Advanced self-organizing polynomial neural network

In this paper, we introduce a concept of advanced self-organizing polynomial neural network (Adv_SOPNN). The SOPNN is a flexible neural architecture whose structure is developed through a modeling process. But the SOPNN has a fatal drawback; it cannot be constructed for nonlinear systems with few input variables. To relax this limitation of the conventional SOPNN, we combine a fuzzy system and neural networks with the SOPNN. Input variables are partitioned into several subspaces by the fuzzy system or neural network, and these subspaces are utilized as new input variables to the SOPNN architecture. Two types of the advanced SOPNN are obtained by combining not only the fuzzy rules of a fuzzy system with SOPNN but also the nodes in a hidden layer of neural networks with SOPNN into one methodology. The proposed method is applied to the nonlinear system with two inputs, which cannot be identified by conventional SOPNN to show the performance of the advanced SOPNN. The results show that the proposed method is efficient for systems with limited data set and a few input variables and much more accurate than other modeling methods with respect to identification error.     

Category classification method using a self-organizing neural network

We apply a new category classification method to remote sensing data. This is a supervised and non-parametric method and employs both a selforganizing neural network and a k -nearest neighbour method. One of the features of the category is represented by the neuron weights after training the neural network based on a competitive learning role. From experimental results, we can see that the proposed method obtains superior classification results compared to other methods.     

GenSoFNN: a generic self-organizing fuzzy neural network

Existing neural fuzzy (neuro-fuzzy) networks proposed in the literature can be broadly classified into two groups. The first group is essentially fuzzy systems with self-tuning capabilities and requires an initial rule base to be specified prior to training. The second group of neural fuzzy networks, on the other hand, is able to automatically formulate the fuzzy rules from the numerical training data. No initial rule base needs to be specified prior to training. A cluster analysis is first performed on the training data and the fuzzy rules are subsequently derived through the proper connections of these computed clusters. However, most existing neural fuzzy systems (whether they belong to the first or second group) encountered one or more of the following major problems. They are (1) inconsistent rule-base; (2) heuristically defined node operations; (3) susceptibility to noisy training data and the stability-plasticity dilemma; and (4) needs for prior knowledge such as the number of clusters to be computed. Hence, a novel neural fuzzy system that is immune to the above-mentioned deficiencies is proposed in this paper. This new neural fuzzy system is named the generic self-organizing fuzzy neural network (GenSoFNN). The GenSoFNN network has strong noise tolerance capability by employing a new clustering technique known as discrete incremental clustering (DIC). The fuzzy rule base of the GenSoFNN network is consistent and compact as GenSoFNN has built-in mechanisms to identify and prune redundant and/or obsolete rules. Extensive simulations were conducted using the proposed GenSoFNN network and its performance is encouraging when benchmarked against other neural and neural fuzzy systems.     

IP core implementation of a self-organizing neural network

This paper reports on the design issues and subsequent performance of a soft intellectual property (IP) core implementation of a self-organizing neural network. The design is a development of a previous 0.65-/spl mu/m single silicon chip providing an array of 256 neurons, where each neuron stores a 16 element reference vector. Migrating the design to a soft IP core presents challenges in achieving the required performance as regards area, power, and clock speed. This same migration, however, offers opportunities for parameterizing the design in a manner which permits a single soft core to meet the requirements of many end users. Thus, the number of neurons within the single instruction multiple data (SIMD) array, the number of elements per reference vector, and the number of bits of each such element are defined by synthesis time parameters. The construction of the SIMD array of neurons is presented including performance results as regards power, area, and classifications per second . For typical parameters (256 neurons with 16 elements per reference vector) the design provides over 2 000 000 classifications per second using a mainstream 0.18-/spl mu/m digital process. A RISC processor, the array controller (AC), provides both the instruction stream and data to the SIMD array of neurons and an interface to a host processor. The design of this processor is discussed with emphasis on the control aspects which permit supply of a continuous instruction stream to the SIMD array and a flexible interface with the host processor.     

结构自适应的半监督自组织过程神经网络

针对时域空间中模式识别、聚类分析和未标记样本的有效利用问题,提出一种基于半监督学习的网络结构自适应的二维自组织过程神经网络模型和算法。通过构建可度量时变样本间相似性的广义Fréchet距离,利用部分已标记动态样本的类别信息和过程特征,采用奖励-惩罚更新规则,根据网络学习目标函数,对网络二维平面竞争层节点进行动态拆分或合并,实现网络结构的自适应调整和样本的有效聚类。仿真实验结果验证了模型和算法的有效性。     

Approximate reconstruction of PET data with a self-organizing neural network.

Self-organization was observed using the algorithm of Kohonen with an original "distance" adapted to stimuli resulting from coincident detections of electron-positron annihilation photon pairs. This has led to a method for approximate reconstruction of two-dimensional positron emission tomography (2-D PET) images that is totally independent of the number of detectors. To obtain meaningful information about the distribution of the radioactive tracer, a toroidal architecture must be used for the network.     

自组织增量神经网络IDS研究

理想的网络入侵检测系统(IDS)是无监督学习的、在线学习的。现有的满足这两个标准的方法训练速度较慢,无法保证入侵检测系统所需要的低丢包率。为了提高训练速度,提出一种基于改进的自组织增量神经网络(improved SOINN)的网络异常检测方法,用于在线地、无监督地训练网络数据分类器;并提出使用三种数据精简(Data Reduction)的方法,包括随机子集选取,k-means聚类和主成分分析的方法,来进一步加速改进的SOINN的训练。实验结果表明,提出的方法在保持较高检测率的前提下,减少了训练时间。     

Optimization of self-organizing polynomial neural networks

The main disadvantage of self-organizing polynomial neural networks (SOPNN) automatically structured and trained by the group method of data handling (GMDH) algorithm is a partial optimization of model weights as the GMDH algorithm optimizes only the weights of the topmost (output) node. In order to estimate to what extent the approximation accuracy of the obtained model can be improved the particle swarm optimization (PSO) has been used for the optimization of weights of all node-polynomials. Since the PSO is generally computationally expensive and time consuming a more efficient Levenberg–Marquardt (LM) algorithm is adapted for the optimization of the SOPNN. After it has been optimized by the LM algorithm the SOPNN outperformed the corresponding models based on artificial neural networks (ANN) and support vector method (SVM). The research is based on the meta-modeling of the thermodynamic effects in fluid flow measurements with time-constraints. The outstanding characteristics of the optimized SOPNN models are also demonstrated in learning the recurrence relations of multiple superimposed oscillations (MSO).     

Manufacturing cell formation using a new self-organizing neural network

Cellular manufacturing consists of grouping similar machines in cells and dedicating each of them to process a family of similar part types. In this paper, grouping parts into families and machines into cells is done in two steps: first, part families are formed and then machines are assigned. In phase one, weighted similarity coefficients are computed and parts are clustered using a new self-organizing neural network. In phase two, a linear network flow model is used to assign machines to families. To test the proposed approach, different problems from the literature have been solved. As benchmarks we have used a Maximum Spanning Tree heuristic.     

A recurrent self-organizing neural fuzzy inference network

A recurrent self-organizing neural fuzzy inference network (RSONFIN) is proposed. The RSONFIN is inherently a recurrent multilayered connectionist network for realizing the basic elements and functions of dynamic fuzzy inference, and may be considered to be constructed from a series of dynamic fuzzy rules. The temporal relations embedded in the network are built by adding some feedback connections representing the memory elements to a feedforward neural fuzzy network. Each weight as well as node in the RSONFIN has its own meaning and represents a special element in a fuzzy rule. There are no hidden nodes initially in the RSONFIN. They are created online via concurrent structure identification and parameter identification. The structure learning together with the parameter learning forms a fast learning algorithm for building a small, yet powerful, dynamic neural fuzzy network. Two major characteristics of the RSONFIN can thus be seen: 1) the recurrent property of the RSONFIN makes it suitable for dealing with temporal problems and 2) no predetermination, like the number of hidden nodes, must be given, since the RSONFIN can find its optimal structure and parameters automatically and quickly. Moreover, to reduce the number of fuzzy rules generated, a flexible input partition method, the aligned clustering-based algorithm, is proposed. Various simulations on temporal problems are done and performance comparisons with some existing recurrent networks are also made. Efficiency of the RSONFIN is verified from these results.     

Feature recognition using ART2: a self-organizing neural network

A self-organizing neural network, ART2, based on adaptive resonance theory (ART), is applied to the problem of feature recognition from a boundary representation (B-rep) solid model. A modified face score vector calculation scheme is adopted to represent the features by continuous-valued vectors, suitable to be input to the network. The face score is a measure of the face complexity based upon the convexity or concavity of the surrounding region. The face score vector depicts the topological relations between a face and its neighbouring faces. The ART2 network clusters similar features together. The similarity of the features within a cluster is controlled by a vigilance parameter. A new feature presented to the net is associated with one of the existing clusters, if the feature is similar to the members of the cluster. Otherwise, the net creates a new cluster. An algorithm of the ART2 network is implemented and tested with nine different features. The results obtained indicate that the network has significant potential for application to the problem of feature recognition.     

Blind source separation based on self-organizing neural network

This contribution describes a neural network that self-organizes to recover the underlying original sources from typical sensor signals. No particular information is required about the statistical properties of the sources and the coefficients of the linear transformation, except the fact that the source signals are statistically independent and nonstationary. This is often true for real life applications. We propose an online learning solution using a neural network and use the nonstationarity of the sources to achieve the separation. The learning rule for the network's parameters is derived from the steepest descent minimization of a time-dependent cost function that takes the minimum only when the network outputs are uncorrelated with each other. In this process divide the problem into two learning problems one of which is solved by an anti-Hebbian learning and the other by an Hebbian learning process. We also compare the performance of our algorithm with other solutions to this task.     

一种改进的动态二叉树的自组织神经网络算法

分析了自组织神经网络各种改进算法的优缺点,详细设计和实现了一种基于改进动态二叉树的自组织映射树（DBTSONN）。在改进动态二叉树中神经元节点可以自动生长和剪除,无需在训练前预先确定自组织神经网络结构。DBTSONN1算法采用单路径自组织树中搜索最匹配叶节点（获胜神经元）,DBTSONN2算法考虑了获胜神经元节点所在自组织二叉树的层次,采用双向搜索获胜叶节点,提高了搜索效率。实验结果表明,该算法在向量量化器设计方面具有很好的效果。     

A noisy self-organizing neural network with bifurcation dynamics for combinatorial optimization

The self-organizing neural network (SONN) for solving general "0-1" combinatorial optimization problems (COPs) is studied in this paper, with the aim of overcoming existing limitations in convergence and solution quality. This is achieved by incorporating two main features: an efficient weight normalization process exhibiting bifurcation dynamics, and neurons with additive noise. The SONN is studied both theoretically and experimentally by using the N-queen problem as an example to demonstrate and explain the dependence of optimization performance on annealing schedules and other system parameters. An equilibrium model of the SONN with neuronal weight normalization is derived, which explains observed bands of high feasibility in the normalization parameter space in terms of bifurcation dynamics of the normalization process, and provides insights into the roles of different parameters in the optimization process. Under certain conditions, this dynamical systems view of the SONN reveals cascades of period-doubling bifurcations to chaos occurring in multidimensional space with the annealing temperature as the bifurcation parameter. A strange attractor in the two-dimensional (2-D) case is also presented. Furthermore, by adding random noise to the cost potentials of the network nodes, it is demonstrated that unwanted oscillations between symmetrical and "greedy" nodes can be sufficiently reduced, resulting in higher solution quality and feasibility.     

基于自组织神经网络的QRS波聚类方法

为提高查看大量数据动态心电(ECG)图时的效率,将波形聚类,采用埃尔米特函数和自组织神经网络,实现了室性早搏占比高情况下的心电波形聚类算法.使用MIT-BIH心率失常数据库,利用埃尔米特函数分解QRS波形为QRS向量,将所有QRS向量输入自组织神经网络进行分类.使用特征向量元素分析聚类结果,用阳性率指标对结果进行统计,平均真阳性率为91.2％,假阳性率为1.03％,验证了基于自组织神经网络的心电聚类算法的有效性.达到了将正常心搏和室性早搏心搏聚类的目标.     

A multilayered self-organizing artificial neural network forinvariant pattern recognition

An artificial neural network that self-organizes to recognize various images presented as a training set is described. One application of the network uses multiple functionally disjoint stages to provide pattern recognition that is invariant to translations of the object in the image plane. The general form of the network uses three stages that perform the functionally disjoint tasks of preprocessing, invariance, and recognition. The preprocessing stage is a single layer of processing elements that performs dynamic thresholding and intensity scaling. The invariance stage is a multilayered connectionist implementation of a modified Walsh-Hadamard transform used for generating an invariant representation of the image. The recognition stage is a multilayered self-organizing neural network that learns to recognize the representation of the input image generated by the invariance stage. The network can successfully self-organize to recognize objects without regard to the location of the object in the image field and has some resistance to noise and distortions     

Prediction of activated sludge bulking based on a self-organizing RBF neural network

Despite extensive research that has been done on sludge bulking, it remains a widespread problem in the operation of activated sludge processes, which brings severe economic and environmental consequences. In this study, a self-organizing radial basis function (SORBF) neural network method is utilized to predict the evolution of the sludge volume index (SVI). The hidden nodes in the SORBF neural network can be grown or pruned based on the node activity (NA) and mutual information (MI) to achieve the appropriate network complexity and maintain overall computational efficiency. The growing and pruning criteria of the SORBF can vary its structure dynamically with the objective to enhance its performance. Moreover, the input–output selection to calculate the SVI values is also discussed. The variables with key relations to the sludge bulking are used as the inputs for the SVI. Finally, the SORBF neural network is applied to the activated sludge wastewater treatment processes (WWTPs) for predicting the SVI, and then for predicting the sludge bulking. Experimental results show the excellent performance of the SORBF method. The performance comparison demonstrates the effectiveness of the proposed SORBF.     

Optimal combination of document binarization techniques using a self-organizing map neural network

This paper proposes an integrated system for the binarization of normal and degraded printed documents for the purpose of visualization and recognition of text characters. In degraded documents, where considerable background noise or variation in contrast and illumination exists, there are many pixels that cannot be easily classified as foreground or background pixels. For this reason, it is necessary to perform document binarization by combining and taking into account the results of a set of binarization techniques, especially for document pixels that have high vagueness. The proposed binarization technique takes advantage of the benefits of a set of selected binarization algorithms by combining their results using a Kohonen self-organizing map neural network. Specifically, in the first stage the best parameter values for each independent binarization technique are estimated. In the second stage and in order to take advantage of the binarization information given by the independent techniques, the neural network is fed by the binarization results obtained by those techniques using their estimated best parameter values. This procedure is adaptive because the estimation of the best parameter values depends on the content of images. The proposed binarization technique is extensively tested with a variety of degraded document images. Several experimental and comparative results, exhibiting the performance of the proposed technique, are presented.