Inductive Model Generation for Text Classification Using a Bipartite Heterogeneous Network

Algorithms for numeric data classification have been applied for text classification. Usually the vector space model is used to represent text collections. The characteristics of this representation such as sparsity and high dimensionality sometimes impair the quality of general-purpose classifiers. Networks can be used to represent text collections, avoiding the high sparsity and allowing to model relationships among different objects that compose a text collection. Such network- based representations can improve the quality of the classification results. One of the simplest ways to represent textual collections by a network is through a bipartite heterogeneous network, which is composed of objects that represent the documents connected to objects that represent the terms. Heterogeneous bipartite networks do not require computation of similarities or relations among the objects and can be used to model any type of text collection. Due to the advantages of representing text collections through bipartite heterogeneous networks, in this article we present a text classifier which builds a classification model using the structure of a bipartite heterogeneous network. Such an algorithm, referred to as IMBHN （Inductive Model Based on Bipartite Heterogeneous Network）, induces a classification model assigning weights to objects that represent the terms for each class of the text collection. An empirical evaluation using a large amount of text collections from different domains shows that the proposed IMBHN algorithm produces significantly better results than k-NN, C4.5, SVM, and Naive Bayes algorithms.     

基于一致性的小型四旋翼机群自主编队分布式运动规划

设计一种小型四旋翼无人机群起飞后自主形成正多边形编队的分布式运动规划方法.在四旋翼无人机的串级控制系统框架下,分布式编队控制器以简化agent模型为基础,同时采用平均一致性算法和有领导一致性算法,共同产生各无人机位置与偏航角的期望轨迹.讨论了达成最终协调目标队形的拓扑条件,并给出一种基于有向Hamilton环的通信拓扑设计方案.最后通过数值仿真验证了所提出算法的有效性.     

全面玩转名片二维码

二维码在日常生活中已经得到广泛应用。作为使用最广泛的个人名片信息,如果能很好地利用二维码这个媒介,实现文字信息与实体名片之间的转换,将会大大方便人与人之间的交流。     

游戏玩家的福音 解析G-SYNC技术

正近期ACER发布了旗下最新款4K显示器XB280HK。与传统产品不同的是,该显示器内建G-Sync模块,也因此被很多玩家视为新一代"游戏神器"。那么,G-Sync是什么?为何它会被追捧为游戏世界的神器呢?刷新率与FPS的矛盾在PC游戏的各项数值中,FPS是对"帧"变化速度的描述,单位为"帧/秒"。一般来说,RPG类游戏至少需要24fps,而射击和赛车类游戏则需要达到60fps才可称之为理想。FPS的高低则取决于PC端的硬件,也就是显卡每秒所生成的图像帧数。     

磷化与发蓝工艺的区别及应用

磷化与发蓝在实际生产中应用极为广泛,这两种工艺有着不同的生成机理和应用范围,因为它们在某些方面都能够用于机械零件的防腐蚀,在选择表面处理工艺时容易混淆.本文拟在对磷化与发蓝两种工艺的生成机理、膜层结构与厚度、适用范围等方面进行比较,以便于正确地选择使用.     

用现场生成填料补强的胶料及其制品

本发明涉及通过使橡胶在硅烷化填料表面聚合而制备的胶料，以及含有这种胶料的制品（如至少一种零部件由该胶料制成的轮胎）。在有经烯基硅烷进行了硅烷化的填料存在时，使共轭二烯烃发生聚合反应，可以实现这种补强。具体而言，用丁基锂或过氧化物催化剂对硅烷化补强填料进行预处理，随后在有这种改性填料存在时，通过阴离子聚合反应或在有机溶剂中进行自由基聚合反应，使共轭二烯发生聚合。预期也可由这种预成型复合材料和至少一种其它橡胶构成预成型胶料。填料可以是（例如）沉淀法白炭黑、炭黑和／或改性炭黑。本文还介绍了用这种复合材料或胶料制成的零部件（如胎面）。     

FOF-18结构与性能的量子化学研究

用B3LYP法,在6-31G基组水平上优化了FOF-18的几何构型,得其稳定的几何构型;在振动分析的基础上求得体系的振动频率、IR谱;采用Monte-Carlo方法预估了密度;设计等键等电子反应计算了生成焓;运用Kamlet公式预测爆速、爆压和爆热;将计算性能与CL-20的性能作比较。结果表明,FOF-18整个分子呈N字形,且存在7个强吸收峰,密度2.06g/cm3、生成焓501.03kJ/mol、爆速9411.82m/s、爆压42440.76MPa、爆热6637.46kJ/kg,该化合物的性能与CL-20接近。     

视觉特征对比解耦的广义零样本学习

广义零样本学习通常利用在ImageNet上预训练的深度模型来提取相应的视觉特征,然而预训练模型提取到的视觉特征不可避免地包含和语义无关的信息,这将导致语义—视觉对齐的偏差以及对不可见类的负迁移,从而影响分类结果。为解决上述问题,提出了视觉特征对比解耦的广义零样本学习模型(visual feature contrast decoupling for generalized zero-shot learning, VFCD-GZSL),通过解耦出视觉特征中的语义相关表示来降低冗余信息对分类结果的影响。具体来说,首先用条件变分自编码器生成不可见类的视觉特征。然后通过解耦模块将视觉特征解耦语义相关和语义无关的潜层表示,同时添加总相关惩罚和对比损失来鼓励两者间的相互独立,并用语义关系匹配模型衡量其语义一致性,从而指导模型学习语义相关表示。最后使用特征细化模块细化后的特征和语义相关表示联合学习一个广义零样本学习分类器。在四个数据集上的实验均取得较优的结果,证实了所提方法的有效性。     

硬约束限制的情感文本生成方法研究

预训练语言模型在情感文本的生成任务中取得了良好效果,但现有情感文本生成方法多使用软约束的方式控制文本整体的情感属性,缺乏单词和短语级别的硬性控制。为解决以上问题,提出硬约束限制下的情感文本生成方法。首先使用方面情感分析技术提取句子的方面词、情感词并判断情感极性;之后,选择目标情感的方面词和情感词作为预训练语言模型的硬约束输入来重建完整句子,其中,设计了一种新的单词权重计算方法,旨在使模型优先生成重要单词。实验结果表明,该方法生成的句子不仅具有方面级情感,在文本质量和多样性的评价指标上也有显著提高。     

Generating Web Traffic Based on User Behavioral Model

Generating web traffic is of great importance to analyze performance of new designed network, test new equipment, and verify new protocols, etc.. However, most existing traffic generation systems tend to simulate the overall characteristics of network traffic, while neglecting of the behavior of the individual users. Nevertheless, in principle, the emerged characteristics of overall traffic originate from the aggregation of individual users＇ access behavior. In this paper, we propose an innovative web traffic generating method based on user browsing behavior. Our method simulates the real users＇ accessing behavior, and visits the real web servers. Then, we design and develop a web traffic generating system. Because our system accesses the real websites, it can produce almost the real network traffic. The test results show that the traffic generated by our system has characteristics of burstiness and self-similarity, which are widely found and characterized in many real networks. In addition, our system can better reflect real user＇s web browsing behavior.