On-Line Shape recognition with incremental training using binary synaptic weights algorithm

Recognition of hand drawn shapes is beneficial in drawing packages and automated sketch entry in handheld computers. In this paper, we propose a new approach to on-line geometric shape recognition with incremental training function, which utilizes a heuristic function to reduce noise and a neural network for classification and on-line training. Instead of recognizing segments of a drawing and then performing syntactical analysis to match with a predefined shape, which is weak in terms of generalization and dealing with noise, we examine the shape as a whole. The main concept of the recognition method is derived from the fact that internal angles are very important in the perceived shape of outlines. Our application's aim is to recognize elliptic, rectangular, and triangular shapes in a way similar to human cognition of these shapes. Human beings recognize such basic shapes regardless of the variations in size, noise on the shape border, rotation and in the case of triangles, regardless of the type of the triangle. The key concept is that the neural network learns the relationships between the internal angles of a shape and its classification, therefore only a few training samples which represent the class of the shape are sufficient. Fast meremental training, which is performed on-line, is accomplished by the use of the Binary Synaptic Weights algorithm, a one pass, feedforward neural network training algorithm. Incremental training offers the advantage of adjusting the recognition capability of the system to the user's drawings. the results are very successful, such that the neural network correctly classified shapes that did not have any resemblance to the shapes in the initial training set.     

基于Sql Server BI平台和决策树技术的CET-4成绩分析

文章首先对Sql Server 2008商业智能平台及决策树技术相关理论作了介绍,然后对挖掘数据源数据进行了一系列预处理。利用Sql Server 2008商业智能平台下的决策树技术并采用数据挖掘扩展语言即DMX语言创建了CET-4成绩分析决策树模型。分类矩阵和挖掘提升图分别对该模型的评估结果表明了模型具有较高的可靠性和分类准确度,同时模型对应的一些规则可作为英语教学管理和改革的重要参考依据。     

基于欧式距离的一种新的核函数

支持向量机表现的好坏很大程度上取决于核函数的选取,因此最近几年关于核函数的研究有许多。越来越多的核函数也被提了出来!但是选取合适的核函数往往却不容易,因为数据的特征往往不知道。文中利用函数的Taylor展开思想,提出了一种新的核函数,叫T—KMOD,基于KMOD提出的。该核函数的灵活性更好,可以处理很多分类的问题。用网络入侵的数据对该核函数进行了仿真,从仿真的结果可以看出,和一些常用的核函数相比,它的鲁棒性更好,有更强的分类能力。同时该函数的分类效果更好。所以该核函数和一般常用的核函数相比,可能更具有一般选择性。     

通用型安全操作系统解决方案浅析

在信息安全领域,随着攻击技术的不断升级和数据泄露事件的激增,业界越来越重视服务器操作系统的安全问题。文章从等级保护安全操作系统研究入手,介绍了两种安全操作系统解决方案,对比了通用型安全操作系统相比传统自主研发的安全操作系统的优势所在。文中重点阐述了通用型安全操作系统解决方案的技术优势和实现原理,结合增强型DTE、RBAC、BLP三种访问控制安全模型,重构操作系统的安全子系统(SSOOS),动态、透明提升操作系统安全等级,以实现通用型安全操作系统的解决方案。     

A robust watermarking algorithm based on QR factorization and DCT using quantization index modulation technique

We propose a robust digital watermarking algorithm for copyright protection.A stable feature is obtained by utilizing QR factorization and discrete cosine transform(DCT) techniques,and a meaningful watermark image is embedded into an image by modifying the stable feature with a quantization index modulation(QIM) method.The combination of QR factorization,DCT,and QIM techniques guarantees the robustness of the algorithm.Furthermore,an embedding location selection method is exploited to select blocks with small modifications as the embedding locations.This can minimize the embedding distortion and greatly improve the imperceptibility of our scheme.Several standard images were tested and the experimental results were compared with those of other published schemes.The results demonstrate that our proposed scheme can achieve not only better imperceptibility,but also stronger robustness against common signal processing operations and lossy compressions,such as filtering,noise addition,scaling,sharpening,rotation,cropping,and JPEG/JPEG2000 compression.     

影响ETM影像土地利用/覆盖分类精度因素的研究

训练样本量、辅助数据和分类法是影响土地利用/覆盖分类精度的3个主要因素,通过找到这3个因素的最佳组合方式以提高分类精度,分别在25%、50%、75%、100%样本量下,加入NDVI、DEM和纹理均值特征作为辅助数据,比较了分类回归树、支持向量机、最大似然法3种分类法的效果,探讨了训练样本、辅助数据以及分类技术对土地利用/覆盖分类精度的影响。结果表明：支持向量机总体分类精度较高,在相同样本量和没有有效辅助数据的情况下,SVM可以获得最佳的分类结果,总体分类精度在85%以上;在进行分类时,加入NDVI和纹理均值特征使分类回归树分类精度提高了2.82%,说明该方法对有效辅助数据的加入较为敏感;在获取的训练样本集有限而可获取有效的辅助数据时,应优先考虑利用分类回归树进行土地利用/覆盖分类。     

自适应激素调节遗传算法

基于生物内分泌系统的激素调节原理,提出了一种新的自适应遗传算法。该算法以内分泌激素调节的Hill函数下降形式为基础,设计了自适应交叉算子和自适应变异算子,使交叉率和变异率在遗传算法迭代过程中,能够根据各代种群多样性的变化进行自适应调节,在整个进化过程中将种群多样性维持在合理水平。4种测试函数及三维人脑图像分割的实验结果显示,提出的自适应遗传算法可较好地保持种群多样性并克服早熟现象,性能优于其他两种自适应遗传算法及传统遗传算法。     

基于APR—SVM的音频分类方法

音频分类在多媒体应用中十分广泛,主要有时域分析和频域分析方法。文中提出了一种基于自适应间距比（APR）算法和支持向量机（svrd）算法的音频分类方法,先用APR算法区分语音与非语音;对于非语音,再通过SVM进行音频分类。APR算法是比较PR参数和阈值来区分语音和非语音,它和信噪比密切相关;而将非语音分成四组：音乐,汽车,会议,雨声,提取特征因子。实验结果表明：文中设计的分类器的精度达到93．75％以上,能很好地把各类型音频分开。     

基于DMT的1553B带宽扩展研究

由于传统的MIL-STD-1553B总线难以满足高速数据传输需求且更换现有总线代价过高,因此迫切需要在不影响现有基带通信的条件下升级1553B系统以提供高速通信接口。本文分析1553B的信道特性并据此选择频谱利用率高、抗频率选择性衰落的离散多音调制(DMT)作为扩展带宽的技术,基于离散多音调制,提出一个与现有通信相互兼容的扩展方案以显著提高传输速率,并对该方案涉及的关键技术进行介绍。     

基于粗糙集与改进KNN算法的文本分类方法的研究

KNN算法是文本自动分类领域中的一种常用算法,对于低维度的文本分类,其分类准确率较高。然而在处理大量高维度文本时,传统KNN算法由于需处理大量训练样本导致样本相似度的计算量增加,降低了分类效率。为解决相关问题,本文首先利用粗糙集对高维文本信息进行属性约简,删除冗余属性,而后用改进的基于簇的KNN算法进行文本分类。通过仿真实验,证明该方法能够提高文本的分类精度和准确率。