Research on the comprehensive traffic state evaluation model linked with drivers’ perception under the vehicle networking

Unified judgment standards and methods are often adopted to identify traffic state in certain road network based on traffic flow parameters. However, drivers often have different perceptions about the traffic state on different road sections, since their expectations on traffic state vary more or less from each other on different road sections. In particular, under the vehicle networking, out of considerations for safety and other relevant factors, requirements for the correlation and coordination of running vehicles have also raised significantly. Therefore, it is necessary to take driver’s perception about the driving conditions of certain road sections into consideration to adjust the release of traffic state. This paper has provided a comprehensive traffic state evaluation model linked with driver’s perception under the vehicle networking. The authors first establish an ANFIS model based on the T–S model and then conduct statistical analysis on drivers’ perceptions about certain traffic state. At last, the authors use the results of statistical analysis as regulatory factors to amend the parameters input through ANFIS. Through simulation, this paper has demonstrated that the model established has a high rate of convergence, a high identification precision and the generalization ability to conduct researches on the identification of traffic state.     

基于条件随机场的中医临床病历命名实体抽取

中医临床病历是中医重要的科研数据资源,但目前临床病历仍以文本为主要表达形式,对病历数据深入分析的前提是进行结构化信息抽取,而命名实体抽取是其基础性步骤。针对中医临床病历的命名实体,如症状、疾病和诱因等的抽取问题,通过手工标注的413份病历数据(以中文字为特征)与4类特征模版,将条件随机场(CRF)、隐马尔科夫模型(HMM)和最大熵马尔科夫模型(MEMM)用于中医病历命名实体抽取的实验,并进行比较分析。结果表明,结合合适的特征模版,CRF命名实体抽取方法取得了较好的性能,F1值的症状达到0.80,疾病名称达到0.74,诱因0.74。与HMM和MEMM相比,CRF有最高的准确率和召回率,是一种较为适用的中医临床病历命名实体抽取方法。     

基于有限状态机的RFID流数据过滤与清理技术

为了实现从大量不可靠、冗余的RFID（radio frequency identification）流数据中提取有效信息,提高RFID系统中数据的质量,提出了一种基于有限状态机的RFID 流数据过滤与清理方法.实验结果表明：该方法能够有效过滤系统外标签数据,清理系统内部冗余标签数据,筛选有效标签数据,并能够降低漏读、误读带来的风险.最后,利用地理信息系统的可视化技术,将过滤与清理结果展示在地图上.     

直接甲醇燃料电池用碳气凝胶载铂催化剂的研究

利用溶胶—疑胶方法制备了高比表面积的碳气凝胶,利用浸渍还原法制备了Pt/碳气凝胶和Pt/C催化剂。采用BJH和TEM考察碳气凝胶的孔径分布和金属粒子的大小与分布,循环伏安曲线测试考察Pt/碳气凝胶对甲醇催化氧化性能的影响。结果表明,碳气凝胶的比表面积达到480 m2/g,孔径分布良好,催化剂金属颗粒较小,分散较好,循环伏安曲线图显示出Pt/碳气凝胶比传统的Pt/C对甲醇催化氧化性能高。     

一种基于条带划分的低延迟帧内编码方法

现有编解码系统所产生的固有延迟比较大,例如对于标清视频,系统延迟要大于260ms,因此难以用于对延迟有严格要求的系统中。为此,研究了一种新的低延迟帧内编解码结构,在该结构中,将输入的视频划分成若干个条带,在采集端以条带为单位进行采集,以有效降低采集延迟;同时,给出了以条带为基本单位的I帧编码方法,对每一编码条带下采样,将其分成4个子图,以子图为单位进行预测,以提高预测的精度,进而降低编码延时。实验表明,新的编码结构在采集和编码过程中能有效降低帧内编码延迟,在保证恢复图像质量的同时,可以将延迟降低到150ms。     

基于EFPN的模糊离散事件系统可诊断性分析

针对模糊有限自动机及模糊Petri网在模糊离散事件系统(Fuzzy Discrete Event System,FDES)行为建模中的不足,提出一种扩展模糊Petri网(Extended Fuzzy Petri Net,EFPN),并基于EFPN构造了FDES行为模型及系统故障诊断器。EFPN以一种新的事件模型为基础对FDES的系统行为进行建模,并根据事件触发矩阵计算下一系统状态中各分量的可能性分布。与模糊有限自动机及模糊Petri网的对比分析表明,在描述FDES模糊事件时,对于同步距离为0的一组事件所造成的影响,EFPN的表达能力强于经典模糊Petri网;在对含有多个状态分量的FDES建模时,EFPN模型的规模远小于模糊有限自动机。在基于EFPN构造的系统行为模型中,运用可达状态标识图分析系统状态集,可有效地构造FDES的故障诊断器,并可据此进行系统可诊断性分析。     

基于多核学习的投影非负矩阵分解算法

非负矩阵分解(NMF)把给定的数据矩阵分解成低维的非负基矩阵和对应的系数矩阵,两者之间存在必然联系。为此,研究者将基矩阵转换为系数矩阵的投影,进一步提高分解效率。但是该方法无法处理非线性数据,核函数的引入部分解决了此问题,却同时导致核函数参数选择的问题。基于多核学习理论,提出了一种多核学习的投影非负矩阵分解(MKPNMF)算法,该算法有效地避免了核函数参数选择的问题,同时提高了学习性能。在实际人脸数据上的实验结果表明,MKPNMF较已有的NMF类方法具备明显的性能优势。     

一种基于空间滤波的钢轨表面擦伤检测改进算法

钢轨表面擦伤检测是保障铁路运输安全的重要手段之一。应用图像处理和模式识别技术来处理钢轨数字图像,检测并定位擦伤区域是一种可行且发展迅速的研究手段。课题组在前期工作中提出了一种鲁棒实时的钢轨表面擦伤检测算法,该算法首先对钢轨图像进行灰度对比度增强,在此基础上定位可疑擦伤区域并进行判定。算法对于常规擦伤图像具有较高的检测性能,但对于钢轨图像包含多处擦伤且擦伤区域灰度值差异较大的情况,往往造成漏检。针对原算法的不足,提出了一种基于空间滤波的钢轨表面擦伤检测改进算法,该算法对原算法检测到的擦伤区域进行钢轨灰度图均值填充,并对填充后的图像进行二次检测,在重新生成的灰度对比度图中,原检测图像中灰度值不明显的擦伤区域的灰度对比度值得到增强,从而增加了检出的可能性。经实验结果验证,改进算法具有较高的检测性能:在总的时间耗费没有明显增加的情况下,检测的平均准确率为90.8%,平均漏检率为4.0%,较原算法有较大改善。     

基于广义数学期望算法模型的中国企业工资水平宏观调控评价研究

随着我国经济进入加速转型期,市场机制在劳动力资源配置中作用不断加大,我国企业工资水平宏观调控体系机制已成为繁复的工程系统。本文运用广义数学期望算法构建企业工资水平宏观调控评价体系,从经济发展,社会和谐,生活协调三个方面对中国企业工资水平宏观调控体系展开综合评价,分析存在的问题,为优化和完善中国企业工资水平宏观调控机制提供决策依据和政策建议。     

End-User Development of Mashups with NaturalMash

Context: The emergence of the long-tail in the market of software applications is shifting the role of end-users from mere consumers to becoming developers of applications addressing their unique, personal, and transient needs. On the Web, a popular form of such applications is called mashup, built out of the lightweight composition of Web APIs (reusable software components delivered as a service through the Web). To enable end-users to build mashups, there is a key problem that must be overcome: End-users lack programming knowledge as well as the interest to learn how to master the complex set of Web technologies required to develop mashups. End-User Development (EUD) is an emerging research field dealing with this type of problems. Its main goal is to design tools and techniques facilitating the development of software applications by non-programmers.Objective: The paper describes the design and evaluation of NaturalMash, an innovative EUD tool for mashups (a mashup tool). NaturalMash aims at enabling non-professional users without any knowledge of programming languages and skills to create feature-rich, interactive, and useful mashups.Methods: The design of NaturalMash adopts a formative evaluation approach, and has completed three design and evaluation iterations. The formative evaluations utilize usability testing, think aloud protocol, questionnaires, observation, and unstructured interviews. Additionally, we compare the expressive power of naturalmash with the state-of-the-art mashup tools.Results: The results from the formative evaluations helped us identify important usability problems. From an assessment point of view, the results were promising and sggested that the proposed tool has a short and gentle learning curve in a way that even non-programmers are able to rapidly build useful mashups. Also, the comparative evaluation results showed that NaturalMash offers a competitive level of expressive power compared with existing mashup tools targeting non-programmers.Conclusion: As the evaluation results indicate, NaturalMash provides a high level of expressive power while it is still highly usable by non-programmers. These suggest that we have successfully achieved the objective of the proposed tool, distinguishing it from existing mashup tools that are either too limited or highly specialized for non-professional users.