Brief CV – Qingxue Zhang

15-year Footprints

Thanks for the great journey at Harvard that provides me opportunities to work with and learn from world-leading experts.

I am grateful for the NSF CAREER Award that strongly supports the UbiEi Lab to advance our research. To make AI more effective, efficient, and holographic, we innovate Intelligent Analytics & Theories, Computing On-the-fly & Mobile-Cloud Platform, and Wearable Computers, respectively, thereby advancing Full-stack Wearable Medical Big Data Science.

I am thankful for the opportunity to launch a startup now, and I have been honored to commercialize the Application-specific Big Data Computers serving 1 billion people globally when in industry.

Many appreciations to all current and upcoming sponsors, mentors, collaborators, and colleagues for the invaluable help, supports, and opportunities!!

Professional Preparation


With a memorable six-year journey in the world-leading company, and opportunities to lead excellent teams to R&D multiple commercial products used worldwide by about a billion people, I made a decision to further develop my career in academia.

What attracted me most was – the field of pervasive intelligence and big data was emerging but still in its infancy, which ignited my passion to think about new possibilities and ways to convert new ideas to transformative technologies.


It was a great journey at Harvard and Mass General Hospital from 2017 to 18, to learn from Dr. Anthony Rosenzweig (Chief, Cardiology Division @ MGH/Harvard Medical School), Dr. Antonis Armoundas (Harvard/MIT), and CVRC, among many.

It was really interesting to combine my research and industrial experience to advance medical big data science. By leveraging AI, Mobile Health, and Wearable Sensing, multiple system prototypes have been researched, designed, and developed for precision medicine big data purposes.


Working with Dr. Dian Zhou (NSF Presidential Award; Panelist, World Economy Forum in Davos; IEEE CAS Society Darlington Award) at UT Dallas from 2013 to 17, I had researched, built and validated the world first AI-enabled ear-worn blood pressure monitor for precision hypertension big data, empowered by both AI Learning/Computing and Wearable Sensing (Featured Article on IEEE Access Journal and patented), among many.


With great curiosity on how and why things work, during my MS(2004-2007)/BS (2000-2004), I had not only taken diverse courses in CS, CE, EE, and others but also done my thesis, under the supervision of Dr. Hongcai Wu (Vice President, Xi’an Jiaotong-Liverpool University; Dean, School of Electronics and Information Engineering, Xi’an Jiaotong University).

Director, UbiEi Lab

AI Capability Boosting <= Brain-inspired Spiking Neural Network and Deep Learning: Neural Dynamics and Learning Algorithms

Learning Capability, as indicated by how effective the brain abstracts and conceptualizes knowledge, is key to measure how intelligent Deep Learning is. Through diving into brain-inspired and neural science-driven learning theories and principles, my lab tackles challenges in the Spiking Neural Network (SNN) learning algorithms, which is expected to be one of the paradigms that bring new possibilities towards human-level intelligence.

One demo algorithm selected below is the ‘SpikeBASE’ we proposed and developed, which, through backpropagating the error through the neural synapses and adapting neural synaptic responses, enables globally, supervisedly, and comprehensively learning SNN. We have demonstrated that SpikeBASE can, not only learn the challenging scarce data learning task (News: eye-movement decoding for assisted living, mental monitoring and human-computer interaction applications, among many), but also mine spatiotemporal neural spiking patterns that non-spiking networks usually could not effectively leverage.

AI Productivity Boosting <= Brain-inspired Knowledge Distillation: Pervasive Inference and Edge Efficiency

Learning Productivity, as indicated by how efficiently the brain processes information, is crucial to measure how concise Deep Learning is. Google AlphoGo Zero takes 10 trillion operations/s in contract to 50/s on humans, indicating the efficiency disparity, and inspiring our lab to innovate concise learning, pertinence learning, and real-time edge-deployable AI.

A demo system selected below is the edge-deployable efficient ‘RP-KDL’ algorithm for precision cardiac health, which, enabled by Robust-Preservation Knowledge Distillation Learning, yields a lightweight model for ECG analysis with 45x parameter reduction. The ultra-high efficiency is achieved by distilling the knowledge of a heavy teacher model’s soft target distribution to a student model, while enhancing its robustness through learning under adversarial perturbation.

AI Perception Boosting <= Brain-inspired Holographic Sensing: Biomedical Dynamics and Ambient Reality

Perceptual learning, as indicated by how comprehensively the brain perceives the world, is essential to reflect the extent to which the system can sense necessary, or even holographic information for deep learning. To achieve novel perception systems, my lab systematically builds sensors, sensor boards, embedded systems, and wearable/IoT monitors.

A demo perception system selected below is ‘FlexBio’, which is a flexible, multi-channel sensor board for bio-potential sensing purposes. This small flex patch we made, can provide the comprehensive spatial perception of target biomedical dynamics, or even holographic dynamics after easily boosting # channels. Applications we are investigating include but are not limited to, perceiving dynamics from brain, heart, and muscular subsystems, for big data deep learning.



I am very thankful for and enjoy the opportunity to transform research into products. I am now launching a startup on mobile health big data applications, the foundation of which is laid on validated AI Algorithms, Edge Deployment, and Health Sensor technologies.

Same time, we are working on the FDA process to meet regulations and safety requirements. With strong support from Digital Health Center at FDA, we are confidently advancing the process forward.

Also, we have patents pending, and with continued transformative research, new patents are under preparation and/or to be filed.

R&Ded Big Data Computers

I was honored in the industry (2007-2013) to work with hundreds of talents, lead excellent teams, spend several years, R&Ded multiple versions, and finally commercialize an application-specific big data computer for the world’s first Super-Big-Data system. It is one of the most successful and impressive products, used by about 1 billion people worldwide, among multiple products.

With this system, the global market share of the company boosted to top 1 and reached 39% in just 2 years (2013), followed by hitting the top 1 market share of the whole equipment market in another half a year.

The opportunity to work at a world-leading ICT company rewarded me with systematic commercialization experience, including global market analysis, system solution determination, algorithm/hardware/software co-design, customer relationship management, project management, and team management.

I am honored to receive Gold Medal Team Award, Outstanding Individual Contributor Award, Three Excellent Employee Awards, and Team Collaboration Award.


I, as a lead system architect in addition to the team and project management roles, also have seven international patents commercialized in the industry. Thanks to the co-inventors in my team and collaborators in international research centers in US and Europe.

Sponsors, Collaborators & Services

I am very grateful for the valuable support from sponsors. I am very excited to receive the NSF Career Award and I am committed to leading UbiEi to make AI more effective, efficient, and holographic.

I have also appreciated the sponsorships from and/or collaborations with Google, Intel, Amazon, American Heart Association, Harvard, MIT, WUSTL, UNIMI, Purdue, IU, among many.

Last but not least, I thank for the opportunities to serve the communities as NSF CISE/ENG/Initiative/GRFP panelists, NIH SBIR/STTR Study Section Panelist, NIST SBIR/STTR panelist, IEEE DACI2021 Workshop Chair, IEEE paiIoT2021 Workshop Chair, IEEE AEs, IEEE Deep Learning Technical Committee, IEEE ICCE Track Chair, and so on.

Selected are listed below.

Again, thanks for all these and upcoming valuable supports and opportunities!!