Search for: All records

Cardiovascular disease (CVD) remains one of the leading causes of mortality worldwide. Computational medicine and digital twins hold promise in mitigating the impact and prevalence of CVD. Recent advances in image-based computational methods have enabled the quantification of functional and biologically important metrics that would otherwise be difficult to obtain from the standard of care. However, significant challenges remain due to the manual/semi-automated nature of the processes and the domain expertise required to perform them. This paper addresses these challenges by proposing a novel framework that builds on our recently developed direct point cloud-to-CFD approach using immersogeometric analysis. The proposed method leverages advanced auto-segmentation techniques to extract medically relevant geometries as point clouds, which are then directly used for CFD simulations. The framework is validated using benchmark flow problems with analytical and computational solutions and is subsequently applied to patient-specific images to demonstrate its capabilities. The results highlight the method's ability to facilitate rapid CFD simulations directly on point clouds derived from patient scans, underscoring its potential to accelerate the image-to-simulation pipeline and enable the tractability of cardiovascular digital twins. 

Federated learning (FL) has emerged as a new paradigm of machine learning (ML) with the goal of collaborative learning on the vast pool of private data available across distributed edge devices. The focus of most existing works in FL systems has been on addressing the challenges of computation and communication heterogeneity inherent in training with edge devices. However, the crucial impact of I/O and the role of limited on-device storage has not been explored fully in FL context. Without policies to exploit the on-device storage for placement of client data samples, and schedule clients based on I/O benefits, FL training can lead to inefficiencies, such as increased training time and impacted accuracy convergence. In this paper, we propose FedCaSe, a framework for efficiently caching client samples in-situ on limited on-device storage and scheduling client participation. FedCaSe boosts the I/O performance by exploiting a unique characteristic--- the experience, i.e., relative impact on overall performance, of data samples and clients. FedCaSe utilizes this information in adaptive caching policies for sample placement inside the limited memory of edge clients. The framework also exploits the experience information to orchestrate the future selection of clients. Our experiments with representative workloads and policies show that compared to the state of the art, FedCaSe improves the training time by 2.06× for accuracy convergence at the scale of thousands of clients. 

Abstract Fish fin rays constitute a sophisticated control system for ray-finned fish, facilitating versatile locomotion within complex fluid environments. Despite extensive research on the kinematics and hydrodynamics of fish locomotion, the intricate control strategies in fin-ray actuation remain largely unexplored. While deep reinforcement learning (DRL) has demonstrated potential in managing complex nonlinear dynamics; its trial-and-error nature limits its application to problems involving computationally demanding environmental interactions. This study introduces a cutting-edge off-policy DRL algorithm, interacting with a fluid–structure interaction (FSI) environment to acquire intricate fin-ray control strategies tailored for various propulsive performance objectives. To enhance training efficiency and enable scalable parallelism, an innovative asynchronous parallel training (APT) strategy is proposed, which fully decouples FSI environment interactions and policy/value network optimization. The results demonstrated the success of the proposed method in discovering optimal complex policies for fin-ray actuation control, resulting in a superior propulsive performance compared to the optimal sinusoidal actuation function identified through a parametric grid search. The merit and effectiveness of the APT approach are also showcased through comprehensive comparison with conventional DRL training strategies in numerical experiments of controlling nonlinear dynamics.