基于改进GIPF和形态学滤波的快速人眼定位方法

针对传统积分投影方法易受眉毛、睫毛、阴影、遮挡及噪声等干扰的问题,提出了一种改进梯度积分投影(GIPF)和形态学滤波相结合的快速人眼定位算法.该算法首先采用二维梯度算子计算人脸图像的行列积分投影,完成人眼粗定位,减少眉毛和光照等的干扰;其次,利用形态学滤波平滑图像边界的特点,准确分离出瞳孔区域;最后采用不规则矩求质心的方法精确定位人眼.该方法在耶鲁大学的Yale B图像库、ORL及日本表情库(JAFFE)上表现优异.实验结果表明,本方法不易受眉毛及噪声干扰,对不同光照条件及头部姿态都有良好的鲁棒性,并且运算速度更快.

电子概率密度对气体绝缘强度预测的影响

为提高SF6替代气体研发效率,需分析气体分子微观参数与宏观绝缘强度的关系。本文基于密度泛函理论,采用M06-2X方法与6-311++G(d,p)基组,计算了72种气体分子的结构参数,以及不同电子概率密度等值面的相互作用性质函数(general interaction properties function,简称GIPF)算符,研究了各参数与气体相对绝缘强度的相关性,并提出了绝缘强度预测模型。结构参数中分子量、极化率,以及GIPF参数中分子体积、分子表面积、分子正静电势表面积、分子非极性表面积、分子极性表面积,与相对绝缘强度相关性较强。结构参数不受电子概率密度取值影响,GIPF参数在不同电子概率密度等值面差异较大,多数GIPF参数在电子概率密度3.374~33.742nm^(-3)的范围内与绝缘强度的相关性最强。仅使用GIPF参数的预测模型,在电子概率密度10.123 nm^(-3)时其决定系数R2达到最大值0.762,均方误差为0.119;加入极化率后,在电子概率密度16.871 nm^(-3)时R2可达最大值0.801,均方误差为0.099。考虑不同电子概率密度等值面的GIPF参数,联合结构参数,可有效提高绝缘强度预测精度。

First Isolation and Identification of Shewanella xiamenensis from Diseased Nile Tilapia(Oreochromis niloticus L.)

A gram-negative, motile, and rod-shaped bacterium, strain JF02, was isolated from the liver of diseased GIFT （ genetically improved farmed tilapia） in Hainan, China. The strain JF02 was lethal to GIFT, and most GIFT infected with JF02 exhibited the same clinical signs, such as black body, pale or focally necrosis of the gills, scale shedding, fin rot, liver hyperemia, and hydroabdomen. The 16S rRNA gene sequences of strain JF02 showed 99.7% similarity with that of Shewanella xiamenensis strain S4^T. In addition, the gyrB gene sequences of strain JF02 showed 99.0% similarity with that of S. xiarrvenertsis strain S4^T. Combining the results of morphological, physiological and biochemical characteristics, the isolated strain JF02 was confirmed to be S. xiamenensis. The chemotherapeutic antibiotics tests showed that the strain JF02 was sensitive to most antibiotics except for several common antibiotics that were frequently used in human medicines and treatment of bacterial diseases of fish, indicating that the strain JF02 has obtained many antibiotic resistance genes due to the long-term abuse of antibiotics in aquaculture. In this paper, it was the first time to report that the S. xiamenensis may be a potential pathogen for GIFT. It is time to promote awareness of the potential harm of this strain to the health of human and aquatic animals.

基于电子定域化函数表面分析的气体介质绝缘强度预测

为提高SF替代气体研发效率,需探究气体介质微观参数与宏观绝缘强度的关系。本文基于密度泛函理论,采用M06-2X方法与6-311++G(d, p)基组计算了72种气体分子结构参数,通过电子定域化函数(ELF)确定分子等值面,分析了ELF等值面的静电势分布参数(GIPF),最终构建了极性与非极性分子绝缘强度预测模型。气体分子ELF等值面静电势参数与绝缘强度存在显著相关性,且在ELF为0.2时,整体相关性最优。联合ELF为0.2的等值面静电势参数以及分子极化率与偶极矩,分别建立了极性与非极性分子绝缘强度预测模型。非极性分子模型决定系数R=0.948,均方误差(MSE)为0.0232,极性分子模型R=0.723,MSE为0.1264。利用电子定域化函数定义分子表面,并获取分子微观参数,可有效预测气体分子绝缘强度。