Tag: IEEE

FCP researchers built a diffusion-model AI framework that reconstructs lost data at the receiver, boosting efficiency for future 6G networks

by jiayan_li

As wireless networks connect an ever-growing number of devices, from smartphones and vehicles to AR/VR applications, ensuring reliable communication becomes increasingly challenging. What happens when parts of the transmitted data are lost due to limited bandwidth or poor channel conditions? FCP researchers from the Singapore University of Technology and Design (SUTD), together with international collaborators … Continue reading FCP researchers built a diffusion-model AI framework that reconstructs lost data at the receiver, boosting efficiency for future 6G networks

Multi-Cluster Decentralized Federated Edge Learning (MD-FEEL)

by jiayan_li

As AI moves from the cloud to billions of connected devices, a major challenge emerges: how can these devices learn together without constantly sending data to a central server? FCP researchers from the Singapore University of Technology and Design (SUTD), together with collaborators, have developed a new approach called 𝗠𝘂𝗹𝘁𝗶-𝗖𝗹𝘂𝘀𝘁𝗲𝗿 𝗗𝗲𝗰𝗲𝗻𝘁𝗿𝗮𝗹𝗶𝘇𝗲𝗱 𝗙𝗲𝗱𝗲𝗿𝗮𝘁𝗲𝗱 𝗘𝗱𝗴𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (𝗠𝗗-𝗙𝗘𝗘𝗟) … Continue reading Multi-Cluster Decentralized Federated Edge Learning (MD-FEEL)

SIG-SDP (Sparse Interference Graph-Aided Semidefinite Programming)

by jiayan_li

Modern factories, autonomous vehicles, and industrial robots all depend on a constant stream of wireless data. As more devices come online, ensuring that critical information arrives on time without interference becomes increasingly challenging. FCP researchers from the Singapore University of Technology and Design (SUTD), together with researchers from the University of Sydney and the University … Continue reading SIG-SDP (Sparse Interference Graph-Aided Semidefinite Programming)

What do satellite mega-constellations, global internet connectivity, and data centres have in common?

by jiayan_li

They all face the same challenge: 𝗛𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝗺𝗼𝘃𝗲 𝗺𝗮𝘀𝘀𝗶𝘃𝗲 𝗮𝗺𝗼𝘂𝗻𝘁𝘀 𝗼𝗳 𝗱𝗮𝘁𝗮 𝗮𝘀 𝗾𝘂𝗶𝗰𝗸𝗹𝘆 𝗮𝘀 𝗽𝗼𝘀𝘀𝗶𝗯𝗹𝗲 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗻𝗲𝘁𝘄𝗼𝗿𝗸𝘀 𝘁𝗵𝗮𝘁 𝗮𝗿𝗲 𝗰𝗼𝗻𝘀𝘁𝗮𝗻𝘁𝗹𝘆 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴? A new study led by FCP researchers from the Singapore University of Technology and Design (SUTD) introduces 𝗢𝗣𝗦𝗦 (𝗢𝗻𝗲-𝗣𝗮𝘀𝘀 & 𝗦𝗺𝗮𝗿𝘁-𝗦𝗲𝗮𝗿𝗰𝗵), a novel algorithm designed to dramatically speed up data delivery … Continue reading What do satellite mega-constellations, global internet connectivity, and data centres have in common?

Congratulations to Prof Park Jihong – MLSP Technical Committee Member

by Dawn Chia

We are thrilled to announce that FCP Deputy Director, Prof Park Jihong, has been elected as one of the twelve new Technical Committee members for Machine Learning for Signal Processing (MLSP). This is a testament to Jihong’s dedication and significant contributions to the MLSP community. We are confident that Jihong will continue to bring valuable … Continue reading Congratulations to Prof Park Jihong – MLSP Technical Committee Member