Efficient similarity-based operations for data integration

Dealing with discrepancies in data is still a big challenge in data integration systems. The problem occurs both during eliminating duplicates from semantic overlapping sources as well as during combining complementary data from different sources. Though using SQL operations like grouping and join seems to be a viable way, they fail if the attribute values of the potential duplicates or related tuples are not equal but only similar by certain criteria. As a solution to this problem, we present in this paper similarity-based variants of grouping and join operators. The extended grouping operator produces groups of similar tuples, the extended join combines tuples satisfying a given similarity condition. We describe the semantics of this operator, discuss efficient implementations for the edit distance similarity and present evaluation results. Finally, we give examples of application from the context of a data reconciliation project for looted art.     

Cycle detection using a stack

We present an algorithm for detecting periodicity in sequences produced by repeated application of a given function. Our algorithm uses logarithmic memory with high probability, runs in linear time, and is guaranteed to stop within the second loop through the cycle. We also present a partitioning technique that offers a time/memory tradeoff. Our algorithm is especially well suited for sequences where the cycle length is typically small compared to the length of the acyclic prefix.     

Pedestrian detection and tracking at crossroads

This paper presents a system that can perform pedestrian detection and tracking using vision-based techniques. A very important issue in the field of intelligent transportation system is to prevent pedestrians from being hit by vehicles. Recently, a great number of vision-based techniques have been proposed for this purpose. In this paper, we propose a vision-based method, which combines the use of a pedestrian model as well as the walking rhythm of pedestrians to detect and track walking pedestrians. Through integrating some spatial and temporal information grabbed by a vision system, we are able to develop a reliable system that can be used to prevent traffic accidents happened at crossroads. In addition, the proposed system can deal with the occlusion problem. Experimental results obtained by executing some real world cases have demonstrated that the proposed system is indeed superb.     

An immune oriented multi-agent system for biological image processing

In this article, we present a parallel image processing system based on the concept of reactive agents. Our system lies in the oRis language, which allows to describe finely and simply the agents’ behaviors to detect image features. We also present a method of segmentation using a multi-agent system, and two biological applications made with oRis. The stopping of this multi-agent system is implemented through a technique issued from immunology: the apoptosis.     

Employing optimized combinations of one-class classifiers for automated currency validation

Automated currency validation requires a decision to be made regarding the authenticity of a banknote presented to the validation system. This decision often has to be made with little or no information regarding the characteristics of possible counterfeits as is the case for issues of new currency. A method for automated currency validation is presented which segments the whole banknote into different regions, builds individual classifiers on each region and then combines a small subset of the region specific classifiers to provide an overall decision. The segmentation and combination of region specific classifiers to provide optimized false positive and false negative rates is achieved by employing a genetic algorithm. Experiments based on high value notes of Sterling currency were carried out to assess the effectiveness of the proposed solution.     

Kernel Spectral Matched Filter for Hyperspectral Imagery

In this paper a kernel-based nonlinear spectral matched filter is introduced for target detection in hyperspectral imagery, which is implemented by using the ideas in kernel-based learning theory. A spectral matched filter is defined in a feature space of high dimensionality, which is implicitly generated by a nonlinear mapping associated with a kernel function. A kernel version of the matched filter is derived by expressing the spectral matched filter in terms of the vector dot products form and replacing each dot product with a kernel function using the so called kernel trick property of the Mercer kernels. The proposed kernel spectral matched filter is equivalent to a nonlinear matched filter in the original input space, which is capable of generating nonlinear decision boundaries. The kernel version of the linear spectral matched filter is implemented and simulation results on hyperspectral imagery show that the kernel spectral matched filter outperforms the conventional linear matched filter.     

基于DTW算法的语音识别系统实现

动态时间归整(DTW)算法的实现简单有效,在孤立词语音识别系统中得到了广泛的应用.介绍了将DTW算法移植到TMS320VC5402上实现孤立词语音识别的原理、系统硬件组成和软件设计.研究结果表明,系统能满足实时性能要求,识别效果良好.     

CDMA系统中联合功率控制、波束赋形与多用户检测

应用功率控制、波束赋形和多用户检测可以有效地消除和减少CDMA系统中的干扰。本文结合波束赋形和多用户检测的特性，提出一种应用波束赋形增益和多用户相关矩阵的解相关算法。基于算法的复杂性，提出一种区分聚集用户进行多用户检测的的算法。由于波束赋形能够消减主瓣波束之外的多用户干扰，对聚集移动台采用解相关检测达到减少运算量和消除多用户干扰的目的。对算法进行了仿真分析，证明了本算法的优越性。     

基于DMF捕获系统频率选择性信道下捕获性能的分析

对基于数字匹配滤波器(DMF)捕获系统在频率选择性信道下的捕获性能进行了深入讨论，利用状态转移图推导出单次驻留判决方式时平均捕获时间的表达式，对平均捕获时间与多径分量的关系进行了数字分析。得出的主要结论是：对于多径分量为非衰落信号时，多径分量之间的能量差别越大，系统捕获性能越好，多径分量的能量相等时，系统捕获性能最差，且随着可以分离的多径路数的增加下降；对于多径分量为慢衰落信号时，多径信道的捕获性能好于单径信道(非频率选择性衰落信道)，且多径分量之间的能量差别越大，系统捕获性能越差，当多径分量的能量相等时，捕获性能最好，这与非衰落信道的情形相反。因此在频率选择性衰落信道中，采用分集接收可以改善系统的捕获性能。     

A Theoretical Framework for Core Material Properties Identification in Cellular Solids using Novelty Detection

Abstract:  This paper presents a novelty detection-based technique to identify core material properties of honeycombs and cellular structures. A numerical model (finite element) representing full scale and/or reduced size of the cellular solid is used to generate transmissibilities between topological homologous points at cells in different locations. In order to make the procedure robust against noise, these transmissibilities are artificially corrupted. This step is representative of a series of experimentally obtained measurements which automatically return information relating to the size and shape of data noise along with the mean measurement. The next stage, both in this paper and in the proposal for the experimental approach, is to generate several further sets of transmissibilities from the finite element model; the only difference being that the core material properties are altered from the original values. A novelty detection framework is then adopted to find a similarity measure between each of these 'test' transmissibilities and the original set thereby identifying the material properties. Although this work is concerned with identifying only one material property, the methodology extends to identifying several properties.