Performance enhancement of extreme learning machine for power system disturbances classification

This paper proposes an optimal feature and parameter selection approach for extreme learning machine (ELM) for classifying power system disturbances. The relevant features of non-stationary time series data from power disturbances are extracted using a multiresolution S-transform which can be treated either as a phase corrected wavelet transform or a variable window short-time Fourier transform. After extracting the relevant features from the time series data, an integrated PSO and ELM architectures are used for pattern recognition of disturbance waveform data. The particle swarm optimization is a powerful meta-heuristic technique in artificial intelligence field; therefore, this study proposes a PSO-based approach, to specify the beneficial features and the optimal parameter to enhance the performance of ELM. One of the advantages of ELM over other methods is that the parameter that the user must properly adjust is the number of hidden nodes only. In this paper, a hybrid optimization mechanism is proposed which combines the discrete-valued PSO with the continuous-valued PSO to optimize the input feature subset selection and the number of hidden nodes to enhance the performance of ELM. The experimental results showed the proposed algorithm is faster and more accurate in discriminating power system disturbances.     

Advanced machine learning techniques for microarray spot quality classification

It is well known that microarray printing, hybridization, and washing oftentimes create erroneous measurements, and these errors detrimentally impact machine microarray spot quality classification. Thus, it is crucial to identify and remove these errors if automation is to replace the still common practice of visually assessing spot quality, an extremely expensive and time-consuming procedure. A major problem in microarray spot quality classification methods proposed in the literature is the correlation among the features extracted from the spots. In this paper, we propose using a random subspace ensemble of neural networks and a feature selection algorithm to improve the performance of our microarray spot quality classification method. Our best method obtains an error under the receiver operating characteristic curve (EAUR) of 0.3 outperforming the stand-alone support vector machine EAUR of 1.7. The consistency of our proposed approach makes it a viable alternative to the labour-intensive manual method of spot quality assessment.     

Study of digital image processing techniques for leaf disease detection and classification

Multimedia Tools and Applications - In this paper, we address a comprehensive study on disease recognition and classification of plant leafs using image processing methods. The traditional manual...     

Evolutionary algorithm based optimization for power quality disturbances classification using support vector machines

Classification and detection of power signal disturbances are most essential to ensure the good power quality. The power disturbance signals are non-stationary in nature. Non-stationary signal classification is a complex problem and equally a difficult task. In this paper we present a new method for accurate classification of power quality signals using Support Vector Machines (SVM) with Optimized Time-Frequency Kernels by a stochastic genetic algorithm. The Cohen’s class of time-frequency-transformation has been chosen as the Kernel for the SVM. An Evolutionary Algorithm has been used to optimize the parameters of the Kernels. The proposed classification method with optimized parameters is promising for classification of such non-stationary signals. Comparative simulation results demonstrate a significant improvement in the classification accuracy in case of these optimized Kernels. The important contribution of the paper is the optimization of the Kernels for the power system signal classification problem.     

A methodology for the classification of quality of requirements using machine learning techniques

ContextOne of the most important factors in the development of a software project is the quality of their requirements. Erroneous requirements, if not detected early, may cause many serious problems, such as substantial additional costs, failure to meet the expected objectives and delays in delivery dates. For these reasons, great effort must be devoted in requirements engineering to ensure that the project’s requirements results are of high quality. One of the aims of this discipline is the automatic processing of requirements for assessing their quality; this aim, however, results in a complex task because the quality of requirements depends mostly on the interpretation of experts and the necessities and demands of the project at hand.ObjectiveThe objective of this paper is to assess the quality of requirements automatically, emulating the assessment that a quality expert of a project would assess.MethodThe proposed methodology is based on the idea of learning based on standard metrics that represent the characteristics that an expert takes into consideration when deciding on the good or bad quality of requirements. Using machine learning techniques, a classifier is trained with requirements earlier classified by the expert, which then is used for classifying newly provided requirements.ResultsWe present two approaches to represent the methodology with two situations of the problem in function of the requirement corpus learning balancing, obtaining different results in the accuracy and the efficiency in order to evaluate both representations. The paper demonstrates the reliability of the methodology by presenting a case study with requirements provided by the Requirements Working Group of the INCOSE organization.ConclusionsA methodology that evaluates the quality of requirements written in natural language is presented in order to emulate the quality that the expert would provide for new requirements, with 86.1 of average in the accuracy.     

A novel time-varying modeling and signal processing approach for epileptic seizure detection and classification

Neural Computing and Applications - Electroencephalogram (EEG) signal analysis plays an essential role in detecting and understanding epileptic seizures. It is known that seizure processes are...     

An expert system based on S-transform and neural network for automatic classification of power quality disturbances

In this paper, an S-transform-based neural network structure is presented for automatic classification of power quality disturbances. The S-transform (ST) technique is integrated with neural network (NN) model with multi-layer perceptron to construct the classifier. Firstly, the performance of ST is shown for detecting and localizing the disturbances by visual inspection. Then, ST technique is used to extract the significant features of distorted signal. In addition, an optimum combination of the most useful features is identified for increasing the accuracy of classification. Features extracted by using the S-transform are applied as input to NN for automatic classification of the power quality (PQ) disturbances that solves a relatively complex problem. Six single disturbances and two complex disturbances as well pure sine (normal) selected as reference are considered for the classification. Sensitivity of proposed expert system under different noise conditions is investigated. The analysis and results show that the classifier can effectively classify different PQ disturbances.     

基于改进S 变换和贝叶斯相关向量机的电能质量扰动识别

提出一种改进S变换和相关向量机相结合的电能质量扰动分类法.首先通过引入调节因子构建时频分辨率可控的改进S变换,从而提取各类扰动信号的时频特性;然后利用层次分类法与最小输出编码法构建贝叶斯相关向量机多级分类树模型,实现电能质量扰动信号的分类与识别.研究表明,该方法能在强噪声背景下获得高精度的扰动分类识别率,具备比S变换更高的时频分析能力,较支持向量机需要更少的相关向量数目,测试时间更短.     

Low power architectures for digital signal processing

Low power architectures for digital signal processing algorithms requiring inner product computation are presented. In the first step a power efficient memory organization exploiting data reuse is determined. In the second step an order of evaluation of the partial products that reduces the switching activity at the inputs of the computational units is derived. Information related to both coefficients which are static and data which are dynamic, is used to drive the reordering of computation. Experimental results for several signal processing algorithms prove that the proposed techniques lead to significant savings in net switching activity and thus in power consumption.     

Hybrid intelligent techniques for MRI brain images classification

This paper presents a hybrid technique for the classification of the magnetic resonance images (MRI). The proposed hybrid technique consists of three stages, namely, feature extraction, dimensionality reduction, and classification. In the first stage, we have obtained the features related to MRI images using discrete wavelet transformation (DWT). In the second stage, the features of magnetic resonance images have been reduced, using principal component analysis (PCA), to the more essential features. In the classification stage, two classifiers have been developed. The first classifier based on feed forward back-propagation artificial neural network (FP-ANN) and the second classifier is based on k-nearest neighbor (k-NN). The classifiers have been used to classify subjects as normal or abnormal MRI human images. A classification with a success of 97% and 98% has been obtained by FP-ANN and k-NN, respectively. This result shows that the proposed technique is robust and effective compared with other recent work.     

Feature extraction and gating techniques for ultrasonic shaft signal classification

Discrete wavelet transform (DWT) coefficients of ultrasonic test signals are considered useful features for input into classifiers due to their effective time–frequency representation of non-stationary signals. However, DWT exhibits a time-variance problem that has resulted in reservations for its wide acceptance. In this paper, a new technique to derive a preprocessing method for time-domain A-scans signal is presented. This technique offers consistent extraction of a segment of the signal from long signals that occur in the non-destructive testing of shafts. Two different classifiers using artificial neural networks and support vector machines are supplied with features generated by our new preprocessing method and their classification performance are compared and evaluated. Their performances are also compared with other alternatives and report the results here. This investigation establishes experimentally that DWT coefficients can be used as a feature extraction scheme more reliably by using our new preprocessing technique.     

Optimization techniques for improving power quality data mining using wavelet packet based support vector machine

This paper aims at automatic classification of power quality events using Wavelet Packet Transform (WPT) and Support Vector Machines (SVM). The features of the disturbance signals are extracted using WPT and given to the SVM for effective classification. Recent literature dealing with power quality establishes that support vector machine methods generally outperform traditional statistical and neural methods in classification problems involving power disturbance signals. However, the two vital issues namely the determination of the most appropriate feature subset and the model selection, if suitably addressed, could pave way for further improvement of their performances in terms of classification accuracy and computation time. This paper addresses these issues through a classification system using two optimization techniques, the genetic algorithms and simulated annealing. This system detects the best discriminative features and estimates the best SVM kernel parameters in a fully automatic way. Effectiveness of the proposed detection method is shown in comparison with the conventional parameter optimization methods discussed in literature like grid search method, neural classifiers like Probabilistic Neural Network (PNN), fuzzy k-nearest neighbor classifier (FkNN) and hence proved that the proposed method is reliable as it produces consistently better results.     

一种新的电能质量自适应滤波方法*

在电能质量检测中,去噪和保留突变点信息是两个十分重要的问题.为此提出了一种新的基于梯度倒数加权平均算法的自适应滤波方法.该方法首先对电能质量采样信号点建立五个模板,依据检测点与五个模板均值的梯度变化规律,进行突变点判决.在传统梯度法的基础上,选择最佳模板,并用该模板均值与模板内各点幅值的差值代替传统梯度算法中的梯度值,然后对不同类型的点采用不同的算法去噪.实验结果表明,与传统的梯度倒数加权算法和五点均值滤波法相比,改进的算法能够更好地清除噪声,同时较好地保留突变点信息,有针对性地解决了电能质量检测中的两大重要问题.     

一种火焰检测系统的信号处理方法

设计了一种用于热能设备的火焰检测系统处理信号的方法.系统以AVR单片机为核心芯片,信号放大处理电路采用多级放大器与多路ADC通道相结合,实现自适应增益调整,以提高输入动态范围.火焰信号强度用输入信号的统计平均值表示,火焰信号的频率用快速傅里叶变换(FFT)进行分析计算.在FFT运算中,利用定点运算和查表法简化计算过程,降低资源消耗,提高运算速度,在300 ms时间内完成了512个采样点的定点FFT运算,频率分辨率为1 Hz,保证火焰信号检测的实时性、精度和可靠性.     

Performance analysis of power and power variance for classification,detection and localization of epileptic multi-channel EEG

There are a large number of data sets of EEG signal for which, it is difficult to judge and monitor brain activity through observations. Epilepsy is a disorder in which a recurrent and sudden malfunction of the brain is characterized. It is proposed to classify, detect and localize Epileptic multi-channel EEG through various power and novel power variance features non-invasively. This work presents power spectral estimation (PSE) using time–frequency analysis of EEG signals in both parametric (FFT) and non-parametric methods (i.e. Welch, Burg, Covariance, MUSIC and Yule–Walker). To examine the robustness of power features for different methods, the analysis of p value is performed. The detection of epileptic seizure is classified using different kernels through SVM. It is observed from the PSE that the power features have higher values in epileptic subjects as compared to non-epileptic subjects. Amongst all the parametric and non-parametric methods, the MUSIC method gives the highest average power. Sensitivity, specificity, and classification accuracy are 100% for Welch, Burg, Covariance, and Yule–Walker methods while MUSIC and FFT methods deliver 98.73 and 99.52% respectively. The novelty is introduced through the quantification of power and power variance robust feature region/lobe-wise. This quantification is used for the localization of 25 epileptic subjects. Analysis of the parametric and non-parametric PSD methods for extraction of power and power variance features is not used by any study. These are effectively utilized for detection and localization of epilepsy non-invasively.

     

Comparing and experimenting machine learning techniques for code smell detection

Several code smell detection tools have been developed providing different results, because smells can be subjectively interpreted, and hence detected, in different ways. In this paper, we perform the largest experiment of applying machine learning algorithms to code smells to the best of our knowledge. We experiment 16 different machine-learning algorithms on four code smells (Data Class, Large Class, Feature Envy, Long Method) and 74 software systems, with 1986 manually validated code smell samples. We found that all algorithms achieved high performances in the cross-validation data set, yet the highest performances were obtained by J48 and Random Forest, while the worst performance were achieved by support vector machines. However, the lower prevalence of code smells, i.e., imbalanced data, in the entire data set caused varying performances that need to be addressed in the future studies. We conclude that the application of machine learning to the detection of these code smells can provide high accuracy (>96 %), and only a hundred training examples are needed to reach at least 95 % accuracy.     

Non-stationary power signal processing for pattern recognition using HS-transform

A new approach to time-frequency transform and pattern recognition of non-stationary power signals is presented in this paper. In the proposed work visual localization, detection and classification of non-stationary power signals are achieved using hyperbolic S-transform known as HS-transform and automatic pattern recognition is carried out using GA based Fuzzy C-means algorithm. Time-frequency analysis and feature extraction from the non-stationary power signals are done by HS-transform. Various non-stationary power signal waveforms are processed through HS-transform with hyperbolic window to generate time-frequency contours for extracting relevant features for pattern classification. The extracted features are clustered using Fuzzy C-means algorithm and finally the algorithm is optimized using genetic algorithm to refine the cluster centers. The average classification accuracy of the disturbances is 93.25% and 95.75% using Fuzzy C-means and genetic based Fuzzy C-means algorithm, respectively.     

Clustering technique-based least square support vector machine for EEG signal classification

This paper presents a new approach called clustering technique-based least square support vector machine (CT-LS-SVM) for the classification of EEG signals. Decision making is performed in two stages. In the first stage, clustering technique (CT) has been used to extract representative features of EEG data. In the second stage, least square support vector machine (LS-SVM) is applied to the extracted features to classify two-class EEG signals. To demonstrate the effectiveness of the proposed method, several experiments have been conducted on three publicly available benchmark databases, one for epileptic EEG data, one for mental imagery tasks EEG data and another one for motor imagery EEG data. Our proposed approach achieves an average sensitivity, specificity and classification accuracy of 94.92%, 93.44% and 94.18%, respectively, for the epileptic EEG data; 83.98%, 84.37% and 84.17% respectively, for the motor imagery EEG data; and 64.61%, 58.77% and 61.69%, respectively, for the mental imagery tasks EEG data. The performance of the CT-LS-SVM algorithm is compared in terms of classification accuracy and execution (running) time with our previous study where simple random sampling with a least square support vector machine (SRS-LS-SVM) was employed for EEG signal classification. We also compare the proposed method with other existing methods in the literature for the three databases. The experimental results show that the proposed algorithm can produce a better classification rate than the previous reported methods and takes much less execution time compared to the SRS-LS-SVM technique. The research findings in this paper indicate that the proposed approach is very efficient for classification of two-class EEG signals.     

面向电力设备缺陷检测的多模态层次化分类

目的 电力设备的状态检测和故障维护是保障电力系统正常运行的重要基础。针对目前多数变电站存在电力设备缺陷类型复杂且现有的单分类缺陷检测方法无法满足电力设备的多标签分类缺陷检测需求的问题,提出一种面向电力设备缺陷检测的多模态层次化分类方法。方法 首先采集来自多个变电站的电力设备缺陷图像并进行人工标注、数据增强及归一化等预处理,构建了一个具有层次标签结构的电力设备缺陷图像数据集。然后提出一种基于多模态特征融合的层次化分类模型,采用 ResNet50 网络对图像进行特征提取,利用区域生成网络对目标进行定位以及前景、背景预测;为避免对区域生成网络生成的位置坐标进行量化时引入误差,进一步采用 ROI Align（region of interest align）方法连续操作,生成位置坐标。最后采用层次化分类,将父类别标签嵌入到当前层目标特征表示进行逐层缺陷分类,最后一层得到最终的缺陷检测结果。结果 在电力设备缺陷数据集和基准数据集上,与多标签分类电力设备缺陷检测方法和流行的常用目标检测算法进行对比实验。实验结果表明,模型对绝大部分设备缺陷类别的检测准确率最高,平均检测准确率达到 86. 4%,相比性能第 2 的模型,准确率提升了 5. 1%,并且在基准数据集上的平均检测准确率也提高了 1. 1%～3%。结论 提出的电力设备缺陷检测方法充分利用设备缺陷标签的语义信息、层次结构和设备缺陷数据的图像特征,通过多模态层次化分类模型,能够提升电力设备缺陷检测的准确率。