Prof. Yang CHAI, the Management Committee member of RI-IWEAR, Associate Dean of Faculty of Science, has been bestowed as the top ten winners of the prestigious Falling Walls Science Breakthroughs Award. This is a recognition of his groundbreaking research on sensory artificial intelligence (AI), which has paved the way for more energy-efficient, low-latency, and memory-optimized systems, enhancing for diverse applications such as mobile devices, IoT sensors and edge computing.
Prof. CHAI has developed novel hardware architectures and optimization techniques, leading the transformation applications in smart cities, autonomous vehicles, and industrial automation. His research has overcome crucial barriers in power consumption, latency and memory within sensory AI systems, demonstrating their potential for application. Furthermore, the in-sensor computing strategy has sparked progress in improving decision-making and situational awareness, strengthening privacy and security, and transforming intelligent automation.
The Falling Walls Science Breakthroughs of the Year Award, initiated by the Berlin-based Falling Walls Foundation, to nominate the latest breakthroughs and outstanding science projects worldwide. This year, the high-level jury comprising globally recognized experts in the fields reviewed over 1,000 entries from 52 countries and selected 10 excellent winners in the Engineering & Technology category, who were shortlisted for the Science Breakthrough of the Year 2024 title.
Prof. CHAI said, “The proliferation of data from ubiquitously distributed sensors leads to massive increases in sensory terminals. It is crucial to partially shift computation tasks to the sensory terminals. This transition substantially compresses the collected information and extracts key information, especially for sensor-rich platforms.”
Prof. CHAI’s research clearly defines near-sensor concepts and in-sensor computing paradigms based on the physical distance between sensory and computing units. This classification further divides functions into low-level and high-level processing. His study explores the implementation of near-/in-sensor computing for different physical sensing systems and provide possible solutions for integrating sensing and processing units through advanced manufacturing technologies.
While Prof. CHAI and his team focus on advancing computational hardware for sensory AI systems, the extraordinary capabilities of natural bioinspired sensory systems are a vital research inspiration. By emulating human visual adaptability, which allows accurate object identification under various lighting conditions, the new bioinspired sensors developed by Prof. CHAI’s team offer a solution by directly adapting to different light intensities. The sensors reduce hardware complexity, boost image contrast in varied lighting conditions, thus improving machine vision systems for visual analysis and identification tasks. The work on bioinspired in-sensor vision adaptation was recognized as one of the “Top 10 Hong Kong Innovation Technology News in 2022”.
Inspired by flying insects’ high flicker function frequency (FFF), Prof. CHAI’s research has developed optoelectronic graded neurons that efficiently encode temporal information at sensory terminals, reducing the transfer of abundant vision data of fusing spatiotemporal (spatial and temporal) information in a computation unit. With minimal hardware resource, promising potential applications in autonomous vehicles and surveillance systems.
Prof. CHAI has been invited to express views on the development of in-sensor computing in Nature Podcast. He also demonstrated the latest results to Chief Executive during her visit at PolyU in 2021. The work on in-sensor motion perception has been recognized as one of China Chip10 Science in 2023. This in-sensor computing paradigm is also highlighted in US Semiconductor Research Corporation’s Decadal Plan. These outstanding findings have been published in high-impact journals such as Nature Electronics, Nature Nanotechnology, and have been highlighted in Nature, IEEE Spectrum, and more and are highly cited by research teams worldwide.
Prof. CHAI envisions, “My long-term goal is to develop cutting-edge microelectronic and nano-electronic devices with new functionalities and unprecedented performance. Specifically, we intend to create imaging technology capable of perceiving three-dimensional (3D) depth, four-dimensional (4D) spatial-temporal and multiple spectral (beyond visible light) information. To achieve this, a bioinspired mechanism will be utilized to reduce power consumption and latency.”
