Transformations in machining. Part 1. enhancement of wavelet transformation neural network (WT-NN) combination with a preprocessor

Properly selected transformation methods obtain the most significant characteristics of metal cutting data efficiently and simplify the classification. Wavelet Transformation (WT) and Neural Networks (NN) combination was used to classify the experimental cutting force data of milling operations previously. Preprocessing (PreP) of the approximation coefficients of the WT is proposed just before the classification by using the Adaptive Resonance Theory (ART2) type NNs. Genetic Algorithm (GA) was used to estimate the weights of each coefficient of the PreP. The WT-PreP-NN (ART2) combination worked at lower vigilances by creating only a few meaningful categories without any errors. The WT-NN (ART2) combination could obtain the same error rate only if very high vigilances are used and many categories are allowed.     

基于自适应共振理论(ART)网络的机床设备实例的分类

阐述了自适应共振理论(ART)网络的原理及训练算法.利用ART网络良好的自组织,自学习,可塑性强的特点,提出基于神经网络的机床设备实例分类的策略.该方法求解简单快速,容易实现,效率高,在实际工程中具有良好的应用前景.     

基于RFS和ART的高光谱图像主成分提取方法

针对传统高光谱图像主成分提取方法受数据分布状态和噪声影响大的缺点,提出基于区域特征光谱的ART(Adaptive Resonance Theory)神经网络主成分提取算法.首先通过多方向阈值空间邻域聚类提取区域特征光谱作为ART的输入模式,利用ART网络的自适应特性获取地物光谱矢量特征,并通过对光谱矢量聚类完成图像的主成分提取.对高光谱图像仿真结果表明:通过提取区域特征光谱,神经网络的数据处理量减少了约97%;算法能够较准确地提取图像主成分且提取效果明显好于K-均值算法.     

基于递归小波与ART2网络的刀具状态智能监测

为实现刀具的实时状态监测,以超高斯函数为基础,构造出一类用递推公式进行小波变换的小波基,提出该系列小波基的优化方法,对其时频特性进行了分析.对刀具AE信号进行递归小波分解,提取特征并应用ART2网络识别刀具状态.结果表明,基于递归小波与ART2网络的刀具状态监测具有鲁棒性强、实时性好的特点.     

基于ART2神经网络的车辆感应波形识别的方法

在智能交通系统中,无论是在交通监控领域还是在不停车收费系统方面,对车辆进行自动分类都十分重要;环形线圈车辆检测器以其良好的适应性、稳定性和高效性在车辆监测方面得到了广泛的应用,同时利用同类型或同种车辆经过环形线圈产生轮廓相似的电磁感应波形这一特点也可以进行车型识别;对波形进行预处理,以波形轮廓的抽样、量化值作为特征向量,将特征向量作为ART2神经网络的输入向量,经ART2神经网络的自动聚类最终实现车辆感应波形的聚类与识别。     

3n镜像适应性随机测试算法

针对适应性随机测试中的边缘效应问题,借鉴镜像适应性随机测试(MART)的基本思想,在引入镜像距离的基础上,提出3n MART算法,通过改变候选用例与成功用例之间的距离判断策略,使其产生的用例在输入域中更均匀地分布。仿真实验结果证明,该算法可以较好地解决边缘效应问题,相比基于距离的适应性随机测试算法与MART算法,失效发现效率更高。     

模糊ART神经网络模型及其在图像识别中的应用

提出了采用低通过率波、去最小亮度和向量柱状图来提取人脸特征的方法,设计了模糊ART神经网络的结构、学习规则和识别算法,并采用模糊ART神经网络对向量柱状图生成的特征向量进行识别。仿真实验证明,通过调整神经网络的警戒参数值,不同的人具有不同的最大在线识别率,所有人平均的在线最大识别率可以达到89％。     

Growing fuzzy topology adaptive resonance theory models with a push-pull learning algorithm

A new incrementally growing neural network model, called the growing fuzzy topology ART (GFTART) model, is proposed based on integrating the conventional fuzzy ART model with the incremental topology-preserving mechanism of the growing cell structure (GCS) model. This is in addition, to a new training algorithm, called the push-pull learning algorithm. The proposed GFTART model has two purposes: First, to reduce the proliferation of incrementally generated nodes in the F2 layer by the conventional fuzzy ART model based on replacing each F2 node with a GCS. Second, to enhance the class-dependent clustering representation ability of the GCS model by including the categorization property of the conventional fuzzy ART model. In addition, the proposed push-pull training algorithm enhances the cluster discriminating property and partially improves the forgetting problem of the training algorithm in the GCS model.     

一种改进的基于 ART2神经网络的文字识别算法

为了解决 ART2神经网络的漂移问题,提出了一种改进的基于 ART2神经网络的文字分类和识别方法.此方法能够自主学习,收敛速度快,识别率和识别速度都比 BP神经网络高.实践证明,基于此设计的脱机手写体文字识别系统能对较规范的手写体文字进行识别,识别率达到85%.     

A Dynamic Network Model of the Color Visual Pathways for Attentive Recognition

A neural network architecture for the segmentation and recognition of colored and textured visual stimuli is presented. The architecture is based on the Boundary Contour System and Feature Contour System (BCS/FCS) of S. Grossberg and E. Mingolla. The architecture proposes a biologically-inspired mechanism for color processing based on antagonist interactions. It suggests how information from different modalities (i.e. color or texture) can be fused together to form a coherent segmentation of the visual scene. It identifies two stages of visual pattern recognition, namely, a global preattentive recognition of the visual scene followed by a local attentive recognition within a particular visual context. The global and local classification and recognition of visual stimuli use ART-type models of G. Carpenter and S. Grossberg for pattern learning and recognition based on color and texture. One example is presented corresponding to an figure-figure separation task. The architecture provides a mechanism for segmentation, categorization and recognition of images from different classes based on self-organizing principles of perception and pattern recognition.