Change-point Management: Active Sensing and Ensemble Learning (CAIMAN)

Online detection of abrupt changes in time series has received much attention in the past due to its importance in applications such as structural health monitoring or target detection and tracking. In particular, the signal processing community has established the basic theory of change-point detection, which more recently has also attracted the interest of the machine learning community. In any case, and despite numerous research efforts, modern applications face several challenging problems due to the need of working with high-dimensional, temporally structured, missing, and distributed data.

The goal of the CAIMAN project focuses on the development of online change-point management algorithms, and their application to three selected modern applications: human behavioral change detection, wireless communications, and finance/econometrics. Thus, CAIMAN aims to advance in two different but complementary directions. On one hand, in order to address the aforementioned challenges, the techniques to be developed must go beyond the typical assumptions and simple models considered in classical change-point detection theory. On the other hand, the new framework of change-point management encompasses not only the detection of change points, but also the smart design of the measurement process to optimize performance (change-point sensing).