对抗样本三元组约束的度量学习算法

针对已有三元组约束的度量学习算法大多利用先验知识构建约束,一定程度上制约了度量学习算法性能的问题,本文借鉴对抗训练中样本扰动的思想,在原始样本附近学习对抗样本以构造对抗三元组约束,基于对抗三元组和原始三元组约束构建了度量学习模型,提出了对抗样本三元组约束的度量学习算法(metric learning algorithm with adversarial sample triples constraints,ASTCML)。实验结果表明,提出的算法既克服了已有固定约束方法受先验知识影响大的问题,也提高了分类精度,说明区分更加难以区分的三元组约束能够提升算法的性能。     

Compositional metric learning for multi-label classification

Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples.We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.     

基于多层注意力机制—柔性AC算法的机器人路径规划

针对行动者—评论家（AC）算法存在的经验学习样本维度高、策略梯度模型鲁棒性低等问题,依据多代理系统的信息协作优势,构建注意力机制网络并作为代理体,引入多层并行注意力机制网络模型对AC算法进行改进,提出一种基于多层并行注意力机制的柔性AC算法。将其用于解决动态未知环境下的机器人路径规划问题,可增强行动者的策略梯度鲁棒性并降低评论家的回归误差,实现机器人路径规划最优方案的快速收敛。实验结果表明,该算法有效克服机器人路径规划的局部最优,具有计算速度快、稳定收敛的优点。     

SFT中的因素作用路径与作用历史

为了描述SFT中系统或元件在不同工作环境状态下经历变化的特征,提出了因素作用路径和作用历史的概念。作用路径描述系统或元件在不同工作状态变化过程中所经历状态的集合。作用历史描述经历作用路径过程中的可积累状态量。给出使用作用路径和作用历史分析问题的步骤。列举一例子,计算在设定条件下的元件维护成本。计算作用路径分别为AB和ACB两种,作用历史中使元件故障概率等于20%的维护成本,该维护成本是通过调整使用时间t和使用温度c产生的。最后给出以实例为背景的作用历史计算方法的不足、面临的问题和可能的解决方法。     

数控程序的高效设计及其刀具轨迹优化

介绍了提高数控程序编制效率的途径 ,并以实例说明了如何对数控程序刀具轨迹的质量进行优化 ,对从事数控工艺与编程的技术人员有参考和借鉴的作用。     

One-to-one disjoint path covers on multi-dimensional tori

The multi-dimensional torus is one of the most popular underlying topologies for massively parallel systems. In this study, we consider a non-bipartite n-dimensional torus where n≥2 and prove that for 1≤m≤2n, m vertex disjoint paths exist that cover all vertices between any two distinct vertices. In other words, we construct the one-to-one m-disjoint path cover of a non-bipartite torus for any m where 1≤m≤2n.     

基于云计算的混合并行遗传算法求解最短路径

为提高最短路径求解问题的效率,提出一种基于云计算的细粒度混合并行遗传算法求解最短路径的方法。方法采用云计算中H adoop的Map Reduce并行编程模型,提高编码效率,同时将细粒度并行遗传算法和禁忌搜索算法结合,提高了寻优算法的计算速度和局部寻优能力,进而提高最短路径的求解效率。仿真结果表明,该方法在计算速度和性能上优于经典遗传算法和并行遗传算法,是一种有效的最短路径求解方法。     

多宿主连接环境下隧道传输网络的一体化路由模型

现有隧道传输只考虑异构网络基本连通性,是一种分段独立实施路由选择的路由模型,没能对端到端跨越异构网络的传输路径进行一体化考虑.针对边缘网到支撑网的多宿主连接网络环境,提出了一种跨异构网络的一体化路由模型URM(Unified Routing Model).URM模型采用参考度量实现对异构网络路由优劣的统一描述,利用BGP协议扩展实现参考度量的传递,并设计了参考度量与传统度量的转换方法.URM模型实施时影响范围很小,只需对隧道网关进行简单改造即可完成,最终的一体化路由机制也是透明地利用现有路由机制完成.URM模型会给异构网关和边缘网路由器带来更多的信息存储,但其优势却非常明显,在实现端到端一体化最优路由选择的同时,增加了隧道传输的可用路径并提高了隧道传输可靠性.仿真实验及真实设备组网实验验证了URM模型的一体化路由选择能力及路由收敛能力.     

A Hybrid Color Quantization Algorithm Incorporating a Human Visual Perception Model

Color quantization is a common image processing technique where full color images are to be displayed using a limited palette of colors. The choice of a good palette is crucial as it directly determines the quality of the resulting image. Standard quantization approaches aim to minimize the mean squared error (MSE) between the original and the quantized image, which does not correspond well to how humans perceive the image differences. In this article, we introduce a color quantization algorithm that hybridizes an optimization scheme based with an image quality metric that mimics the human visual system. Rather than minimizing the MSE, its objective is to maximize the image fidelity as evaluated by S‐CIELAB, an image quality metric that has been shown to work well for various image processing tasks. In particular, we employ a variant of simulated annealing with the objective function describing the S‐CIELAB image quality of the quantized image compared with its original. Experimental results based on a set of standard images demonstrate the superiority of our approach in terms of achieved image quality.     

基于支持向量机的炒作微博识别方法

微博是舆论传播的中心和渠道,同时参与舆论的形成、发展与引导过程,其自媒体发布、意见领袖参与等因素在一定程度上造成了微博谣言、虚假炒作、社会动员等现象。针对炒作微博的传播特点,分析其群体的隐蔽策划现象,挖掘出普通微博和炒作微博在传播网络结构、转发增量统计等方面的差异。通过社交网站的应用程序接口对目标微博的所有评论、转发和点赞用户进行信息获取,构建该微博的传播网络,利用社团模块度、平均最短路径和网络直径这3个属性度量该网络的紧密程度,基于支持向量机对所抽取的微博进行分类,进而识别出炒作微博。实验结果表明,该方法对微博传播用户的属性信息依赖小以及传播网络结构特征敏感,并且具有较高的炒作微博识别准确率。