具有敏感区域的华南虎图像配准研究

对数极坐标映射是一种具有刚体不变性的模板匹配算法,以它获得的刚体变换矩阵为初值经LMA(Levenberg Marquardt algorithm)迭代可以实现图像的高精度配准,但对于场景发生剧烈变化的图像对,上述方法无法获得正确的配准参数。为此,提出了一种具有敏感区域的图像配准算法,在LMA迭代中仅考虑落在人工选取的敏感区域中的像素点,通过对陕西林业厅公布的华南虎照片进行的图像配准实验表明了该算法的有效性。     

Differential Evolution and Levenberg Marquardt Trained Neural Network Scheme for Nonlinear System Identification

This paper proposes a new nonlinear system identification scheme using differential evolution (DE), neural network and Levenberg Marquardt algorithm (LM). Here, DE and LM in a combined framework are used to train a neural network for achieving better convergence of neural network weight optimization. A number of examples including a practical case-study have been considered for implementation of different system identification methods namely, only NN, DE+NN and DE+LM+NN. After, a series of simulation studies of these methods on the different nonlinear systems it has been confirmed that the proposed DE and LM trained NN approach to nonlinear system identification has yielded better identification results in terms of time of convergence and less identification error.     

A new semismooth Newton method for NCPs based on the penalized KK function

In this paper, based on the Kanzow-Kleinmichel (KK) function, we introduce a new nonlinear complementarity problem (NCP) function: penalized KK function. We show that the function possesses desirable properties similar to those of the KK function. Based on this new NCP function, we reformulate the NCP to a system of semismooth equations. We also propose a new semismooth Levenberg–Marquardt method to solve the system of semismooth equations that employs both trust region techniques and line searches. The global and quadratic convergence properties can be established under very mild assumptions. Numerical results show the effectiveness of the proposed algorithm and also indicate that superior behaviour of the proposed new NCP function.     

基于改进BP神经网络的连铸漏钢预报

针对传统BP神经网络在训练过程中存在收敛速度慢的缺陷,将LM(levenberg marquardt)算法引入到BP神经网络的训练过程,建立了LM-BP神经网络模型,并将其应用于连铸过程中的漏钢预报系统。结合某钢厂连铸现场历史数据对系统进行了测试,测试结果以96.15%的预报率及100%的报出率,验证了基于LM算法的BP神经网络连铸漏钢预报方案的可行性和有效性。     

Development and performance evaluation of an improved complex valued radar pulse compressor

Pulse compression is an important and burning issue in radar signal processing. In the recent past, many adaptive and neural network based methods have been proposed to achieve effective pulse compression performance for real coded transmitted waveforms. Even though the radar signal is complex, it is mostly processed as real-valued in-phase and quadrature components. Hence it is desirable that for processing complex radar signal for pulse compression both the structure as well as the learning algorithm associated with it need to be complex in nature. Accordingly in this paper a novel adaptive method is proposed by employing a complex valued fully connected cascaded (CFCC) neural network. For training this network, a new complex Levenberg–Marquardt (CLM) algorithm is derived and used for imparting effective training of its weights. The new CLM based CFCC (CFCC-CLM) model offers superior convergence performance with the least residual mean squared error during training phase compared to those provided by the multilayer perceptron (MLP) trained with complex domain backpropagation (CDBP) and CLM based methods. Further the comparison of peak signal-to-sidelobe ratio (PSR) under noisy and Doppler shift conditions of the proposed method exhibits best performance compared to those offered by the MLP-CDBP, MLP-CLM and the matched filter (MF) based methods.     

Object-oriented approach applied to ANFIS modeling and control of a distillation column

Neurofuzzy networks are hybrid systems that combine neural networks with fuzzy systems, and the Adaptive Neuro-Fuzzy inference system (ANFIS) is a particular case in which a fuzzy system is implemented in the framework of an adaptive neural network. This neurofuzzy approach represents an effective structure to the modeling of plant dynamics, and the oriented-object programming environments offer an intuitive way to address this task. In this paper the MODELICA object-oriented environment has been applied to the ANFIS modeling and indirect control of the heavy and light product composition in a binary methanol-water distillation column by using the adaptive Levenberg–Marquardt approach. The results obtained demonstrate the potential of the adaptive ANFIS scheme under MODELICA for the dual control of composition both for changes in set points with null stationary error even when disturbances are present.     

Identification model of multi-layered neural network parameters and its applications in the petroleum production

This paper creates a LM (Levenberg-Marquardt) algorithm model which is appropriate to solve the problem about weights value of feedforward neural network. On the base of this model, we provide two applications in the oilfield production. Firstly, we simulated the functional relationships between the petrophysical and electrical properties of the rock by neural networks model, and studied oil saturation. Under the precision of data is confirmed, this method can reduce the number of experiments. Secondly, we simulated the relationships between investment and income by the neural networks model, and studied invest saturation point and income growth rate. It is very significant to guide the investment decision. The research result shows that the model is suitable for the modeling and identification of nonlinear systems due to the great fit characteristic of neural network and very fast convergence speed of LM algorithm.     

Video enhancement through image registration based on structural similarity

Abstract

It is commonly known that the mean square error (MSE) does not accurately reflect the subjective image quality for most video enhancement tasks. Among the various image quality metrics, structural similarity (SSIM) metric provides remarkably good prediction of the subjective scores. In this paper, a new registration method based on contribution of structural similarity measurement to the well known Lucas–Kanade (LK) algorithm has been proposed. The core of the proposed method is contributing the SSIM in the sum of squared difference of images along with the Levenberg–Marquardt optimisation approach in LK algorithm. Mathematical derivation of the proposed method, based on the unified framework of Baker et al., is given. The proposed registration algorithm is applied to a video enhancement successfully. Various objective and subjective comparisons show the superior performance of the proposed method.     

An improved differential evolution trained neural network scheme for nonlinear system identification

This paper presents an improved nonlinear system identification scheme using di？erential evolution （DE）, neural network （NN） and Levenberg Marquardt algorithm （LM）. With a view to achieve better convergence of NN weights optimization during the training, the DE and LM are used in a combined framework to train the NN. We present the convergence analysis of the DE and demonstrate the efficacy of the proposed improved system identification algorithm by exploiting the combined DE and LM training of the NN and suitably implementing it together with other system identification methods, namely NN and DE＋NN on a number of examples including a practical case study. The identification results obtained through a series of simulation studies of these methods on different nonlinear systems demonstrate that the proposed DE and LM trained NN approach to nonlinear system identification can yield better identification results in terms of time of convergence and less identification error.