Reverse nearest neighbor search with a non-spatial aspect

With the recent surge in the use of the location-based service (LBS), the importance of spatial database queries has increased. The reverse nearest neighbor (RNN) search is one of the most popular spatial database queries. In most previous studies, the spatial distance is used for measuring the distance between objects. However, as the demands of users of the LBSs are becoming more complex, considering only the spatial factor as a distance measure is not sufficient. For example, through a hotel finding service, users want to choose a hotel considering not only the spatial distance, but also the non-spatial aspect of the hotel such as the quality which can be represented by the number of stars. Therefore, services that consider both spatial and non-spatial factors in measuring the distance are more useful for users. In such a case, techniques proposed in the previous studies cannot be used since the distance measure is different. In this paper, we propose an efficient method for the RNN search in which a distance measure involves both the spatial distance and the non-spatial aspect of an object. We conduct extensive experiments on a large dataset to evaluate the efficiency of the proposed method. The experimental results show that the proposed method is significantly efficient and scalable.     

Multidimensional reverse <Emphasis Type="Italic">k</Emphasis>NN search

Given a multidimensional point q, a reverse k nearest neighbor (RkNN) query retrieves all the data points that have q as one of their k nearest neighbors. Existing methods for processing such queries have at least one of the following deficiencies: they (i) do not support arbitrary values of k, (ii) cannot deal efficiently with database updates, (iii) are applicable only to 2D data but not to higher dimensionality, and (iv) retrieve only approximate results. Motivated by these shortcomings, we develop algorithms for exact RkNN processing with arbitrary values of k on dynamic, multidimensional datasets. Our methods utilize a conventional data-partitioning index on the dataset and do not require any pre-computation. As a second step, we extend the proposed techniques to continuous RkNN search, which returns the RkNN results for every point on a line segment. We evaluate the effectiveness of our algorithms with extensive experiments using both real and synthetic datasets.     

移动对象的动态反向k最近邻研究

反向最近邻查询是空间数据库中最重要的算法之一。传统的反向最近邻查询方法主要是针对静态对象的查询,随着无线通讯和定位技术的快速发展,移动对象发出的查询请求成为新的研究热点。该文将TPR-tree作为算法的索引结构,并提出了基于矩形框的对角线的修剪策略,将半平面修剪策略进行改进,给出了移动对象的动态反向k最近邻的查询方案。     

Optimal selection of reference set for the nearest neighbor classification by Tabu search

In this paper,a new approach is presented to find the reference set for the nearest neighbor classifer.The optimal reference set,which has minimum sample size and satisfies a certain error rate threshold,is obtained through a Tabu search algorithm.When the error rate threshold is set to zero,the algorithm obtains a near minimal consistent subset of a given training set.While the threshold is set to a small appropriate value,the obtained reference set may compensate the bias of the nearest neighbor estimate.An aspiration criterion for Tabu search is introduced,which aims to prevent the search process form the inefficient wandering between the feasible and infeasible regions in the search space and speed up the convergence.Experimental results based on a number of typical data sets are presented and analyzed to illustrate the benefits of the proposed method.Compared to conventional methods,such as CNN and Dasarathy‘s algorithm,the size of the reduced reference sets is much smaller,and the nearest neighbor classification performance is better,especially when the error rate thresholds are set to appropriate nonzerovalues,The experimental results also illustrate that the MCS(inimal consistent set)of Dasarathy‘s algorithm is not minimal,and its candidate consistent set is not always ensured to reduce monotonically.A counter example is also given to confirm this claim.     

Succinct nearest neighbor search

An efficient and universal similarity search solution is a holy grail for multimedia information retrieval. Most similarity indexes work by mapping the original multimedia objects into simpler representations, which are then searched by proximity using a suitable distance function.     

基于最近邻子空间搜索的两类文本分类方法

在文本分类中,最近邻搜索算法具有思想简单、准确率高等优点,但通常在分类过程中的计算量较大。为克服这一不足,提出了一种基于最近邻子空间搜索的两类文本分类方法。首先提取每一类样本向量组的特征子空间,并通过映射将子空间变换为高维空间中的点,然后把最近邻子空间搜索转化为最近邻搜索完成分类过程。在Reuters-21578数据集上的实验表明,该方法能够有效提高文本分类的性能,具有较高的准确率、召回率和F1值。     

一种基于VARdnn-Tree的反向最近邻查询方法*

空间数据库中反向最近邻查询在低维查询时一般利用基于R-Tree的改进树作为索引结构,由于树型索引结构本身的限制,R-Tree等索引结构的查询在高维中都会出现维数灾难。针对这个问题,提出了一种基于VARdnn-Tree的索引结构,采用量化压缩的方法存储数据,能够有效地支持高维查询。     

应用多索引加法量化编码的近邻检索算法

目的 海量图像检索技术是计算机视觉领域研究热点之一,一个基本的思路是对数据库中所有图像提取特征,然后定义特征相似性度量,进行近邻检索。海量图像检索技术,关键的是设计满足存储需求和效率的近邻检索算法。为了提高图像视觉特征的近似表示精度和降低图像视觉特征的存储空间需求,提出了一种多索引加法量化方法。方法 由于线性搜索算法复杂度高,而且为了满足检索的实时性,需把图像描述符存储在内存中,不能满足大规模检索系统的需求。基于非线性检索的优越性,本文对非穷尽搜索的多索引结构和量化编码进行了探索新研究。利用多索引结构将原始数据空间划分成多个子空间,把每个子空间数据项分配到不同的倒排列表中,然后使用压缩编码的加法量化方法编码倒排列表中的残差数据项,进一步减少对原始空间的量化损失。在近邻检索时采用非穷尽搜索的策略,只在少数倒排列表中检索近邻项,可以大大减少检索时间成本,而且检索过程中不用存储原始数据,只需存储数据集中每个数据项在加法量化码书中的码字索引,大大减少内存消耗。结果 为了验证算法的有效性,在3个数据集SIFT、GIST、MNIST上进行测试,召回率相比近几年算法提升4%~15%,平均查准率提高12%左右,检索时间与最快的算法持平。结论 本文提出的多索引加法量化编码算法,有效改善了图像视觉特征的近似表示精度和存储空间需求,并提升了在大规模数据集的检索准确率和召回率。本文算法主要针对特征进行近邻检索,适用于海量图像以及其他多媒体数据的近邻检索。     

基于概率的反向K最近邻高效查询算法研究

反向K最近邻查询需要确定以给定查询对象作为其k个最近邻之一的所有对象。然而由于大量应用需要处理未知数据,人们迫切需要能够处理未知对象的新算法。这里的主要问题是,一个对象属于RKNN结果集的事件不再是一个确定性事件,而是一个以一定概率成立的随机变量。对基于概率论的未知数据集反向K最近邻(PRKNN)搜索问题展开研究,以足够大的概率返回以查询对象为其最近邻的未知对象。基于一种新的考虑了距离相关性的修剪机制,提出一种PRNN高效查询算法。此外,还给出了如何将该算法扩展至PRKNN(其中k>1)查询处理。最后,将该算法与当前其他最新算法作比较,实验评估结果表明,该算法性能明显优于其他算法。     

时空数据库变体最近邻查询问题探讨

最近邻查询在地理信息系统、智能交通系统、多媒体应用以及数据挖掘等领域有着广泛的应用,随着对最近邻查询问题研究的深入,其应用前景和发展空间将更为广阔。针对近几年时空数据库中提出的最近邻查询的多种变体查询问题进行了详细地介绍和分析,总结了解决这些变体最近邻查询问题的有效方法,最后对最近邻查询问题的发展方向进行了展望。     

On the symmetric angle-restricted nearest neighbor problem

We present an O(nlogn) time divide-and-conquer algorithm for solving the symmetric angle-restricted nearest neighbor (SARNN) problem for a set of n points in the plane under any Lp metric, 1?p?∞. This algorithm is asymptotically optimal (within a multiplicative constant) for any constant p?1.     

Efficient processing of probabilistic reverse nearest neighbor queries over uncertain data

Reverse nearest neighbor (RNN) search is very crucial in many real applications. In particular, given a database and a query object, an RNN query retrieves all the data objects in the database that have the query object as their nearest neighbors. Often, due to limitation of measurement devices, environmental disturbance, or characteristics of applications (for example, monitoring moving objects), data obtained from the real world are uncertain (imprecise). Therefore, previous approaches proposed for answering an RNN query over exact (precise) database cannot be directly applied to the uncertain scenario. In this paper, we re-define the RNN query in the context of uncertain databases, namely probabilistic reverse nearest neighbor (PRNN) query, which obtains data objects with probabilities of being RNNs greater than or equal to a user-specified threshold. Since the retrieval of a PRNN query requires accessing all the objects in the database, which is quite costly, we also propose an effective pruning method, called geometric pruning (GP), that significantly reduces the PRNN search space yet without introducing any false dismissals. Furthermore, we present an efficient PRNN query procedure that seamlessly integrates our pruning method. Extensive experiments have demonstrated the efficiency and effectiveness of our proposed GP-based PRNN query processing approach, under various experimental settings.     

DKNNS:面向延迟敏感型应用的可扩展精确分布式K近邻搜索算法研究

为了降低用户访问延迟,延迟敏感型网络应用需要选择合适的邻近服务节点响应用户访问请求.分布式K近邻搜索通过可扩展的选择距任意用户节点邻近的K个服务节点,可以有效满足网络应用延迟优化的目的.已有工作在精确度以及可扩展性等方面存在不足.针对可扩展精确的K近邻搜索问题,文中提出了分布式K近邻搜索方法DKNNS(distributed K nearest neighbor search).DKNNS将大量的服务节点组织为邻近性感知的多级环,通过最远节点搜索机制选择优化的K近邻搜索初始化节点,然后基于回退方式快速的在目标节点邻近区域发现K个近邻.基于理论分析,模拟测试以及真实环境下的部署实验发现,在不同规模的节点集合下,DKNNS算法能够确定近似最优的K个服务节点.且DKNNS的查询延迟,查询开销均显著低于Meridian算法.最后,DKNNS的返回结果相对于Meridian具有较高的稳定性.     

Center-based nearest neighbor classifier

In this paper, a novel center-based nearest neighbor (CNN) classifier is proposed to deal with the pattern classification problems. Unlike nearest feature line (NFL) method, CNN considers the line passing through a sample point with known label and the center of the sample class. This line is called the center-based line (CL). These lines seem to have more capacity of representation for sample classes than the original samples and thus can capture more information. Similar to NFL, CNN is based on the nearest distance from an unknown sample point to a certain CL for classification. As a result, the computation time of CNN can be shortened dramatically with less accuracy decrease when compared with NFL. The performance of CNN is demonstrated in one simulation experiment from computational biology and high classification accuracy has been achieved in the leave-one-out test. The comparisons with nearest neighbor (NN) classifier and NFL classifier indicate that this novel classifier achieves competitive performance.     

基于网格的共享近邻聚类算法

提出了一种基于网格的共享近邻聚类算法(Grid based shared Nearest Neighbor algorithm, GNN)。该算法主要利用网格技术去除数据集中的部分孤立点或噪声,使用密度阈值处理技术来处理网格的密度阈值,使用中心点技术提高聚类效率。GNN算法仅对数据集进行一遍扫描,且能处理任意形状和大小的聚类。实验表明,GNN有较好的可扩展性,其精度和效率明显地好于共享近邻SNN算法。     

空间对象的反最近邻查询处理技术研究

空间数据库中反最近邻查询的研究是空间查询的研究热点。在对现有的反最近邻查询技术进行分析比较的基础上,针对提高动态数据集的查询效率问题,给出了基于R树索引结构的反最近邻查询方案。通过实验结果的分析比较,可以看出该方案能够有效地解决动态数据集的查询问题。