For many KDD applications finding the outliers, i.e. the rare events, is more interesting and useful than finding the common cases, e.g. detecting criminal activities in E-commerce. Being an outlier, however, is not just a binary property. Instead, it is a property that applies to a certain degree to each object in a data set, depending on how ‘isolated’ this object is, with respect to the surr...

Urbanization significantly alters natural ecosystems and has accelerated globally. Urban wildlife populations are often highly fragmented by human infrastructure, and isolated populations may adapt in response to local urban pressures. However, relatively few studies have identified genomic signatures of adaptation in urban animals. We used a landscape genomic approach to examine signatures of ...

Outlier detection is an integral part of robust evaluation for crowdsourceable Quality of Experience (QoE) and has attracted much attention in recent years. In QoE for multimedia, outliers happen because of different test conditions, human errors, abnormal variations in context, etc. In this paper, we propose a simple yet effective algorithm for outlier detection and robust QoE evaluation named...

In this paper we propose to introduce backing-off in the acoustic contributions of the local distance functions used during Viterbi decoding as an operationalisation of missing feature theory for increased recognition robustness. Acoustic backing-off effectively removes the detrimental influence of outlier values from the local decisions in the Viterbi algorithm. It does so without the need for...

Outlier detection is an integral part of robust evaluation for crowdsourceable Quality of Experience (QoE) and has attracted much attention in recent years. In QoE for multimedia, outliers happen because of different test conditions, human errors, abnormal variations in context, etc. In this paper, we propose a simple yet effective algorithm for outlier detection and robust QoE evaluation named...

The affinity propagation (AP) clustering algorithm has received a lot of attention over the past few years. AP is efficient and insensitive to initialization, generates results with lower error in less time. However, there are still two key limitations: AP-related algorithms cannot identify outliers clusters. And they usually not ideal for processing nonlinear data. To address above issues, we ...

We present a method to find outliers using ‘commute distance’ computed from a random walk on graph. Unlike Euclidean distance, commute distance between two nodes captures both the distance between them and their local neighborhood densities. Indeed commute distance is the Euclidean distance in the space spanned by eigenvectors of the graph Laplacian matrix. We show by analysis and experiments t...

This paper describes an approach to Bayesian sensitivity analysis that uses an innuence statistic and an outlier statistic to assess the sensitivity of a model to perturbations. The basic outlier statistic is a Bayes factor, while the innuence statistic depends strongly on the purpose of the analysis. The task of innuence analysis is aided by having an interpretable innuence statistic. Two alte...