is tested by two simulated interference scenarios: the urban canyon and the urban residential area. Results show that the algorithm provides better localization reliability and smaller position errors compared with traditional localization methods.

关键词： Well logs interpretation   Facies classification   Naive Bayes classifier   Nearest Neighbor   Sarvak Formation  

摘要： The facies is a frequently used term for describing sedimentary units. In the literature, this term has been used for different purposes, as depositional environment, rock type, lithofacies, etc. In subsurface geology, the core samples are essential for facies studies. While lacking cored intervals, the well logs provide precious subsurface information, but the complexity of well log responses leads most of the time to the complexity of interpretations. In this paper, a method is proposed to study the facies types through well logs. The case study is a carbonate platform system, deposited in the upper Cretaceous, named Sarvak Formation, in one of Iranian onshore oilfields, located in the Abadan Plain. For this purpose, parametric and non-parametric (k-nearest neighbor) classifiers were applied to the dataset. Detailed petrography, assisted by core descriptions, led to 37 microfacies, grouped into three main lithofacies, four carbonate rock types and six environmental facies. Classifiers could not identify the microfacies due to a limited number of observations and high variations. However, the environmental facies were truly classified. In addition, lithofacies classification and Dunham carbonate rock typing were carried out correctly. It is discussed that k-nearest neighbor is clearly the outperformed classifier, and the classical parametric models were inadequate due to the nature of the input well logs (dependency of well logs and may be their distribution), and the overlapping of the input feature space. [GRAPHICS] .

关键词： Moment invariants   Fractional-order legendre polynomials   Image classification   Rotation scale translation invariants   Systematic parameter selection   Adaptive feature extraction  

摘要： In this paper, we present a new set of rotation, scale and translation invariants, named Generalized Legendre Moment Invariants (GLMI). This new set of invariants is defined on the Cartesian coordinate system, where we can derive the GLMI based on the algebraic relation between the fractional-order Legendre polynomials and the geometric basis. Consequently, several experiments are carried out to evaluate the performance of the proposed GLMI, with regard to their invariability property, object recognition capability and computation efficiency, in comparison with the most representative families of moment invariants. In addition, we have presented a systematic parameter selection method for finding the optimal fractional parameter values with respect to pattern recognition applications. Just as important, we have introduced an adaptive scheme to set the fractional parameters according to the characteristics of the image. The obtained results clearly show that the proposed invariants provide higher features accuracy and discrimination power even in the presence of noisy effects. (C) 2019 Elsevier B.V. All rights reserved.

关键词： 模糊系统   神经网络   故障诊断   模式识别   信号处理  

摘要： 从模糊系统和神经网络基本理论出发,研究其在网络故障诊断中应用的可行性、优越性,并将模糊系统和神经网络理论与故障诊断实际相结合,针对网络故障诊断中的一些具体问题应用MATLAB软件中的模糊系统工具箱和神经网络工具箱进行仿真加以解决。

关键词： 固体绝缘开关柜   支持向量数据描述   局部放电   模式识别  

摘要： 电力设备内部绝缘缺陷引起的局部放电,含有可用于绝缘状态评估的特征信息。可以有效识别不同局部放电的类型。现有基于传统BP神经网络或SVDD模式识别方法在函数参数选择自主性很强,但由于不同放电类型的特征量在分布上是重叠、非线性的,BP神经网络容易陷入局部最优,识别率不高,SVDD算法在自由金属微粒缺陷识别效果不好。文中对SVDD算法提出了改进,在AP聚类与GPAM-PSO优化算法基础上提出一种用于固体绝缘开关柜局部放电模式识别的SA-SVDD算法。以解决传统模式识别算法在参数选择、训练方法上的不足,通过训练不同放电类型下的分类器,以达到准确识别不同放电类型。仿真结果显示该方法能自主识别不同PD类型,识别率、收敛速度较传统方法有较大提高,以便电力人员准确判断局部放电类型并制定相对应的抢修方案。