maintaining only frequent itemsets to mine approximate frequent itemsets over online data streams

IEEE

Discriminative Orthogonal Neighborhood-Preserving Projections for Classification

Orthogonal neighborhood-preserving projection (ONPP) is a recently developed orthogonal linear algorithm for overcoming the out-of-sample problem existing in the well-known manifold learning algorithm, i.e., locally linear embedding. It has been shown that ONPP is a strong analyzer of high-dimensional data. However, when applied to classification problems in a supervised setting, ONPP only focuses on the intraclass geometrical information while ignores the interaction of samples from different classes. To enhance the performance of ONPP in classification, a new algorithm termed discriminative ONPP (DONPP) is proposed in this paper. DONPP 1) takes into account both intraclass and interclass geometries; 2) considers the neighborhood information of interclass relationships; and 3) follows the orthogonality property of ONPP. Furthermore, DONPP is extended to the semisupervised case, i.e., semisupervised DONPP (SDONPP). This uses unlabeled samples to improve the classification accuracy of the original DONPP. Empirical studies demonstrate the effectiveness of both DONPP and SDONPP.

Diffusive coevolution and mutualism maintenance mechanisms in a fig-fig wasp system

In reciprocal mutualism systems, the exploitation events by exploiters might disrupt the reciprocal mutualism, wherein one exploiter species might even exclude other coexisting exploiter species over an evolutionary time frame. What remains unclear is how such a community is maintained. Niche partitioning, or spatial heterogeneity among the mutualists and exploiters, is generally believed to enable stability within a mutualistic system. However, our examination of a reciprocal mutualism between a fig species (Ficus racemosa) and its pollinator wasp (Ceratosolen fusciceps) shows that spatial niche partitioning does not sufficiently prevent exploiters from overexploiting the common resource (i.e., the female flowers), because of the considerable niche overlap between the mutualists and exploiters. In response to an exploiter, our experiment shows that the fig can (1) abort syconia-containing flowers that have been galled by the exploiter, Apocryptophagus testacea, which oviposits before the pollinators do; and (2) retain syconia-containing flowers galled by Apocryptophagus mayri, which oviposit later than pollinators. However, as a result of (2), there is decreased development of adult non-pollinators or pollinator species in syconia that have not been sufficiently pollinated, but not aborted. Such discriminative abortion of figs or reduction in offspring development of exploiters while rewarding cooperative individuals with higher offspring development by the fig will increase the fitness of cooperative pollinating wasps, but decrease the fitness of exploiters. The fig fig wasp interactions are diffusively coevolved, a case in which fig wasps diversify their genotype, phenotype, or behavior as a result of competition between wasps, while figs diverge their strategies to facilitate the evolution of cooperative fig waps or lessen the detrimental behavior by associated fig wasps. In habitats or syconia that suffer overexploitation, discriminative abortion of figs or reduction in the offspring development of exploiters in syconia that are not or not sufficiently pollinated will decrease exploiter fitness and perhaps even drive the population of exploiters to local extinction, enabling the evolution and maintenance of cooperative pollinators through the movement between habitats or syconia (i.e., the metapopulations).

The evolution of cooperation in asymmetric systems

Explaining "Tragedy of the Commons" of evolution of cooperation remains one of the greatest problems for both biology and social science. Asymmetrical interaction, which is one of the most important characteristics of cooperative system, has not been sufficiently considered in the existing models of the evolution of cooperation. Considering the inequality in the number and payoff between the cooperative actors and recipients in cooperation systems, discriminative density-dependent interference competition will occur in limited dispersal systems. Our model and simulation show that the local but not the global stability of a cooperative interaction can be maintained if the utilization of common resource remains unsaturated, which can be achieved by density-dependent restraint or competition among the cooperative actors. More intense density dependent interference competition among the cooperative actors and the ready availability of the common resource, with a higher intrinsic contribution ratio of a cooperative actor to the recipient, will increase the probability of cooperation. The cooperation between the recipient and the cooperative actors can be transformed into conflict and, it oscillates chaotically with variations of the affecting factors under different environmental or ecological conditions. The higher initial relatedness (i.e. similar to kin or reciprocity relatedness), which is equivalent to intrinsic contribution ratio of a cooperative actor to the recipient, can be selected for by penalizing less cooperative or cheating actors but rewarding cooperative individuals in asymmetric systems. The initial relatedness is a pivot but not the aim of evolution of cooperation. This explains well the direct conflict observed in almost all cooperative systems.

Neuronal activity in dorsomedial frontal cortex and prefrontal cortex reflecting irrelevant stimulus dimensions

Previous studies of the dorsomedial frontal cortex (DMF) and the prefrontal cortex (PF) have shown that, when monkeys respond to nonspatial features of a discriminative stimulus (e.g., color) and the stimulus appears at a place unrelated to the movement t

Biologically Inspired Tensor Features

According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate's visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition.

数据流上的频繁项集挖掘技术研究

数据流是近年出现的一个新的应用类型，具有连续、无限、高速等特点。典型的数据流包括：无线传感器网络应用环境中由传感器传回的各种监测数据、股票交易所的股票价格信息、网络监测系统与道路交通监测系统的监测数据、电信部门的通话记录数据，以及网站的日志信息等。数据流的出现对传统的数据管理和挖掘技术提出了巨大的挑战。传统的数据挖掘技术往往对静态数据集合做多遍扫描，其时间和空间复杂度均较高，难以直接应用到数据流环境中。本文对数据流上的频繁项集挖掘问题做了深入研究，主要研究内容和创新性成果概述如下： 本文首先对频繁项集挖掘问题做了一个全面的综述。综述部分先对静态数据集上的频繁项集挖掘的概念、分类、经典算法等相关研究做全面的介绍，然后分析了在数据流上进行频繁项集挖掘面临的问题和挑战、以及研究现状。 针对数据流上的频繁元素挖掘问题，本文提出了一个简单而高效的算法，挖掘数据流滑动窗口上的频繁元素。算法既可以定期返回满足ε-近似要求的频繁元素，也可以响应用户在任意时间提交的请求，返回满足误差要求的结果。 针对数据流上的频繁项集挖掘问题，本文提出了BFI-Stream算法，挖掘数据流滑动窗口上的所有频繁项集，实时返回精确结果。该算法使用前缀树数据结构，并且在创建和更新过程中裁剪了一部分非频繁节点，因此算法的空间和时间复杂度都较低。 接着，本文针对现有的在数据流上挖掘频繁项集的算法存在维护过多非频繁项集而导致使用空间过大的问题，提出了一种乐观裁剪方法，大大降低了算法的空间复杂度。文中先对实际数据集分析了项集的频率分布情况，提出了乐观裁剪方法，裁剪大部分非频繁项集；实验结果表明乐观裁剪方法不仅大大降低了内存使用量，还提高了算法的更新效率。 再次，本文针对用户指定最小支持度和允许误差的近似查询，提出了在数据流滑动窗口上挖掘频繁项集的近似算法AFI-Stream，返回满足误差要求的结果。AFI-Stream仅仅维护频繁项集，不维护非频繁项集，因此能大大降低算法使用的内存。 为了满足在数据流上挖掘频繁项集研究的需要，本文设计并开发了一个数据流频繁项集挖掘原型系统StreamMiner，进行相关算法的评测和研究。

Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e. g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method.