AIConfPaper
← Search

David J. Love

6 accepted papers

2025

Physics-based Generative Models for Geometrically Consistent and Interpretable Wireless Channel Synthesis

Satyavrat Wagle, Akshay Malhotra, Shahab Hamidi-Rad, Aditya Sant, David J. Love, Christopher G. Brinton
IJCAI 2025

In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resou

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Coded Matrix Computations for D2D-Enabled Linearized Federated Learning

Anindya Bijoy Das, Aditya Ramamoorthy, David J. Love, Christopher G. Brinton
ICASSP 2023accepted

Federated learning (FL) is a popular technique for training a global model on data distributed across client devices. Like other distributed training techniques, FL is susceptible to straggler (slower or failed) clients. Recent work has proposed to address this through device-to-device (D2D) offload…

Cited by 0Source ↗Scholar ↗
2017

Multiple-input multiple-output (MIMO) MRI: An efficient pulse design algorithm to combine parallel excitation and parallel imaging

Xianglun Mao, David J. Love, Joseph Vincent Rispoli, Thomas M. Talavage
ICASSP 2017accepted

Magnetic resonance imaging (MRI) plays a critical role in medicine today. Over the last few years, there has been an interest in techniques that use multiple coils on one side of the imaging system such as parallel excitation or parallel imaging to improve performance in high-field MRI. In this pape…

Cited by 0Source ↗Scholar ↗
2017

Simultaneous wireless information and power transfer over inductively coupled circuits

Tomohiro Arakawa, Andrew C. Marcum, James V. Krogmeier, David J. Love
ICASSP 2017accepted

This paper introduces a system model for simultaneous information and power transfer (SWIPT) over inductively coupled circuits from the standard communication-theoretic perspective. It is shown that the rate-energy (R-E) regions, which characterize the performance of SWIPT, for inductively coupled c…

Cited by 0Source ↗Scholar ↗