Bayesian and Markov chain Monte Carlo methods for identifying nonlinear systems in the presence of uncertainty

Green, P. L.; Worden, Keith

doi:10.1098/rsta.2014.0405

Cited by 70 publications

(44 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Originally tested at the University of Southampton's Institute of Sound and Vibration Research, only a very brief description of the device and experimental procedure is given here -more information can be found in the references [19,20]. It should be noted that the data from this experiment can be found in the electronic supplementary material of the paper [22].…”

Section: Example 2 -Experimental Datamentioning

confidence: 98%

Bayesian system identification of dynamical systems using large sets of training data: A MCMC solution

Green

2015

Probabilistic Engineering Mechanics

View full text Add to dashboard Cite

Section: Example 2 -Experimental Datamentioning

confidence: 98%

Bayesian system identification of dynamical systems using large sets of training data: A MCMC solution

Green

2015

Probabilistic Engineering Mechanics

View full text Add to dashboard Cite

“…It should be noted that a wide variety of hysteretic models can be described by using the two extended Masing rules through the choice of the initial load curve. Thus, the class of Masing hysteretic model with restoring force-deflection relation (42) used here is only a special class of Masing models.…”

Section: Example 2: Three-story Masing Shear-building Under Seismic Ementioning

confidence: 99%

Using Approximate Bayesian Computation by Subset Simulation for Efficient Posterior Assessment of Dynamic State-Space Model Classes

Vakilzadeh¹,

Beck²,

Abrahamsson³

2018

SIAM J. Sci. Comput.

View full text Add to dashboard Cite

Approximate Bayesian Computation (ABC) methods have gained in their popularity over the last decade because they expand the horizon of Bayesian parameter inference methods to the range of models for which only forward simulation is available. The majority of the ABC methods rely on the choice of a set of summary statistics to reduce the dimension of the data. However, as has been noted in the ABC literature, the lack of convergence guarantees that is induced by the absence of a vector of sufficient summary statistics that assures inter-model sufficiency over the set of competing models, hinders the use of the usual ABC methods when applied to Bayesian model selection or assessment. In this paper, we present a novel ABC model selection procedure for dynamical systems based on a newly appeared multi-level Markov chain Monte Carlo method, self-regulating ABC-SubSim, and a hierarchical state-space formulation of dynamic models. We show that this formulation makes it possible to independently approximate the model evidence required for assessing the posterior probability of each of the competing models. We also show that ABC-SubSim not only provides an estimate of the model evidence as a simple by-product but also it gives the posterior probability of each model as a function of the tolerance level, which allows the ABC model choices made in previous studies to be understood. We illustrate the performance of the proposed framework for ABC model updating and model class selection by applying it to two problems in Bayesian system identification: a single degree-offreedom bilinear hysteretic oscillator and a three-story shear building with Masing hysteresis, both of which are subject to a seismic excitation.

show abstract

“…Databases are also essential to establish the outcome of unusual situations, such as the case of an older woman with breast cancer, hemiparesis, and a myeloproliferative disorder. The American Society of Clinical Oncology has instituted the CancerLinQ program to study unusual neoplasms that are not amenable to randomized clinical trials due to their rarity. Through CancerLinQ, these cases are registered and closely followed, and the outcome of different treatments may be compared.…”

Section: Analysis Of the Clinical Casesmentioning

confidence: 99%

Management of Cancer in the Older Age Person: An Approach to Complex Medical Decisions

et al. 2017

View full text Add to dashboard Cite

The management of cancer in older aged people is becoming a common problem due to the aging of the population. There are many variables determining the complex situation that are interconnected. Some of them can be assessed, such as risk of mortality and risk of treatment complications, but many others are still unknown, such as the course of disease, the host-related factors that influence cancer aggressiveness, and the phenotype heralding risk of permanent treatment-related damage.This article presents a dynamic and personalized approach to older people with cancer based on our experience on aging, cancer, and their biological interactions. Also, novel treatments and management approaches to older individuals, based on their functional age and their social and emotional needs, are thoughtfully explored here. The Oncologist 2017;22:335-342 Implications for Practice: The goal of this article is to suggest a practical approach to complexity, a clinical situation becoming increasingly common with the aging of the population. Beginning with the analysis of two clinical cases, the authors offer an algorithm for approaching cancer in the older person that involves the assessment of life expectancy without cancer, the risk that cancer might compromise a patient's survival, function, or quality of life, and the potential benefits and risks of the treatments based on a clinical evaluation. The authors then review possible laboratory assessment of functional age and the importance of rapid-learning databases in the study of cancer and age.

show abstract

Bayesian and Markov chain Monte Carlo methods for identifying nonlinear systems in the presence of uncertainty

Cited by 70 publications

References 55 publications

Bayesian system identification of dynamical systems using large sets of training data: A MCMC solution

Bayesian system identification of dynamical systems using large sets of training data: A MCMC solution

Using Approximate Bayesian Computation by Subset Simulation for Efficient Posterior Assessment of Dynamic State-Space Model Classes

Management of Cancer in the Older Age Person: An Approach to Complex Medical Decisions

Contact Info

Product

Resources

About