A fuzzy hybrid learning algorithm for radial basis function neural network with application in human face recognition

This paper presents a fuzzy hybrid learning algorithm (FHLA) for the radial basis function neural network (RBFNN). The method determines the number of hidden neurons in the RBFNN structure by using cluster validity indices with majority rule while the characteristics of the hidden neurons are initialized based on advanced fuzzy clustering. The FHLA combines the gradient method and the linear least-squared method for adjusting the RBF parameters and the neural network connection weights. The RBFNN with the proposed FHLA is used as a classifier in a face recognition system. The inputs to the RBFNN are the feature vectors obtained by combining shape information and principal component analysis. The designed RBFNN with the proposed FHLA, while providing a faster convergence in the training phase, requires a hidden layer with fewer neurons and less sensitivity to the training and testing patterns. The efficiency of the proposed method is demonstrated on the ORL and Yale face databases, and comparison with other algorithms indicates that the FHLA yields excellent recognition rate in human face recognition.     

High-speed face recognition using self-adaptive radial basis function neural networks

In this work, we have proposed a self-adaptive radial basis function neural network (RBFNN)-based method for high-speed recognition of human faces. It has been seen that the variations between the images of a person, under varying pose, facial expressions, illumination, etc., are quite high. Therefore, in face recognition problem to achieve high recognition rate, it is necessary to consider the structural information lying within these images in the classification process. In the present study, it has been realized by modeling each of the training images as a hidden layer neuron in the proposed RBFNN. Now, to classify a facial image, a confidence measure has been imposed on the outputs of the hidden layer neurons to reduce the influences of the images belonging to other classes. This process makes the RBFNN as self-adaptive for choosing a subset of the hidden layer neurons, which are in close neighborhood of the input image, to be considered for classifying the input image. The process reduces the computation time at the output layer of the RBFNN by neglecting the ineffective radial basis functions and makes the proposed method to recognize face images in high speed and also in interframe period of video. The performance of the proposed method has been evaluated on the basis of sensitivity and specificity on two popular face recognition databases, the ORL and the UMIST face databases. On the ORL database, the best average sensitivity (recognition) and specificity rates are found to be 97.30 and 99.94%, respectively using five samples per person in the training set. Whereas, on the UMIST database, the above quantities are found to be 96.36 and 99.81%, respectively using eight samples per person in the training set. The experimental results indicate that the proposed method outperforms some of the face recognition approaches.     

A novel self-adaptive extreme learning machine based on affinity propagation for radial basis function neural network

In this paper, a novel self-adaptive extreme learning machine (ELM) based on affinity propagation (AP) is proposed to optimize the radial basis function neural network (RBFNN). As is well known, the parameters of original ELM which developed by G.-B. Huang are randomly determined. However, that cannot objectively obtain a set of optimal parameters of RBFNN trained by ELM algorithm for different realistic datasets. The AP algorithm can automatically produce a set of clustering centers for the different datasets. According to the results of AP, we can, respectively, get the cluster number and the radius value of each cluster. In that case, the above cluster number and radius value can be used to initialize the number and widths of hidden layer neurons in RBFNN and that is also the parameters of coefficient matrix H of ELM. This may successfully avoid the subjectivity prior knowledge and randomness of training RBFNN. Experimental results show that the method proposed in this thesis has a more powerful generalization capability than conventional ELM for an RBFNN.     

Power transformer differential protection using neural network Principal Component Analysis and Radial Basis Function Neural Network

Many methods have been used to discriminate magnetizing inrush from internal faults in power transformers. Most of them follow a deterministic approach, i.e. they rely on an index and fixed threshold. This article proposes two approaches (i.e. NNPCA and RBFNN) for power transformer differential protection and address the challenging task of detecting magnetizing inrush from internal fault. These approaches based on the pattern recognition technique. In the proposed algorithm, the Neural Network Principal Component Analysis (NNPCA) and Radial Basis Function Neural Network (RBFNN) are used as a classifier. The principal component analysis is used to preprocess the data from power system in order to eliminate redundant information and enhance hidden pattern of differential current to discriminate between internal faults from inrush and over-excitation condition. The presented algorithm also makes use of ratio of voltage-to-frequency and amplitude of differential current for detection transformer operating condition. For both proposed cases, optimal number of neurons has been considered in the neural network architectures and the effect of hidden layer neurons on the classification accuracy is analyzed. A comparison among the performance of the FFBPNN (Feed Forward Back Propagation Neural Network), NNPCA, RBFNN based classifiers and with the conventional harmonic restraint method based on Discrete Fourier Transform (DFT) method is presented in distinguishing between magnetizing inrush and internal fault condition of power transformer. The algorithm is evaluated using simulation performed with PSCAD/EMTDC and MATLAB. The results confirm that the RBFNN is faster, stable and more reliable recognition of transformer inrush and internal fault condition.     

Optimizing radial basis function neural network based on rough sets and affinity propagation clustering algorithm

A novel method based on rough sets (RS) and the affinity propagation (AP) clustering algorithm is developed to optimize a radial basis function neural network (RBFNN). First, attribute reduction (AR) based on RS theory, as a preprocessor of RBFNN, is presented to eliminate noise and redundant attributes of datasets while determining the number of neurons in the input layer of RBFNN. Second, an AP clustering algorithm is proposed to search for the centers and their widths without a priori knowledge about the number of clusters. These parameters are transferred to the RBF units of RBFNN as the centers and widths of the RBF function. Then the weights connecting the hidden layer and output layer are evaluated and adjusted using the least square method (LSM) according to the output of the RBF units and desired output. Experimental results show that the proposed method has a more powerful generalization capability than conventional methods for an RBFNN.     

Face recognition using point symmetry distance-based RBF network

In this paper, a face recognition technique using a radial basis function neural network (RBFNN) is presented. The centers of the hidden layer units of the RBFNN are selected by using a heuristic approach and point symmetry distance as similarity measure. The performance of the present method has been evaluated using the AT&T Laboratories Cambridge database (formerly called ORL face database) and compared with some other methods, which use the same database. The evaluation has been done using two methodologies; first with no rejection criteria, and then with rejection criteria. The experimental results show that the present method achieves excellent performance, both in terms of recognition rates and learning efficiency. The average recognition rates, as obtained using 10 different permutations of 1, 3 and 5 training images per subject are 76.06, 92.61 and 97.20%, respectively, when tested without any rejection criteria. On the other hand, by imposing rejection criteria, the average recognition rates of the system become 99.34, 99.80 and 99.93%, respectively, for the above permutations of the training images. The system recognizes a face within about 22 ms on a low-cost computing system with a 450 MHz P-III processor, and thereby extending its capability to identify faces in interframe periods of video and in real time.     

Recognizing arabic handwritten characters using deep learning and genetic algorithms

Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country’s history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named “HMB-AHCR-DLGA” is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.

     

A novel adaptive crossover bacterial foraging optimization algorithm for linear discriminant analysis based face recognition

This paper presents a modified bacterial foraging optimization algorithm called adaptive crossover bacterial foraging optimization algorithm (ACBFOA), which incorporates adaptive chemotaxis and also inherits the crossover mechanism of genetic algorithm. First part of the research work aims at improvising evaluation of the optimal objective function values. The idea of using adaptive chemotaxis is to make it computationally efficient and crossover technique is to search nearby locations by offspring bacteria. Four different benchmark functions are considered for performance evaluation. The purpose of this research work is also to investigate a face recognition algorithm with improved recognition rate. In this connection, we propose a new algorithm called ACBFO-Fisher. The proposed ACBFOA is used for finding optimal principal components for dimension reduction in linear discriminant analysis (LDA) based face recognition. Three well-known face databases, FERET, YALE and UMIST, are considered for validation. A comparison with the results of earlier methods is presented to reveal the effectiveness of the proposed ACBFO-Fisher algorithm.     

A Self-Organizing RBF Neural Network Based on Distance Concentration Immune Algorithm

Radial basis function neural network (RBFNN) is an effective algorithm in nonlinear system identification. How to properly adjust the structure and parameters of RBFNN is quite challenging. To solve this problem, a distance concentration immune algorithm (DCIA) is proposed to self-organize the structure and parameters of the RBFNN in this paper. First, the distance concentration algorithm, which increases the diversity of antibodies, is used to find the global optimal solution. Secondly, the information processing strength (IPS) algorithm is used to avoid the instability that is caused by the hidden layer with neurons split or deleted randomly. However, to improve the forecasting accuracy and reduce the computation time, a sample with the most frequent occurrence of maximum error is proposed to regulate the parameters of the new neuron. In addition, the convergence proof of a self-organizing RBF neural network based on distance concentration immune algorithm (DCIA-SORBFNN) is applied to guarantee the feasibility of algorithm. Finally, several nonlinear functions are used to validate the effectiveness of the algorithm. Experimental results show that the proposed DCIA-SORBFNN has achieved better nonlinear approximation ability than that of the art relevant competitors.      

基于自适应角度损失函数的深度人脸识别算法研究

角度空间损失函数往往因需要手动调节超参数而引起算法训练的不稳定,类别标签数量的不同也将导致算法的移植性较差。针对这些问题,提出一种带有下界判断的自适应角度空间损失函数并应用于人脸识别。该方法以假设人脸表达特征分布在超球体空间为切入点,通过分析不同超参数对训练结果的影响,使预测概率公式的二阶导数为零并动态地计算当前mini-batch角度分布的去尾平均数; 为了提高算法的可移植性,根据类别中心的最小期望后验概率给出自适应调节超参数的下界。通过在LFW和MegaFace百万级人脸数据集上进行算法评估,证明提出的方法可以有效地提高人脸识别精度以及模型收敛率,在亚洲人脸数据集上的实验证明该方法具有较好的鲁棒性与移植性。     

基于快速回归算法的RBF神经网络及其应用

针对径向基神经网络(RBFNN)中存在的径向基函数中心的数F1及其位置难以确定的问题,提出了一种新型的基于快速回归算法(FRA)的RBFNN.采用快速回归算法,不但能够确定RBF的中心和中心个数,而且能够求出隐含层到输出层的权重.通过一元函数拟合和Mackey-Glass混沌时间序列预测的仿真,验证了该网络的有效性与实用性.     

数字信号调制识别的RBFNN分类器算法研究与实现

提出了一种新的用于数字信号调制识别的径向基函数神经网络（RBFNN）分类器算法。该算法采用减法聚类算法和最小均方算法实现了对隐含层中心点个数及位置和输出层权值系数的自适应训练。此算法能够综合考虑所有特征参量,能够在多维空间内找到最佳分界面;同时,解决了隐含层中心点个数及位置的盲目性和随机性的问题。仿真实验表明,在相同特征参量情况下,该算法能够有效提高正确识别率。     

基于遗传算法的径向基神经网络及其在同时测定Fe Mn Cu Zn中应用

介绍了两种新的基于遗传算法的径向基神经网络(GA-Based RBFNN)训练算法.这两种算法均将遗传算法用于优化径向基神经网络的聚类中心和网络结构.第一种GA-Based RBFNN算法对所有训练样本采取二进制编码构成个体,优化径向基函数中心的选取和网络结构;第二种GA-Based RBFNN算法中,RBFNN采用自增长算法训练网络隐含层中心、采用十进制对距离因子ε编码构成染色体,优化网络.将两种GA-Based RBFNN算法应用于Fe、Mn、Cu、Zn同时测定的光谱解析,计算结果表明,本文的GA-Based RBFNN算法较通常的遗传算法与径向基人工神经网络(GA-RBFNN)联用,即在GA选择变量的基础上,再用RBFNN作数据解析的GA-RBFNN方法,在增强网络的泛化能力、提高预测的准确性等方面具有明显的优势.从这两种GA-Based RBFNN的比较看,第二种算法在性能上优于第一种算法.     

Modelling the nonlinear dynamic behaviour of a boiler‐turbine system using a radial basis function neural network

Building an appropriate mathematical model that describes the system behaviour with a certain degree of satisfaction is quite challenging owing to the uncertain and volatile nature of thermodynamic constants and geometric parameters. In this paper, we present a technique to approximate and validate the dynamic behaviour of the Aström–Bell boiler‐turbine power plant based on an RBFNN over a large operating range. The proposed RBFNN is applied to solve the parametric identification problem for nonlinear and complex systems using an optimiser based on a hybrid genetic algorithm. This optimiser is composed of the gradient descent optimiser and a genetic algorithm for fast convergence. Two simulations were performed to show the effectiveness of the proposed technique under different situations with several boiler‐turbine input variables. The optimal structure and parameters of the obtained RBFNN‐based model emulates well the dynamic behaviour of the Aström–Bell boiler‐turbine system. Copyright © 2013 John Wiley & Sons, Ltd.     

堆叠隐空间模糊C 均值聚类算法

基于极限学习机理论, 将主成分分析技术与ELM特征映射相结合, 提出一种基于主成分分析的压缩隐空间构建新方法. 结合多层神经网络学习方法对隐空间进行多层融合, 进一步提出了堆叠隐空间模糊C 均值聚类算法,从而提高对非线性数据的学习能力. 实验结果表明, 所提出算法在处理复杂非线性数据时更加高效、稳定, 同时克服了模糊聚类算法对模糊指数的敏感性问题.

     

Akin-based Orthogonal Space (AOS): a subspace learning method for face recognition

A projection learning space is an approach to mapping a high-dimensional vector space to a lower dimensional vector space. In this paper, we proposed an algorithm, namely, AOS: Akin based Orthogonal Space. The algorithm is driven with two major targets - (i) to choose most representative image(s) from a group of face images of an individual, (ii) finally to produce a learning space which follows a Gaussian distribution to reduce the influence of grosses like non-Gaussianly distributed data noises, variations in facial expression and illumination. To improve the recognition performance, we proposed another approach i.e. fusion between AOS features and a custom VGG features. We justify the effectiveness of the proposed approaches over five benchmark face datasets using two classifiers. Experimental results show that the proposed learning algorithm has obtained maximum of 92.22% recognition rate, as well deep learning based fusion approch greatly improves the recognition accuracy. The comparative performances demonstrate that the proposed method could significantly outperform other relevant subspace learning methods.

     

精英正交学习萤火虫算法

针对萤火虫算法后期收敛较慢以及求解精度不高的问题,提出了精英正交学习萤火虫算法。该算法利用精英萤火虫采用正交学习策略来构造指导向量,以保存和发现最优方向信息,从而引导群体更准确地飞向全局最优区域。同时,还采用了自适应步长技术来更好地平衡算法探索与开发能力,采用最小吸引力参数保证高维空间距离过大的个体之间的相互吸引。在6个经典测试函数上与标准萤火虫算法及其它3种改进的萤火虫算法进行了对比,实验结果表明,提出的算法具有较快的收敛速度和较高的收敛精度。     

带权重的贪心萤火虫算法求解0-1背包问题

根据萤火虫算法的自身特点，将自适应权重、改进贪心算法、变异算子与基本萤火虫算法相结合，提出一种带权重的贪心萤火虫算法。通过加入自适应权重与变异算子，可以提高算法全局搜索能力，加入贪心算法在一定程度上可提高算法收敛速度，整体看，改进萤火虫算法提高了算法性能。通过仿真实验将改进后的算法与一些基本算法进行比较，实验结果表明，该算法在求解0-1背包问题时，无论在运算速度还是求解精度上都有明显改进。     

A novel adaptive cuckoo search algorithm for intrinsic discriminant analysis based face recognition

This paper presents a novel adaptive cuckoo search (ACS) algorithm for optimization. The step size is made adaptive from the knowledge of its fitness function value and its current position in the search space. The other important feature of the ACS algorithm is its speed, which is faster than the CS algorithm. Here, an attempt is made to make the cuckoo search (CS) algorithm parameter free, without a Levy step. The proposed algorithm is validated using twenty three standard benchmark test functions. The second part of the paper proposes an efficient face recognition algorithm using ACS, principal component analysis (PCA) and intrinsic discriminant analysis (IDA). The proposed algorithms are named as PCA + IDA and ACS–IDA. Interestingly, PCA + IDA offers us a perturbation free algorithm for dimension reduction while ACS + IDA is used to find the optimal feature vectors for classification of the face images based on the IDA. For the performance analysis, we use three standard face databases—YALE, ORL, and FERET. A comparison of the proposed method with the state-of-the-art methods reveals the effectiveness of our algorithm.