Conception of complex probabilistic neural network system for classification of partial discharge patterns using multifarious inputs

Pattern recognition has a long history within electrical engineering but has recently become much more widespread as the automated capture of signal and images has been cheaper. Very many of the application of neural networks are to classification, and so are within the field of pattern recognition and classification. In this paper, we explore how probabilistic neural networks fit into the earlier framework of pattern recognition of partial discharge patterns since the PD patterns are an important tool for diagnosis of HV insulation systems. Skilled humans can identify the possible insulation defects in various representations of partial discharge (PD) data. One of the most widely used representation is phase resolved PD (PRPD) patterns. Also this paper describes a method for the automated recognition of PRPD patterns using a novel complex probabilistic neural network system for the actual classification task. The efficacy of composite neural network developed using probabilistic neural network is examined.     

Structure damage diagnosis using neural network and feature fusion

A structure damage diagnosis method combining the wavelet packet decomposition, multi-sensor feature fusion theory and neural network pattern classification was presented. Firstly, vibration signals gathered from sensors were decomposed using orthogonal wavelet. Secondly, the relative energy of decomposed frequency band was calculated. Thirdly, the input feature vectors of neural network classifier were built by fusing wavelet packet relative energy distribution of these sensors. Finally, with the trained classifier, damage diagnosis and assessment was realized. The result indicates that, a much more precise and reliable diagnosis information is obtained and the diagnosis accuracy is improved as well.     

A new watermarking approach based on probabilistic neural network in wavelet domain

A novel scheme of digital image watermarking based on the combination of dual-tree wavelet transform (DTCWT) and probabilistic neural network is proposed in this paper. Firstly, the original image is decomposed by DTCWT, and then the watermark bits are added to the selected coefficients blocks. Because of the learning and adaptive capabilities of neural networks, the trained neural networks can recover the watermark from the watermarked images. Experimental results show that the proposed scheme has good performance against several attacks.     

A hybrid intrusion detection system design for computer network security

Intrusions detection systems (IDSs) are systems that try to detect attacks as they occur or after the attacks took place. IDSs collect network traffic information from some point on the network or computer system and then use this information to secure the network. Intrusion detection systems can be misuse-detection or anomaly detection based. Misuse-detection based IDSs can only detect known attacks whereas anomaly detection based IDSs can also detect new attacks by using heuristic methods. In this paper we propose a hybrid IDS by combining the two approaches in one system. The hybrid IDS is obtained by combining packet header anomaly detection (PHAD) and network traffic anomaly detection (NETAD) which are anomaly-based IDSs with the misuse-based IDS Snort which is an open-source project.The hybrid IDS obtained is evaluated using the MIT Lincoln Laboratories network traffic data (IDEVAL) as a testbed. Evaluation compares the number of attacks detected by misuse-based IDS on its own, with the hybrid IDS obtained combining anomaly-based and misuse-based IDSs and shows that the hybrid IDS is a more powerful system.     

Web document clustering using a hybrid neural network

The list of documents returned by Internet search engines in response to a query these days can be quite overwhelming. There is an increasing need for organising this information and presenting it in a more compact and efficient manner. This paper describes a method developed for the automatic clustering of World Wide Web documents, according to their relevance to the user’s information needs, by using a hybrid neural network. The objective is to reduce the time and effort the user has to spend to find the information sought after. Clustering documents by features representative of their contents—in this case, key words and phrases—increases the effectiveness and efficiency of the search process. It is shown that a two-dimensional visual presentation of information on retrieved documents, instead of the traditional linear listing, can create a more user-friendly interface between a search engine and the user.     

多传感器数据融合系统中联合概率数据互联算法的研究

概述了多传感器数据融合系统中的联合概率数据互联算法，给出了MSJPDA的两种处理结构，分析了其算法的复杂度。并在此基础上，结合B．zhou提出的直接概率计算和近似概率计算的方法，提出了一种基于近似聚的近似概率数据互联算法(MSJPDA)，通过仿真研究以及和最近邻法所做的比较表明，该方法确实能提高在密集情况下的数据融合精度，算法耗时与最近邻法相差不大，精确度接近完全概率互联算法。     

A novel Parzen probabilistic neural network based noncoherent detection algorithm for distributed ultra-wideband sensors

Ultra-wideband (UWB) has been widely recommended for significant commercial and military applications. However, the well-derived coherent structures for UWB signal detection are either computationally complex or hardware impractical in the presence of the intensive multipath propagations. In this article, based on the nonparametric Parzen window estimator and the probabilistic neural networks, we suggest a low-complexity and noncoherent UWB detector in the context of distributed wireless sensor networks (WSNs). A novel characteristic spectrum is firstly developed through a sequence of blind signal transforms. Then, from a pattern recognition perspective, four features are extracted from it to fully exploit the inherent property of UWB multipath signals. The established feature space is further mapped into a two-dimensional plane by feature combination in order to simplify algorithm complexity. Consequently, UWB signal detection is formulated to recognize the received patterns in this formed 2-D feature plane. With the excellent capability of fast convergence and parallel implementation, the Parzen Probabilistic Neural Network (PPNN) is introduced to estimate a posteriori probability of the developed patterns. Based on the underlying Bayesian rule of PPNN, the asymptotical optimal decision bound is finally determined in the feature plane. Numerical simulations also validate the advantages of our proposed algorithm.     

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.     

A modal specification theory for components with data

Modal specification is a well-known formalism used as an abstraction theory for transition systems. Modal specifications are transition systems equipped with two types of transitions: must-transitions that are mandatory to any implementation, and may-transitions that are optional. The duality of transitions allows for developing a unique approach for both logical and structural compositions, and eases the step-wise refinement process for building implementations. We propose Modal Specifications with Data (MSDs), the first modal specification theory with explicit representation of data. Our new theory includes the most commonly seen ingredients of a specification theory; that is parallel composition, conjunction and quotient. As MSDs are by nature potentially infinite-state systems, we propose symbolic representations based on effective predicates. Our theory serves as a new abstraction-based formalism for transition systems with data.     

A modal learning adaptive function neural network applied to handwritten digit recognition

A novel combination of the adaptive function neural network (ADFUNN) and on-line snap-drift learning is presented in this paper and applied to optical and pen-based recognition of handwritten digits [E. Alpaydin, F. Alimoglu for Optical Recognition of Handwritten Digits and E. Alpaydin, C. Kaynak for Pen-Based Recognition of Handwritten Digits http://www.ics.uci.edu/~mlearn/databases/optdigits/http://www.ics.uci.edu/~mlearn/databases/pendigits/]. Snap-drift [S.W. Lee, D. Palmer-Brown, C.M. Roadknight, Performance-guided neural network for rapidly self-organising active network management (Invited Paper), Journal of Neurocomputing, 61C, 2004, pp. 5-20] employs the complementary concepts of common (intersection) feature learning (called snap) and LVQ (drift towards the input patterns) learning, and is a fast, unsupervised method suitable for on-line learning and non-stationary environments where new patterns are continually introduced. ADFUNN [M. Kang, D. Palmer-Brown, An adaptive function neural network (ADFUNN) for phrase recognition, in: The International Joint Conference on Neural Networks (IJCNN05), Montréal, Canada, 2005, D. Palmer-Brown, M. Kang, ADFUNN: An adaptive function neural network, in: The 7th International Conference on Adaptive and Natural Computing Algorithms (ICANNGA05), Coimbra, Portugal, 2005] is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning algorithm. It has recently been applied to the Iris dataset, and a natural language phrase recognition problem, exhibiting impressive generalisation classification ability with no hidden neurons. The unsupervised single layer snap-drift is effective in extracting distinct features from the complex cursive-letter datasets, and the supervised single layer ADFUNN is capable of solving linearly inseparable problems rapidly. In combination within one network (SADFUNN), these two methods are more powerful and yet simpler than MLPs, at least on this problem domain. We experiment on SADFUNN with two handwritten digits datasets problems from the UCI Machine Learning repository. The problems are learned rapidly and higher generalisation results are achieved than with a MLP.     

A neural network approach for data masking

In this letter we present a neural network based data masking solution, in which the database information remains internally consistent yet is not inadvertently exposed in an interpretable state. The system differs from the classic data masking in the sense that it can understand the semantics of the original data and mask it using a neural network which is a priori trained by some rules. Our adaptive data masking (ADM) concentrates on data masking techniques such as shuffling, substitution, masking and number variance in an intelligent fashion with the help of adaptive neural network. The very nature of being adaptive makes data masking easier and content agnostic, and thus finds place in various vertical domains and systems.     

A hybrid model of partial least squares and neural network for traffic incident detection

Development of a universal freeway incident detection algorithm is a task that remains unfulfilled and many promising approaches have been recently explored. The partial least squares (PLS) method and artificial neural network (NN) were found in previous studies to yield superior incident detection performance. In this article, a hybrid model which combines PLS and NN is developed to detect automatically traffic incident. A real traffic data set collected from motorways A12 in the Netherlands is presented to illustrate such an approach. Data cleansing has been introduced to preprocess traffic data sets to improve the data quality in order to increase the veracity and reliability of incident model. The detection performance is evaluated by the common criteria including detection rate, false alarm rate, mean time to detection, classification rate and the area under the curve (AUC) of the receiver operating characteristic. Computational results indicate that the hybrid approach is capable of increasing detection performance comparing to PLS, and simplifying the NN structure for incident detection. The hybrid model is a promising alternative to the usual PLS or NN for incident detection.     

基于BP神经网络的多传感器数据融合技术优化

传统的数据融合算法要求获得比较精确的对象数学模型,对于复杂的难于建立模型的场合无法适用。为解决上述问题,提出了一种基于BP神经网络算法的多传感器数据融合方法,对对象的先验要求不高,具有较强的自适应能力。仿真结果表明,采用BP神经网络对传感器数据进行融合处理大大提高了传感器的稳定性及其精度,效果良好。     

基于人工神经网络的压力传感器三维数据融合

针对压力传感器对温度变化和电流波动的交叉灵敏度问题,采用径向基函数(RBF)人工神经网络法对其进行数据融合处理,详细讨论了网络的训练过程和数据融合过程,消除温度和电流对压力传感器的影响。仿真结果表明:当温度变化48.5℃,电流波动3%时,经RBF神经网络数据融合后,压力波动为0.544%,大大降低了交叉干扰,提高传感器的稳定性及其精度,满足在线融合的需要。     

基于可拓神经网络的火灾探测算法

为解决传统单一传感器式的火灾探测器容易造成火灾报警的漏报和误报的问题,采用多传感器信息融合技术,将温度、烟雾浓度和CO浓度等多个参数相结合,进行综合分析,对火灾进行早期预测。采用可拓神经网络作为数据融合算法,以温度、烟雾浓度、CO气体浓度三个物理参量作为输入,以三种火灾预警等级作为输出。通过仿真分析结果表明：火灾正确识别率很高,达到93.9%以上。同时通过与传统BP神经网络的对比,表明可拓神经网络在数据融合的速度和可靠性上有突出的优势,从而使可拓神经网络实际应用于火灾早期预测成为可能。     

多层神经网络在入侵检测中的应用

对多层ANN的结构和向后传播算法进行了设计,提出了移动窗口和事件子视图等概念,通过提取审计事件类型的方法,采样了ANN的训练数据和测试数据.具体实现了设计算法,并用该软件分别对UNIX和Windows XP两个操作系统的数据进行了实验.实验结果表明,多层ANN可以作为一个入侵检测的模型和技术应用于入侵检测之中.     

Classification of MRI brain images using combined wavelet entropy based spider web plots and probabilistic neural network

Magnetic resonance imaging (MRI) is a non-invasive diagnostic tool very frequently used for brain imaging. The classification of MRI images of normal and pathological brain conditions pose a challenge from technological and clinical point of view, since MR imaging focuses on soft tissue anatomy and generates a large information set and these can act as a mirror reflecting the conditions of the brain. A new approach by integrating wavelet entropy based spider web plots and probabilistic neural network is proposed for the classification of MRI brain images. The two step method for classification uses (1) wavelet entropy based spider web plots for the feature extraction and (2) probabilistic neural network for the classification. The spider web plot is a geometric construction drawn using the entropy of the wavelet approximation components and the areas calculated are used as feature set for classification. Probabilistic neural network provides a general solution to the pattern classification problems and the classification accuracy is found to be 100%.     

A data clustering algorithm for stratified data partitioning in artificial neural network

The statistical properties of training, validation and test data play an important role in assuring optimal performance in artificial neural networks (ANNs). Researchers have proposed optimized data partitioning (ODP) and stratified data partitioning (SDP) methods to partition of input data into training, validation and test datasets. ODP methods based on genetic algorithm (GA) are computationally expensive as the random search space can be in the power of twenty or more for an average sized dataset. For SDP methods, clustering algorithms such as self organizing map (SOM) and fuzzy clustering (FC) are used to form strata. It is assumed that data points in any individual stratum are in close statistical agreement. Reported clustering algorithms are designed to form natural clusters. In the case of large multivariate datasets, some of these natural clusters can be big enough such that the furthest data vectors are statistically far away from the mean. Further, these algorithms are computationally expensive as well. We propose a custom design clustering algorithm (CDCA) to overcome these shortcomings. Comparisons are made using three benchmark case studies, one each from classification, function approximation and prediction domains. The proposed CDCA data partitioning method is evaluated in comparison with SOM, FC and GA based data partitioning methods. It is found that the CDCA data partitioning method not only perform well but also reduces the average CPU time.     

A region-based multi-sensor image fusion scheme using pulse-coupled neural network

For most image fusion algorithms split relationship among pixels and treat them more or less independently, this paper proposes a region-based image fusion scheme using pulse-coupled neural network (PCNN), which combines aspects of feature and pixel-level fusion. The basic idea is to segment all different input images by PCNN and to use this segmentation to guide the fusion process. In order to determine PCNN parameters adaptively, this paper brings forward an adaptive segmentation algorithm based on a modified PCNN with the multi-thresholds determined by a novel water region area method. Experimental results demonstrate that the proposed fusion scheme has extensive application scope and it outperforms the multi-scale decomposition based fusion approaches, both in visual effect and objective evaluation criteria, particularly when there is movement in the objects or mis-registration of the source images.     

Ensemble of hybrid neural network learning approaches for designing pharmaceutical drugs

Designing drugs is a current problem in the pharmaceutical research. By designing a drug we mean to choose some variables of drug formulation (inputs), for obtaining optimal characteristics of drug (outputs). To solve such a problem we propose an ensemble of three learning algorithms namely an evolutionary artificial neural network, Takagi-Sugeno neuro-fuzzy system and an artificial neural network. The ensemble combination is optimized by a particle swarm optimization algorithm. The experimental data were obtained from the Laboratory of Pharmaceutical Techniques of the Faculty of Pharmacy in Cluj-Napoca, Romania. Bootstrap techniques were used to generate more samples of data since the number of experimental data was low due to the costs and time durations of experimentations. Experiment results indicate that the proposed methods are efficient.