Robert G. Pettit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Robert G. Pettit has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Abhishek Dey
Department of Computer Science George Mason University Fairfax USA
1 shared publication - Gaurav Singh
University University of Maryland ARLIS
1 shared publication J. S. Fant
The Aerospace Corporation
1 shared publication- Julie Street Fant
The Aerospace Corporation
1 shared publication - Saurabh Srivastava
George Mason University Fairfax VA
1 shared publication
Latest Publications
- Open Access
Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded systems. Evaluating key metrics such as inference latency, CPU utilization, memory efficiency, and prediction stability, the framework provides insights into computational trade-offs and platform-specific optimizations. We benchmark three representative TinyML models -- Gesture Classification, Keyword Spotting, and MobileNet V2 -- on two widely adopted platforms, BeagleBone AI64 and Raspberry Pi 4, using real-world datasets. Results reveal critical trade-offs: the BeagleBone AI64 demonstrates consistent inference latency for AI-specific tasks, while the Raspberry Pi 4 excels in resource efficiency and cost-effectiveness. These findings offer actionable guidance for optimizing TinyML deployments, bridging the gap between theoretical advancements and practical applications in embedded systems.
Open AccessReal-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded systems. Evaluating key metrics such as inference latency, CPU utilization, memory efficiency, and prediction stability, the framework provides insights into computational trade-offs and platform-specific optimizations. We benchmark three representative TinyML models -- Gesture Classification, Keyword Spotting, and MobileNet V2 -- on two widely adopted platforms, BeagleBone AI64 and Raspberry Pi 4, using real-world datasets. Results reveal critical trade-offs: the BeagleBone AI64 demonstrates consistent inference latency for AI-specific tasks, while the Raspberry Pi 4 excels in resource efficiency and cost-effectiveness. These findings offer actionable guidance for optimizing TinyML deployments, bridging the gap between theoretical advancements and practical applications in embedded systems.
- 8 July 2023
- Published by Springer Nature
- p. 861-893
MBSE Mission Assurance
- 29 May 2022
- Published by Springer Nature
- p. 1-33
MBSE Mission Assurance