An official website of the United States government
This work discusses an optimization framework to embed dictionary learning frameworks with the wave equation as a strategy for incorporating prior scientific knowledge into a machine learning algorithm. We modify dictionary learning to study ultrasonic guided wave-based defect detection for non-destructive structural health monitoring systems. Specifically, this work involves altering the popular-SVD algorithm for dictionary learning by enforcing prior knowledge about the ultrasonic guided wave problem through a physics-based regularization derived from the wave equation. We confer it the name “wave-informed K-SVD.” Training dictionary on data simulated from a fixed string added with noise using both K-SVD and wave-informed K-SVD, we show an improved physical consistency of columns of dictionary matrix with the known modal behavior of different one-dimensional wave simulations is observed.
more »
« less
Wave Physics Informed Dictionary Learning In One Dimension
Detecting and locating damage information from waves reflected off damage is a common practice in non-destructive structural health monitoring systems. Yet, the transmitted ultrasonic guided waves are affected by the physical and material properties of the structure and are often complicated to model mathematically. This calls for data-driven approaches to model the behaviour of waves, where patterns in wave data due to damage can be learned and distinguished from non-damage data. Recent works have used a popular dictionary learning algorithm, K-SVD, to learn an overcomplete dictionary for waves propagating in a metal plate. However, the domain knowledge is not utilized. This may lead to fruitless results in the case where there are strong patterns in the data that are not of interest to the domain. In this work, instead of treating the K-SVD algorithm as a black box, we create a novel modification by enforcing domain knowledge. In particular, we look at how regularizing the K-SVD algorithm with the one-dimensional wave equation affects the dictionary learned in the simple case of vibrating string. By adding additional non-wave patterns (noise) to the data, we demonstrate that the “wave-informed K-SVD” does not learn patterns which do not obey the wave equation hence learning patterns from data and not the noise.
more »
« less
- Award ID(s):
- 1839704
- PAR ID:
- 10195474
- Date Published:
- Journal Name:
- 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)It has recently been shown that periodicity in discrete-time data can be analyzed using Ramanujan sums and associated dictionaries. This paper explores the role of dictionary learning methods in the context of period estimation and periodic signal representation using dictionaries. It is shown that a wellknown dictionary learning algorithm, namely K-SVD, is able to learn Ramanujan and Farey periodicity dictionaries from the noisy, sparse coefficient data generated from them without imposing any periodicity structure in the learning stage. This similarity between the learned dictionary and the underlying original periodicity dictionary reaffirms the power of the KSVD in predicting the right dictionary from data without explicit application-specific constraints. The paper also examines how the choice of different parameter values affect the similarity of the learned dictionary to the underlying dictionary. Two versions of K-SVD along with different initializations are analyzed for their effect on representation and denoising error for the data.more » « less
-
The inverse problem of inferring clinical gold-standard electrocardiogram (ECG) from photoplethysmogram (PPG) that can be measured by affordable wearable Internet of Healthcare Things (IoHT) devices is a research direction receiving growing attention. It combines the easy measurability of PPG and the rich clinical knowledge of ECG for long-term continuous cardiac monitoring. The prior art for reconstruction using a universal basis, such as discrete cosine transform (DCT), has limited fidelity for uncommon ECG shapes due to the lack of representative power. To better utilize the data and improve data representation, we design two dictionary learning frameworks, the cross-domain joint dictionary learning (XDJDL), and the label-consistent XDJDL (LC-XDJDL), to further improve the ECG inference quality and enrich the PPG-based diagnosis knowledge. Building on the K-SVD technique, the proposed joint dictionary learning frameworks extend the expressive power by optimizing simultaneously a pair of signal dictionaries for PPG and ECG with the transforms to relate their sparse codes and disease information. The proposed models are evaluated with a variety of PPG and ECG morphologies from two benchmark datasets that cover various age groups and disease types. The results show the proposed frameworks achieve better inference performance than previous methods with average Pearson coefficients being 0.88 using XDJDL and 0.92 using LC-XDJDL, suggesting an encouraging potential for ECG screening using PPG based on the proactively learned PPG-ECG relationship. By enabling the dynamic monitoring and analysis of the health status of an individual, the proposed frameworks contribute to the emerging digital twins paradigm for personalized healthcare.more » « less
-
Sparse coding, which refers to modeling a signal as sparse linear combinations of the elements of a learned dictionary, has proven to be a successful (and interpretable) approach in applications such as signal processing, computer vision, and medical imaging. While this success has spurred much work on provable guarantees for dictionary recovery when the learned dictionary is the same size as the ground-truth dictionary, work on the setting where the learned dictionary is larger (or over-realized) with respect to the ground truth is comparatively nascent. Existing theoretical results in this setting have been constrained to the case of noise-less data. We show in this work that, in the presence of noise, minimizing the standard dictionary learning objective can fail to recover the elements of the ground-truth dictionary in the over-realized regime, regardless of the magnitude of the signal in the data-generating process. Furthermore, drawing from the growing body of work on self-supervised learning, we propose a novel masking objective for which recovering the ground-truth dictionary is in fact optimal as the signal increases for a large class of data-generating processes. We corroborate our theoretical results with experiments across several parameter regimes showing that our proposed objective also enjoys better empirical performance than the standard reconstruction objective.more » « less
-
Ultrasonic guided waves are commonly used to localize structural damage in infrastructures such as buildings, airplanes, bridges. Damage localization can be viewed as an inverse problem. Physical model based techniques are popular for guided wave based damage localization. The performance of these techniques depend on the degree of faithfulness with which the physical model describes wave propagation. External factors such as environmental variations and random noise are a source of uncertainty in wave propagation. The physical modeling of uncertainty in an inverse problem is still a challenging problem. In this work, we propose a deep learning based model for robust damage localization in presence of uncertainty. Wave data with uncertainty is simulated to reflect variations due to external factors and Gaussian noise is added to reflect random noise in the environment. After evaluating the localization error on test data with uncertainty, we observe that the deep learning model trained with uncertainty can learn robust representations. The approach shows the potential for dealing with uncertainty in physical science problems using deep learning models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/MLSP.2019.8918835
