Vanessa Chen
Carnegie Mellon University, PA·Engineering·Early-career
Sensors are spreading into health monitors, vehicles and environmental networks, and many must run all the time. Sending all their raw data elsewhere for analysis costs power and time and opens the door to cyberattacks.
- Fields
Engineering
Computer Science
- Topics
low-power sensors
sensory interfaces
in-sensor computing
- Grants
- 1 known grant, through Sep 2027
What they work on
- Design bio-inspired, time-domain analog classifiers that exploit transistor mismatch and nonlinearity to perform energy-efficient hierarchical classification at low supply voltages within a sensor.
- Develop a computationally efficient multi-layer Bayesian neural network using Bernoulli variational distributions, with medical knowledge, sparsity and hardware constraints built into training, to adapt to real-time sensor signals.
- Build in-sensor encryption using a trainable pipeline chaotic system and physically unclonable device characteristics to scramble data into deterministic noise and resist side-channel attacks.
More about the research
Running machine learning and strong encryption inside a tiny sensor normally takes too much energy. This project asks how to build sensors that analyze and protect their own data while using very little power.
Why it matters
Continuous, secure monitoring could support health, transportation and environmental applications. Sensors that classify data on the spot and encrypt it with minimal energy could make always-on devices faster and more private. Such sensors could also be harder to attack and would need to send less data wirelessly. This may help wearable medical monitors and other edge devices run longer on limited power.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Aatmesh Shrivastava
Northeastern University, MA·Engineering·Early-career
Develop a distributed beamforming technique that combines RF energy from multiple Wi-Fi or Bluetooth-type transmitters and directs it to a remote IoT receiver, using closed-loop optimization between transmitters and receiver.
Himanshu Thapliyal
Southern Methodist University, TX·Engineering·Early-career
Investigate how secret information leaks through the power traces of energy recovery circuits, and propose design methods that reduce leakage against differential power analysis attacks.
Weidong Cao
George Washington University, DC·Engineering
Build AnalogEDA-Hub, an open-source platform with multi-modal datasets, learning-based tools and standard design environments, so researchers can benchmark AI methods for analog circuit design in a reproducible way.
The school
Carnegie Mellon University: 28 labs on PI Pages, $505M a year on research, 346 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.