skip to main content

Search for: All records

Creators/Authors contains: "Cao, S."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. The fluid dynamics of a bubble collapsing near an elastic or viscoelastic material is coupled with the mechanical response of the material. We apply a multiphase fluid–solid coupled computational model to simulate the collapse of an air bubble in water induced by an ultrasound shock wave, near different types of materials including metals (e.g. aluminium), polymers (e.g. polyurea), minerals (e.g. gypsum), glass and foams. We characterize the two-way fluid–material interaction by examining the fluid pressure and velocity fields, the time history of bubble shape and volume and the maximum tensile and shear stresses produced in the material. We show thatmore »the ratio of the longitudinal acoustic impedance of the material compared to that of the ambient fluid, $Z/Z_0$ , plays a significant role. When $Z/Z_0<1$ , the material reflects the compressive front of the incident shock into a tensile wave. The reflected tensile wave impinges on the bubble and decelerates its collapse. As a result, the collapse produces a liquid jet, but not necessarily a shock wave. When $Z/Z_0>1$ , the reflected wave is compressive and accelerates the bubble's collapse, leading to the emission of a shock wave whose amplitude increases linearly with $\log (Z/Z_0)$ , and can be much higher than the amplitude of the incident shock. The reflection of this emitted shock wave impinges on the bubble during its rebound. It reduces the speed of the bubble's rebound and the velocity of the liquid jet. Furthermore, we show that, for a set of materials with $Z/Z_0\in [0.04, 10.8]$ , the effect of acoustic impedance on the bubble's collapse time and minimum volume can be captured using phenomenological models constructed based on the solution of Rayleigh–Plesset equation.« less
  2. Building a predictive model based on historical Electronic Health Records (EHRs) for personalized healthcare has become an active research area. Benefiting from the powerful ability of feature ex- traction, deep learning (DL) approaches have achieved promising performance in many clinical prediction tasks. However, due to the lack of interpretability and trustworthiness, it is difficult to apply DL in real clinical cases of decision making. To address this, in this paper, we propose an interpretable and trustworthy predictive model (INPREM) for healthcare. Firstly, INPREM is designed as a linear model for interpretability while encoding non-linear rela- tionships into the learning weightsmore »for modeling the dependencies between and within each visit. This enables us to obtain the contri- bution matrix of the input variables, which is served as the evidence of the prediction result(s), and help physicians understand why the model gives such a prediction, thereby making the model more in- terpretable. Secondly, for trustworthiness, we place a random gate (which follows a Bernoulli distribution to turn on or off) over each weight of the model, as well as an additional branch to estimate data noises. With the help of the Monto Carlo sampling and an ob- jective function accounting for data noises, the model can capture the uncertainty of each prediction. The captured uncertainty, in turn, allows physicians to know how confident the model is, thus making the model more trustworthy. We empirically demonstrate that the proposed INPREM outperforms existing approaches with a significant margin. A case study is also presented to show how the contribution matrix and the captured uncertainty are used to assist physicians in making robust decisions.« less
  3. Building a predictive model based on historical Electronic Health Records (EHRs) for personalized healthcare has become an active research area. Benefiting from the powerful ability of feature ex- traction, deep learning (DL) approaches have achieved promising performance in many clinical prediction tasks. However, due to the lack of interpretability and trustworthiness, it is difficult to apply DL in real clinical cases of decision making. To address this, in this paper, we propose an interpretable and trustworthy predictive model (INPREM) for healthcare. Firstly, INPREM is designed as a linear model for interpretability while encoding non-linear rela- tionships into the learning weightsmore »for modeling the dependencies between and within each visit. This enables us to obtain the contri- bution matrix of the input variables, which is served as the evidence of the prediction result(s), and help physicians understand why the model gives such a prediction, thereby making the model more in- terpretable. Secondly, for trustworthiness, we place a random gate (which follows a Bernoulli distribution to turn on or off) over each weight of the model, as well as an additional branch to estimate data noises. With the help of the Monto Carlo sampling and an ob- jective function accounting for data noises, the model can capture the uncertainty of each prediction. The captured uncertainty, in turn, allows physicians to know how confident the model is, thus making the model more trustworthy. We empirically demonstrate that the proposed INPREM outperforms existing approaches with a significant margin. A case study is also presented to show how the contribution matrix and the captured uncertainty are used to assist physicians in making robust decisions.« less
  4. Free, publicly-accessible full text available June 1, 2023