Using fuzzy partitions to create fuzzy systems from input-outputdata and set the initial weights in a fuzzy neural network

We create a set of fuzzy rules to model a system from input-output data by dividing the input space into a set of subspaces using fuzzy partitions. We create a fuzzy rule for each subspace as the input space is being divided. These rules are combined to produce a fuzzy rule based model from the input-output data. If more accuracy is required, we use the fuzzy rule-based model to determine the structure and set the initial weights in a fuzzy neural network. This network typically trains in a few hundred iterations. Our method is simple, easy, and reliable and it has worked well when modeling large “real world” systems     

基于模糊逻辑带权重的模糊查询研究*

在已研究的模糊查询中,其逻辑连接均为and或or,具有一定的狭隘性,不符合自然语言表述的特点,也不能充分满足查询要求。引入模糊语言量词作为模糊逻辑连接词,同时引入权重,利用Zadeh 的模糊集合理论与SQL系统函数相结合,研究了基于模糊逻辑连接的带权重的模糊查询技术,进一步丰富了SQL模糊查询体系,提高了查询能力。     

A fuzzy neural network with fuzzy impact grades

Fuzzy rule derivation is often difficult and time-consuming, and requires expert knowledge. This creates a common bottleneck in fuzzy system design. In order to solve this problem, many fuzzy systems that automatically generate fuzzy rules from numerical data have been proposed. In this paper, we propose a fuzzy neural network based on mutual subsethood (MSBFNN) and its fuzzy rule identification algorithms. In our approach, fuzzy rules are described by different fuzzy sets. For each fuzzy set representing a fuzzy rule, the universe of discourse is defined as the summation of weighted membership grades of input linguistic terms that associate with the given fuzzy rule. In this manner, MSBFNN fully considers the contribution of input variables to the joint firing strength of fuzzy rules. Afterwards, the proposed fuzzy neural network quantifies the impacts of fuzzy rules on the consequent parts by fuzzy connections based on mutual subsethood. Furthermore, to enhance the knowledge representation and interpretation of the rules, a linear transformation from consequent parts to output is incorporated into MSBFNN so that higher accuracy can be achieved. In the parameter identification phase, the backpropagation algorithm is employed, and proper linear transformation is also determined dynamically. To demonstrate the capability of the MSBFNN, simulations in different areas including classification, regression and time series prediction are conducted. The proposed MSBFNN shows encouraging performance when benchmarked against other models.     

A neural fuzzy system with linguistic teaching signals

A neural fuzzy system learning with linguistic teaching signals is proposed. This system is able to process and learn numerical information as well as linguistic information. It can be used either as an adaptive fuzzy expert system or as an adaptive fuzzy controller. First, we propose a five-layered neural network for the connectionist realization of a fuzzy inference system. The connectionist structure can house fuzzy logic rules and membership functions for fuzzy inference. We use α-level sets of fuzzy numbers to represent linguistic information. The inputs, outputs, and weights of the proposed network can be fuzzy numbers of any shape. Furthermore, they can be hybrid of fuzzy numbers and numerical numbers through the use of fuzzy singletons. Based on interval arithmetics, two kinds of learning schemes are developed for the proposed system: fuzzy supervised learning and fuzzy reinforcement learning. Simulation results are presented to illustrate the performance and applicability of the proposed system     

一种定点数权值神经网络的优化方法及其应用

为了使得神经网络的应用符合嵌入式系统快速计算、存储量精简的要求,提出了一种定点数权值神经网络的优化方法。采用精度可调的比例数格式定点数表示神经网络的权值和阈值,用遗传算法对神经网络进行训练,并用最小二乘法对网络的非线性连续节点激励函数进行了线性离散化。将这种优化的神经网络应用于触摸屏校准。实验表明,采用该方法进行触摸屏校准比传统的校准方法具有更高的准确率。     

Adaptive fuzzy inference neural network

An adaptive fuzzy inference neural network (AFINN) is proposed in this paper. It has self-construction ability, parameter estimation ability and rule extraction ability. The structure of AFINN is formed by the following four phases: (1) initial rule creation, (2) selection of important input elements, (3) identification of the network structure and (4) parameter estimation using LMS (least-mean square) algorithm. When the number of input dimension is large, the conventional fuzzy systems often cannot handle the task correctly because the degree of each rule becomes too small. AFINN solves such a problem by modification of the learning and inference algorithm.     

改进的模糊CMAC神经网络

提出了一种改进的模糊CMAC神经网络（IFCMAC）,该神经网络是在经典的FCMAC神经网络的模糊后相连层和输出层之间引入了输入矢量的线性加权和来补偿逼近的误差,所以它的逼近精度得到提高,解决了CMAC系列神经网络逼近精度不高的弱点,在颅脑磁共振图像分割仿真实验中,把当前像素点的子图像的纹理特征和该像素点的灰度值作为该像素的特征向量,将该特征向量作为IFCMAC神经网络的输入,实验结果表明其具有较高的分割准确性。     

A reconfigurable fuzzy neural network with in-situ learning

Our reconfigurable fuzzy processor (RFP) implements both aggregative and referential operations. Its architecture combines structural and parametric flexibility in a network implementing RFPs as a collection of fuzzy neurons. A fuzzy neural network using a bidirectionally linked series of shared buses facilitates a modular and scalable design environment for the RFP. An appropriate interface, separate from the RFP neuron itself, promotes the reuse of the neuron design with alternative interconnection networks     

Mass lesion detection with a fuzzy neural network

This paper presents a novel fuzzy neural network (FNN) approach to detect malignant mass lesions on mammograms. The FNN is a self-adjusting and adaptive system. It is simple in structure and easy to incorporate experts’ knowledge and fuzzified factors in the detection of malignant mass lesions on mammograms. The FNN has four layers. The first layer is the input layer consisting of 4 fuzzy neurons. The second layer has 4 ordinary neurons. The third layer consists of N maximum fuzzy neurons. The number of fuzzy neurons, N, in the third layer is determined during the training process and varies with the network parameters and data distribution. The fourth layer has 2 maximum fuzzy neurons and one competitive fuzzy neuron. Mammograms were obtained from the digital database for screening mammography, DDSM. Six-hundred and seventy regions of interest (ROIs) were extracted from 100 mammograms. All extracted ROIs were randomly divided into two sets: training and testing sets. The co-occurrence matrix of each ROI was computed. Textural features were calculated at sizes of 256×256 and 768×768, respectively. The feature differences at these two image sizes were computed for each feature. These feature differences are very discriminant in differentiating between malignant masses and normal tissues regardless of lesion shape, size, and subtlety. After training, the FNN can correctly detect all malignant masses on mammograms in the testing group. The true-positive fraction (TPF) is 0.92 when the number of false positives (FP) is 1.33 per mammogram and 1.0 when the FP is 2.15 per mammogram. The proposed approach will be very useful for breast cancer control.     

Hermite插值神经网络权值和结构确定理论探讨*

为了克服BP神经网络固有的缺陷,基于Hermite插值理论,构造了一种新型的前向神经网络模型（即Hermite插值神经网络模型）。针对该网络模型,提出了一种基于矩阵伪逆的权值直接确定方法,并在此基础上探讨了隐神经元数目自动确定的方法（即网络结构自确定方法）。计算机仿真结果表明,相比于传统的BP神经网络,使用权值与结构双确定方法的Hermite插值神经网络具有更好的收敛速度和校验能力。同时,也验证了该神经网络良好的降噪和预测能力。     

Fuzzy wavelet neural network based on fuzzy clustering and gradient techniques for time series prediction

This paper presents the development of fuzzy wavelet neural network system for time series prediction that combines the advantages of fuzzy systems and wavelet neural network. The structure of fuzzy wavelet neural network (FWNN) is proposed, and its learning algorithm is derived. The proposed network is constructed on the base of a set of TSK fuzzy rules that includes a wavelet function in the consequent part of each rule. A fuzzy c-means clustering algorithm is implemented to generate the rules, that is the structure of FWNN prediction model, automatically, and the gradient-learning algorithm is used for parameter identification. The use of fuzzy c-means clustering algorithm with the gradient algorithm allows to improve convergence of learning algorithm. FWNN is used for modeling and prediction of complex time series and prediction of foreign-exchange rates. Exchange rates are dynamic process that changes every day and have high-order nonlinearity. The statistical data for the last 2 years are used for the development of FWNN prediction model. Effectiveness of the proposed system is evaluated with the results obtained from the simulation of FWNN-based systems and with the comparative simulation results of previous related models.     

一种自组织双模糊神经网络控制算法

针对传统模糊神经网络设计复杂、控制实时性滞后的问题,提出自组织双模糊神经网络算法。将样本数据进行聚类划分,形成原始的模糊隶属函数集;在神经网络的离线训练过程中,完善并优化模糊隶属函数和规则;采用双神经网络结构,在线工作时,一个神经网络完成在线学习任务,另一个神经网络完成工业控制任务;经过一定的系统周期,同步系统中两组神经网络的参数;提取完成控制任务的神经网络的输出作为算法的输出。应用于火箭发动机试验台控制系统中,表明算法能够提升控制系统中针对输入参数越界的鲁棒性,提高控制实时性,简化了模糊神经网络的设计复杂度。     

Feedforward neural network for blind equalization with PSK signals

Most of the cost functions used for blind equalization are nonconvex and nonlinear functions of tap weights, when implemented using linear transversal filter structures. Therefore, a blind equalization scheme with a nonlinear structure that can form nonconvex decision regions is desirable. The efficacy of complex-valued feedforward neural networks for blind equalization of linear and nonlinear communication channels has been confirmed by many studies. In this paper we present a complex valued neural network for blind equalization with M-ary phase shift keying (PSK) signals. The complex nonlinear activation functions used in the neural network are especially defined for handling the M-ary PSK signals. The training algorithm based on constant modulus algorithm (CMA) cost function is derived. The improved performance of the proposed neural network in both, stationary and nonstationary environments, is confirmed through computer simulations.     

On multistage fuzzy neural network modeling

In the past couple of years, there has been increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fuzzy neural network (FNN) models have been proposed to implement different types of single-stage fuzzy reasoning mechanisms and inevitably they suffer from the dimensionality problem when dealing with complex real-world problems. To address the problem, FNN modeling based on multistage fuzzy reasoning (MSFR) is pursued here and two hierarchical network models, namely incremental type and aggregated type, are introduced. The new models called multistage FNN (MSFNN) model a hierarchical fuzzy rule set that allows the consequence of a rule passed to another as a fact through the intermediate variables. From the stipulated input-output data pairs, they can generate an appropriate fuzzy rule set through structure and parameter learning procedures proposed in this paper. In addition, we have particularly addressed the input selection problem of these two types of multistage network models and proposed two efficient methods for them. The effectiveness of the proposed MSFNN models in handling high-dimensional problems is demonstrated through various numerical simulations     

Fuzzy identification using fuzzy neural networks with stable learning algorithms

In general, fuzzy neural networks cannot match nonlinear systems exactly. Unmodeled dynamic leads parameters drift and even instability problem. According to system identification theory, robust modification terms must be included in order to guarantee Lyapunov stability. This paper suggests new learning laws for Mamdani and Takagi-Sugeno-Kang type fuzzy neural networks based on input-to-state stability approach. The new learning schemes employ a time-varying learning rate that is determined from input-output data and model structure. Stable learning algorithms for the premise and the consequence parts of fuzzy rules are proposed. The calculation of the learning rate does not need any prior information such as estimation of the modeling error bounds. This offer an advantage compared to other techniques using robust modification.     

基于模糊三角数模糊神经网络的软件质量评价方法

用户对软件质量的评价与其体验密切相关,但由于软件产品的抽象性、复杂性以及用户需求的模糊性,目前软件质量评价方法都缺乏对该方面内容的关注,忽略了用户需求在软件质量评价中的作用。针对于此,考虑用户需求对软件质量的影响,将用户需求作为一种特殊的软件特性,构建了基于模糊三角数的模糊神经网络来处理软件开发过程中用户需求同软件特性之间的非线性关系,符合软件产品复杂性的特点,使软件质量评价结果更客观、全面。结果表明,基于模糊三角数模糊神经网络能够更好地反映用户需求同软件特性之间的非线性关系,是一种研究软件综合质量评价的有效方法。     

Fuzzy neural network sliding mode control for long delay time systems based on fuzzy prediction

Delay time, which may degrade the control performance, is frequently encountered in various control processes. The fuzzy neural network sliding mode controller (FNNSMC), which incorporates the fuzzy neural network (FNN) with the sliding mode controller (SMC), is developed to control the long delay system with unknown model based on fuzzy prediction algorithm in the paper. According to the characteristics of the long delay systems, we simulate the manual operating process and predict the delayed error and its derivative based on the information of the input and output variables of the process, and then feedback these prediction values to the FNN and train the FNN with the regulation function by the idea of sliding mode control until the better control results are obtained. The FNNSMC has more robustness due to the abilities of the learning and reasoning and can eliminate the drawbacks of the general SMC, namely the chattering in the control signal and the needing knowledge of the bounds of the disturbances and uncertainties. Simulation examples demonstrate the advantages of the proposed control scheme.     

Accelerated gradient learning algorithm for neural network weights update

This work proposes decomposition of square approximation algorithm for neural network weights update. Suggested improvement results in alternative method that converge in less iteration and is inherently parallel. Decomposition enables parallel execution convenient for implementation on computer grid. Improvements are reflected in accelerated learning rate which may be essential for time critical decision processes. Proposed solution is tested and verified on multilayer perceptrons neural network case study, varying a wide range of parameters, such as number of inputs/outputs, length of input/output data, number of neurons and layers. Experimental results show time savings up to 40% in multiple thread execution.     

Fault diagnosis competitive neural network with prioritized modification rule of connection weights

In this paper, a competitive neural network architecture is used as an intelligent fault diagnosis system to detect the fault sources in different subsystems or elements of a plant or any other device. The prioritized modification rule for connection weights is introduced and four different procedures are studied and compared from the viewpoint of their efficiency. It is shown that the fourth procedure is more convenient for human type decision-making. The output functions of different neurons are considered as the possibility of being fault sources for different units. The system starts from a vague initial state and the connection weights are modified during the learning procedures. The simulation results of different strategies are analyzed and compared. A typical CNC machine is considered as a case study.