单项资料异常变化信息提取的一种新方法：多点组信息法

在前人工作的基础上提出了多点组信息法，包容了以前各种各样的数据处理方法，并赋予了新的内容，以４点组斜率信息法为例，做了系统的论述，并以小水峪垂直基线资料为例，给出了初步的处理结果，证明该方法在各种数据的分析处理、提取地震前兆异常信息的应用中有较大的价值，最后给出了标准化信息流，对多项不同量纲的异常信息合成提供了方便。     

SHORT COMMUNICATION PATTERN RECOGNITION IN CLINICAL CHEMISTRY:TUMOR MARKERS

Pattern recognition techniques(PCA,Bayesian analysis,LDA and KNN)are applied to a set of datacomposed of cancer patients and controls.A rather good separation between different populations isobtained using four tumor markers determined for each patient.     

A NON-PARAMETRIC CLASS MODELLING TECHNIQUE

A non-parametric method for supervised pattern recognition is presented. The method is of the classmodelling type, meaning that a classification rule is developed for each class, using the dissimilaritiesbetween the objects of the class. The dissimilarities between the objects within a class are related to thedistances between all pairs of training objects. As distance metric, a measure is proposed that takes thecorrelation between the interval-scale variables into account, and that moreover can be used for mixedtypes of variables. The classification rule is based on the construction of a boundary in the measurementspace. For the determination of the class boundary, several strategies are proposed and compared. The performance of the technique is evaluated on the basis of several data sets. Comparison with theclass modelling technique UNEQ shows its usefulness for practical applications.     

基于D-S推理的灰关联雷达辐射源识别方法研究

在战场实际环境中，多数情况下传感器设备获得辐射源的信息在时间上是冗余的。针对这种实际侦测环境，基于信息融合的思想，提出了一种新的辐射源识别方法。该方法在灰关联识别的过程中．引入D-S证据理论，通过对信号的积累和对信任度的重新分配．对识别结果进行了有效的融合．提高了辐射源的正确识别率。仿真结果表明了该方法的可行性和有效性．为工程应用提供了参考。     

人工神经网络信息融合及其在机场识别中的应用研究

以机场识别为研究对象,以两种改进的BP网络作为算法工具,以TM影像作为原始数据,在特征级信息融合技术框架下进行机场识别研究。首先对可用于机场识别的特征进行分析,提出使用光谱特征、纹理特征和几何形状特征这三个特征的7维矢量作为BP网络的输入,并对BP网络的训练、测试和识别三个过程进行了详细的讨论。     

基于规则的高分辨率影像港口识别模型

针对港口自身的结构特点并融合专家知识,采用结构化分析方法,提出了基于黑板结构的产生式网港口识别模型。该方法突破了传统的仅从直线等几何特征出发建立模型并识别目标的局限性,体现港口的结构关系,是对结构模式识别方法的再次尝试。     

基于聚类分析的运动目标检测与分割算法及实现

提出了一种基于模式识别的时间序列影像运动目标检测与分割方法,利用聚类分析的思想改进了简单差分方法,引入模式特征空间及运动模式识别作为运动目标检测的判据,实现了运动目标的检测、识别与分割。     

用双通道动态阈值对GMS-5图像进行自动云检测

该文用双通道动态阈值法对GMS-5图像进行自动的云检测。在红外通道和可见光通道，分别对每32×32个像元组成的像元阵进行直方图统计，求出区别云和地物值域的阈值，然后对每个像元阵内的逐个像元进行云判识。讨论了在进行直方图分析以求取阈值的过程中，像元阵大小的选取和动态平滑间距的选取对云检测结果的影响。分析结果表明:像元阵大小取32×32时，像元阵所占的地域空间尺度足够小，像元阵内的观测像元样本数足够多，保证了在直方图聚类分析时，每一类含有足够多的样本；GMS-5观测图像的红外通道对原始直方图进行二次平滑时小平滑间距取1.6 K，可见光通道小平滑间距取1.2%，使得确定动态阈值时步长相对小，保证了分析的精度。用目视图像对分析结果进行真实性检验，在中低纬度地区，可见光和红外两个通道都有资料时，该算法的云判识精度较好。在高纬度地区，由于地表温度低，积雪覆盖多，太阳光照角低，该算法的云判识精度较差。     

Application of Fisher method to discriminating earthquakes and explosions using criterion m_b/M_S

Introduction Earthquake magnitude is a measurement of earthquake intensity, which is one of the basic seismic parameters. The body-wave magnitude mb and surface-wave magnitude MS are based re- spectively on different wave spectrum amplitudes, therefore, the magnitude used as a criterion has its sound physical basis, which is in fact to distinguish the frequency components of seismic waves excited by explosion and earthquake. The magnitude criterion has a very clear physical meaning. Proposed …