Chelsea Parlett-Pelleriti

Papers

Total Citations

H-Index

About

Chelsea Parlett-Pelleriti is a rising researcher at the intersection of embedded systems and machine learning, with a core focus on enabling intelligent, resource-constrained devices. Her most cited work, "Towards QoS-Based Embedded Machine Learning" (2022, 4 citations), tackles the critical challenge of deploying ML models on embedded platforms—from computer vision and speech recognition to healthcare—where performance must be balanced against strict quality-of-service (QoS) constraints. This contribution is particularly timely as machine learning proliferates through edge devices, and Parlett-Pelleriti’s research provides a framework for ensuring reliability and efficiency in real-time applications. By addressing the trade-offs between model accuracy, latency, and power consumption, she is helping to bridge the gap between cutting-edge AI and practical, deployable systems. Her work signals a growing emphasis on making machine learning not just powerful, but also practical and trustworthy for embedded environments. As the field moves toward ubiquitous AI, Parlett-Pelleriti’s contributions are foundational for students and researchers interested in the future of smart, efficient, and QoS-aware embedded intelligence.