Rakesh Sarma
YOU?
Author Swipe
View article: Effects of Pelvic Floor Muscle Training on Peak Expiratory Flow Rate and Muscle Strength in Postpartum Women - An Experimental Study
Effects of Pelvic Floor Muscle Training on Peak Expiratory Flow Rate and Muscle Strength in Postpartum Women - An Experimental Study Open
Background: The pelvic floor muscles primarily protect the end of pelvic organs and are also involved in breathing during speaking, deep breathing and coughing. The diaphragm and pelvic floor have a symbiotic relationship, and the pelvic f…
View article: Resource-adaptive successive doubling for hyperparameter optimization with large datasets on high-performance computing systems
Resource-adaptive successive doubling for hyperparameter optimization with large datasets on high-performance computing systems Open
View article: Surrogate Modeling of Fluid Flow Under Different Conditions Using Physicsinformed Deep Operator Networks
Surrogate Modeling of Fluid Flow Under Different Conditions Using Physicsinformed Deep Operator Networks Open
View article: Towards a European HPC/AI ecosystem: a community-driven report
Towards a European HPC/AI ecosystem: a community-driven report Open
View article: Resource-Adaptive Successive Doubling for Hyperparameter Optimization with Large Datasets on High-Performance Computing Systems
Resource-Adaptive Successive Doubling for Hyperparameter Optimization with Large Datasets on High-Performance Computing Systems Open
On High-Performance Computing (HPC) systems, several hyperparameter configurations can be evaluated in parallel to speed up the Hyperparameter Optimization (HPO) process. State-of-the-art HPO methods follow a bandit-based approach and buil…
View article: Parallel and scalable AI in HPC systems for CFD applications and beyond
Parallel and scalable AI in HPC systems for CFD applications and beyond Open
This manuscript presents the library AI4HPC with its architecture and components. The library enables large-scale trainings of AI models on High-Performance Computing systems. It addresses challenges in handling non-uniform datasets throug…
View article: Prediction of Turbulent Boundary Layer Flow Dynamics with Transformers
Prediction of Turbulent Boundary Layer Flow Dynamics with Transformers Open
Time-marching of turbulent flow fields is computationally expensive using traditional Computational Fluid Dynamics (CFD) solvers. Machine Learning (ML) techniques can be used as an acceleration strategy to offload a few time-marching steps…
View article: Distributed hybrid quantum-classical performance prediction for hyperparameter optimization
Distributed hybrid quantum-classical performance prediction for hyperparameter optimization Open
Hyperparameter optimization (HPO) of neural networks is a computationally expensive procedure, which requires a large number of different model configurations to be trained. To reduce such costs, this work presents a distributed, hybrid wo…
View article: On the choice of physical constraints in artificial neural networks for predicting flow fields
On the choice of physical constraints in artificial neural networks for predicting flow fields Open
The application of Artificial Neural Networks (ANNs) has been extensively investigated for fluid dynamic problems. A specific form of ANNs are Physics-Informed Neural Networks (PINNs). They incorporate physical laws in the training and hav…
View article: Distributed Hybrid Quantum-Classical Performance Prediction for Hyperparameter Optimization
Distributed Hybrid Quantum-Classical Performance Prediction for Hyperparameter Optimization Open
Hyperparameter Optimization of neural networks is a computationally expensive procedure, which requires a large number of different model configurations to be trained. To reduce such costs, this work presents a distributed, hybrid workflow…
View article: Resource-Adaptive Successive Doubling for Hyperparameter Optimization with Large Datasets on High-Performance Computing Systems
Resource-Adaptive Successive Doubling for Hyperparameter Optimization with Large Datasets on High-Performance Computing Systems Open
View article: interTwin D6.1 Report on requirements and core modules definition
interTwin D6.1 Report on requirements and core modules definition Open
interTwin co-designs and implements the prototype of an interdisciplinary Digital Twin Engine (DTE). The developed DTE will be an open source platform that includes software components for modelling and simulation to integrate application-…
View article: Large scale performance analysis of distributed deep learning frameworks for convolutional neural networks
Large scale performance analysis of distributed deep learning frameworks for convolutional neural networks Open
Continuously increasing data volumes from multiple sources, such as simulation and experimental measurements, demand efficient algorithms for an analysis within a realistic timeframe. Deep learning models have proven to be capable of under…
View article: Bayesian Inference of Quasi‐Linear Radial Diffusion Parameters using Van Allen Probes
Bayesian Inference of Quasi‐Linear Radial Diffusion Parameters using Van Allen Probes Open
The Van Allen radiation belts in the magnetosphere have been extensively studied using models based on radial diffusion theory, which is derived from a quasi‐linear approach with prescribed inner and outer boundary conditions. The 1D diffu…
View article: Aeroelastic validation and Bayesian updating of a downwind wind turbine
Aeroelastic validation and Bayesian updating of a downwind wind turbine Open
Summary Downwind wind turbine blades are subjected to tower wake forcing at every rotation, which can lead to structural fatigue. Accurate characterisation of the unsteady aeroelastic forces in the blade design phase requires detailed repr…
View article: Reconstruction and reduction of uncertainties in aeroelastic systems
Reconstruction and reduction of uncertainties in aeroelastic systems Open
The growing demand for energy worldwide has resulted in the exploration and
development of sustainable forms of energy, such as wind energy. Wind turbines
are typically used to extract power from the wind through the rotational mot…
development of sustainable forms of energy, such as wind energy. Wind turbines
are typically used to extract power from the wind through the rotational mot…
View article: Dust Deposition Mechanism and Cleaning Strategy for Open Volumetric Air Receiver Based Solar Tower Sub-systems
Dust Deposition Mechanism and Cleaning Strategy for Open Volumetric Air Receiver Based Solar Tower Sub-systems Open
Desert regions like Rajasthan and Gujarat in India receives abundant solar energy. At the same time these regions are blessed with dust or sand. Solar thermal systems are one of the ways to harness this available energy. Open Volumetric Ai…
View article: SYSTEM IDENTIFICATION FOR UNCERTAINTY QUANTIFICATION IN AEROELASTIC PROBLEMS
SYSTEM IDENTIFICATION FOR UNCERTAINTY QUANTIFICATION IN AEROELASTIC PROBLEMS Open
Aeroelastic problems involve coupling of fluid and structural solvers to obtain the response of the system under a set of operating conditions.Unsteady aeroelastic phenomena such as flutter require the solution of these coupled equations f…