Examining the Capacity of Text Mining and Software Metrics in Vulnerability Prediction

Software security is a very important aspect for software development organizations who wish to provide high-quality and dependable software to their consumers. A crucial part of software security is the early detection of software vulnerabilities. Vulnerability prediction is a mechanism that facilitates the identification (and, in turn, the mitigation) of vulnerabilities early enough during the software development cycle. The scientific community has recently focused a lot of attention on developing Deep Learning models using text mining techniques for predicting the existence of vulnerabilities in software components. However, there are also studies that examine whether the utilization of statically extracted software metrics can lead to adequate Vulnerability Prediction Models. In this paper, both software metrics- and text mining-based Vulnerability Prediction Models are constructed and compared. A combination of software metrics and text tokens using deep-learning models is examined as well in order to investigate if a combined model can lead to more accurate vulnerability prediction. For the purposes of the present study, a vulnerability dataset containing vulnerabilities from real-world software products is utilized and extended. The results of our analysis indicate that text mining-based models outperform software metrics-based models with respect to their F₂-score, whereas enriching the text mining-based models with software metrics was not found to provide any added value to their predictive performance.     

你也需要蒙特卡罗方法——一个得心应手的工具

本文通过几个例子和通俗的语言简要介绍蒙特卡罗(MC)方法的应用.文中例子显示,即使是一些尚无其它办法计算的复杂问题,应用MC方法也可以获得可用的结果,并且使用中档的个人电脑也可以在极短的时间内完成.文中还提供了一个品质优良的随机数发生器,据此读者不难把MC方法立刻用于自己的研究工作中。     

Advanced Development of Supercritical Fluid Chromatography in Herbal Medicine Analysis

The greatest challenge in the analysis of herbal components lies in their variety and complexity. Therefore, efficient analytical tools for the separation and qualitative and quantitative analysis of multi-components are essential. In recent years, various emerging analytical techniques have offered significant support for complicated component analysis, with breakthroughs in selectivity, sensitivity, and rapid analysis. Among these techniques, supercritical fluid chromatography (SFC) has attracted much attention because of its high column efficiency and environmental protection. SFC can be used to analyze a wide range of compounds, including non-polar and polar compounds, making it a prominent analytical platform. The applicability of SFC for the separation and determination of natural products in herbal medicines is overviewed in this article. The range of applications was expanded through the selection and optimization of stationary phases and mobile phases. We also focus on the two-dimensional SFC analysis. This paper provides new insight into SFC method development for herbal medicine analysis.     

基于改进Hopfield神经网络的自适应二维噪声对消器

提出了基于连续型Hopfield神经网络(CHNN)的自适应二维噪声对消器,讨论了神经网络的结构和原理及相应的自适应滤波算法,并从理论上进行了论证.仿真结果表明相对于采用最小均方算法的二维线性噪声对消器,CHNN噪声对消器能更有效实现二维噪声的消除,保持原信号的完整性,获得较好的去噪声效果.     

Comprehensive reversed-phase×chiral two-dimensional liquid chromatography coupled to quadrupole-time-of-flight tandem mass spectrometry with post-first dimension flow splitting for untargeted enantioselective amino acid analysis

This work describes a comprehensive achiral × chiral two-dimensional liquid chromatography separation for enantioselective amino acid analysis coupled to electrospray ionization-tandem mass spectrometry detection using data-independent acquisition. Flow splitting after the first and second dimension separation was utilized for volumetric flow reduction and for enabling a multi-detector approach (with ultraviolet, fluorescence, charged aerosol, and MS detection), respectively. Derivatization with 6-aminoquinolyl-N-hydroxysuccinimidyl carbamate provided a chromophore, a fluorophore, and an efficient mass tag for efficient ionization in positive electrospray ionization-mass spectrometry. Chiral columns often have limitations in terms of their chemoselectivity, which may be a problem when complex sample mixtures with structurally related compounds need to be separated. It can be alleviated by a reversed-phase×chiral two-dimensional-liquid chromatography setup, in which the first dimension provides the chemoselectivity and a chiral tandem column constituted of quinine-carbamate derived weak anion-exchanger and zwitterionic ion-exchanger in the second dimension separation of D- and L-amino acid enantiomers. The method was used to control the stereointegrity of the therapeutic peptide octreotide. After hydrolysis, all amino acid constituents were detected with the correct configuration and composition. Some options for flow splitting and integration of destructive detectors in the first dimension separation are outlined.     

基于WENO重构的真正多维黎曼求解器

具有良好守恒性与网格适应性的有限体积格式在流体力学的数值计算中占有重要地位。其中，求解数值流通量是实施有限体积法的关键步骤。一维情形下，通过求解局部黎曼问题来获得数值流通量的相关理论已经比较成熟。但是在计算多维问题时，传统的维度分裂方法仅考虑沿界面法向传播的信息，这不仅影响格式的精度，还可能会造成数值不稳定性从而诱发非物理现象。本文基于对流-压力通量分裂方法来构造真正多维的黎曼求解器，通过求解网格顶点处的多维黎曼问题来实现格式的多维特性。采用五阶WENO重构方法来获得空间的高阶精度，时间离散采用三阶TVD龙格-库塔格式。一系列数值实验的结果表明，真正多维的黎曼求解器不仅具有更高的分辨率还能有效克服多维强激波模拟中的数值不稳定性。