Robust spatial flood vulnerability assessment for Han River using fuzzy TOPSIS with α-cut level set

This study aims to improve the general flood vulnerability approach using fuzzy TOPSIS based on α-cut level sets which can reduce the uncertainty inherent in even fuzzy multi-criteria decision making process. Since fuzzy TOPSIS leads to a crisp closeness for each alternative, it is frequently argued that fuzzy weights and fuzzy ratings should be in fuzzy relative closeness. Therefore, this study used a modified α-cut level set based fuzzy TOPSIS to develop a spatial flood vulnerability approach for Han River in Korea, considering various uncertainties in weights derivation and crisp data aggregation. Two results from fuzzy TOPSIS and modified fuzzy TOPSIS were compared. Some regions which showed no or small ranking changes have their centro-symmetric distributions, while other regions whose rankings varied dynamically, have biased (anti-symmetric) distributions. It can be concluded that α-cut level set based fuzzy TOPSIS produce more robust prioritization since more uncertainties can be considered. This method can be applied to robust spatial vulnerability or decision making in water resources management.     

激光遥感图像高速滤波器算法的FPGA实现

针对激光遥感信号高速高精度的要求,利用FPGA的多任务、高速并行性设计系统进行滤波。考虑到激光光电传感器设计的滤波器会有很大的信号衰减,且具有精度要求高的特点,提出了基于 FPGA内部基本逻辑单元、乘法器、存储器,经过乘法分解和时序设计,实现具有可移植性的图像高速分辨的方法。系统采用FPGA设计平台,并用Verilog语言设计程序。试验结果验证,该滤波器对激光遥感信号具有高速、精确滤波功能,同时表明利用低端FPGA设计激光滤波器必将成为未来发展趋势。     

动态受限区域内的单纯型连续近邻链查询方法

受限区域内的单纯型连续近邻链查询在空间数据挖掘、数据的相似分析和推理、空间数据库等方面具有重要的作用。为了弥补已有方法的不足,详细研究了动态受限区域内的单纯型连续近邻链查询方法。基于计算几何中的Voronoi图给出了VOR_IN_CRSCNNC算法、VOR_EX_CRSCNNC算法和VOR_DE_CRSCNNC算法。进一步进行了实验比较和分析。理论研究和实验分析表明,所提出的算法在查询过程中减少了数据逐一筛选和判断的冗余计算,在处理空间数据量较大、初始受限区域数据量较多、受限区域形状较为复杂的单纯型连续近邻链查询方面具有较大的优势。     

Measurement of minimum angle of resolution (MAR) in the stereoscopic display using the optotype of stereoscopic stimuli

In stereoscopic images, the crossing point of the viewing directions of the two eyes determines the perceived depth. Assuming that accommodation is affected by the positions of the crossing point, the effect of crossing point on minimum angle of resolution (MAR) was investigated. For 40 participants, MAR was measured by two‐alternative forced choice where Snellen optotype E of up and down directions were used as two kinds of stimuli. As the crossing point of the viewing direction of the left and right eyes moves farther from the sample display, the ability to identify the direction of letter E decreases at the optotype of the same line thickness. The change of MAR shows linear trends with respect to the optical power change that are the reciprocal of the distance from the participant to the crossing points located out of screen and on screen.     

一种面向软件产品概念设计的CSCW模型

随着计算机和网络技术的发展,各种CSCW模型和技术先后被提出,来满足各行业产品和概念设计的复杂工作需求。软件产品的概念设计作为一项复杂的工作和业务流程,对CSCW系统的需求也越来越高。文中针对软件产品概念设计的特殊性质,提出一种新的CSCW软件产品概念设计模型,并且对其中包含的冲突检测和协调机制进行了详细的设计和优化。使用基于Java平台的相关技术对模型主要功能架构和冲突协调过程进行了仿真。实验表明,文中提出的模型具有更加简洁和高效的复杂冲突解决能力和用户交互能力。     

Biologically adaptive robust mean shift algorithm with Cauchy predator-prey BBO and space variant resolution for unmanned helicopter formation

Visual tracking technology can provide measurement information for unmanned helicopter formation and thus, more attention is being paid to this research area. We propose a novel mean shift （MS） algorithm that is both adaptive and robust for unmanned helicopter formation and apply it to the leading unmanned helicopter tracking. The movement of an unmanned helicopter is very flexible and changeable, which makes the tracking there of more difficulty than for common targets. In creating an algorithm that can adapt to the acceleration of the unmanned helicopter and estimates both the scale and orientation of the movement changes, we combine the traditional MS with the bio-inspired Cauchy predator-prey biogeography-based optimization （CPPBBO） evolutionary algorithm, and also the space variant resolution （SVR） mechanism of the human visual system （MS-CPPBBO-SVR）. To demonstrate the effectiveness and robustness of the proposed method and justify the importance of the CPPBBO algorithm and SVR mechanism at the same time, a series of comparative exper- iments were carried out. The experimental results of the proposed MS-CPPBBO-SVR method are compared with other competitive tracking methods, such as MS, MS with SVR （MS-SVR）, MS-SVR with several other optimization algorithms, and the robust particle filter algorithm. The experimental results demonstrate that our proposed tracking approach, MS-CPPBBO-SVR, is more adaptive, robust and efficient in target tracking than the other methods.     

民航领域突发事件的实体链接方法

实体链接的相关研究主要集中于医疗、生物和新闻领域,但在民航领域的研究较少。因此针对民航领域实体链接任务进行了研究,发现在实体链接中存在实体变体多、歧义少等问题。为解决上述问题,提出了一种基于语义推断的实体链接框架以及一种用于增强框架鲁棒性的负采样策略。在民航领域数据集上进行了对比实验,结果表明所提框架链接效果优于现有基准框架,并通过消融实验,验证了负采样策略的有效性。在负采样策略的作用下,该实体链接框架的Acc@top1高达0.875。     

基于深度网络的出租车Pick-up需求预测

在智慧城市建设中,区域的出租车需求预测是一个十分重要的模块。为了预测指定区域未来时刻的出租车需求,本文通过拓展已有序列模型,提出一个多时间分辨率的基于层次注意力机制的循环高速网络（Multi-Time Resolution Hierarchical Attention-Based Recurrent Highway Networks, MTR-HRHN）。MTR-HRHN将对外生数据时空特征的提取和目标数据的时空建模整合到单个框架中,并且通过多分辨率（例如每个小时或者每天）对序列数据不同的时间属性建模,从而捕获更全面的时间模式。最后,在纽约市出租车数据集上评估MTR-HRHN的预测性能。实验结果表明,与其他经典时间序列预测方法相比,MTR-HRHN在多个高需求区域的短期需求预测上表现出更好的预测性能。     

学习小波超分辨率系数的人脸超分算法

目前基于卷积神经网络的超分方法虽然在峰值信噪比和结构相似性评价指标上能取得优异的结果,但是得到的超分图像视觉质量较差,会丢失人脸五官区域的细节信息。针对这一现象,设计了一种新的深度神经网络来预测超分小波系数以获得信息丰富的超分辨率人脸图像,首先利用人脸图像的先验知识手动地给予五官区域更多的关注,然后在网络中引入线性低秩卷积运算,最后利用长距离依赖的思想补充超分图像的细节。实验验证该算法可以在获得较高的峰值信噪比和结构相似性的同时,使超分人脸图像五官区域更加清晰、视觉质量更优。     

基于字典学习的遥感图像去模糊研究

对高分辨率遥感图像进行去模糊是遥感研究中的一个主要难题,针对此提出了一种新的基于稀疏表示的高分辨率遥感图像去模糊算法。该算法利用快速梯度投影算法实现去模糊,并且保留原图像的有用信息。通过对"高分一号"获取的遥感图像进行验证,表明该算法能较好地滤除遥感图像的模糊,提高图像的峰值性噪比,且比其他字典学习算法具有更好的性能。