B
Batool Salehi
Researcher at Northeastern University
Publications - 11
Citations - 105
Batool Salehi is an academic researcher from Northeastern University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 1, co-authored 5 publications receiving 5 citations.
Papers
More filters
Journal ArticleDOI
RF Fingerprinting Unmanned Aerial Vehicles With Non-Standard Transmitter Waveforms
Nasim Soltani,Guillem Reus-Muns,Batool Salehi,Jennifer G. Dy,Stratis Ioannidis,Kaushik R. Chowdhury +5 more
TL;DR: A multi-classifier scheme with a two-step score-based aggregation method, using RF data augmentation to increase neural network robustness to hovering-induced variations, and extending the multi- classifier scheme for detecting a new UAV, not seen earlier during training are proposed.
Proceedings ArticleDOI
Open-World Class Discovery with Kernel Networks
Zifeng Wang,Batool Salehi,Andrey Gritsenko,Kaushik R. Chowdhury,Stratis Ioannidis,Jennifer G. Dy +5 more
TL;DR: This work proposes Class Discovery Kernel Network with Expansion (CD-KNet-Exp), a deep learning framework, which utilizes the Hilbert Schmidt Independence Criterion to bridge supervised and unsupervised information together in a systematic way, such that the learned knowledge from old classes is distilled appropriately for discovering new classes.
Proceedings ArticleDOI
Machine Learning on Camera Images for Fast mmWave Beamforming
Batool Salehi,Mauro Belgiovine,Sara Garcia Sanchez,Jennifer G. Dy,Stratis Ioannidis,Kaushik R. Chowdhury +5 more
TL;DR: In this paper, a machine learning approach with two sequential convolutional neural networks (CNNs) is proposed to identify the locations of the transmitter and receiver nodes, and then return the optimal beam pair.
Journal ArticleDOI
Deep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network
Batool Salehi,Guillem Reus-Muns,Debashri Roy,Zifeng Wang,Tong Jian,Jennifer Dy,Stratis Ioannidis,Kaushik R. Chowdhury +7 more
TL;DR: This work proposes individual modality and distributed fusion-based deep learning (F-DL) architectures that can execute locally as well as at a mobile edge computing center (MEC) with a study on associated tradeoffs.
Proceedings ArticleDOI
FLASH: Federated Learning for Automated Selection of High-band mmWave Sectors
TL;DR: A multimodal deep learning architecture is proposed that fuses the inputs from these data sources and locally predicts the sectors for best alignment at a vehicle using data from multiple non-RF sensors, such as LiDAR, GPS, and camera images.