A new method for expiration code detection and recognition using gabor features based collaborative representation

Text in images and video contains important information for visual content understanding, indexing, and recognizing. Extraction of this information involves preprocessing, localization and extraction of the text from a given image. In this paper, we propose a novel expiration code detection and recognition algorithm by using Gabor features and collaborative representation based classification. The proposed system consists of four steps: expiration code location, character isolation, Gabor features extraction and characters recognition. For expiration code detection, the Gabor energy (GE) and the maximum energy difference (MED) are extracted. The performance of the recognition algorithm is tested over three Gabor features: GE, magnitude response (MR) and imaginary response (IR). The Gabor features are classified based on collaborative representation based classifier (GCRC). To encompass all frequencies and orientations, downsampling and principal component analysis (PCA) are applied in order to reduce the features space dimensionality. The effectiveness of the proposed localization algorithm is highlighted and compared with other existing methods. Extensive testing shows that the suggested detection scheme outperforms existing methods in terms of detection rate for large image database. Also, GCRC show very competitive results compared with Gabor feature sparse representation based classification (GSRC). Also, the proposed system outperforms the nearest neighbor (NN) classifier and the collaborative representation based classification (CRC).     

Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions

This study developed a methodology for formulating water level models to forecast river stages during typhoons, comparing various models by using lazy and eager learning approaches. Two lazy learning models were introduced: the locally weighted regression (LWR) and the k-nearest neighbor (kNN) models. Their efficacy was compared with that of three eager learning models, namely, the artificial neural network (ANN), support vector regression (SVR), and linear regression (REG). These models were employed to analyze the Tanshui River Basin in Taiwan. The data collected comprised 50 historical typhoon events and relevant hourly hydrological data from the river basin during 1996–2007. The forecasting horizon ranged from 1 h to 4 h. Various statistical measures were calculated, including the correlation coefficient, mean absolute error, and root mean square error. Moreover, significance, computation efficiency, and Akaike information criterion were evaluated. The results indicated that (a) among the eager learning models, ANN and SVR yielded more favorable results than REG (based on statistical analyses and significance tests). Although ANN, SVR, and REG were categorized as eager learning models, their predictive abilities varied according to various global learning optimizers. (b) Regarding the lazy learning models, LWR performed more favorably than kNN. Although LWR and kNN were categorized as lazy learning models, their predictive abilities were based on diverse local learning optimizers. (c) A comparison of eager and lazy learning models indicated that neither were effective or yielded favorable results, because the distinct approximators of models that can be categorized as either eager or lazy learning models caused the performance to be dependent on individual models.     

Convergence Analysis of Wireless Remote Iterative Learning Control Systems with Channel Noise

Channel noise, including sensor‐to‐controller(SC) noise and controller‐to‐actuator(CA) noise, impacts the convergence of wireless remote iterative learning control (ILC) system significantly. In this paper, the relationship between output error, SC noise and CA noise is obtained firstly by super‐vector formulation, and then the norm of output error vector covariance matrix is employed to analyze the convergence of the system in presence of SC noise and CA noise. Upper bound of the norm at any sample time reveals that the SC noise is accumulated only in iteration domain, while the CA noise is accumulated not only in iteration domain but also in time domain. Furthermore, the accumulated effect of the CA noise in time domain is ruled by system matrices, so the values of which determine the effect of the CA noise is greater or less than that of the SC noise on convergence of the system. Finally, some simulation results are given to illustrate correctness of the result.     

Optimal Terminal Iterative Learning Control for the Automatic Train Stop System

The train stop control is a typical set‐point control task, where only the final state (i.e., the terminal train stop position) is of concern and specified. For such a control problem, an optimal terminal iterative learning control (TILC) approach is presented in this paper, where the stopping position and initial braking speed are chosen as the terminal system output and the control input, respectively. The controller design only depends on the measured input/output (I/O) data without requiring any modeling information of the train operation system, and the learning gain is updated by the system I/O data iteratively to accommodate the system uncertainties. The monotonic convergence of the terminal tracking error is guaranteed by rigorous mathematical analysis. Extensive simulation results are provided to show the applicability and effectiveness of the proposed approach.     

糖厂澄清工段生产指标建模及操作参数优化

针对亚法糖厂澄清工段清汁色值和清汁残硫量难以在线测量的问题,提出了一种基于人工蜂群优化的在线极限学习机软测量方法;先用核主元分析法确定影响清汁质量的关键参数,建立基于在线极限学习机的软测量模型;同时利用人工蜂群算法对在线极限学习机的隐层参数进行寻优,优化所建模型;最后,使用带约束的粒子群对软测量模型进行优化求解,得到典型工况下的最优操作设定值,为后续工况操作提供参考依据;仿真结果表明,基于人工蜂群优化的在线极限学习机模型能够准确地预测清汁色值和残硫量,同时基于此模型优化的操作参数设定值能够达到期望的指标.     

基于动态性有效资源分配的云计算效益学习模型研究

为了将有限的资源合理地分配给用户,并尽可能地提高云系统的资源和能量利用效率,提出了一种改进的面向动态性有效资源分配的云计算效益学习模型算法,在动态性有效资源分配上提出了服务质量准则框架(QSSF)来得出云服务的计费管理机制;采用资源竞拍策略和动态双向博弈策略更好地权衡用户和云计算提供商之间的利益关系,并将资源分配给资源需求量大的用户;在云系统的运算和存储任务的资源和能量分配上,采用了基于云计算的效益学习模型,通过权衡任务对资源和能量的需求量来实现系统效益的最优化;实验仿真结果表明,该算法能够更加合理地为系统的运算和存储任务分配资源和能量,在资源和能量的利用率上优于其他对比算法.     

运载火箭控制系统的BIT设计与实现

根据拓扑性质知觉原理,视觉原语是从整体到局部,拓扑感知优先。根据此仿生原理,建立感知目标物的形状拓扑信息的数学模型。首先提取物体三维轮廓信息;将空间图形轮廓降维映射到二维投影平面中进行处理;建立提取空间图形拓扑特征的数学模型。将轮廓拓扑空间同胚映射到(Hausdorf或度量空间或)二维投影平面,保持了拓扑不变性,因此便于分析出拓扑特征,可继续应用拓扑映射原理,分析点集拓扑。最终,拓扑特征与知识库模型相匹配,识别出物体。     

一种半监督网络入侵检测系统SSIDS-CV

为了提高网络入侵检测的性能,提出一种基于半监督学习的网络入侵检测系统SSIDS-CV.系统由网络嗅探器、训练集生成器和半监督分类器三部分组成.通过对无标记入侵数据进行伪标记,将伪标记后的样本加入到有标记数据集中,参与交叉验证,选取能使分类器误差最小的标记作为最终的标记,扩充有标记数据数目,训练入侵检测分类器.使用KDD Cup 99数据集模拟半监督入侵检测过程,实验结果表明SSIDS-CV能有效地挖掘未标记入侵数据信息,具有较高的入侵检测率.     

基于支持向量机的自同步音频水印算法*

针对如何有效抵抗去同步攻击的问题,论文提出了一种基于支持向量机的自同步音频水印新算法。该算法利用能量特性从载体音频中提取能量特征,再结合音频包络信息,利用支持向量机训练出较稳定的特征点,同时结合听觉掩蔽特性将水印信息在混合域内嵌入到数字音频中。水印检测时,利用音频的特征点实现水印的重同步,无须求助于原始音频。仿真实验结果表明,所提出的算法不仅具有较好的不可感知性,而且对音频常规处理与攻击和破坏水印检测同步特性的恶意攻击均具有较好的稳健性。     

中文事件触发词的自动抽取研究*

随着自然语言处理领域中信息抽取技术的不断发展,越来越多的学者开始关注事件的识别和抽取研究,其中触发词的识别和抽取是事件识别和抽取的关键。针对目前中文触发词抽取结果的 F值不够理想的情况,选用中文事件语料库C EC语料作为训练语料和测试语料,提出了一种基于触发词扩展表和机器学习相结合的触发词抽取方法,实验表明,该方法抽取效果比较理想,F值可达到69．7％。