Spiking neural P systems with anti-spikes and without annihilating priority as number acceptors

Spiking neural P systems with anti-spikes （ASN P systems） are variant forms of spiking neural P systems, which are inspired by inhibitory impulses/spikes or inhibitory synapses. The typical feature of ASN P systems is when a neuron contains both spikes and anti-spikes, spikes and anti-spikes wil immediately annihilate each other in a maximal way. In this paper, a restricted variant of ASN P systems, cal ed ASN P systems without anni-hilating priority, is considered, where the annihilating rule is used as the standard rule, i.e., it is not obligatory to use in the neuron associated with both spikes and anti-spikes. If the annihilating rule is used in a neuron, the annihilation wil consume one time unit. As a result, such systems using two categories of spiking rules （identified by （a, a） and （a,a^-）） can achieve Turing completeness as number accepting devices.     

Series expansion feasibility of singular integral in method of moments

When calculating electromagnetic scattering using method of moments （MoM）, integral of the singular term has a significant influence on the results. This paper transforms the singular surface integral to the contour integral. The integrand is expanded to Taylor series and the integral results in a closed form. The cut-off error is analyzed to show that the series converges fast and only about 2 terms can agree wel with the accurate result. The comparison of the perfect electric conductive （PEC） sphere＇s bi-static radar cross section （RCS） using MoM and the accurate method validates the feasibility in manipulating the singularity. The error due to the facet size and the cut-off terms of the series are analyzed in examples.     

Solution for polarimetric radar cross section measurement and calibration

The exact radar cross-section （RCS） measurement is difficult when the scattering of targets is low. Ful polarimetric cali-bration is one technique that offers the potential for improving the accuracy of RCS measurements. There are numerous polarimetric calibration algorithms. Some complex expressions in these algo-rithms cannot be easily used in an engineering practice. A radar polarimetric coefficients matrix （RPCM） with a simpler expression is presented for the monostatic radar polarization scattering matrix （PSM） measurement. Using a rhombic dihedral corner reflector and a metal ic sphere, the RPCM can be obtained by solving a set of equations, which can be used to find the true PSM for any target. An example for the PSM of a metal ic dish shows that the proposed method obviously improves the accuracy of cross-polarized RCS measurements.     

Method of neural network modulation recognition based on clustering and Polak-Ribiere algorithm

To improve the recognition rate of signal modulation recognition methods based on the clustering algorithm under the low SNR, a modulation recognition method is proposed. The characteristic parameter of the signal is extracted by using a clustering algorithm, the neural network is trained by using the algorithm of variable gradient correction （Polak-Ribiere） so as to enhance the rate of convergence, improve the performance of recognition under the low SNR and realize modulation recognition of the signal based on the modulation system of the constellation diagram. Simulation results show that the recognition rate based on this algorithm is enhanced over 30% compared with the methods that adopt clustering algorithm or neural network based on the back propagation algorithm alone under the low SNR. The recognition rate can reach 90% when the SNR is 4 dB, and the method is easy to be achieved so that it has a broad application prospect in the modulating recognition.     

Direct adaptive control for a class of MIMO nonlinear discrete-time systems

This paper considers the problem of adaptive con-trol for a class of multiple input multiple output （MIMO） nonlinear discrete-time systems based on input-output model with unknown interconnections between subsystems. Based on the Taylor ex-pand technology, an equivalent model in affine-like form is derived for the original nonaffine nonlinear system. Then a direct adap-tive neural network （NN） control er is implemented based on the affine-like model. By finding an orthogonal matrix to tune the NN weights, the closed-loop system is proven to be semiglobal y uni-formly ultimately bounded. The σ-modification technique is used to remove the requirement of persistence excitation during the adaptation. The control performance of the closed-loop system is guaranteed by suitably choosing the design parameters.     

IUKF neural network modeling for FOG temperature drift

A novel neural network based on iterated unscented Kalman filter （IUKF） algorithm is established to model and com- pensate for the fiber optic gyro （FOG） bias drift caused by temperature. In the network, FOG temperature and its gradient are set as input and the FOG bias drift is set as the expected output. A 2-5-1 network trained with IUKF algorithm is established. The IUKF algorithm is developed on the basis of the unscented Kalman filter （UKF）. The weight and bias vectors of the hidden layer are set as the state of the UKF and its process and measurement equations are deduced according to the network architecture. To solve the unavoidable estimation deviation of the mean and covariance of the states in the UKF algorithm, iterative computation is introduced into the UKF after the measurement update. While the measure- ment noise R is extended into the state vectors before iteration in order to meet the statistic orthogonality of estimate and mea- surement noise. The IUKF algorithm can provide the optimized estimation for the neural network because of its state expansion and iteration. Temperature rise （-20-20℃） and drop （70-20℃） tests for FOG are carried out in an attemperator. The temperature drift model is built with neural network, and it is trained respectively with BP, UKF and IUKF algorithms. The results prove that the proposed model has higher precision compared with the back- propagation （BP） and UKF network models.     

NETWORK ANALYSIS OF TERRORIST ACTIVITIES

This paper uses an extensive network approach to "East Turkistan" activities by building both the one-mode and the bipartite networks for these activities.In the one-mode network,centrality analysis and spectrum analysis are used to describe the importance of each vertex.On this basis,two types of core vertices——The center of communities and the intermediary vertices among communities— are distinguished.The weighted extreme optimization(WEO) algorithm is also applied to detect communities in the one-mode network.In the "terrorist-terrorist organization" bipartite network,the authors adopt centrality analysis as well as clustering analysis based on the original bipartite network in order to calculate the importance of each vertex,and apply the edge clustering coefficient algorithm to detect the communities.The comparative and empirical analysis indicates that this research has been proved to be an effective way to identify the core members,key organizations,and communities in the network of "East Turkistan" terrorist activity.The results can provide a scientific basis for the analysis of "East Turkistan" terrorist activity,and thus provide decision support for the real work of "anti-terrorism".     

Fuzzy Q learning algorithm for dual-aircraft path planning to cooperatively detect targets by passive radars

The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.     

Novel magnetic field computation model in pattern classification

Field computation, an emerging computation technique, has inspired passion of intelligence science research. A novel field computation model based on the magnetic field theory is constructed. The proposed magnetic field computation （MFC） model consists of a field simulator, a non-derivative optimization algo- rithm and an auxiliary data processing unit. The mathematical model is deduced and proved that the MFC model is equivalent to a quadratic discriminant function. Furthermore, the finite element prototype is derived, and the simulator is developed, combining with particle swarm optimizer for the field configuration. Two benchmark classification experiments are studied in the numerical experiment, and one notable advantage is demonstrated that less training samples are required and a better generalization can be achieved.     

Iterative learning based fault diagnosis for discrete linear uncertain systems

In order to detect and estimate faults in discrete lin-ear time-varying uncertain systems, the discrete iterative learning strategy is applied in fault diagnosis, and a novel fault detection and estimation algorithm is proposed. And the threshold limited technology is adopted in the proposed algorithm. Within the chosen optimal time region, residual signals are used in the proposed algorithm to correct the introduced virtual faults with iterative learning rules, making the virtual faults close to these occurred in practical systems. And the same method is repeated in the rest optimal time regions, thereby reaching the aim of fault diagnosis. The proposed algorithm not only completes fault detection and estimation for discrete linear time-varying uncertain systems, but also improves the reliability of fault detection and decreases the false alarm rate. The final simulation results verify the validity of the proposed algorithm.     

Comparison on neural networks and support vector machines in suppliers' selection

Suppliers＇ selection in supply chain management （SCM） has attracted considerable research interests in recent years. Recent literatures show that neural networks achieve better performance than traditional statistical methods. However, neural networks have inherent drawbacks, such as local optimization solution, lack generalization, and uncontrolled convergence. A relatively new machine learning technique, support vector machine （SVM）, which overcomes the drawbacks of neural networks, is introduced to provide a model with better explanatory power to select ideal supplier partners. Meanwhile, in practice, the suppliers＇ samples are very insufficient. SVMs are adaptive to deal with small samples＇ training and testing. The prediction accuracies for BPNN and SVM methods are compared to choose the appreciating suppliers. The actual examples illustrate that SVM methods are superior to BPNN.     

基于支持向量机的金融时间序列预测

基于数据的机器学习就是由观测样本数据得出目前尚不能通过原理分析得到的规律,利用其对未来数据进行预测。神经网络以其优越的函数逼近性能广泛用于建立时间序列过去与未来数据之间某种确定的映射关系,实现预测。首先分析了以经验风险最小化为准则的神经网络的局限性,以及针对此提出的结构风险最小化准则的优点;其次引出支持向量机;最后利用支持向量机对上海证券综合指数序列趋势做较准确的多步预测。     

基于卷积神经网络的OFDM频谱感知方法

在认知无线电网络中,高效且准确的频谱感知是必不可少的一个环节。针对传统机器学习算法在频谱感知训练慢的难题,提出一种基于卷积神经网络的正交频分复用(orthogonal frequency division multiplexing,OFDM)频谱感知方法,将深度学习在图像处理上的优势应用到OFDM信号频谱感知中。该方法首先分析OFDM信号的循环自相关和频谱感知模型,对循环自相关进行归一化灰度处理,形成循环自相关灰度图;然后以LeNet-5网络为基础设计卷积神经网络分层地对训练数据进行学习,提取出更加抽象的特征;最后将测试数据输入到训练好的卷积神经网络模型,完成频谱感知。仿真实验表明,该方法能够完成OFDM信号的频谱感知,在低信噪比条件下具有较高的检测概率。     

基于卡尔曼滤波的二次型神经网络学习算法及收敛性分析

提出了二次型多层前馈神经网络的卡尔曼滤波学习算法,并证明了该算法的收敛性。与文献［２,３］中的学习算法和经典的误差反向传播学习算法相比,新的学习算法具有更快的学习速度、良好的泛化能力,并且对学习率有很好的鲁棒性,不容易陷入局部极小点。仿真实验结果表明了新算法的有效性。     

一类新的离散时延递归RBF神经网络

提出了一类带有离散时间 FIR/ IIR滤波器的递归 RBF神经网络 ,用离散时间 FIR/ IIR滤波器代替通常的 RBF神经网络中的线性输出权值 ,以适用于离散动力学系统的辨识和控制以及混沌时间序列预测 .本文给出的学习算法简单 ,可以避免传统的递归算法的不稳定性 .将该类神经网络用于动力学系统的建模 ,收到很好的效果 .     

基于DA-RKELM算法的光伏发电功率预测方法

针对光伏发电功率具有的波动性和随机性等特点造成的电网安全问题,提出了一种基于蜻蜓算法优化的正则核极限学习机光伏发电功率预测方法。通过相关性分析确定影响光伏发电功率的关键影响因子,构建光伏发电功率预测模型;利用蜻蜓算法获取网络最优的权重和阈值,在标准极限学习基础上引入正则化函数和核函数以避免传统梯度下降法造成的过拟合问题,增强模型空间映射能力;仿真实验表明,与DA-ELM、PSO-ELM以及标准-DA-ELM模型相比,DA-RKELM预测模型能达到更高的预测精度,更贴近光伏发电的实际运行功率。     

一种聚类神经网络初始聚类中心的确定方法

在基于聚类神经网络提取模糊规则方法中,其初始聚类数及聚类中心往往是事先给定的,这样会给规则提取带来一定的盲目性,并影响神经网络的学习时间和聚类效果。本文提出了一种根据测量数据集自动确定聚类神经网络初始聚类中心的方法,该方法可客观地确定聚类数和初始聚类中心,能够有效地缩短神经网络的学习时间。     

跨越连接BP算法及其在卷烟制丝工艺中的应用

传统BP神经网络算法及其改进算法都是非完全全连接神经网络算法,具有收敛速度慢,泛化能力差等不足.通过对神经网络连接方式的转化,可以得到一种完全全连接神经网络--跨越连接神经网络,并给出了跨越连接BP神经网络算法.针对卷烟制丝工艺的仿真实验表明,该算法具备描述复杂数据的能力,与传统BP算法相比,网络训练收敛速度快且泛化能力强.     

高阶带阻滤波器优化设计研究

众所周知，传统BP神经网络收敛速度慢、学习效率低。之所以如此，主要原因在于人工神经元输出函数的同一化。本文提出的神经网络模型的主要特点是：用正交基函数作人工神经元的输出函数，而且每个神经元的输出函数各不相同。该神经网络模型有效克服了传统BP神经网络收敛速度慢、学习效率低的致命缺陷。本文还详细研究了FIR线性相位滤波器的幅频特性与余弦基函数神经网络算法的关系，给出了高阶带阻滤波器优化设计实例。计算机仿真结果表明了该算法在高阶带阻滤波器设计中的有效性和优异性能。     

基于遗传算法的进化神经网络

提出一种基于遗传算法的多层前向神经网络的自动化设计方法(genetic multiplayer feedforward neural network，GMFNN)，用以同时完成对网络结构空间和权值空间的搜索。该算法利用双种群权值优化、结构进化自适应变异率等方法来加快算法的收敛速度，改善解的性能。仿真结果显示本文提出的算法能够有效抑制遗传算法初期收敛的发生，有效地提高多层前向神经网络的收敛精度，并可获得更为简洁的网络结构。