智驾新“视”代——兴嘉林“沃·智驾”智能后视镜新品测评

从去年年底开始,后视镜导航产品开始在国内窜红。原因无他,车技市场的竞争一直惨烈,通过新品吸引车主及经销商注意已经成为了不少导航厂家们的主要手段。当然,后视镜导航也分个三六九等。好比说本月测试的兴嘉林“沃·智驾”正是其中的佼佼者。通过后视镜为切入点,整合智能操控及语音识别操控等人性化功能,又是否能够一举博得关注呢？     

改进教与学优化算法的LQR控制器优化设计

为了快速有效地确定线性二次最优控制(linear quadratic regulator,LQR)问题中的加权矩阵Q和R,针对主动悬架LQR控制器权系数设计问题,提出一种改进的教与学优化算法进行LQR优化设计。算法对基本教与学优化算法中的"教"与"学"阶段进行了进一步的改进,同时提出一种"自我学习"策略。通过仿真实验表明,和基本教与学算法、粒子群算法、遗传算法相比,本文算法在对主动悬架LQR控制器优化时,具有收敛速度快,求解精度高和稳定性强等优势。     

改进的细菌觅食优化算法求解0-1背包问题

细菌觅食优化算法作为一种新兴的智能优化算法,一般用来解决连续域的问题。为了解决离散域问题,提出了一种改进的细菌觅食优化算法。采用线性递减的思想和随机的游动长度代替固定步长和随机游动方向,改进了趋向性操作方案,并将其应用于解决0-1背包问题。将改进的细菌觅食优化算法与遗传算法、离散粒子群优化算法及基本的离散化细菌觅食优化算法分别在小规模和大规模的0-1背包问题上进行了仿真比较,表明了改进的细菌觅食优化算法能取得较好的效果,寻优能力强。     

结合图论的JSEG彩色图像分割算法

静态图像压缩标准（ JSEG）分割算法是一种经典的图像分割方法,它充分考虑到了图像的局部信息,可以获得比较精确的分割边界。但JSEG算法在分割过程中计算量相当大并且分割结果容易出现过分割现象。由此,文中提出一种结合图论的JSEG图像分割算法。首先去除JSEG算法中在多个尺度上反复计算J值的过程,改为仅在一个小尺度上进行计算。其次,在得到的J图上使用K-means方法进行聚类,分割得到过分割区域。最后,将分割后的小区域对应为图中的点,进而利用图理论的方法进行区域合并。实验结果表明新算法具有高精度和低复杂度的优势。     

Research on technology of desktop virtualization based on SPICE protocol and its improvement solutions

Increasingly mature cloud computing technology promotes virtual desktop technology, which can solve many problems existing in traditional computing models. However, virtual desktop solutions introduce the thorny problem of how to deliver a real desktop experience to users, as if they are using it locally, especially when playing video. The SPICE （simple protocol for independent computing environments） virtual desktop solution provides several image compression algorithms to address this problem with the purpose of making virtual desktops as real as possible. Although different compression algorithms can contribute their own abilities to different images to a large extent, switching between them is a big problem that consumes a large amount of resources to detect the different type of image and also causes jitter of the virtual desktop. This paper proposes a new solution, called SPICEx, using the JPEG2000 compression algorithm with dynamic compression ratios to solve the problem and finally validates that the performance is better than that of SPICE. With better quality of user experience and also reducing bandwidth consumption, SPICEx solution is meaningful in virtual desktop fields and can be widely used.     

Image decomposing for inpainting using compressed sensing in DCT domain

Inpainting images with occlusion or corruption is a challenging task. Most existing algorithms are pixel based, which construct a statistical model from image features. However, in these algorithms, the frequency component is not sufficiently addressed. In this paper, we propose a novel algorithm that utilizes compressed sensing （CS） in frequency domain to reconstruct corrupted images. In order to reconstruct image, we first decompose the image into two functions with different basic characteristics - structure component and textual component. We seek a sparse representation for the functions and use the DCT coefficients of this representation to generate an over-complete dictionary. Experimental results on real world datasets demonstrate the efficacy of our method in image inpainting. We compare our method with three state-of-the-art inpalnting algorithms and demonstrate its advantages in terms of both quantitative and qualitative aspects.     

条码技术为身份识别树起第二道安全屏障

计算机技术的快速发展,促进了信息技术的数字化、网络化进程,人与人之间的信息交互越来越方便快捷,使得需要个人身份验证的场所和领域增多,这就对身份信息安全和自动识别能力提出了更高的要求。身份识别技术是信息安全保密最基本的措施,也是身份信息安全保密的第一道防线。而身份信息的数字化和隐性化是身份信息安全的关键技术,传统的身份识别技术已不能满足网络时代的要求,迫切需要寻找一种技术去处理和表示身份信息,使身份信息不能轻易被获取和利用,条码的技术特点可以满足这种需求。     

Feature selection on probabilistic symbolic objects

In data analysis tasks, we are often confronted to very high dimensional data. Based on the purpose of a data analysis study, feature selection will find and select the relevant subset of features from the original features. Many feature selection algorithms have been proposed in classical data analysis, but very few in symbolic data analysis （SDA） which is an extension of the classical data analysis, since it uses rich objects instead to simple matrices. A symbolic object, compared to the data used in classical data analysis can describe not only individuals, but also most of the time a cluster of individuals. In this paper we present an unsupervised feature selection algorithm on probabilistic symbolic objects （PSOs）, with the purpose of discrimination. A PSO is a symbolic object that describes a cluster of individuals by modal variables using relative frequency distribution associated with each value. This paper presents new dissimilarity measures between PSOs, which are used as feature selection criteria, and explains how to reduce the complexity of the algorithm by using the discrimination matrix.     

应用于临床生存时间预测的二次学习算法研究

生存时间预测在医学、经济和工程等领域有着广泛的应用。随着机器学习技术和数据挖掘技术的发展和广泛应用,研究人员提出了很多基于机器学习技术的生存时间预测算法。这些算法虽然都取得了良好的效果,但预测精度均有提升的空间。因此,提出了一种基于二次学习风范的生存时间预测算法,并结合最近邻算法在截尾样本估计上的应用以及支持向量机在泛化性能上的优势,实现了对临床生存时间的建模。实验结果表明,该算法能够获取精确的生存时间,且具有预测精度上的性能优势。     

由粗到精的虹膜图像离焦模糊评价方法

离焦模糊评价在虹膜识别系统中尤为重要。传统的方法是通过频谱分析测量虹膜图像的离焦模糊程度,这类方法容易受到光照变化以及睫毛和眼皮等噪声区域的影响。提出了一种由粗到精的虹膜图像离焦模糊评价方法。第一步,通过频谱分析去除严重模糊的虹膜图像,进行虹膜图像离焦模糊粗分类。第二步,通过方向金字塔分解,提取虹膜图像的质量特征。在人工合成的离焦模糊虹膜图像数据库中,利用径向基神经网络建立起质量特征与质量等级间的对应关系。通过建立起的模型进行实际的虹膜图像离焦模糊等级预测,以及虹膜图像离焦模糊精分类。在Clarkson数据库上的实验结果证明了该方法不仅可以准确区分清晰图像和离焦模糊图像,而且相比于传统的虹膜图像离焦评价方法更接近于人的视觉感知。