Big Data Analytics and Structural Health Monitoring: A Statistical Pattern Recognition-Based Approach

Recent advances in sensor technologies and data acquisition systems opened up the era of big data in the field of structural health monitoring (SHM). Data-driven methods based on statistical pattern recognition provide outstanding opportunities to implement a long-term SHM strategy, by exploiting measured vibration data. However, their main limitation, due to big data or high-dimensional features, is linked to the complex and time-consuming procedures for feature extraction and/or statistical decision-making. To cope with this issue, in this article we propose a strategy based on autoregressive moving average (ARMA) modeling for feature extraction, and on an innovative hybrid divergence-based method for feature classification. Data relevant to a cable-stayed bridge are accounted for to assess the effectiveness and efficiency of the proposed method. The results show that the offered hybrid divergence-based method, in conjunction with ARMA modeling, succeeds in detecting damage in cases strongly characterized by big data.

Realized Variance Modeling: Decoupling Forecasting from Estimation*

This article evaluates the in-sample fit and out-of-sample forecasts of various combinations of realized variance models and functions delivering estimates (estimation criteria). Our empirical findings highlight that: independently of the econometrician’s forecasting loss (FL) function, certain estimation criteria perform significantly better than others; the simple ARMA modeling of the log realized variance generates superior forecasts than the Heterogeneous Autoregressive (HAR) family, for any of the FL functions considered; the (2, 1) parameterizations with negative lag-2 coefficient emerge as the benchmark specifications generating the best forecasts and approximating long-range dependence as does the HAR family.