Research round-up — April
This month has been filled with awards and recognition for EEE staff, students and alumni. Here are four good news research stories to celebrate.
Industry innovation
Junkosha, manufacturer of high performance polymers, has named Professor Stepan Lucyszyn and his team as the winner of its inaugural Technology Innovator of the Year Awards in the Microwave and Millimeter Wave category.
For the last seven years, Stepan and his team have been pioneering 3D printed components — designing, simulating, manufacturing, testing and analysing novel materials, components and subsystems that can operate in the microwave-to-terahertz spectrum, for lightweight applications including low-cost communications, radar and sensor systems.
Assistive robotics
Dr Fan Zhang and Professor Yiannis Demiris’s work on robot-assisted dressing was featured in New Scientist earlier this month.
Assistive robots have the potential to support people with disabilities in a variety of activities of daily living, such as dressing. People who have lost their upper limb movement functionality may benefit from robot-assisted dressing.
Flexible objects like a hospital gown are extremely difficult for robots to work with, so the robot focuses only on key points that it needs to grasp and manipulate.
In their paper, published in Science Robotics, they demonstrate the robot grasping a hospital gown hung on a rail, fully unfolding the gown, navigating around a bed, and lifting up the user’s arms in sequence to finally dress them. Their proposed method enabled the robot to put back-opening hospital gowns on to a medical manikin with a success rate of more than 90%.
Sensor success
Congratulations to PhD student Harry Davies, whose work was selected for an Editor's Choice article in the Sensors journal.
The article "In-Ear SpO2: A tool for wearable, unobtrusive monitoring of core blood oxygen saturation'' has applications for clinical and everyday-life.
Young author
Congratulations also to Dr Mohammad Amiri, now a postdoctoral associate at MIT, who has won the EEE ComSoc Best Young Author Paper Award for his paper: Federated Learning Over Wireless Fading Channels, undertaken during his PhD with Professor Deniz Gunduz. Mohammad was a recipient of one of our department's PhD Scholarships, awarded to outstanding applicants.
Federated learning is a distributed machine learning framework that enables mobile devices to learn a shared model in a collaborative manner without offloading their data to a cloud server. Data distributed across many mobile devices provides a certain level of privacy.
Deniz explains: “The paper brings machine learning and wireless communication together, and proposes a highly efficient federated learning method by exploiting physical characteristics of the wireless medium. While conventional communication systems are designed to minimize interference among devices, our solution, instead, benefits from interference. Mobile devices transmit their locally trained models simultaneously, so that they are automatically aligned over the air. This turns air into a computation medium, and opens the way to a whole new set of more efficient distributed machine learning algorithms, which we call “machine learning in the air.”
Mohammad’s award will be presented at a ceremony next month at the IEEE International Conference on Communications in Seoul, South Korea.
Article text (excluding photos or graphics) © Imperial College London.
Photos and graphics subject to third party copyright used with permission or © Imperial College London.