Object tracking based on an online learning network with total error rate minimization

This paper presents a visual object tracking system which is tolerant to external imaging factors such as illumination, scale, rotation, occlusion and background changes. Specifically, an integration of an online version of total-error-rate minimization based projection network with an observation model of particle filter is proposed to effectively distinguish between the target object and the background. A re-weighting technique is proposed to stabilize the sampling of particle filter for stochastic propagation. For self-adaptation, an automatic updating scheme and extraction of training samples are proposed to adjust to system changes online. Our qualitative and quantitative experiments on 16 public video sequences show convincing performances in terms of tracking accuracy and computational efficiency over competing state-of-the-art algorithms.     

基于改进支持向量机的高维隐写盲检测方法

针对高维大样本空间中支持向量机( SVM)存在计算复杂度高、分类精度低等问题,在随机子空间方法与主成分分析方法的基础上,提出一种特征加权支持向量机的高维隐写盲检测方法。通过随机子空间对原始高维样本的特征空间进行随机采样,产生多个低维的特征子集,在特征子集中采用主成分分析法进行特征提取,并利用卡方统计计算特征权重,运用特征加权核函数训练各基SVM分类器,并用多数投票法融合各基分类器结果得到最终分类结果。对HUGO隐写算法的实验结果表明,该方法能有效降低SVM计算复杂度,与传统方法相比,具有较高的隐写检测率和更快的分类速度。     

基于纹理特征与随机森林的生态声音识别

针对真实环境中普遍存在的非平稳噪声,提出一种基于纹理特征与随机森林的生态声音识别方法。该方法首先使用一种基于噪声估计的音频增强算法,即短时谱估计对输入端声音信号进行前端处理,得到增强信号功率谱;然后根据得到的增强信号功率谱图的纹理信息,采用和差统计法对其进行纹理特征提取;最后,利用基于决策树的组合分类器,即随机森林进行识别和分类。设计了两组对比实验,结果表明该方法不仅有良好的识别性能,而且具有噪声鲁棒性。     

基于集成学习的离子通道药物靶点预测

新药研制成功的关键在于药物靶点的发现和准确定位.在已知的药物靶点中,离子通道蛋白是一类广受欢迎的靶点,它与免疫系统、心血管等疾病密切相关.对于靶点的发现,传统生物方法成本高、耗时久.因此,探讨了基于机器学习的离子通道蛋白药物靶点的挖掘,以加快药物靶点发现过程,节约经费.由于药物靶点相关序列的长度不一致,考虑了蛋白质序列编码的13种特征,它们能将不等长的蛋白质序列转化成等长序列.通过数值实验筛选能够较好地区分靶点和非靶点的特征子集,并采用集成学习的方法整合特征得到预测模型.通过与已有工作的比较表明,提出的集成模型能得到较高的准确率,具有很好的应用前景.     

随机背包公钥密码的分析与改进

针对随机背包公钥密码方案,提出一种私钥恢复攻击方法.发现Wang等人所构造的随机背包公钥方案实际上是隐含使用了一个特殊的超递增背包.通过使用普通超递增背包代替该特殊超递增背包,将超递增背包隐藏在随机选择的背包中,对原方案进行了改进,提出一种新的基于中国剩余定理的背包公钥密码方案.改进后的方案消除了原方案存在的设计缺陷,能够抵抗针对原方案提出的格规约攻击、低密度攻击以及shamir攻击.     

Joint underwater target detection and tracking with the Bernoulli filter using an acoustic vector sensor

In this paper, we study the problem of joint underwater target detection and tracking using an acoustic vector sensor (AVS). For this challenging problem, first a realistic frequency domain simulation is set up. The outputs of this simulation generate the two dimensional FRequency–AZimuth (FRAZ) image. On this image, the random finite set (RFS) framework is employed to characterize the target state and sensor measurements. We propose to use the Bernoulli filter, which is the optimal Bayes filter emerged from the RFS framework for randomly on/off switching single dynamic systems. Moreover, to increase the performance of detection and azimuth tracking in low signal-to-noise ratio (SNR) scenarios, a track-before-detect (TBD) measurement model for AVS is proposed to be used with the Bernoulli filter. Sequential Monte Carlo (SMC) implementation is preferred for the Bernoulli filter recursions. Extensive simulation results prove the performance gain obtained by the proposed approach both in estimation accuracy and detection range of the system.     

装备故障样本优化方法研究

测试性验证装备的故障样本往往相互关联,全部注入费用较高、代价较大.为了降低验证试验费用,采用适当方法对故障样本进行优化分析.为提高故障检测率,提出了一种等价样本的故障样本优化方法.方法在分析故障-测试关联矩阵及其扩展、故障模式功能等价集合和故障模式测试等价集合的基础上,构建了故障样本等价集合,并进行重要度特征分析和最大熵求解,确定了最小的故障样本集合.通过对某型试验台故障样本优化实例分析,并与传统的方法进行了试验结果对比分析,使得故障样本数量、试验费用大为减少,提高了测试性验证的经济性.     

Multi-target tracking on confidence maps: An application to people tracking

We propose a generic online multi-target track-before-detect (MT-TBD) that is applicable on confidence maps used as observations. The proposed tracker is based on particle filtering and automatically initializes tracks. The main novelty is the inclusion of the target ID in the particle state, enabling the algorithm to deal with unknown and large number of targets. To overcome the problem of mixing IDs of targets close to each other, we propose a probabilistic model of target birth and death based on a Markov Random Field (MRF) applied to the particle IDs. Each particle ID is managed using the information carried by neighboring particles. The assignment of the IDs to the targets is performed using Mean-Shift clustering and supported by a Gaussian Mixture Model. We also show that the computational complexity of MT-TBD is proportional only to the number of particles. To compare our method with recent state-of-the-art works, we include a postprocessing stage suited for multi-person tracking. We validate the method on real-world and crowded scenarios, and demonstrate its robustness in scenes presenting different perspective views and targets very close to each other.     

基于UVM实现随机测试的先进方法

随机设计越来越复杂,受约束的随机化测试方法已成为验证的发展趋势。本文以数据流交叉模块的验证为例,介绍如何基于UVM验证方法学构建受约束的随机化测试平台,其主要内容包括：UVM验证平台的建立、受约束的随机的实现、功能覆盖率的实现、自动检查结构等方面。     

基于事件的主动队列管理研究

针对随机早期检测RED存在的对参数过于敏感、时延抖动、队长不稳定等问题,采用特殊事件标记法,通过调整丢弃概率的增减幅度,对RED算法进行了改进。实验表明,改进的算法在稳定性、链路利用率方面有了较好的改善。