We present a simple technique for estimating parts of the Singular Value Decomposition (SVD) of a data matrix from a small randomly compressed “sketch” of that matrix. In sensor network settings–where each column of the data matrix comes from a separate sensor–the sketch can be assembled using operations local to each sensor. As an application of this work, we consider the problem of Structural Health Monitoring (SHM). SHM systems are critical for monitoring aging infrastructure (such as buildings or bridges) in a cost-effective manner. Such systems typically involve collections of battery-operated wireless sensors that sample vibration data over time. After the data is transmitted to a central node, modal analysis can be used to detect damage in the structure. We propose and study three frameworks for Compressive Sensing (CS) in SHM systems; these methods are intended to minimize power consumption by allowing the data to be sampled and/or transmitted more efficiently. At the central node, all of these frameworks involve a very simple technique for estimating the structure’s mode shapes without requiring a traditional CS reconstruction of the vibration signals; all that is needed is to compute a simple SVD. We support our proposed techniques theoretically and using simulations based on synthetic and real data. This project is joint work with Anna Gilbert and Jae Young Park.
April 2 @ 12:30
12:30 pm (1h)
Discovery Building, Orchard View Room