Unlike conventional anomaly detection research that focuses on point anomalies, our goal is to detect anomalous collections of individual data points. In particular, we perform group anomaly detection (GAD) with an emphasis on irregular group distributions (e.g. irregular mixtures of image pixels). GAD is an important task in detecting unusual and anomalous phenomena in real-world applications such as high energy particle physics, social media and medical imaging. In this paper, we take a generative approach by proposing deep generative models: Adversarial autoencoder (AAE) and variational autoencoder (VAE) for group anomaly detection. Both AAE and VAE detect group anomalies using point-wise input data where group memberships are known a priori. We conduct extensive experiments to evaluate our models on real world datasets. The empirical results demonstrate that our approach is effective and robust in detecting group anomalies.

Pointwise anomaly detection and change detection focus on the study of individual data instances; however, an emerging area of research involves groups or collections of observations. From applications of high-energy particle physics to health care collusion, group deviation detection techniques result in novel research discoveries, mitigation of risks, prevention of malicious collaborative activities, and other interesting explanatory insights. In particular, static group anomaly detection is the process of identifying groups that are not consistent with regular group patterns, while dynamic group change detection assesses significant differences in the state of a group over a period of time. Since both group anomaly detection and group change detection share fundamental ideas, this survey article provides a clearer and deeper understanding of group deviation detection research in static and dynamic situations.

No abstract

We report on the opinions of respondents to a survey of native plant material (NPM) users east of the Mississippi River. We sought respondents who would have a sufficient depth of experience and interest to be able to answer the survey questions. To find potential respondents, we first built a geographically diverse list of NPM-user organizations and then asked them to help us promote the survey through their social networks. Survey respondents expressed a preference for local ecotypes (74%) and almost no interest in cultivars (0.3%). Respondents identified commercial availability as the greatest barrier to their use of local ecotypes. Of the respondents, 92% use native seeds, and those who prefer local ecotypes are shopping farther afield than their concept of "local" would support. The most popular seed vendor is on average 584 km (363 mi) away from the respondent's location, and the second most popular is 1296 km (805 mi) away. Respondents who think of local as being in-state buy out-of-state 85% of the time. Of the respondents, 90% have less than 2 year's lead time before acquiring NPM, which is not enough time to have wild seeds agronomically increased or plants contract grown. Given those circumstances, 83% would be willing to pay a premium to obtain the ecotypes they want. Among potential solutions to the commercial shortage problem, 99% of respondents supported creation of an online marketplace for sharing supply-and-demand information. Respondents expect their demand for NPMs to increase, highlighting the importance of addressing these issues now.

Given a portfolio of stocks or a series of frames in a video how do we detect significant changes in a group of values for real-time applications? In this article, we formalize the problem of sequentially detecting temporal changes in a group of stochastic processes. As a solution to this particular problem, we propose the group temporal change (GTΔ) algorithm, a simple yet effective technique for the sequential detection of significant changes in a variety of statistical properties of a group over time. Due to the flexible framework of the GTΔ algorithm, a domain expert is able to select one or more statistical properties that they are interested in monitoring. The usefulness of our proposed algorithm is also demonstrated against state-of-the-art techniques on synthetically generated data as well as on two real-world applications; a portfolio of healthcare stocks over a 20 year period and a video monitoring the activity of our Sun.