BA-PNN-based methods for power transformer fault diagnosis

This paper presents a machine learning-based approach to power transformer fault diagnosis based on dissolved gas analysis (DGA), a bat algorithm (BA), optimizing the probabilistic neural network (PNN). PNN is a radial basis function feedforward neural network based on Bayesian decision theory, which has a strong fault tolerance and significant advantages in pattern classification. However, one challenge still remains: the performance of PNN is greatly affected by its hidden layer element smooth factor which impacts the classification performance. The proposed approach addresses this challenge by deploying the BA algorithm, a kind of bio-inspired algorithm to optimize PNN. Using the real data collected from a transformer system, we conducted the experiments for validating the performance of the developed method. The experimental results demonstrated that BA is an effective algorithm for optimizing PNN smooth factor and BA-PNN can improve the fault diagnosis performance; in turn, and the machine learning-based model (BA-PNN) can significantly enhance the accuracies of power transformer fault diagnosis.     

Polynomial neural networks architecture: analysis and design

In this study, we introduce and investigate a class of neural architectures of Polynomial Neural Networks (PNNs), discuss a comprehensive design methodology and carry out a series of numeric experiments. Two kinds of PNN architectures, namely a basic PNN and a modified PNN architecture are discussed. Each of them comes with two types such as the generic and the advanced type. The essence of the design procedure dwells on the Group Method of Data Handling. PNN is a flexible neural architecture whose structure is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but becomes dynamically meaning that the network grows over the training period. In this sense, PNN is a self-organizing network. A comparative analysis shows that the proposed PNN are models with higher accuracy than other fuzzy models.     

Multi-label incremental learning applied to web page categorization

Multi-label problems are challenging because each instance may be associated with an unknown number of categories, and the relationship among the categories is not always known. A large amount of data is necessary to infer the required information regarding the categories, but these data are normally available only in small batches and distributed over a period of time. In this work, multi-label problems are tackled using an incremental neural network known as the evolving Probabilistic Neural Network (ePNN). This neural network is capable of continuous learning while maintaining a reduced architecture, so that it can always receive training data when available with no drastic growth of its structure. We carried out a series of experiments on web page data sets and compared the performance of ePNN to that of other multi-label categorizers. On average, ePNN outperformed the other categorizers in four out of five metrics used for evaluation, and the structure of ePNN was less complex than that of the other algorithms evaluated.     

An expert system for fault diagnosis in internal combustion engines using probability neural network

An expert system for fault diagnosis in internal combustion engines using adaptive order tracking technique and artificial neural networks is presented in this paper. The proposed system can be divided into two parts. In the first stage, the engine sound emission signals are recorded and treated as the tracking of frequency-varying bandpass signals. Ordered amplitudes can be calculated with a high-resolution adaptive filter algorithm. The vital features of signals with various fault conditions are obtained and displayed clearly by order figures. Then the sound energy diagram is utilized to normalize the features and reduce computation quantity. In the second stage, the artificial neural network is used to train the signal features and engine fault conditions. In order to verify the effect of the proposed probability neural network (PNN) in fault diagnosis, two conventional neural networks that included the back-propagation (BP) network and radial-basic function (RBF) network are compared with the proposed PNN network. The experimental results indicated that the proposed PNN network achieved the best performance in the present fault diagnosis system.     

Implementing spiking neural networks for real-time signal-processing and control applications: a model-validated FPGA approach.

In this paper, we present two versions of a hardware processing architecture for modeling large networks of leaky-integrate-and-fire (LIF) neurons; the second version provides performance enhancing features relative to the first. Both versions of the architecture use fixed-point arithmetic and have been implemented using a single field-programmable gate array (FPGA). They have successfully simulated networks of over 1000 neurons configured using biologically plausible models of mammalian neural systems. The neuroprocessor has been designed to be employed primarily for use on mobile robotic vehicles, allowing bio-inspired neural processing models to be integrated directly into real-world control environments. When a neuroprocessor has been designed to act as part of the closed-loop system of a feedback controller, it is imperative to maintain strict real-time performance at all times, in order to maintain integrity of the control system. This resulted in the reevaluation of some of the architectural features of existing hardware for biologically plausible neural networks (NNs). In addition, we describe a development system for rapidly porting an underlying model (based on floating-point arithmetic) to the fixed-point representation of the FPGA-based neuroprocessor, thereby allowing validation of the hardware architecture. The developmental system environment facilitates the cooperation of computational neuroscientists and engineers working on embodied (robotic) systems with neural controllers, as demonstrated by our own experience on the Whiskerbot project, in which we developed models of the rodent whisker sensory system.     

A study of cloud classification with neural networks using spectraland textural features

The problem of cloud data classification from satellite imagery using neural networks is considered. Several image transformations such as singular value decomposition (SVD) and wavelet packet (WP) were used to extract the salient spectral and textural features attributed to satellite cloud data in both visible and infrared (IR) channels. In addition, the well-known gray-level cooccurrence matrix (GLCM) method and spectral features were examined for the sake of comparison. Two different neural-network paradigms namely probability neural network (PNN) and unsupervised Kohonen self-organized feature map (SOM) were examined and their performance were also benchmarked on the geostationary operational environmental satellite (GOES) 8 data. Additionally, a postprocessing scheme was developed which utilizes the contextual information in the satellite images to improve the final classification accuracy. Overall, the performance of the PNN when used in conjunction with these feature extraction and postprocessing schemes showed the potential of this neural-network-based cloud classification system.     

Integration of independent component analysis and neural networks for ECG beat classification

In this paper, we propose a scheme to integrate independent component analysis (ICA) and neural networks for electrocardiogram (ECG) beat classification. The ICA is used to decompose ECG signals into weighted sum of basic components that are statistically mutual independent. The projections on these components, together with the RR interval, then constitute a feature vector for the following classifier. Two neural networks, including a probabilistic neural network (PNN) and a back-propagation neural network (BPNN), are employed as classifiers. ECG samples attributing to eight different beat types were sampled from the MIT-BIH arrhythmia database for experiments. The results show high classification accuracy of over 98% with either of the two classifiers. Between them, the PNN shows a slightly better performance than BPNN in terms of accuracy and robustness to the number of ICA-bases. The impressive results prove that the integration of independent component analysis and neural networks, especially PNN, is a promising scheme for the computer-aided diagnosis of heart diseases based on ECG.     

A Normalized Probabilistic Expectation-Maximization Neural Network for Minimizing Bayesian Misclassification Cost Risk

In this paper, we propose a normalized semi-supervised probabilistic expectation-maximization neural network (PEMNN) that minimizes Bayesian misclassification cost risk. Using simulated and real-world datasets, we compare the proposed PEMNN with supervised cost sensitive probabilistic neural network (PNN), discriminant analysis (DA), mathematical integer programming (MIP) model and support vector machines (SVM) for different misclassification cost asymmetries and class biases. The results of our experiments indicate that the PEMNN performs better when class data distributions are normal or uniform. However, when class data distribution is exponential the performance of PEMNN deteriorates giving slight advantage to competing MIP, DA, PNN and SVM techniques. For real-world data with non-parametric distributions and mixed decision-making attributes (continuous and categorical), the PEMNN outperforms the PNN.     

A self-adaptive data analysis for fault diagnosis of an automotive air-conditioner blower

This paper presents a fault diagnosis system for an automotive air-conditioner blower based on a noise emission signal using a self-adaptive data analysis technique. The proposed diagnosis system consists of feature extraction using the empirical mode decomposition (EMD) method and fault classification using the artificial neural network technique. The EMD method has been developed quite recently to adaptively decompose the non-stationary and non-linear signals. It sifts the complex signal of time series without losing its original properties and then obtains some useful intrinsic mode function (IMF) components. Calculating the energy of each component can reduce the computation dimensions and enhance classification performance. These energy features of various fault conditions are used as inputs to train the artificial neural network. In the fault classification, the probabilistic neural network (PNN) is used to verify the performance of the proposed system and compare with the traditional technique, back-propagation neural network (BPNN). The experimental results indicated the proposed technique performed well for quickly and accurately estimating fault conditions.     

PARTICLE SWARM OPTIMIZATION-BASED FEATURE SELECTION AND PARAMETER OPTIMIZATION FOR POWER SYSTEM DISTURBANCES CLASSIFICATION

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. The appropriate input features of the classifier are selected from a given set of possible features, and the structure parameters of the classifier are adapted with respect to these features and a given dataset. This paper describes the particle swarm optimization algorithm (PSO) that performs feature and model selection simultaneously for the probabilistic neural network (PNN) classifier for power system disturbances. The probabilistic neural network is one of the successful classifiers used to solve many classification problems. However, the computational effort and storage requirement of the PNN method will prohibitively increase as the number of patterns used in the training set increases. An important issue that has not been given enough attention is the selection of a “spread parameter,” also called a “smoothing parameter,” in the PNN classifier. PSO is a powerful meta-heuristic technique in the artificial intelligence field; therefore, this study proposes a PSO-based approach, called PSO-PNN, to specify the beneficial features and the value of spread parameter to enhance the performance of PNN. The experimental results indicate that the proposed PSO-based approach significantly improves the classification accuracy with the discriminating input features for PNN.     

Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features

The aim of the present study was to design, implement and evaluate a software system for discriminating between metastatic and primary brain tumors (gliomas and meningiomas) on MRI, employing textural features from routinely taken T1 post-contrast images. The proposed classifier is a modified probabilistic neural network (PNN), incorporating a non-linear least squares features transformation (LSFT) into the PNN classifier. Thirty-six textural features were extracted from each one of 67 T1-weighted post-contrast MR images (21 metastases, 19 meningiomas and 27 gliomas). LSFT enhanced the performance of the PNN, achieving classification accuracies of 95.24% for discriminating between metastatic and primary tumors and 93.48% for distinguishing gliomas from meningiomas. To improve the generalization of the proposed classification system, the external cross-validation method was also used, resulting in 71.43% and 81.25% accuracies in distinguishing metastatic from primary tumors and gliomas from meningiomas, respectively. LSFT improved PNN performance, increased class separability and resulted in dimensionality reduction.     

Exhaustive and heuristic search approaches for learning a software defect prediction model

In this paper, we propose a software defect prediction model learning problem (SDPMLP) where a classification model selects appropriate relevant inputs, from a set of all available inputs, and learns the classification function. We show that the SDPMLP is a combinatorial optimization problem with factorial complexity, and propose two hybrid exhaustive search and probabilistic neural network (PNN), and simulated annealing (SA) and PNN procedures to solve it. For small size SDPMLP, exhaustive search PNN works well and provides an (all) optimal solution(s). However, for large size SDPMLP, the use of exhaustive search PNN approach is not pragmatic and only the SA–PNN allows us to solve the SDPMLP in a practical time limit. We compare the performance of our hybrid approaches with traditional classification algorithms and find that our hybrid approaches perform better than traditional classification algorithms.     

Pyramidal neural networks with evolved variable receptive fields

Pyramidal neural networks (PNN) are computational systems inspired by the concept of receptive fields from the human visual system. These neural networks are designed for implicit feature extraction and have been applied in pattern recognition applications. In the original approach, the size of the receptive field within the same 2D layer is a constant parameter, while in the human visual system, the receptive field size is variable. This paper proposes a PNN with variable receptive fields determined by an evolutionary algorithm, called variable pyramidal neural network with evolutionary algorithms. We observed from experiments aiming at detecting faces in images that our approach can achieve better classification rates than the original PNN. We also observed that regions with more information (such as nose and eyes) are more emphasized by variable receptive fields. These results confirm the application of intelligent algorithms to determine adjustable receptive fields in neural networks is useful to find out relevant information for recognition task. Besides, the model is comparable to biological systems regarding the flexibility assigned to receptive fields.

     

Temporal updating scheme for probabilistic neural network withapplication to satellite cloud classification

In cloud classification from satellite imagery, temporal change in the images is one of the main factors that causes degradation in the classifier performance. In this paper, a novel temporal updating approach is developed for probabilistic neural network (PNN) classifiers that can be used to track temporal changes in a sequence of images. This is done by utilizing the temporal contextual information and adjusting the PNN to adapt to such changes. Whenever a new set of images arrives, an initial classification is first performed using the PNN updated up to the last frame while at the same time, a prediction using Markov chain models is also made based on the classification results of the previous frame. The results of both the old PNN and the predictor are then compared. Depending on the outcome, either a supervised or an unsupervised updating scheme is used to update the PNN classifier. Maximum likelihood (ML) criterion is adopted in both the training and updating schemes. The proposed scheme is examined on both a simulated data set and the Geostationary Operational Environmental Satellite (GOES) 8 satellite cloud imagery data. These results indicate the improvements in the classification accuracy when the proposed scheme is used.     

On the generalization ability of neural network classifiers

This correspondence presents a method for evaluation of artificial neural network (ANN) classifiers. In order to find the performance of the network over all possible input ranges, a probabilistic input model is defined. The expected error of the output over this input range is taken as a measure of generalization ability. Two essential elements for carrying out the proposed evaluation technique are estimation of the input probability density and numerical integration. A nonparametric method, which depends on the nearest M neighbors, is used to locally estimate the distribution around each training pattern. An orthogonalization procedure is utilized to determine the covariance matrices of local densities. A Monte Carlo method is used to perform the numerical integration. The proposed evaluation technique has been used to investigate the generalization ability of back propagation (BP), radial basis function (RBF) and probabilistic neural network (PNN) classifiers for three test problems     

基于神经网络的变压器故障诊断方法研究

针对概率神经网络(PNN)模型强大的非线性分类能力,PNN能够很好地对变压器故障进行分类;文章通过对PNN神经网络的结构和原理的分析,应用PNN概率神经网络方法对变压器故障进行诊断;通过实例仿真表明,PNN网络的训练时间比BP网络少,比之预测准确度也要高,而且还具有高度的泛化能力,这使得PNN网络可以有效地运用到变压器故障诊断中,具有一定的可操作性。     

用过程神经网络和遗传算法实现系统逆向求解

对于多输入多输出系统,针对如何根据系统模型和期望输出反求系统输入的问题,本文提出了一种基于过程神经网络和遗传算法相结合的方法.首先根据实际系统的领域知识和学习样本集,建立满足系统实际输入输出映射关系的正向过程神经网络.然后按照系统在过程区间的某一期望输出,用过程神经网络的输出误差构造适应度函数,用遗传算法逆向确定系统的过程输入信号,使该输入信号满足已建立的正向过程映射关系,从而完成系统的逆向过程控制.文中给出了具体的实现算法并给出了此方法的一个应用实例.     

A nodal link perceptron network with applications to control of anonholonomic system

A new perceptron neural network (PNN) for functional approximation and control of a general class of nonlinear systems is introduced. The basic structure of the network along with the conditions for its exponential convergence under a suitable training law are derived. A novel discrete-time control strategy is formulated that employs the PNN for direct online estimation of the feedforward control input. The developed controller can be applied to both discrete- and continuous-time plants. Unlike most of the existing direct adaptive or learning schemes, the nonlinear plant is not assumed to be feedback linearizable. The developed controller is then applied for tracking control of a nonholonomic (free-flying) robot. The simulation results of this application demonstrate a perfect tracking performance after the network is fully trained.     

基于气体传感器阵列和非线性信号分析技术的龙井茶品质检测方法研究

本文研究了一种基于传感器阵列信号分析的龙井茶品质检测技术,采用多气体传感器阵列构建检测平台,实验检测不同储存时间的龙井茶样品,并对传感器阵列信号开展信号分析。为了进一步优化传感器阵列检测龙井茶品质的准确性,对传感器阵列参数优化,得到优化之后的阵列,优化后的传感器阵列具有更高的准确性。采用载荷分析（Loadings）、归一化处理进行数据的预处理。实验采用模糊c均值聚类（FCM）、k近邻函数（KNN）和概率神经网络（PNN）三种方法对传感器阵列检测信息进行了模式识别,以评估所构建系统的检测精度。结果表明三种方法的识别正确率分别为90.83%,90%和93.3%。结果表明KNN和PNN针对气体传感器阵列检测龙井茶品质领域均呈现了较好的模式识别结果。以上结果证明该系统具有较好的检测精度,随机共振系统输出相关系数曲线可以较好的区分不同茶叶样品,并且依托互相关系数特征峰值构建了其品质分析模型。     

A perceptron network for functional identification and control ofnonlinear systems

Tracking control of a general class of nonlinear systems using a perceptron neural network (PNN) is presented. The basic structure of the PNN and its training law are first derived. A novel discrete-time control strategy is introduced that employs the PNN for direct online estimation of the required feedforward control input. The developed controller can be applied to both discrete- and continuous-time plants. Unlike most of the existing direct adaptive or learning schemes, the nonlinear plant is not assumed to be feedback linearizable. The stability of the neural controller under ideal conditions and its robust stability to inexact modeling information are rigorously analyzed.