INTRATUMORAL DNA PLOID HETEROGENEITY IN ESOPHAGEAL SQUAMOUS CELL CARCINOMA

AgreatmanystudiesshowedthattheabnormalityofDNAploidyoftumorcellsinatum0rhadac10secorrelati0nwithitsprogressionandclinical-pathol0gicalchar-acteristicst1～31Ibutinthemeantime,therewasmuchdisc0rdanceamongdifferentre-sults[4～sa-Asaresult,s0mesch0larshavebegunt0investigatetheintratumoralDNAploidheterogeneity(PH),andshowedthatmanykindsoftumorshadPHphen0menatodifferentextentc7～1'3.Chinaisanareawherees0phagealcarcinomaismuchprevalentandtherehavebeenn0resp0rtsonthisrespectathome.A1thoughitwasrep…     

基于FCM聚类的山区高速公路事故多发点成因分析

归纳总结了现有事故成因分析方法的特点和适用条件,提出了包括人、车、路和环境的山区高速公路交通事故影响因素,分析了各因素间的交互作用.提出了基于FCM聚类的山区高速公路事故多发点成因分析方法,并以京珠高速公路为例进行了验证.结果表明,该方法目标函数的聚类方法设计简单、解决问题范围广、易于计算机实现;山区高速公路最主要的事故因素是车辆追尾和刹车失灵.     

基于特征匹配和分箱技术的FCM算法研究

在基于聚类分析算法的入侵检测技术中,聚类的划分方法直接影响入侵检测的检测率。文章在基于分箱统计的HCM算法研究的基础上,针对模糊C-均值(FCM)算法的局限性,设计出一种改进的FCM算法。实验表明该算法比已有的FCM算法在对聚类的划分情况又有所改善,从而能提高检测率,且能较好地发现新的攻击类型。     

基于遗传算法的FCM聚类分析在边坡稳定性评价中的应用

FCM聚类分析在边坡稳定性评价研究中已得到广泛的应用,但传统的FCM算法存在着对初始聚类中心值敏感的问题。引入遗传算法来克服这个问题,提出了基于遗传算法的FCM聚类分析。以具体实例,采用基于遗传算法的FCM聚类分析对边坡进行稳定性评价,然后进行模式识别。研究结果表明:基于遗传算法的FCM聚类分析,克服了传统FCM聚类分析对初始聚类中心敏感的问题,其结果明显好于传统的FCM聚类分析。     

考虑航段相关性的航路拥挤态势多模型 融合动态预测方法

研究航路交通拥挤状态动态实时预测问题,可为缓解航路交通拥挤,优化拥挤管控 策略提供科学的依据.首先,采用神经网络理论建立考虑航段相关性的交通流参数预测模型, 预测航段流量和航段密度参数;然后,运用多模型融合预测算法提高预测精度,基于模糊C均 值聚类算法和航段历史及预测交通流参数预测航段交通拥挤态势;最后,采用雷达实测航迹 数据验证模型的有效性.研究结果表明,本文建立的预测模型同时考虑了时间和空间因素,对 航路拥挤状态预测准确率达到82.29%,预测方法符合实际且对航路交通态势的预测具有应用 价值;同时考虑航段相关性影响和采用多模型融合预测算法能够明显提高预测精度.     

A novel variable selection method based on frequent pattern tree for real-time traffic accident risk prediction

With the availability of large volumes of real-time traffic flow data along with traffic accident information, there is a renewed interest in the development of models for the real-time prediction of traffic accident risk. One challenge, however, is that the available data are usually complex, noisy, and even misleading. This raises the question of how to select the most important explanatory variables to achieve an acceptable level of accuracy for real-time traffic accident risk prediction. To address this, the present paper proposes a novel Frequent Pattern tree (FP tree) based variable selection method. The method works by first identifying all the frequent patterns in the traffic accident dataset. Next, for each frequent pattern, we introduce a new metric, herein referred to as the Relative Object Purity Ratio (ROPR). The ROPR is then used to calculate the importance score of each explanatory variable which in turn can be used for ranking and selecting the variables that contribute most to explaining the accident patterns. To demonstrate the advantages of the proposed variable selection method, the study develops two traffic accident risk prediction models, based on accident data collected on interstate highway I-64 in Virginia, namely a k-nearest neighbor model and a Bayesian network. Prior to model development, two variable selection methods are utilized: (1) the FP tree based method proposed in this paper; and (2) the random forest method, a widely used variable selection method, which is used as the base case for comparison. The results show that the FP tree based accident risk prediction models perform better than the random forest based models, regardless of the type of prediction models (i.e. k-nearest neighbor or Bayesian network), the settings of their parameters, and the types of datasets used for model training and testing. The best model found is a FP tree based Bayesian network model that can predict 61.11% of accidents while having a false alarm rate of 38.16%. These results compare very favorably with other accident prediction models reported in the literature.     

Classification of Automatic Radar Plotting Aid targets based on improved Fuzzy C-Means

Maritime ARPA, Automatic Radar Plotting Aid, systems often complicate navigation by mistaking channel structures and land objects for vessels in inland rivers and harbors. By using Fuzzy C-Means (FCM), it is possible to construct an artificial intelligence to classify and identify ARPA target types and calculate the possibility of a target being a real vessel based on the target’s speed over ground, vector over ground, and location. The membership functions of each attribute are constructed using statics, expert knowledge, and electronic chart information. The main difficulty in developing a successful FCM framework to achieve the previously stated goals is the determination of a proper method of calculating the classification number C and fuzzy coefficient m. Because the value of C for the case of ARPA targets classification is finite, the best C would be determined by assessing the Euclidean distance. The value of m is related to the discreteness of the evidence and results, which is evaluated using the Shannon entropy and the gain. A number of methods exist to properly evaluate the contributions from different forms of evidence so that the best m can be found using the tendentiousness of the evidence. In field testing, the improved FCM was able to accurately classify the ARPA targets, decrease the workload on the ship’s officer, and increase safety.     

基于最小二乘支持向量机的彩色磨粒图像分割

分析了磨粒的自动识别研究在铁谱技术发展和应用中的重要性。指出铁谱磨粒图像分割是磨粒自动识别的重要环节,铁谱图像所包含的彩色信息对磨粒识别和磨损形式分析非常重要。将最小二乘支持向量机LS-SVM用于彩色磨粒图像的分割,利用模糊c均值选取训练样本,把磨粒图像的R,G,B分量,同一像素点各分量的方差以及像素点邻域像素均值作为特征,对彩色磨粒图像分割,取得了很好的效果,为磨粒自动识别提供了更有效的信息。     

基于HSI空间的模糊C均值彩色图像分割方法

给出了一种在HSI空间上基于模糊C均值的彩色图像分割方法．首先对每个像素根据H分量和I分量计算出4个隶属度,然后将其中的两个隶属度结合形成一个二雏特征矢量来表征像素的全部颜色特征,最后对二维矢量运用模糊C均值聚类算法得到最终的彩色图像分割结果．     

鼻咽癌患者中CD4~+CD25~+T细胞与CCR4的相关性

目的 探讨鼻咽癌患者全身及肿瘤局部的免疫状态及其与CC类趋化因子受体-4(CCR4)的关系.方法 采用流式细胞术检测初诊鼻咽癌患者组织(25例)及外周血(35例)中CD4~+CD25~+T细胞与CCR4阳性细胞在淋巴细胞中的比例,并进行统计学分析.结果 鼻咽癌组织及外周血中CD4~+CD25~+T细胞及CCR4阳性细胞的比例高于对照组(P<0.05);两种细胞在鼻咽癌组织中的比例高于外周血(P<0.05),而对照组外周血与组织中却无明显差别(P>0.05);鼻咽癌Ⅲ+Ⅳ期组织中的 CD4~+CD25~+T细胞比例高于Ⅰ+Ⅱ期(P<0.05),外周血中两组无明显差别(P>0.05);鼻咽癌组织及外周血中的CD4~+CD25~+T细胞与CCR4阳性细胞存在正相关关系.结论 鼻咽癌患者存在不同程度的免疫抑制,肿瘤局部免疫抑制更为严重;CD4~+CD25~+T细胞的比例与鼻咽癌分期相关,分期越晚,该细胞比例越高;CCR4在介导CD4~+CD25~+T 细胞趋化到肿瘤局部的过程中起了一定作用.