基于径向基神经网络的月降水量预测模型研究

针对月降水量高度非线性的特点,以合肥20年的月降水量为时间序列,综合运用径向基函数（RBF）神经网络,建立了一种基于径向基函数的神经网络预测模型。首先对RBF神经网络进行介绍,并将该网络应用于月降水量预测,应用归一化方法对原始数据进行预处理;然后运用MATLABR2008神经网络工具箱函数建立月降水量预测模型;最后进行仿真实验与分析,将RBF神经网络与传统的BP网络训练预测结果进行比较。结果显示,RBF神经网络模型训练的迭代次数和训练时间、预测结果明显好于传统BP神经网络。     

基于GCPSO算法的RFID读写器网络规划的研究

无线射频识别（RFID）在现实中有广泛的应用,RFID网络规划是RFID网络部署的核心挑战。提出了一种新的GCPSO算法来实现RFID网络优化调度规划,该算法以广泛学习粒子群优化算法（MCPSO）思想为基础,针对从群之间没有信息的交流而降低算法速度问题,设定一种中心交流机制。同时在参数的设置中结合高斯分布的概念,以提高算法的收敛性。为了证明所提出GCPSO算法的效率和性能,将其与MCPSO算法、PSO基本算法共同对15个读写器进行网络规划并做比较。实验结果表明,改进后的粒子群算法GCPSO不仅收敛性能和速度上有了明显的增强,而且实现了RFID读写器网络良好规划。     

Analysis of radar images for rainfall forecasting using neural networks

This paper describes a new approach to the analysis of weather radar data for short-range rainfall forecasting based on a neural network model. This approach consists in extracting synthetic information from radar images using the approximation capabilities of multilayer neural networks. Each image in a sequence is approximated using a modified radial basis function network trained by a competitive mechanism. Prediction of the rain field evolution is performed by analysing and extrapolating the time series of weight values. This method has been compared to the conventional cross-correlation technique and the persistence method for three different rainfall events, showing significant improvement in 30 and 60 min ahead forecast accuracy.     

A reliable model for global planning of mobile networks

In this paper, we propose a global model for WiMAX networks planning. This model represents the network planning problem and helps to solve it entirely without dividing it into several subproblems. The objective of the model is to minimize the cost of the network while maximizing its survivability. The model has been compared to a sequential model with the same constraints, which consists in solving the subproblems sequentially, and to a global model without reliability constraints. The results show that the proposed model performs on an average 25% better than the other models.     

Relevance vector machines approach for long-term flow prediction

Over the past years, some artificial intelligence techniques like artificial neural networks have been widely used in the hydrological modeling studies. In spite of their some advantages, these techniques have some drawbacks including possibility of getting trapped in local minima, overtraining and subjectivity in the determining of model parameters. In the last few years, a new alternative kernel-based technique called a support vector machines (SVM) has been found to be popular in modeling studies due to its advantages over popular artificial intelligence techniques. In addition, the relevance vector machines (RVM) approach has been proposed to recast the main ideas behind SVM in a Bayesian context. The main purpose of this study is to examine the applicability and capability of the RVM on long-term flow prediction and to compare its performance with feed forward neural networks, SVM, and multiple linear regression models. Meteorological data (rainfall and temperature) and lagged data of rainfall were used in modeling application. Some mostly used statistical performance evaluation measures were considered to evaluate models. According to evaluations, RVM method provided an improvement in model performance as compared to other employed methods. In addition, it is an alternative way to popular soft computing methods for long-term flow prediction providing at least comparable efficiency.     

Multilevel network characterization using regular topologies

Multilevel networks have been a good solution in large-scale networks scenarios. The implementation of a network into different levels or sub-layers improves the performance and reduces the investment against plain topologies. This paper tries to characterize important parameters on multilevel networks such as diameter, average distance and gateway location to be able to optimize the global network topology with no need for additional path calculations. The study focuses on the lower level of the network formed by subnetworks with regular structures such as Single Ring, Double Ring and Torus Grid. The achieved results will ease and improve the network planning of large-scale networks.     

SenCar: An Energy-Efficient Data Gathering Mechanism for Large-Scale Multihop Sensor Networks

In this paper, we propose a new data gathering mechanism for large-scale multihop sensor networks. A mobile data observer, called SenCar, which could be a mobile robot or a vehicle equipped with a powerful transceiver and battery, works like a mobile base station in the network. SenCar starts the data gathering tour periodically from the static data processing center, traverses the entire sensor network, gathers the data from sensors while moving, returns to the starting point, and, finally, uploads data to the data processing center. Unlike SenCar, sensors in the network are static and can be made very simple and inexpensive. They upload sensed data to SenCar when SenCar moves close to them. Since sensors can only communicate with others within a very limited range, packets from some sensors may need multihop relays to reach SenCar. We first show that the moving path of SenCar can greatly affect network lifetime. We then present heuristic algorithms for planning the moving path/circle of SenCar and balancing traffic load in the network. We show that, by driving SenCar along a better path and balancing the traffic load from sensors to SenCar, network lifetime can be prolonged significantly. Our moving planning algorithm can be used in both connected networks and disconnected networks. In addition, SenCar can avoid obstacles while moving. Our simulation results demonstrate that the proposed data gathering mechanism can prolong network lifetime significantly compared to a network that has only a static observer or a network in which the mobile observer can only move along straight lines.     

Comparing interpolation techniques for monthly rainfall mapping using multiple evaluation criteria and auxiliary data sources: A case study of Sri Lanka

Interpolating climatic variables such as rainfall is challenging due to the highly variable nature of meteorological processes, the effects of terrain and geography, and the difficulty in establishing a representative network of stations. While interpolation models are being adapted to include these effects, often the rainfall data contain significant gaps in coverage. In this paper, we evaluated rainfall data from an agro-ecological monitoring network for producing maps of total monthly rainfall in Sri Lanka. We compared four spatial interpolation techniques: inverse distance weighting, thin-plate splines, ordinary kriging, and Bayesian kriging. Error metrics were used to validate interpolations against independent data. Satellite data were used to assess the spatial pattern of rainfall. Results indicated that Bayesian kriging and splines performed best in low and high rainfall, respectively. Rainfall maps generated from the agro-ecological network were found to have accuracies consistent with previous studies in Sri Lanka.     

Performance comparison of artificial neural network models for daily rainfall prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network (BPN), cascade-forward back propagation neural network (CBPN), distributed time delay neural network (DTDNN) and nonlinear autoregressive exogenous network (NARX), and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor (a taluk of Nilgiris). Based on the performance analysis, NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.     

无线传感器网络数据收集算法研究

对于无线传感器网络而言,可靠的数据收集是推进其大规模应用的关键,本文引入了移动传感器网络解决静态传感网络中的通信中断问题.针对移动传感器网络的数据收集,提出了数据收集的分类,分析了移动节点不同移动模式对网络数据收集的影响,比较了移动节点受控移动路径对比固定移动模式的优势,最后介绍了典型的移动节点受控移动的路径规划算法.     

Rules extraction from constructively trained neural networks based on genetic algorithms

The application of neural networks in the data mining has become wider. Although neural networks may have complex structure, long training time, and the representation of results is not comprehensible, neural networks have high acceptance ability for noisy data, high accuracy and are preferable in data mining. On the other hand, It is an open question as to what is the best way to train and extract symbolic rules from trained neural networks in domains like classification. In this paper, we train the neural networks by constructive learning and present the analysis of the convergence rate of the error in a neural network with and without threshold which have been learnt by a constructive method to obtain the simple structure of the network.The response of ANN is acquired but its result is not in understandable form or in a black box form. It is frequently desirable to use the model backwards and identify sets of input variable which results in a desired output value. The large numbers of variables and nonlinear nature of many materials models that can help finding an optimal set of difficult input variables. We will use a genetic algorithm to solve this problem. The method is evaluated on different public-domain data sets with the aim of testing the predictive ability of the method and compared with standard classifiers, results showed comparatively high accuracy.     

Modeling and performance analysis of ad hoc broadcasting schemes

Broadcasting is a technique widely used for distributing control packets in ad hoc networks. The traditional flooding scheme has been proven to unnecessarily consume network capacity and may lead to severe packet collisions in high-density networks. New schemes have been proposed for alleviating this so-called broadcast storm problem and their efficiencies are usually analyzed and compared by ns-2 simulations. However, little work has been done on mathematical modeling and rigorous analysis. In this paper, we focus on two popular ad hoc broadcasting schemes and provide their detailed analysis in one-dimensional and two-dimensional ideal networks. The statistical results obtained have revealed new relationships between network parameters and the performance metrics. These results are useful for optimally setting network parameters in designing protocols. It is also expected that the analytical methods developed will lay a solid foundation for the development of mathematical models for other ad hoc broadcast and multicast schemes.     

Design of continuous attractor networks with monotonic tuning using a symmetry principle

Neurons that sustain elevated firing in the absence of stimuli have been found in many neural systems. In graded persistent activity, neurons can sustain firing at many levels, suggesting a widely found type of network dynamics in which networks can relax to any one of a continuum of stationary states. The reproduction of these findings in model networks of nonlinear neurons has turned out to be nontrivial. A particularly insightful model has been the "bump attractor," in which a continuous attractor emerges through an underlying symmetry in the network connectivity matrix. This model, however, cannot account for data in which the persistent firing of neurons is a monotonic -- rather than a bell-shaped -- function of a stored variable. Here, we show that the symmetry used in the bump attractor network can be employed to create a whole family of continuous attractor networks, including those with monotonic tuning. Our design is based on tuning the external inputs to networks that have a connectivity matrix with Toeplitz symmetry. In particular, we provide a complete analytical solution of a line attractor network with monotonic tuning and show that for many other networks, the numerical tuning of synaptic weights reduces to the computation of a single parameter.     

基于模型的深度学习通信信号鲁棒识别算法

深度学习现在是计算机视觉和自然语言处理的热门话题.在许多应用中,深度神经网络(DNN)的性能都优于传统的方法,并且已经成功应用于调制分类和无线电信号表示等任务的学习.近几年研究发现深度神经网络极易受到对抗性攻击,对“对抗性示例”缺乏鲁棒性.笔者就神经网络的通信信号识别算法的鲁棒性问题,将经过PGD攻击的数据看作基于模型...     

Dealing with missing values in neural network-based diagnostic systems

Backpropagation neural networks have been applied to prediction and classification problems in many real world situations. However, a drawback of this type of neural network is that it requires a full set of input data, and real world data is seldom complete. We have investigated two ways of dealing with incomplete data — network reduction using multiple neural network classifiers, and value substitution using estimated values from predictor networks — and compared their performance with an induction method. On a thyroid disease database collected in a clinical situation, we found that the network reduction method was superior. We conclude that network reduction can be a useful method for dealing with missing values in diagnostic systems based on backpropagation neural networks.     

On robustness of radial basis function network with input perturbation

In this article, we have proposed a methodology for making a radial basis function network (RBFN) robust with respect to additive and multiplicative input noises. This is achieved by properly selecting the centers and widths for the radial basis function (RBF) units of the hidden layer. For this purpose, firstly, a set of self-organizing map (SOM) networks are trained for center selection. For training a SOM network, random Gaussian noise is injected in the samples of each class of the data set. The number of SOM networks is same as the number of classes present in the data set, and each of the SOM networks is trained separately by the samples belonging to a particular class. The weight vector associated with a unit in the output layer of a particular SOM network corresponding to a class is used as the center of a RBF unit for that class. To determine the widths of the RBF units, p-nearest neighbor algorithm is used class-wise. Proper selection of centers and widths makes the RBFN robust with respect to input perturbation and outliers present in the data set. The weights between the hidden and output layers of RBFN are obtained by pseudo inverse method. To test the robustness of the proposed method in additive and multiplicative noise scenarios, ten standard data sets have been used for classification. Proposed method has been compared with three existing methods, where the centers have been generated in three ways: randomly, using k-means algorithm, and based on SOM network. Simulation results show the superiority of the proposed method compared to those methods. Wilcoxon signed-rank test also shows that the proposed method is statistically better than those methods.

     

Bi-directional self-healing ring network planning

In this paper we study the network planning problem of bi-directional self-healing ring (BSHR), which is a network structure providing higher survivability when there is a failure on link or node. Given a network with nodes, links, and demand pairs, our target is to design an optimal network comprising rings, which use only the existing links to satisfy all demands. The objective is to minimize the total amount of equipment (add/drop multiplexer) on nodes, thus reducing the major cost of SHR structure. We propose two integer programming models. For larger networks, we have developed an efficient solution procedure based on its hierarchical network structure. Computational results are given to show that the solution procedure is effective in obtaining an optimal or near-optimal solution.Scope and purposeThe merging of information networking and telecommunication services has created an increasing demand for telecommunication networks of high bandwidth, aiming to exchange ever larger volumes of data in a very short time interval. The self-healing ring (SHR) is a ring network that provides redundant bandwidth in which disrupted services can be automatically restored following network failures. In this paper, we study the network planning problem of bi-directional SHR aiming to minimize the amount of equipment.     

基于Prim算法的通信网络架设仿真研究与应用

为了更好地提高通信网络架设实际问题的工作效率,进行了通信网络架设过程的仿真研究.通过算法的比较选择,对通信网络构架进行了动态规划.以最小代价生成树普里母算法为研究基础,采用数据结构的分析方法进行假设论证.文中结合通信网络构架的实际具体问题,讨论了网络规划中线路权重的选取方法,并在C语言环境下设计了适用于各个城市网络的节点-支路邻接表的数据存储结构.经实例验证,该方法具有计算速度快的优点并有效减少资源浪费,不仅可以保证通信网络架设工作效率,而且可以有效提高通信网络架设经济效益.     

基于新型深度神经网络的民机表面缺陷识别

为解决机务人员依靠经验来对民航飞机的表面缺陷进行识别时易发生误判的问题,开发了一种用于民机表面的缺陷识别的结合Inception-net和残差模块的新型深度神经网络。首先,通过对各机场的在修飞机表面缺陷进行采样建立数据集,手段包括使用图像处理修复不合格图像、使用数据增强缓解数据类别不平衡、使用立方卷积插值法降采样保留图像特征等图像预处理操作。然后在自建的数据集上对新型深度神经网络与其他神经网络进行对比测试。实验结果表明,新型神经网络在较少的参数下能够达到最深的网络深度,且在自建数据集的测试集上的识别率和查全率分别为74.23%和62.29%,优于进行对比的其他网络。说明在一定程度上该网络能够有效用于民机表面缺陷识别工作中。