Peiyi Zhao

Papers

Total Citations

H-Index

About

Peiyi Zhao is a researcher at the forefront of embedded machine learning, with a focus on enabling intelligent, resource-constrained systems. Their most cited work, "Towards QoS-Based Embedded Machine Learning" (2022), addresses a critical challenge: deploying sophisticated machine learning models—spanning computer vision, speech recognition, and healthcare—onto embedded platforms without sacrificing performance. Zhao’s key contribution lies in proposing a quality-of-service (QoS) framework that balances computational efficiency with model accuracy, ensuring that embedded devices can run real-time AI applications reliably. This work has garnered attention for its practical approach to bridging the gap between advanced ML algorithms and hardware limitations. With 4 citations, Zhao’s research is gaining traction among engineers and academics working on edge computing and IoT. By tackling the trade-offs between power, latency, and model complexity, Peiyi Zhao is helping to shape a future where intelligent, autonomous devices are both accessible and robust—a vital step for next-generation smart systems.