基于卷积神经网络的大坝安全监测数据异常识别

为了减轻大坝安全监测数据异常识别的数据处理压力,解决传统方法难以辨别非最值异常点的问题,提出利用卷积神经网络(CNN)识别大坝安全监测数据异常模式。监测数据过程线的周期性及异常值的显著差别使CNN得以发挥图像分类功能,分别将存在单个突跳点、无异常、存在震荡段、台阶、多个突跳点、台坎的监测数据过程线作为6类图像,人工生成65 000张训练数据及6 500张测试数据,6类图像的数量比为1∶1.5∶1∶1∶1∶1。利用CNN对混合6种过程线图像的测试数据集进行图像分类,总体准确率为0.973 1,且6种图像的准确率都至少为0.93。进一步对CNN进行改进,构建CNN监测数据异常识别模型,增加数据异常位置搜索功能;模型输入为监测数据过程线图像,输出为图像编号、图像类别及异常位置。研究成果有助于实现大坝自动、及时预警,及时了解大坝安全状况。     

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.     

CNN-XGBoost混合模型在音频场景分类中的应用

在拥有海量数据和强大计算能力的人工智能时代,音频场景分类成为了场景理解的重要研究内容之一.针对音频场景分类建模困难和精确率不高的问题,本文提出一种基于卷积神经网络和极端梯度提升算法相结合的系统模型.首先,将预处理后的音频信号转换成梅尔声谱图,然后输入到卷积神经网络中完成抽象特征提取,最后利用极端梯度提升算法进行分类.为了评估模型的有效性,在城市音频场景UrbanSound8K数据集上进行分类性能测试,结果表明,该混合算法模型对音频场景的分类精确率可以达到89%,优于传统的神经网络算法模型,说明该混合模型对音频场景分类问题的有效性.     

细菌特征分析的革兰氏阴阳性判别算法

自然界中细菌无处不在,细菌的革兰氏阳性和阴性的有效分类对于临床治疗具有重要意义.现有的细菌的革兰氏阴阳性分类主要依赖于革兰氏染色法.这种方法借助细菌细胞壁结构的不同引起的染色性的差异来进行分类,然而涂片的厚薄和脱色时间的掌握制约着革兰氏染色法的准确性,并且实验需要花费一定时间.本文提出一种用计算机智能分析的细菌革兰氏阴阳性判别方法—基于蛋白质序列特征分析的细菌革兰氏阴阳性判别算法GCBPS.该算法首先挖掘出闭合邻接序列模式(FCloConSP)集合并对大量已知阴阳性的细菌蛋白质序列特征进行提取,然后先利用赋参的余弦相似度距离计算方法来衡量待测细菌蛋白质序列与阳性细菌特征集之间的距离来初步判别是否为阳性,再通过去假阴性等处理后得到最终的细菌革兰氏阴阳性判别结果.该算法已在标注的1591条革兰氏阴性菌以及576条革兰阳性菌的标准数据集上进行评估,实验结果表明,判别的平均正确率F1值可达到95.4%.     

面部表情的深度卷积级联森林识别

面部表情识别广泛应用于各种研究领域,针对面部表情识别使用深度神经网络方法结构复杂、可解释性差和传统机器学习方法特征提取缺乏多样性、识别率低的问题.提出了一种新的深度卷积级联森林(Deep Convolution Cascade Forest,DCCF)方法用于人脸面部表情识别,该方法通过卷积神经网络深度学习人脸面部显著特征,并采用基于随机森林的级联结构森林逐层学习识别出不同的面部表情特征,提高了人脸表情的识别准确率.DCCF在JAFFE、CK+和Fer2013 3个公开面部表情数据集进行了实验,并对面部表情提取的5种特征和7种分类方法进行了比较分析,结果显示DCCF在对比的算法中人脸表情识别性能最好,3个数据集的准确率分别达到91.4%,98.7%,71.6%.     

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。     

一种优化的贝叶斯分类算法

贝叶斯分类方法因具有严密的数学理论基础,于是成为一种简单而有效的数据挖掘方法;然而,贝叶斯分类器要求——条件独立性假设和每个属性权值为1,这极大降低了贝叶斯分类器的性能;针对贝叶斯分类器的局限性,文章提出了一种优化的贝叶斯分类算法;文中,首先利用粗糙集理论对待分类数据集进行属性约简,删除冗余属性;然后给出了属性权值的计算方法和公式,目的在于更准确地描述数据集的重要性和相关性;同时,通过weka3.6.2工具,以UCI机器学习数据库中的数据集为测试数据,进行了对比测试;实验结果表明:OBCA具有较高的分类准确率。     

面向信息处理的突发事件语料库分类体系研究

本文分析了突发事件新闻的特点、建设突发事件新闻语料库的目的和意义,研究了突发事件新闻语料的分类体系和编码。研究结果对突发事件新闻语料库的建设、突发事件新闻信息检索、国家相关部门对突发事件应急处理方案制定以及对流行病学的医学研究等领域具有一定的理论意义和应用价值。