基于数据密度的半监督自训练分类算法

在实际的分类任务中,无标记样本数量充足而有标记样本数量稀少的情况经常出现,目前处理这种情况的常用方法是半监督自训练分类算法。提出了一种基于数据密度的半监督自训练分类算法,该算法首先依据数据的密度对数据集进行划分,从而确定数据的空间结构;然后再按照数据的空间结构对分类器进行自训练的迭代,最终得到一个新的分类器。在UCI中6个数据集上的实验结果表明,与三种监督学习算法以及其分别对应的自训练版本相比,提出的算法分类效果更好。     

皮革工业废水的治理技术

介绍了皮革工业废水中所含污染物质铬、硫化物、悬浮物和有机化合物、无机盐等的各种去除方法。     

Multi-label core vector machine with a zero label

Multi-label core vector machine (Rank-CVM) is an efficient and effective algorithm for multi-label classification. But there still exist two aspects to be improved: reducing training and testing computational costs further, and detecting relevant labels effectively. In this paper, we extend Rank-CVM via adding a zero label to construct its variant with a zero label, i.e., Rank-CVMz, which is formulated as the same quadratic programming form with a unit simplex constraint and non-negative ones as Rank-CVM, and then is solved by Frank–Wolfe method efficiently. Attractively, our Rank-CVMz has fewer variables to be solved than Rank-CVM, which speeds up training procedure dramatically. Further, the relevant labels are effectively detected by the zero label. Experimental results on 12 benchmark data sets demonstrate that our method achieves a competitive performance, compared with six existing multi-label algorithms according to six indicative instance-based measures. Moreover, on the average, our Rank-CVMz runs 83 times faster and has slightly fewer support vectors than its origin Rank-CVM.     

纤维素科学与技术研究进展

本文综述纤维素科学与技术的研究进展。阐述了纤维素结构、纤维素的合成、纤维素液晶、功能纤维素、纤维素溶剂、纤维素裂解和纤维素的废物利用等的最新动态。     

压缩机废油回收工艺小结

介绍了压缩机废油回收的原理、工艺及操作要点,达到了节油降耗的目的。     

Chemical Reaction Engineering and Research and development of gas solid systems

A general procedure is proposed for innovative research and development of gas-solid reactor systems, with a brief explanation of the significance of each step in the procedureBased upon the contacting mode between gas and solid phases, as well as the ways of supplying thermal energy to the reacting regions, various types of gas-solid reactor systems are classified by using tables of so called “matrix” form, for thermal cracking and gasification of heavy oils, gasification of coal, gasification of solid waste, calcination of limestone, clinkering of cement and reduction of iron ore.The importance of fundamental concepts is emphasized for successful research and development by presenting several examples; namely, calcination of limestone, thermal cracking of heavy oils and gasification of solid waste materials.In connection with the direction in which fundamental research should be oriented, four primary ways of thinking are proposed, which can be applied to obtain innovative ideas for further research and development in this field.One example of the author's practical experience was selected to show the role of the fundamental research in the course of large scale development. Finally the author outlines the role of chemical reaction engineering to innovate the novel gas-solid reactor systems which may be inevitable for simultaneous solution of the three big E's; namely, Energy, Environment and Economy.     

电解法处理利福霉素SV钠废渣分离液的研究

根据电化学原理，采用电解法，利用铁屑与炭粒作电极，处理利福霉素SV钠药渣分离液，讨论各种因素对分离液污染物作效果的影响，COD去除率可达91．8％左右，脱色率可达95％左右。     

微晶纤维素增粘剂的研制

以棉浆为原料，废盐酸为水解催化剂，所得合成革用微晶纤锥素增粘剂的质量指标达到了德国和日本同类产品的标准。     

基于多特征融合的运动物体识别方法研究

为了实现运动目标的实时检测,本文基于多特征融合,提出了一种运动物体分级识别方法.首先通过对运动目标的分割,分析得到各个物体的形状矩特征、面积大小及运动速度.对上述特征,采用支持向量机方法对其矩特征进行快速的一级分类,然后对一级分类结果及各物体的面积、速度等信源根据其对分类的重要程度,采用模糊积分技术进行多特征融合分类.实验表明,本方法具有较强的学习能力及较高的识别精度,可有效地应用于道路监控等系统.