Education & Workforce Development Theme 7

EDGE AI NSF Project announces Seed Awards for Researchers at Junior Level (SARJ)

The award phase of Seed Awards for Researchers at Junior Level (SARJ) has been completed under Theme 7, Education and Workforce Development.

A total of 17 research proposals were received for award consideration by the November 1, 2023 deadline. Dr. Woods established a review process where each proposal was evaluated anonymously by three faculty experts. 14 faculty members across four Universities participated in the reviews. Based on the faculty feedback and in-person discussions, four research proposals were selected for funding by the EDGE AI NSF program. Each award is for $15k and will run for one year beginning February 1, 2024.

The second phase of the SARJ program now begins with the funded research projects in Year 2 of the EDGE AI NSF program. These one-year projects will report back monthly progress through the EDGE AI Faculty project team meetings.

The four proposals awarded funding are:

Dr. George Clark

Assistant Professor: University of South Alabama, Department of Computer Science

Title: An Investigation of Cyberattacks on Edge AI Components of Self Driving Vehicles

The security of Edge AI devices is often overlooked and this can be a concern, as these devices often are used to perform critical and sometimes dangerous tasks such as autonomous driving. This project aims to develop a small autonomous vehicle with a machine learning based driving architecture for cybersecurity research. The vehicle and its machine learning architecture will first be implemented in a simulation environment and then transferred to a physical vehicle in the form of a small commercially available robot. The robot will serve as an Edge AI test platform for examining cybersecurity attacks and possible defenses across the vehicle’s driving architecture.

Dr. InBae Jeong

Assistant Professor: North Dakota State University, Department of Mechanical Engineering.

Title: Development of Multi UAV System for Context Awareness and Seamless Operation

In this research, a distributed UAV coordination framework to ensure the continuous and seamless operation of multiple UAVs will be developed. These UAVs will be equipped with edge AI computing devices connected through a wireless mesh network. The proposed system will enable UAVs to autonomously recharge their batteries when depleted and dynamically adjust their roles to minimize task disruptions.

Dr. Sicong Shao

Assistant Professor: University of North Dakota, School of Electrical Engineering and Computer Science

Title: TinyML ADD: Tiny Machine Learning for Adaptive Anomaly Detection

Tiny machine learning (TinyML)-based anomaly detection, bringing anomaly detection, edge computing, and AI together to power-constrained edge devices, has become an emerging research topic. However, it may become suboptimal, unreliable, or even catastrophically fail at worst when concept drift affects the data generation process. This project aims to develop a TinyML-based framework that can effectively deploy robust anomaly detection on edge devices and enable edge AI to perform on-device adaptive learning to deal with non-stationary environments.

Dr. Jielun Zhang

Assistant Professor: University of North Dakota, School of Electrical Engineering and Computer Science

Title: Edge AI Driven Data Synthesis with Configurable Privacy and Usability in Edge AI

This project focuses on the crucial role of Edge AI in enabling AI-based services with reduced latency and scalability in modern networks and connected infrastructures. It highlights the challenges of acquiring fresh and comprehensive datasets while protecting privacy and the risk of personal information leakage