Daniele Angelosante

Group lassoing change-points in piecewise- constant AR processes

Regularizing the least-squares criterion with the total number of coefficient changes, it is possible to estimate time-varying (TV) autoregressive (AR) models with piecewise-constant coefficients. Such models emerge in various applications including speech segmentation, biomedical signal processing, and geophysics. To cope with the inherent lack of continuity and the high computational burden when dealing with high-dimensional data sets, this article introduces a convex regularization approach enabling efficient and continuous estimation of TV-AR models. To this end, the problem is cast as a sparse regression one with grouped variables, and is solved by resorting to the group least-absolute shrinkage and selection operator (Lasso). The fresh look advocated here permeates benefits from advances in variable selection and compressive sampling to signal segmentation. An efficient block-coordinate descent algorithm is developed to implement the novel segmentation method. Issues regarding regularization and uniqueness of the solution are also discussed. Finally, an alternative segmentation technique is introduced to improve the detection of change instants. Numerical tests using synthetic and real data corroborate the merits of the developed segmentation techniques in identifying piecewise-constant TV-AR models.

Vibration Sensitivity Reduction of Photoacoustic Gas Analyzers

Optical gas analyzers are devices for measuring gas concentrations with high precision in industrial environments. Unfortunately mechanical shocks and vibrations can impact the measurement accuracy if the analyzer is installed in noisy environments, e.g. near rotating machines. In this paper, we propose two methods to remove the influence of vibrations by using an auxiliary signal measured via an accelerometer. In the first method, the mechanoelectrical transfer function between the vibration and its effects on the microphone is estimated before installation of the analyzer. In the second method, the mechanoelectrical transfer function is updated continuously under normal sensing operations. The two methods have been implemented within an ABB URAS gas analyzer and corrections are executed in real time. Tests on a vibrating table have confirmed the effectiveness of both methods: a reduction in vibration sensitivity up to a factor twenty is achieved.