Autoregressive model extrapolation using cubic splines for damage progression analysis

Yano, Marcus Omori; Villani, Luis Gustavo; Silva, Samuel da; Figueiredo, Elói

doi:10.1007/s40430-020-02734-3

Cited by 4 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The variety of different scenarios applied to the structure is the main reason that induced several researchers to investigate its dynamical behavior. [61][62][63][64] Figure 2(a) shows the structure's layout, where aluminum plates and four aluminum columns were assembled using bolted joints to compose each floor. Figure 2(b) shows the damage mechanism located at the center of the structure's top floor.…”

Section: Damage Detection Methodologymentioning

confidence: 99%

Damage quantification using transfer component analysis combined with Gaussian process regression

Yano

Silva

Figueiredo

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

Machine learning methods used in Structural Health Monitoring applications still have generalization difficulties among structures, even when structures are nominally and topologically similar. The data sets present divergences between their probability distributions that do not allow the model’s generalization for damage detection. This issue is even more complex in situations where one wants to quantify damage levels through data sets collected from different structures. Transfer learning methods offer a solution to overcome those limitations, using relevant information from a labeled structure (source domain) to assist the analysis of another structure (target domain) under unknown conditions. Therefore, this paper proposes the use of transfer component analysis to mitigate divergences between the model/structure’s features, and the label consistency requirement is applied in combination with a Gaussian process regression model for damage quantification. The effectiveness of the estimated model improves when the labels consistency between domains is achieved, indicating the current damage level in the structure when the regression model achieves its best performance (lowest error). The proposed methodology is applied on the benchmark data of a three-story building structure from the Los Alamos National Laboratory using the knowledge from its numerical model under several conditions, where the complete information of its behavior is available. The results compare the analysis in the original space and after applying the proposed methodology, demonstrating an improvement of the performance in the damage detection and quantification steps.

show abstract

Section: Damage Detection Methodologymentioning

confidence: 99%

Damage quantification using transfer component analysis combined with Gaussian process regression

Yano

Silva

Figueiredo

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discrete/continuous State-space and Design Of The Observer/c...mentioning

confidence: 99%

“…This distinction is particularly evidenced by the fluctuation in the values between each condition, especially for II, where the first term (ϕ 1 ) is less stable across the windows presented (characterizing the irregular pattern of II compared to a more regular PIS activity[39]). This characteristic is specific to this type of modeling and has been used in pattern recognition approaches involving, for instance, structural health monitoring[47][48][49][50] as well as analysis and validation of computational models in describing II and PIS activities[39], since the AR coefficients are sensitive to changes in the signal dynamics[48].In fact, Ref[39] used the same signals present in this work, and by applying nonlinear/nonparametric classification techniques, such as logistic regression and confidence intervals, fairly good classifications were obtained. Moreover, within each condition, the coefficients are relatively bounded over the time windows (for further results, please see Fig B in S1 Appendix), which suggests that not only the patterns of II/PIS are sustained differently, but also that the coefficients do reflect this consistency.…”

mentioning

confidence: 99%

Epileptic seizure suppression: A computational approach for identification and control using real data

Brogin,

Faber,

Reyes-Garcia

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Epilepsy affects millions of people worldwide every year and remains an open subject for research. Current development on this field has focused on obtaining computational models to better understand its triggering mechanisms, attain realistic descriptions and study seizure suppression. Controllers have been successfully applied to mitigate epileptiform activity in dynamic models written in state-space notation, whose applicability is, however, restricted to signatures that are accurately described by them. Alternatively, autoregressive modeling (AR), a typical data-driven tool related to system identification (SI), can be directly applied to signals to generate more realistic models, and since it is inherently convertible into state-space representation, it can thus be used for the artificial reconstruction and attenuation of seizures as well. Considering this, the first objective of this work is to propose an SI approach using AR models to describe real epileptiform activity. The second objective is to provide a strategy for reconstructing and mitigating such activity artificially, considering non-hybrid and hybrid controllers − designed from ictal and interictal events, respectively. The results show that AR models of relatively low order represent epileptiform activities fairly well and both controllers are effective in attenuating the undesired activity while simultaneously driving the signal to an interictal condition. These findings may lead to customized models based on each signal, brain region or patient, from which it is possible to better define shape, frequency and duration of external stimuli that are necessary to attenuate seizures.

show abstract

“…This distinction is particularly evidenced by the fluctuation in the values between each condition, especially for II, where the first term (φ 1 ) is less stable across the windows presented (characterizing the irregular pattern of II compared to a more regular PIS activity [50]). This characteristic is specific to this type of modeling and has been used in pattern recognition approaches involving, for instance, structural health monitoring [51][52][53][54] as well as analysis and validation of computational models in describing II and PIS activities [50], since the AR coefficients are sensitive to changes in the signal dynamics [52].…”

Section: Observer/controllermentioning

confidence: 99%

Epileptic seizure suppression: a computational approach for identification and control using real data

Brogin

Faber

Reyes-García

et al. 2023

Preprint

View full text Add to dashboard Cite

Epilepsy affects millions of people worldwide every year and remains an open subject for research. Current development on this field has focused on obtaining computational models to better understand its triggering mechanisms, attain realistic descriptions and study seizure suppression. Controllers have been successfully applied to mitigate epileptiform activity in dynamic models written in state-space notation, whose applicability is, however, restricted to signatures that are accurately described by them. Alternatively, autoregressive modeling (AR), a typical data-driven tool related to system identification (SI), can be directly applied to signals to generate more realistic models, and since it is inherently convertible into state-space, it can thus be used for the artificial reconstruction and attenuation of seizures as well. Considering this, the first objective of this work is to propose an SI approach using AR models to describe real epileptiform activity. The second objective is to provide a strategy for reconstructing and mitigating such activity artificially, considering non-hybrid and hybrid controllers – designed from ictal and interictal events, respectively. The results show that AR models of relatively low order represent epileptiform activities fairly well and both controllers are effective in attenuating the undesired activity while simultaneously driving the signal to an interictal stage. These findings may lead to customized models based on each signal, brain region or patient, from which it is possible to better define shape, frequency and duration of external stimuli that are necessary to attenuate seizures.

show abstract

Autoregressive model extrapolation using cubic splines for damage progression analysis

Cited by 4 publications

References 36 publications

Damage quantification using transfer component analysis combined with Gaussian process regression

Damage quantification using transfer component analysis combined with Gaussian process regression

Epileptic seizure suppression: A computational approach for identification and control using real data

Epileptic seizure suppression: a computational approach for identification and control using real data

Contact Info

Product

Resources

About