基于权值优化神经网络的交通拥堵程度决策方法

针对现有的交通拥堵程度决策方法在证据不确定和不完备情况下评价准确率低的问题,提出了一种基于权值优化神经网络方法。首先,采用二次型隶属度描述了各类交通拥堵证据的不确定性与不完备性。其次,由信息熵计算证据的贡献度,并作为优化神经网络的输入层权值。接下来,由初始权值与前序时刻的梯度和自适应更新各隐层与输出层的神经元权值,以期降低不确定和不完备证据给整个网络带来的累积误差。最后,结合实际交通状况进行算例分析,验证了该方法的准确性与收敛性。结论分析表明,所提出的方法能作出准确的交通拥堵程度决策。     

对混合属性数据表可行的差分隐私保护方法

为加强隐私保护和提高数据可用性,提出一种可对混合属性数据表执行差分隐私的数据保护方法。该方法首先采用ICMD（insensitive clustering for mixed data）聚类算法对数据集进行聚类匿名,然后在此基础上进行
-差分隐私保护。ICMD聚类算法对数据表中的分类属性和数值属性采用不同方法计算距离和质心,并引入全序函数以满足执行差分隐私的要求。通过聚类,实现了将查询敏感度由单条数据向组数据的分化,降低了信息损失和信息披露的风险。最后实验结果表明了该方法的有效性。     

基于遗传蜂群算法的运动想象BCI系统导联选择*

在运动想象脑-机接口系统中,常采用高密度导联获取脑电信号,导致实验准备时间长,系统运行速度慢,性能变差等问题。针对上述不足,本文提出了一种基于遗传算子的蜂群算法用于导联优选,引入交叉和变异算子以提高蜂群算法的邻域搜索能力。通过对第四届国际BCI 竞赛 Dataset 1中四名被试者(a,b,f和g)的59导联运动想象数据进行导联优选,用多类CSP算法和支持向量机对优选导联数据进行特征提取和分类识别。结果表明所提出的算法在大大降低了导联维数的同时,也得到了比采用全部导联更高的分类识别率,验证了本文所提算法的实用性和有效性。     

水电黑启动的实现方法

以水电黑启动在重庆彭水电站的实现方法为例,对彭水电站黑启动初始状态、总体思路及其步骤进行详细论述,总结出彭水电站黑启动的重要性,同时提出实施过程中的注意事项。     

断层模型约束反演在MTH地区煤层横向预测中应用研究

利用相干体确定断层平面的走向特征,在剖面上采用井点处断点引导小断层解释,准确落实其空间位置,并建立精细的断层模型,在此基础上,利用断层约束反演技术,进行煤层的横向预测。MTH地区实例表明,基于断层模型约束反演技术的煤层横向预测方法,可精细描述煤层变薄带、分叉合并带、厚度变化等赋煤状态。     

Rn 上的线性局部保控映射

设φ：Rn →Rn 是一个线性映射,对任意x∈Rn ,都存在与x有关的线性保控映射ψx ,使得φ（x）＝ψx（x）,则称φ是欧氏空间上的一个线性局部保控映射。线性保控映射是线性局部保控映射,其逆命题不成立。文中定义了两个与φ相关的Rn的子集Iφ和IIφ,如果任意Rn上的点都属于Iφ（或IIφ）,那么这个线性局部保控映射φ是线性保控映射。     

Polybrominated Diphenyl Ethers in Surface Sediment from Songhua River Basin, Northeast of China

Sixty sediment samples were collected from the main Songhua River in three years. Twelve polybrominated diphenyl ether ( PBDE) congeners ( BDE17, 28, 47, 66, 99, 100, 153, 154, 138, 183, and BDE?209) w...     

Evolution of insoluble eutectic Si particles in anodic oxidation films during adipic-sulfuric acid anodizing processes of ZL114A aluminum alloys

The effects of insoluble eutectic Si particles on the growth of anodic oxide films on ZL114A aluminum alloy substrates were in-vestigated by optical microscopy (OM) and scanning electron microscopy (SE...     

In situ study of the mechanical properties of airborne haze particles

Particulate pollution has raised serious concerns regarding its potential impacts on human health in developing countries. However, much less attention has been paid to the threat of haze particles to machinery and industry. By employing a state-of-the-art in situ scanning electron microscope compression testing technique, we demonstrate that iron-rich and fly ash haze particles, which account for nearly 70% of the total micron-sized spherical haze particles, are strong enough to generate abrasive damage to most engineering alloys, and therefore can generate significant scratch damage to moving contacting surfaces in high precision machineries. Our finding calls for preventive measures to protect against haze related threat.     

Dynamic buffering performance of the honeycomb paperboard filled with polyurethane

A new kind of composite buffering material was made by filling the voids of honeycomb paperboard with polyurethane. Drop tests were performed to evaluate the dynamic energy absorption capacity of the material. Based on the tests results, we analyzed the mechanical behaviors of the material under different conditions and obtained the inherent influencing laws of some factors on the material＇s dynamic buffering performance. It was shown that the dynamic buffering performance varied directly with impact velocity, and inversely with the void diameter, thickness and buffeting area of the composite material.