短文本分类技术研究综述

短文本由于特征稀疏并且多歧义等特点,导致难以对其进行高效的分类。本文首先针对短文本的特点,介绍了短文本分类的研究现状,其次对短本文分类涉及到的技术及相关理论进行了阐述,并对文本预处理技术、Word2vec以及LDA模型等文本表示方法进行了重点分析。最后总结了短文本分类未来的发展趋势。

Universal composable secure protocol for EPC system

As an important component of internet of things, electronic product code （EPC） system is widely used in many areas. However, the mass deployment of EPC system is frequently degraded by security and privacy problems. Therefore, the major researches focus on the design of a secure EPC system with high efficiency. This paper discusses the security requirements of EPC system and presents a universal composable （UC） model for EPC system, the ideal functionality of EPC system is also formally defined with the UC framework. Then a secure protocol for EPC system under UC framework is proposed and the analysis of security and performance of the proposed protocol is given, in comparison with other protocols, the results show that the proposed protocol is UC secure and can provide privacy protection, untraceability, authorized access, anonymity and concurrent security for EPC system. Furthermore, less computation and storage resource are required by the proposed protocol.

Efficient representation of text with multiple perspectives

An effective text representation scheme dominates the performance of text categorization system. However, based on the assumption of independent terms, the traditional schemes which tediously use term frequency （TF） and document frequency （DF） are insufficient for capturing enough information of a document and result in poor performance. To overcome this limitation, we investigate exploring the relationships between different terms of the same class tendency and the way of measuring the importance of a repetitive term in a document. In this paper, a group of novel term weighting factors are proposed to enhance the category contribution for each term. Then, based on a novel strategy of generating passages from document, we present two schemes, the weighted co-contributions of different terms corresponding to the class tendency and the weighted co-contributions for each term in different passages, to achieve improvements on text representation. The prior scheme works in a dimensionality reduction mode while the second one runs in the conventional way. By employing the support vector machine （SVM） classifier, experiments on four benchmark corpora show that the proposed schemes could achieve a consistent better performance than the conventional methods in both efficiency and accuracy. Further analysis also confirms some promising directions for the future works.

Variational learning for finite Beta-Liouville mixture models

In the article, an improved variational inference （VI） framework for learning finite Beta-Liouville mixture models （BLM） is proposed for proportional data classification and clustering. Within the VI framework, some non-linear approximation techniques are adopted to obtain the approximated variational object functions. Analytical solutions are obtained for the variational posterior distributions. Compared to the expectation maximization （EM） algorithm which is commonly used for learning mixture models, underfitting and overfitting events can be prevented. Furthermore, parameters and complexity of the mixture model （model order） can be estimated simultaneously. Experiment shows that both synthetic and real-world data sets are to demonstrate the feasibility and advantages of the proposed method.

Exposing photo manipulation with inconsistent perspective geometry

Manipulated digital image is got interesting in recent years. Digital images can be manipulated more easily with the aid of powerful image editing software. Forensic techniques for authenticating the integrity of digital images and exposing forgeries are urgently needed. A geometric-based forensic technique which exploits the principle of vanishing points is proposed. By means of edge detection and straight lines extraction, intersection points of the projected parallel lines are computed. The normalized mean value （NMV） and normalized standard deviation （NSD） of the distances between the intersection points are used as evidence for image forensics. The proposed method employs basic rules of linear perspective projection, and makes minimal assumption. The only requirement is that the parallel lines are contained in the image. Unlike other forensic techniques which are based on low-level statistics, this method is less sensitive to image operations that do not alter image content, such as image resampling, color manipulation, and lossy compression. This method is demonstrated with images from York Urban database. It shows that the proposed method has a definite advantage at separating authentic and forged images.