Improvement of automatic Chinese text classification by combining multiple features

In this paper, we present an effective way of combining character‐based (N‐gram) and word‐based approaches for Chinese text classification. Uni‐gram and bi‐gram features are considered as the baseline model, which are then combined with word features of length greater than or equal to 3. A weight coefficient that can be used to give higher weights to word features is also introduced. We further employ a serial approach based on feature transformation and dimension reduction techniques. The results of McNemar's test indicate that the performance is significantly improved by our proposed method. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Hybrid Chinese text classification approach using general knowledge from Baidu Baike

Most of the previous studies focused on enriching text representation to address text classification (TC) task. However, conventional classification approaches with VSM (vector space model) on Chinese text study intensively only the words and their relationship in some specific corpus/dataset but ignore the basic concept of categories and the general knowledge behind the words learned and used to recognize entities by people. This paper focuses on enriching text representation and proposes a novel approach, which complements information from the online Chinese encyclopedia Baidu Baike for Chinese TC. The similarities between every text and each concept of categories and the most related words from Baidu Baike are added to the feature space. The performance of the proposed approach is measured on the Fudan University TC corpus, which is an imbalanced Chinese dataset. In the experiments, the proposed Baidu Baike‐based concept similarity approach obtains promising results when compared with a previous research and the conventional method, with macro‐precision of 90.31%, recall of 75.45%, and F₁ score 80.32%, which are about 0.02%, 0.15%, 0.12%, respectively, higher than the conventional method, which obviously improves the recall for some small categories while keeping precision at high level and improving the macro F₁ score. Moreover, the proposed approach has good expandability, so that many other knowledge bases could be integrated and many other concepts could be referred to improve the effectiveness. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于支持向量机铅酸蓄电池的分类研究

铅酸蓄电池是目前广泛使用的一种二次电池。在胶体电解质铅酸蓄电池的生产中,灌注的胶体电解质量不够的铅酸蓄电池必须在化成结束后重新补充胶体电解质。一般而言,判断铅酸蓄电池是否需要补充电解质是依据其化成后的电池容量和电解液体积。很明显这是一种耗时且不利于胶体电解质铅酸蓄电池配组的方法。文章提出了一种基于支持向量机的铅酸蓄电池补胶分类的方法,通过铅酸蓄电池化成过程中间步骤四个时间点的测试电压判断铅酸蓄电池是否需要补充胶体电解质。研究结果表明,该方法优于基于学习向量量化神经网络的分类方法,可以有效地缩短胶体电解质铅酸蓄电池生产时间。     

面向船舶工业新闻的文本分类

由于船舶工业领域中的新闻内容篇幅较长且专业性较强,同时包含大量船舶领域专业词汇,目前针对该领域新闻文本分类的研究较少且缺少相应的船舶工业新闻语料。构建了一个船舶工业新闻语料库,并提出了一种新的面向船舶工业新闻的文本分类算法,首先基于文档频率、卡方统计量及主题模型LSA进行特征选择和特征降维,将文档-词矩阵映射成文档-主题矩阵后,最终对处理后的特征采用支持向量机进行文本分类。通过新闻文本分类的实验表明,所提出的算法能够有效解决文本向量的高维度、高稀疏性问题,在小样本集和类别有限的前提下相比传统方法具有较好的分类效果。     

基于字符级CNN的调水工程巡检文本智能分类方法

日常安全巡检是维护长距离调水工程安全运行的重要手段.目前巡检采集的非结构化文本数据主要依靠人工进行安全等级评判,在工作效率和准确率方面存在明显不足.本研究基于自然语言处理技术,提出了一种面向字符层面的卷积神经网络的巡检安全文本智能分类方法.该方法通过引入预训练的单个字符向量改进卷积神经网络的输入层,使得分类模型直接从原...     

Design of a qualitative classification model through fuzzy support vector machine with type‐2 fuzzy expected regression classifier preset

Methods of qualitative analysis, such as qualitative classification, have gained importance as an essential complement of existing quantitative analysis in numerous fields. Only a few models have been developed to deal with qualitative inputs in the form of type‐2 fuzzy(T2F) sets properly, given that traditional defuzzification method like the Karnik–Mendel algorithm performs dimensionality reduction at the cost of loss of information. To improve the situation, we define the expected value and variance of T2F set in this paper. By using a combination of them, we transfer the vertical three‐dimensional uncertainty of T2F set to horizontal range uncertainty without much distortion of information. Additionally, current classification models are unsuitable to the partial classification problem if an output is not fully assigned to a single class. We build a comprehensive qualitative classification model based on fuzzy support vector machine (FSVM) combined with type‐2 fuzzy expected regression (FER) to solve the partial classification problem as mentioned. This classifier (i.e. FER‐FSVM) makes it possible to achieve the discrimination of output while characterizing membership for each class in terms of multidimensional qualitative inputs (attributes) in the form of T2F sets. FER‐FSVM also can self‐learn the data structure and shift between FER or FSVM for classification automatically, thus largely improving the efficiency of the classification process. The new model is almost 7 times more efficient than FSVM, as shown by our empirical experiments. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

A new ensemble-based classifier for IGBTopen-circuit fault diagnosis in three-phasePWM converter

Three-phase pulse width modulation converters using insulated gate bipolar transistors (IGBTs) have been widely used in industrial application. However, faults in IGBTs can severely affect the operation and safety of the power electronics equipment and loads. For ensuring system reliability, it is necessary to accurately detect IGBT faults accurately as soon as their occurrences. This paper proposes a diagnosis method based on data-driven theory. A novel randomized learning technology, namely extreme learning machine (ELM) is adopted into historical data learning. Ensemble classifier structure is used to improve diagnostic accuracy. Finally, time window is defined to illustrate the relevance between diagnostic accuracy and data sampling time. By this mean, an appropriate time window is achieved to guarantee a high accuracy with relatively short decision time. Compared to other traditional methods, ELM has a better classification performance. Simulation tests validate the proposed ELM ensemble diagnostic performance.     

基于FPGA-DSP组合的三电平逆变器空间矢量发生器

多电平逆变器空间矢量的发生需要形成复杂的逆变器驱动信号。本文介绍采用FPGA与DSP的组合来实现三电平逆变器空间矢量发生的一个方法。其设计思想是DSP通过算法生成“开关状态码”,FPGA对这些“开关状态码”进行译码并得到逆变器中12个开关元件的驱动信号,从而形成空间矢量。这种三电平逆变器空间矢量发生器的实验结果体现了该方法的可行性和简易性。     

A new segmented oversampling method for imbalanced data classification using quasi‐linear SVM

Data imbalance occurs on most real‐world classification problems and decreases the performance of classifiers. An oversampling method addresses the imbalance problem by generating synthetic samples to balance the data distribution. However, many of the existing oversampling methods have potential problems in generating wrong and unnecessary synthetic samples, which makes the learning tasks difficult. This paper proposes a new segmented oversampling method for imbalanced data classification. The input space is first partitioned into several linearly separable local partitions along the potential separation boundary by introducing a bottom‐up, minimal‐spanning‐tree‐based clustering method; an oversampling method is then applied within each local linear partition to prevent the generation of wrong and unnecessary synthetic samples; a quasi‐linear support vector machine is finally used to realize the classification by taking advantages of the local linear partitions. Simulation results on different real‐world datasets show that the proposed segmented oversampling method is effective for imbalanced data classifications. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

四桥臂变流器新型三维空间矢量脉宽调制策略

四桥臂有源电力滤波器开关状态多,电压调制复杂,为了简化调制算法,提出新型三维空间矢量脉宽调制（three—dimensional space vector pulse width modulation algorithm,3D-SVPWM）策略。基于分类算法,对变流器三相相电压进行线性运算,获取中间变量并比较,得到最大和次大的中间变量,从而判断参考电压矢量所在三棱柱;根据参考电压矢量在a,Oy坐标系下的分量与相邻平面的关系,判断其所在四面体;基矢量的作用时间根据中间变量的线性组合直接获取。针对参考电压对称无畸变及含有谐波两种情况进行了仿真和实验验证,结果表明所提算法均能调制得到与参考电压吻合的输出电压,证实了新型3D．SVPWM算法的正确性和可行性,且该调制算法直接根据中间变量进行三棱柱判断和时间计算,实现简单,计算量小。     

一种基于三电平矢量调制波的多电平调制方法

以五电平为例简述了多电平空间矢量调制（SVM）的实现方法,在此基础上分析了多电平SVM与多电平载波调制的联系和区别,指出多电平SVM比载波调制在开关组合的选择上更加灵活,使得多电平SVM更有利于输出电压波形的优化和输入直流侧的功率平衡,但是多电平SVM的实现相对复杂。因此文中提出了一种改进的多电平调制方法,该方法基于三电平矢量调制波,折衷了多电平SVM和载波调制的优缺点,既利用了SVM在调制波过零点附近增加开关次数来减小输出电压波形畸变的优点,又可以通过三电平矢量调制计算出调制波,使用载波调制的方法实现,使得该方法的计算量不会随着电平数的增多而大幅度增加。所建立的五电平实验模型验证了该方法确实可行。     

Remote monitoring system for real timedetection and classification of transmissionline faults in a power grid using PMUmeasurements

Remote monitoring of transmission lines of a power system is significant for improved reliability and stability during fault conditions and protection system breakdowns. This paper proposes a smart backup monitoring system for detecting and classifying the type of transmission line fault occurred in a power grid. In contradiction to conventional methods, transmission line fault occurred at any locality within power grid can be identified and classified using measurements from phasor measurement unit (PMU) at one of the generator buses. This minimal requirement makes the proposed methodology ideal for providing backup protection. Spectral analysis of equivalent power factor angle (EPFA) variation has been adopted for detecting the occurrence of fault that occurred anywhere in the grid. Classification of the type of fault occurred is achieved from the spectral coefficients with the aid of artificial intelligence. The proposed system can considerably assist system protection center (SPC) in fault localization and to restore the line at the earliest. Effectiveness of proposed system has been validated using case studies conducted on standard power system networks.     

A new mapping method for phase estimation of single‐phase signals: A new generalization and new realizations of the DFT estimation method

This paper proposes and analyzes a new simple real‐time phase‐estimation method for single‐phase signals, which is based on a vector mapping theory of n‐dimensional to 2‐dimensional vectors. According to the analyses, the proposed mapping method can estimate instantly and properly the true phase of the signals that are contaminated by significant amplitude of noise and harmonics. The mapping method contains the conventional DFT method as a special case. In other words, it can be treated as a generalization of the DFT. Several simple realizations of the mapping method are also newly proposed as a single‐input and two‐output digital mapping filter in both nonrecursive and recursive forms. The recursive realization being able to decrease drastically computing load utilizes the normal form that is robust to finite word length effects. As an application of the proposed mapping method, inverter‐using power control system connected with a single‐phase grid is shown. All analytical results are verified by numerical experiments and the usefulness of the newly proposed mapping method is confirmed. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 160(1): 27–38, 2007; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.20263     

基于双分支并联的特征融合电能质量扰动分类方法

为了提高对电能质量扰动信号(power quality disturbance signal, PQDs)在受到噪声和异常数据干扰时的分类准确率,提出了一种双分支并联特征融合网络的PQDs分类方法。首先,采用一维残差神经网络和一维卷积神经网络两个分支进行特征提取。然后,通过特征融合模块将这些特征融合在一起。最终,通过分类模块对PQDs进行准确分类。相对于串联神经网络,所提方法融合特征向量,增强了特征的区分度,同时适用于并行计算,进一步提高了识别速度。仿真结果表明,所提方法在叠加信噪比为13 dB、15 dB和18 dB的PQDs分类任务中,识别率均超过95%,此外,该方法对异常数据的分类效果也具有一定的鲁棒性。     

A new approach for ME image restoration based on CNN

A new approach for image restoration by cellular neural network (CNN) is developed in this paper. Based on the statistical characteristics of Gibbs image model and the analysis of maximum entropy (ME) image restoration, a reasonable template for binary image restoration is proposed. To process multilevel image, a multi‐layer cellular neural network is employed and an extensive algorithm for multilevel image restoration is proposed. The results of computer simulation prove the effectiveness of this approach and show that we can get the effective template of CNN for some special image questions if we apply the statistical characteristics of Gibbs image model and analyse the physical meaning of the questions. Copyright © 1999 John Wiley & Sons, Ltd.     

A new contingency analysis approach for voltage collapse assessment

Voltage collapse analysis in power systems has been the subject of concern of many researchers. Recently, a new technique based on tangent vector behavior has shown to be attractive, because of the accuracy and the low computational effort required. In this paper, tangent vector is employed for contingency analysis. The idea consists of monitoring tangent vector norm associated with each contingency, identifying the most critical ones. The method is tested with the help of the IEEE-118 bus and the Southeastern Brazilian power systems, considering the generators reactive power limits.     

基于相空间重构理论和优化递归神经网络结合的短期负荷预测方法

根据电力负荷序列的混沌特性,提出以相空间重构理论和优化递归神经网络结合的电力系统短期负荷预测方法,以相空间重构理论确定递归神经网络输入维数;训练样本集由对应预测相点的最近邻相点集构成,并按预测相点步进动态相轨迹生成;优化递归神经网络是以双重遗传算法来确定递归神经网络的隐层结构和权值,总体寻优性可抑制伪近邻点的影响,保证提高预测精度及其稳定性。对两类不同负荷系统日、周预测仿真测试,证实其比传统神经网络预测模型能有效地提高预测精度0.8%。因此,所研究的预测模型和方法在实际预测领域有较高的实用价值。     

A rough membership neural network approach for fault classification in transmission lines

Objective: This paper presents a new approach for fault classification in extra high voltage (EHV) transmission line using a rough membership neural network (RMNN) classifier.Methods: Wavelet transform is used for the decomposition of measured current signals and for extraction of ten significant time–frequency domain features (TFDF), as well as three distinctive time domain features (TDF) particularly in terms of getting better classification performance. After extracting useful features from the measured signals, a decision of fault type of a transmission line is carried out using ten RMNN classifiers. Furthermore, to reduce the training times of the neural network, the rough neurons are used as input layer neurons, and the fuzzy neurons are utilized in hidden and output layer in each RMNN. And the Back Propagation (BP) algorithm is employed for determining the optimal connection weights between neurons of the different layers in the RMNN.Results and Conclusions: To verify the effectiveness of the proposed scheme, extensive simulations have been carried out under different fault conditions with wide variations in fault type, fault resistance, fault location and fault inception angle. Simulations results show that the proposed scheme is faster and more accurate than the back-propagation neural network (BPNN), and it is proved to be a robust classifier for digital protection.     

箝位式三电平逆变器空间电压矢量调制方法的研究

本文论述了三电平中点箝位式逆变器SVPWM原理和实现方法，为了避免三电平逆变器在扇区切换中输出矢量突变，提出了一种首发矢量全部采用正小矢量或负小矢量的空间矢量调制算法，利用三个判断规则，可以很方便地确定出参考矢量所在的扇区和小三角形，给出了合成矢量的相应输出电压矢量，并推导了三角形顶点工作矢量的作用时间。通过检测负载电流方向和直流电容的电压，合理分配正负小矢量对的作用时间，实现了电容电压的平衡。仿真研究结果证实了本文提出的空间矢量调制算法的有效性。     

减少间接矩阵变换器共模电压的改进空间矢量调制策略

为抑制间接矩阵变换器工作时产生的共模电压,分析传统空间矢量调制下间接矩阵变换器的共模电压分布规律,并提出一种减少共模电压的改进空间矢量调制方法。该方法的核心思想在于整流级和逆变级的零矢量重组,完全不同于传统空间矢量调制。该方法一方面大幅度的降低了共模电压,另一方面降低了逆变级的开关损耗,改变了系统开关损耗分布。实验和仿真结果验证了该方法的有效性。