Valentin Radu
Scholar

Valentin Radu

Google Scholar ID: 5BHrhxQAAAAJ
University of Sheffield
Edge AIMultimodal Machine LearningUbiquitous ComputingMachine Learning Systems
Citations & Impact
All-time
Citations
978
 
H-index
14
 
i10-index
18
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • May 2022: Paper 'Data selection for efficient model update in federated learning' accepted at EuroMLSys 2022
  • Nov. 2021: Paper 'Sensor-Fusion for Smartphone Location Tracking Using Hybrid Multimodal Deep Neural Networks' published in Sensors
  • Jun. 2021: Two papers accepted at IPIN 2021 on active learning for localization and MM-Loc cross-sensor indoor tracking
  • Apr. 2021: Paper 'Towards Federated Learning with Attention Transfer to mitigate System and Data Heterogeneity of Clients' accepted at EdgeSys (co-located with EuroSys 2021)
  • Mar. 2021: Paper 'Fast Optimisation of Convolutional Neural Network Inference using System Performance Models' accepted at EuroMLSys (EuroSys 2021)
  • Oct. 2020: Paper 'MM-Fit: Multimodal Deep Learning for Automatic Exercise Logging Across Sensing Devices' accepted to ACM IMWUT and presented at Ubicomp 2021
  • Dec. 2020: Released the MM-Fit dataset accompanying the IMWUT paper
  • Aug. 2019: Paper on CNN channel pruning for embedded GPUs presented at IISWC 2019
  • Jul. 2019: Paper 'Vision2Sensor: Knowledge Transfer Across Sensing Modalities for Human Activity Recognition' accepted to ACM IMWUT and presented at Ubicomp 2019
  • Jul. 2019: Two papers accepted at IPIN 2019 on RNN calibration for inertial sensors and CamLoc pedestrian localization
  • Mar. 2021: Became a member of HiPEAC, the European Center of Excellence in computing systems research
  • Mar. 2021: Joined the Insigneo Institute for in silico Medicine
  • 2019–2021: Co-organized the Accelerated Machine Learning (AccML) workshop at HiPEAC conferences