基于自学习规则和改进贝叶斯结合的问题分类*

根据对中文问题的分析可知,问题中的疑问词和中心词等关键词对问题所属类型起着决定性的作用。提出利用自学习方法建立疑问词—类别和疑问词+中心词—类别两种规则,并结合改进贝叶斯模型的问题分类方法。该方法充分利用了关键词对分类的贡献。实验结果表明,该分类方法有很大的改进,准确率达到了84%。     

混合匹配规则的否定选择算法

针对目前基于免疫的检测器生成算法中,匹配规则单一造成的检测器质量低下的问题,提出一种基于混合匹配规则的否定选择算法,采用海明距离整体匹配的各段内R连续比特匹配的否定选择算法,即混合匹配否定选择算法,对算法的性能进行了分析．实验结果表明,该算法能够高效地产生所需要的检测器,提高了检测率,且降低了误报率．     

云计算环境下多来源数据最优选取模型仿真

在云计算环境下多来源数据最优选取的研究中,由于来自不同的服务器数据具有不同特征,数据所含信息的融合度也不同,使得数据可选取特征存在较强的关联性.传统的数据最优选取模型,在进行选择时,关联性会给最优数据的选择带来干扰,选出大量的相关数据,不能很好地排除关联性数据,无法实现数据的最优高效选取,提出一种依据数据估计量变化的云计算环境下多来源数据最优选取模型,利用前几点数据拟合直线或曲线,进行云计算环境下多来源数据最优选取中干扰数据的预测,分析干扰数据点删除前后推断统计量的变化,检测该干扰数据点是不是强干扰点,过滤强干扰数据点后的模型则是云计算环境下多来源数据最优选取模型,通过分析数据排除模型引起的估计量的变化,实现云计算环境下多来源数据的最优选取.仿真结果说明,在大量云计算环境下多来源数据的处理中,采用所提模型可有效选取最优数据,并且具有较高的准确率.     

面向移动机器人应用的跨平台自适应软件框架

摘要：自适应软件在移动机器人上具有广泛的应用前景,然而要在具有不同软硬件平台的移动机器人上开发自适应软件是一件非常困难的事情．．为了解决这个问题,提出并实现了一个面向移动机器人应用的跨平台自适应软件框架该框架屏蔽了运行平台的软硬件差异性,并使用规则文件将自适应逻辑分离出来,从而降低了自适应软件开发的难度。为了便于编写及检查规则文件,还实现了一个可视化的规则文件编辑器,用于自动生成模型图,并检查规则中存在的语法及逻辑错误i,最后,通过实验测试了框架的使用情况,并对框架的应用效果进行了评估、     

Rheological behavior of reactive blending of epoxidized natural rubber with cassava starch and epoxidized natural rubber with natural rubber and cassava starch

Epoxidized natural rubbers (ENR‐25 and ENR‐45) were prepared using the performic epoxidation method. Two‐component (ENR–cassava starch) and three‐component (ENR–NR–cassava starch) blends were prepared. ENR‐25 and ENR‐45 were blended with various quantities of gelatinized cassava starch in the latex state. The pure ENR exhibited lower shear stress and shear viscosity than those of the blends with cassava starch. Furthermore, the shear stress and shear viscosity were increased with an increase in the cassava starch concentration. The chemical interaction between the epoxide groups in the ENR and the hydroxyl groups in the cassava starch molecules might be the reason for the increasing trends of the shear stress and shear viscosity. The blends are classified as compatible blends because of the strong chemical bonding between different phases. SEM micrographs were used to clarify the compatibility. Power law behavior with pluglike flow profiles was observed for all sets of ENR–NR–cassava starch blends. Very low power law index values (<0.34) and highly pseudoplastic fluid behavior were also observed. The log additive rule was applied to plots of zero shear viscosity (consistency index) and the shear viscosity versus the concentration of ENR‐25. Positive deviation blending was observed, which indicates compatible blends. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 91: 1752–1762, 2004     

基于软分区的地区电网自动电压控制系统

介绍贵港地区电网基于软分区的三级自动电压控制（AVC）系统,并对该系统的三级控制原理及区域变电站的控制规则进行说明。     

立方型状态方程结合Eyring理论在液体混合物黏度计算中的应用

Cubic equations of state (EOS) have been combined with the absolute rate theory of Eyring to calculate viscosities of liquid mixtures. A modified Huron Vidal gE-mixing rule is employed in the calculation and in comparison with the van Laar and the Redlich-Kister-type mixing rule. The EOS method gives an accurate correlation of liquid viscosities with an overall average deviation less than 1% for 67 binary systems including aqueous solutions. It is also successful in extrapolating viscosity data over a certain temperature range using parameters obtained from the isotherm at a given temperature and in predicting viscosities of ternary solutions from binary parameters for either polar or associated systems.     

无人驾驶规则的自动提取方法研究

无人驾驶汽车的测试技术主要是通过虚拟测试和场地测试的方法来检测无人驾驶汽车的智能化水平,通过不断的学习和总结经验来提高无人驾驶的安全性,这种方法耗费大量的人力物力以及时间。为此,从文本的角度出发,利用驾驶行为相关文本,通过NLP技术和基于规则的方法构建一个无人驾驶规则库,依据这个规则库来辅助测试无人驾驶汽车能否满足道路安全要求。实验结果表明,对《中华人民共和国道路交通安全法实施条例》处理后规则提取的正确率为89.85%,驾考题库文本的正确率为87.33%。     

Context-aware cognitive design assistant: Implementation and study of design rules recommendations

Design rules are an essential interface to facilitate the information exchange between designers and experts. Despite many innovations in Knowledge-Based Engineering and Knowledge Management, unstructured design rules documents are still widely used in the manufacturing industry. Due to the complexity of the design process, these documents often contain hundreds of design rules, applicable in varying design contexts. Searching for the right rules according to a design context is demanding in time and cognitive resources. In this paper, we propose a Context-Aware Cognitive Design Assistant (CACDA) to capture the design context and perform tasks such as the recommendation of design rules, the verification of design solutions, or the automation of design routines. Contrary to existing works in model quality testing, the CACDA uses a proactive approach of design rules application and helps designers to provide error-free designs on first attempt. In this paper, we present the design rules recommendation system of the CACDA, its capabilities and its implementation. Then, to measure the impact of design rules recommendations on the design process, we compare our approach with the use of traditional design rules documents. Results show that the use of the CACDA’s design rules recommendations lower the perceived difficulty of design rules retrieval from 75 to 43.5 on a scale of 100. On average, participants that used the demonstrator successfully applied 8.6 design rules on the 25 applicable design rules of our set. Participants that used unstructured documentation correctly applied 4.3 design rules. The global cognitive weight of the design activity as well as the design rules retrieval performances appear to be unchanged. These results demonstrate the usability of the demonstrator and show a positive impact on the design process and on the quality of CAD models. Future works will focus on the overcome of the main limitations of our current experiments, with a panel of professional designers, a lager design rules set and the implementation of several lacking features of the CACDA into the demonstrator.