一种基于改进TF-IDF函数的文本分类方法

为了解决传统TF-IDF函数由于忽略特征项之间的联系带来的诸多问题,对TF-IDF函数在文本分类中的应用进行了研究.结合信息论相关知识,找出了类间分布度和类内分布度表征特征项之间的潜在关系,进而提出改进的TF-IDF函数用于文本分类.实验表明,改进后的TF-IDF函数是有效可行的,而且较好的弥补了传统方法所丢失的特征项之间的关联信息,提高了文本分类的准确率.     

江门市经济发展因素的定量分析（1980－1991年）

本文利用改进的柯布－道格拉斯生产函数，对江门市１９８０－１９９１年期间，各经济投入量及科技进步对经济增长的作用进行宏观的定量分析。为了削弱非规律因素对数据的影响，在计算过程中进行了低频滤波处理。     

非风险中性定价意义下幂函数族期权定价模型

利用偏微分方程基本解的方法,推导出非风险中性意义下的幂函数族看涨期权的定价公式和看涨—看跌期权的平价公式。     

函数子卡诺图及其在逻辑设计中的应用

在逻辑电路的设计过程中,经常涉及到用卡诺图化简逻辑函数,本文给出一种新的化简方法,即函数子卡诺图的化简法,同时举例说明在逻辑设计中的应用。     

求解多背包约束下下模集函数最大值的近似算法及其性能保证

将部分穷举法与贪婪算法相结合,给出求解多背包约束下非减下模集函数最大值的近似算法．证明了该算法的性能保证是1-e^-1,算法的时间复杂性为O（3n^4）．     

On actions of Drinfel'd doubles on finite dimensional algebras

Let q be an nth root of unity for $n>2$ and let $T_n(q)$ be the Taft (Hopf) algebra of dimension $n^2$. In 2001, Susan Montgomery and Hans-Jürgen Schneider classified all non-trivial $T_n(q)$-module algebra structures on an n-dimensional associative algebra A. They further showed that each such module structure extends uniquely to make A a module algebra over the Drinfel'd double of $T_n(q)$. We explore what it is about the Taft algebras that leads to this uniqueness, by examining actions of (the Drinfel'd double of) Hopf algebras H “close” to the Taft algebras on finite-dimensional algebras analogous to A above. Such Hopf algebras H include the Sweedler (Hopf) algebra of dimension 4, bosonizations of quantum linear spaces, and the Frobenius–Lusztig kernel $u_q({\mathfrak{sl}}_2)$.     

Dew Points of Binary Methane + Water: Measurement and Correlation

Experimental measurements of dew points for four methane + water mixtures between 2.6 2 10 5 Pa and 100.4 2 10 5 Pa and the temperature range from 225.5 K to 272.7 K were carried out. The experimental results were analysed in terms of both an equation of state model and an excess function-equation of state method, which reproduced the experimental data within AAD from 1.8 to 3.1 K and from 0.9 to 1.8 K, respectively.     

Phase Stability and Elastic Properties of Chromium Borides with Various Stoichiometries

Phase stability is important to the application of materials. By first‐principles calculations, we establish the phase stability of chromium borides with various stoichiometries. Moreover, the phases of CrB₃ and CrB₄ have been predicted by using a newly developed particle swarm optimization (PSO) algorithm. Formation enthalpy–pressure diagrams reveal that the MoB‐type structure is more energetically favorable than the TiI‐type structure for CrB. For CrB₂, the WB₂‐type structure is preferred at zero pressure. The predicted new phase of CrB₃ belongs to the hexagonal P‐6m2 space group and it transforms into an orthorhombic phase as the pressure exceeds 93 GPa. The predicted CrB₄ (space group: Pnnm) phase is more energetically favorable than the previously proposed Immm structure. The mechanical and thermodynamic stabilities of predicted CrB₃ and CrB₄ are verified by the calculated elastic constants and formation enthalpies. The full phonon dispersion calculations confirm the dynamic stability of WB₂‐type CrB₂ and predicted CrB₃. The large shear moduli, large Young’s moduli, low Poisson ratios, and low bulk and shear modulus ratios of CrB₄? PS_C and CrB₄? PS_D indicate that they are potential hard materials. Analyses of Debye temperature, electronic localization function, and electronic structure provide further understanding of the chemical and physical properties of these borides.     

Artificial Neural Networks in water analysis: Theory and applications

Artificial Neural Networks (ANNs) have seen an explosion of interest over the last two decades and have been successfully applied in all fields of chemistry and particularly in analytical chemistry. Inspired from biological systems and originated from the perceptron, i.e. a program unit that learns concepts, ANNs are capable of gradual learning over time and modelling extremely complex functions. In addition to the traditional multivariate chemometric techniques, ANNs are often applied for prediction, clustering, classification, modelling of a property, process control, procedural optimisation and/or regression of the obtained data. This paper aims at presenting the most common network architectures such as Multi-layer Perceptrons (MLPs), Radial Basis Function (RBF) and Kohonen's self-organisations maps (SOM). Moreover, back-propagation (BP), the most widespread algorithm used today and its modifications, such as quick-propagation (QP) and Delta-bar-Delta, are also discussed. All architectures correlate input variables to output variables through non-linear, weighted, parameterised functions, called neurons. In addition, various training algorithms have been developed in order to minimise the prediction error made by the network. The applications of ANNs in water analysis and water quality assessment are also reviewed. Most of the ANNs works are focused on modelling and parameters prediction. In the case of water quality assessment, extended predictive models are constructed and optimised, while variables correlation and significance is usually estimated in the framework of the predictive or classifier models. On the contrary, ANNs models are not frequently used for clustering/classification purposes, although they seem to be an effective tool. ANNs proved to be a powerful, yet often complementary, tool for water quality assessment, prediction and classification.