Microsoft

SimPoly: Simulation of Polymers with Machine Learning Force Fields Derived from First Principles

Polymers are a versatile class of materials with widespread industrial applications. Advanced computational tools could revolutionize their design, but their complex, multi-scale nature poses ...
Microsoft

Rethinking Machine Learning Collective Communication as a Multi Commodity Flow problem

Cloud operators utilize collective communication optimizers to enhance the efficiency of the single-tenant, centrally managed training clusters they manage. However, current optimizers struggle to ...
IEEE

Mathematical Modeling and Simulation of Traffic Flow Control in Urban Environments Using Fuzzy Deep Neural Network With Optimization Algorithm

Abstract: With the enlarging number of transports on the road and fast growth, traffic flow is a significant current worry that obstructs the financial system’s evolution and affects the quality of ...
Scientific Research Publishing

Klose, B., Spedding, G. and Jacobs, G. (2021) Direct Numerical Simulation of Cambered Airfoil Aerodynamics at Re = 20,000.

ABSTRACT: Early stages of ground-effect flight transit vehicle (GEFT) development identify benchmark digital prototype performances with approaches to reduce energy consumption by 20% to 80%. 80% ...
IEEE

FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units

Abstract: Roadside unit (RSU) can significantly improve the safety and robustness of autonomous vehicles through Vehicle-to-Everything (V2X) communication. Currently, the usage of a single RSU mainly ...
Scientific Research Publishing

Jiang, Y., Alexander, D., Jenkins, H., Arthur, R. and Chen, Q. (2003) Natural Ventilation in Buildings: Measurement in a Wind Tunnel and Numerical Simulation with Large-Eddy ...

ABSTRACT: Energy consumption in Bangladesh has been increasing day by day due to population growth, industrial, and technological development. In accordance with the annual report of the Bangladesh ...