A correlative classifiers approach based on particle filter and sample set for tracking occluded target

Target tracking is one of the most important issues in computer vision and has been applied in many fields of science, engineering and industry. Because of the occlusion during tracking, typical approaches with single classifier learn much of occluding background information which results in the decrease of tracking performance, and eventually lead to the failure of the tracking algorithm. This paper presents a new correlative classifiers approach to address the above problem. Our idea is to derive a group of correlative classifiers based on sample set method. Then we propose strategy to establish the classifiers and to query the suitable classifiers for the next frame tracking. In order to deal with nonlinear problem, particle filter is adopted and integrated with sample set method. For choosing the target from candidate particles, we define a similarity measurement between particles and sample set. The proposed sample set method includes the following steps. First, we cropped positive samples set around the target and negative samples set far away from the target. Second, we extracted average Haar-like feature from these samples and calculate their statistical characteristic which represents the target model. Third, we define the similarity measurement based on the statistical characteristic of these two sets to judge the similarity between candidate particles and target model. Finally, we choose the largest similarity score particle as the target in the new frame. A number of experiments show the robustness and efficiency of the proposed approach when compared with other state-of-the-art trackers.

改进势场蚁群算法优化路径自动规划

针对势场与蚁群联合的自主路径规划存在局部最优解、初始路径选择随机导致效率不高及环境适应性差等问题,提出了基于自适应域和参数自适应设置的改进算法。算法首先基于自适应域改进势场目标不可达问题,并过滤震荡点以平滑路径;其次,通过状态转移函数和信息素更新等相关参数的自适应设置,提高算法在收敛效率和搜索能力上的平衡性,进而提高对障碍环境的适应性。实验结果表明,所提算法能够有效避免局部最优、目标不可达和复杂环境的适应性问题,在路径长度和效率上优于实验采用的已有算法,从而验证了算法的有效性。

基于改进SPRINT分类算法的数据挖掘模型

为解决目前数据挖掘模型分类时间长、挖掘准确率不高的问题,提出基于改进决策树分类算法(SPRINT)的数据挖掘模型。先采用最大-最小规范化公式完成原始数据线性变换,利用改进后的SPRINT分类算法按照输入数据特性进行分类,使用协同过滤技术生成与数据相近的属性集,计算数据属性相似度,生成语义规则集,为用户提供更优的数据服务。选取某公司营销数据集作为样本进行对比实验,结果表明,与对比模型相比,所提出的数据挖掘模型分类时间更短,挖掘准确率更高,能为用户提供更优质的数据服务。

针对动态集的矩阵型Bloom filter表示与查找

提出一种针对动态集合的矩阵型Bloom filter表示与查找法(matrix Bloom filter,MBF),它使用一个s×m位矩阵对数据集合进行哈希表示与查找,较同类算法SBF和DBF,能继承Bloom filter算法常数查找开销的基本精髓。

基于Rough Set理论的实时个人邮件过滤系统的研究

电子邮件过滤是网络信息安全研究的热点。RoughSet理论是一种处理含糊和不精确性问题的一种新型数学工具,得到了广泛应用。文章结合RoughSet理论的数据分析方法针对实时个人用户电子邮件过滤系统进行了研究。实验结果表明,该方法是有效的。

基于Bloom filter的远程对称差规模估算法

在内容分发网络、闲谈协议、移动数据同步等分布式系统中,远程主机上集合对称差规模的估算准确程度,直接影响基于CPISync算法的集合调和方法的消息交换轮数以及调和时间。对称差规模的估算误差越低,则集合调和的速度越快。本文提出基于布鲁姆过滤器的准交集查询法,该算法可显著降低对称差规模的估算误差,提高调和算法的效率。

基于卡尔曼滤波与可达集的自主车辆安全性验证方法

针对目前自动驾驶中车辆安全性验证缺少动态验证过程以及安全性验证结果保守度过高的问题,构建车辆动力学和车辆跟踪偏差模型,结合卡尔曼滤波与传感器数据对目标集动态状态进行预测更新,通过可达性分析计算可达集;提出准确度指标、优化度指标以及风险指标评价可达集,通过优化各个指标参数以平衡可达集保守度和危险度,在此基础上建立车辆安全等级,实现了自主车辆动态安全性验证任务。结果表明,基于卡尔曼滤波与可达集的自主车辆安全性验证方法不仅可以在平衡保守度和风险度的情况下验证自主车辆安全等级,还可以为车辆监控预警系统提供依据。

基于标签多伯努利跟踪器的对手风险动态评估方法

在诸多的军事和民用领域都存在对手目标蓄意入侵我方重要区域从事恶意伤害活动的场景。对手风险评估是基于我方传感器获取的量测数据,在线评估和预测对手行动对我方资产造成的潜在伤害和损失。为了评估随机且动态变化的对手风险,该文提出一种基于标签多伯努利(LMB)跟踪器的统计对手风险动态评估方法。首先,在LMB跟踪器的框架下,基于加性模型和乘性模型,分别推导了统计对手风险最小均方误差估计的表达式。其次,针对所涉及的非线性函数积分问题,结合混合高斯近似和抽样近似方法,提出统计对手风险最小均方误差估计的数值计算方法;最后,将统计对手风险估计方法与LMB跟踪器的迭代过程有机结合,可实现入侵的多目标对我方重要资产期望损失的动态在线评估。模拟多个具有杀伤能力的目标攻击我方雷达阵地的场景,利用雷达获取的实时点迹量测数据,验证了提出算法的有效性和性能优势。

Rough Set在垃圾邮件过滤技术中的应用

垃圾邮件是Internet上面临急待解决的问题.Rough集理论是处理模糊和不精确数据的新型工具,能提供描述正常模型的最小预测规则集.重点阐述了Rough set在垃圾邮件过滤中的应用,并对大量数据进行了实验对比,试验验证了Rough set在垃圾邮件过滤技术上的可行性和可靠性.

海量大数据定向采样有差别挖掘算法仿真

在大数据中,不同类别之间可能存在数据分布不均衡的情况,即某些类别的数据样本数量远远少于其他类别。这种情况下,传统的采样方法无法正确反映所有类别的特征和差异。为提升大数据信息的应用性,文中研究海量大数据定向采样有差别挖掘算法。以网站统一资源定位器(URL)初始化为基础,在网络上抓取网页,采集网页的超文本标记语言(HTML)数据,提取定向数据的相关链接,并将其导入URL队列。根据网络搜索策略,实施相关的数据搜索和处理。完成数据搜索后,将自动进行下一网页的URL,继续进行海量大数据定向采样。结合模糊特征匹配与检测滤波方法实现大数据定向采样过程中的抗干扰处理。采用粗糙集算法实施挖掘,利用扩展差别矩阵对大数据决策表内的值实施约简,实现海量大数据的模式分类。实验结果显示,该算法数据采集过程中的丢包率基本控制在0.2%以下,具有较高的鲁棒性。

CEEMD-SG滤波在固井质量测井资料处理中的应用

目前固井质量评价主要依靠声波变密度测井资料,受双层套管影响,变密度图像有时会因内、外层套管波叠加出现明显的畸变现象,对固井质量的评价产生干扰。为获得真实的变密度图像,剔除“假异常”,将互补集合经验模态分解(CEEMD)和Savitzky-Golay(SG)滤波法联合,提出一种CEEMD-SG滤波方法,并应用于声波变密度测井数据处理。首先使用CEEMD方法对变密度数据进行分解,通过傅里叶变换对原始信号及分解得到的各个固有模态函数(IMF)进行频谱分析,然后选取高频IMF分量使用SG滤波算法进行处理,并将滤波后的高频分量与CEEMD分解得到的低频分量联合重构得到处理后的信号。利用该方法对塔里木油田实际变密度资料进行处理,并与CEEMD、小波阈值去噪、SG滤波三种方法进行对比,结果表明,CEEMD-SG滤波方法能更好地消除双层套管带来的波形叠加干扰,处理后的资料能满足现场验收要求。

基于布隆过滤器的零知识集成员证明效率提升

针对区块链中数据的安全验证问题(数据的动态增加导致零知识集成员证明参数更新频繁、参数生成和验证时间变长),进行了创新性的完善。提出了一种新型的数据存储模型,结合优化的跳表索引,提高了数据验证的安全性和效率。实验结果表明,基于布隆过滤器的新型数据存储模型和外部索引,虽然增加了空间复杂度,但是借助预校验机制,提高了约45%的安全校验速度。此外,优化后的时间跳表总体上提高了约50%的区块检索速度,并且索引更新更加便捷。

(∈γ, ∈γ ∨qδ)-intuitionistic Fuzzy(Soft) Filter of BL-algebras

In the paper,in order to further study the properties of filters of BL-algebras,we propose the concepts of the(∈_γ,∈_γ∨_(qδ))-intuitionistic fuzzy filters and(∈_γ,∈_γ∨_(qδ))-intuitionistic fuzzy soft filters of BL-algebras and derive some related results.Finally,we discuss the properties of images and inverse images of(∈_γ,∈_γV_(qδ))-intuitionistic fuzzy soft filters of BL-algebras.

一种基于SET/CMOS电路的二阶低通滤波器

在研究单电子晶体管(single electron transistor,SET)Ⅰ—Ⅴ特性的基础上，依据分区处理法，设计了一个SET积分器电路，并采用级联方法实现了一个SET／CMOS二阶低通滤波器。仿真结果表明，该滤波器的幅频特性增益比采用其它方法描述SET Ⅰ—Ⅴ特性所构成的滤波器的幅频特性增益高出1倍多。

Logical Properties of Lattice Filter of Lattice Implication Algebra

Some new properties of lattice filters are presented based on the order-preserving mapping and lattice homomorphism, and two necessary and sufficient conditions for lattice filters under the chain type are given. Then, the relations between lattice filter and lattice implication algebras （LIAs）, i. e., the relations between lattice filter and LIA-filters, and the related properties are investigated. In addition, three necessary and sufficient conditions for LIA-filters are discussed. The obtained results may serve as some theoretical supports to lattice-valued logical system.

Filtering-efficiency measurement of Chinese-made filter 1by double-filter method

Filtering efficiency of the Chinese-made filter 1 has been measured by the double-filter method with only one set of measurement equipment. The β counts of the two filters are measured in turn for every 3 minutes, from which the decay constants are extracted to be 0.0131 min-1 and 0.0129 min-1 for the first and second filter respectively. After correcting the β counts of the second filter, the filtering efficiency of the filter is obtained to be (87.4±0.7)% in average.

S-rough sets and knowledge separation

The conceptions of the knowledge screen generated by S-rough sets are given: f- screen and - screen , and then puts forward - filter theorem, - filter theorem of knowledge. At last, the applications of knowledge separation are given according to - screen and - screen.

Synthesis of Fractional-order PI Controllers and Fractional-order Filters for Industrial Electrical Drives

This paper introduces an electrical drives control architecture combining a fractional-order controller and a setpoint pre-filter. The former is based on a fractional-order proportional-integral(PI) unit, with a non-integer order integral action, while the latter can be of integer or non-integer type. To satisfy robustness and dynamic performance specifications, the feedback controller is designed by a loop-shaping technique in the frequency domain. In particular, optimality of the feedback system is pursued to achieve input-output tracking. The setpoint pre-filter is designed by a dynamic inversion technique minimizing the difference between the ideal synthesized command signal(i.e., a smooth monotonic response) and the prefilter step response. Experimental tests validate the methodology and compare the performance of the proposed architecture with well-established control schemes that employ the classical PIbased symmetrical optimum method with a smoothing pre-filter.

Effects of transmitter-related parameter settings on ranging accuracy for IR-UWB systems

For impulse radio ultra-wideband (IR-UWB) ranging systems,effects of the settings of transmitter-related parameters, which include the pulse shape, the bandwidth and the pulse repetition interval (PRI), on ranging accuracy were studied through theoretical analysis and simulations. Both the match-filtering based coherent TOA estimation algorithm and the energy-detection based non-coherent algorithm were used during simulations. Results show that the pulse shape has the least effect on the ranging accuracy. Increasing the pulse bandwidth can improve the ranging performance, but the performance is hardly improved any more when the bandwidth is increased beyond a certain level. PRI should be set long enough to guarantee the accurate ranging, because when PRI is shorter than the maximum excess delay of the channel, the ranging accuracy will be deteriorated by inter-pulse interference.