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。     

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。     

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。     

基于灵敏度分析的FPGM剪枝算法研究

针对等比例剪枝导致的重要卷积层剪枝过度、残留大量冗余参数以及精度损失较大的问题,在FPGM剪枝策略基础上融入灵敏度分析进行网络剪枝。算法采用精度反馈来分析每一层卷积层的重要性,控制单层剪枝比例分析每一层不同剪枝比例对精度损失的影响,获取各个卷积层的灵敏度;结合FPGM策略分析卷积层内卷积核的重要程度按灵敏度的剪枝比例剪掉不重要的卷积核,达到对神经网络进行有效剪枝的目的。实验结果表明,所提方法在MobileNet-v1和ResNet50上剪枝率为50%的情况下,精确度仅下降1.56%和0.11%;所提方法在精度损失一致下,ResNet50上具有更高剪枝率和更低计算量。     

基于标签推理和注意力融合的多标签文本分类方法

目前许多多标签文本分类方法主要关注文档表示,而丢失了大量标签相关的语义信息,导致分类效果不理想。针对以上问题,提出一种基于标签推理和注意力融合的分类方法,挖掘文档中与标签相关的特征以及相似标签之间的相关性,学习标签信息进行标签推理,同时采用注意力机制自学习地融合文档表示和标签表示,最终完成多标签分类任务。在AAPD和RCV1-V2数据集上进行实例验证,该方法的F1值分别达到了0.732和0.887,与其他最新方法相比其准确度均有提升,实验结果证明了标签推理和注意力融合策略的有效性。     

Parametric 3D modeling of young women's lower bodies based on shape classification

Three-dimensional (3D) human body modeling is an important research direction in the field of clothing virtual design. On the basis of 3D human body scanning, this paper studied a method to build a 3D parametric lower body model according to body classification. The research includes three main parts. (1) Anthropometry and body shape classification. We randomly selected 333 young women ages 18–25 years old in Northeast China as the experimental sample. Then we divided the lower body shape into three categories using principal component analysis and K-means clustering. (2) Determination of feature cross sections and points, and reconstruction of feature curves. According to the average values of each body type, we obtained the mean reference body by Euclidean distance method. We determined feature cross sections and points, and extracted the 3D coordinates of the feature points of the mean reference body to reconstruct the feature curves. (3) The surface lofting and establishment of parametric 3D lower body model. According to the shape characteristics of the lower body, we constructed the guiding lines for the crotch and lower limbs, and established parametric lower body models for three body types.Relevance to industry3D human modeling is an important part of garment industry digitization. This research provides an effective way to construct a parametric 3D lower body model. The method offers a reference for the parametric virtual human modeling and virtual fitting of trousers.     

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier.     

多字体印刷藏文内容监测系统研究

针对藏文舆情分析中藏文印刷品和藏文图片内容无法自动监测的难题,文章在深入分析印刷藏文字符特征和藏文文本特点的基础上,提出支持多字体印刷藏文内容监测系统的实现方法,重点阐述藏文字符的特征提取、分类算法以及藏文文本内容监测方法。     

浅析管理在信息系统安全中的必要性

在信息系统安全规划和设计中,管理作为信息系统的安全基础和信息系统各安全层面的基本要素,已经成为构建安全、可用信息系统不可或缺的必要条件。文章针对管理在信息系统安全中的作用、特点进行了论述,并结合等级保护政策提出了相应的管理建议。