Cutting-edge intelligence | UDaily


Photo by Evan Krape | Artwork by Joy Smoker

Lena Mashayekhy, assistant professor of computer science at the University of Delaware College of Engineeringtakes a proactive approach to how artificial intelligence and analytics can be used to quickly and securely process large amounts of data across devices as we begin to interact with more and more types of technology in our daily life.

The so-called “Internet of Things”, devices that help our world become more connected – smartwatches and other wearables, drones and autonomous vehicles, for example – is growing and there is a need to anticipate the future challenges of mobility to make decisions in real time – manufacturing.

“In today’s world, we are moving towards a lot of data-driven business intelligence applications,” Mashayekhy said. “In recent years, devices that are at the edge of the Internet generate a lot of data, such as images and videos, and need to make decisions in real time. The significant increase in the size of the Internet of Things network and the volume of data opens interesting opportunities for analyzing data and learning how to extract valuable information to support decision making and derive discoveries and scientific innovations.

His forward thinking and research earned Mashayekhy recognition from the National Science Foundation (NSF) in 2022 with a Faculty Early Career Development Program (CAREER) award, one of the most prestigious awards a young faculty member can receive.

The award includes funding of $671,835 over five years beginning in May 2022 to support this project.

“Just as desktop computers and telephones have transformed our lives over the past few decades, countless small computing devices in almost any object imaginable will likely aid our future existence,” said Rudi Eigenmann, acting president of the Department of Computing and Information Science. “Professor Mashayekhy’s research promises to become a key enabler of this development, enabling us to move – when we walk, drive a car or even fly a plane.”

Think of how a self-driving car should detect someone crossing the street or how a search drone should communicate that it has found a missing person – these decisions need to be made immediately, within seconds. It requires significant processing power to capture an immense amount of data, analyze it, and turn all of that information into a real game-changing answer.

While some control operations, such as maneuvers, route planning and collision avoidance of autonomous vehicles, for example, must be carried out on the device itself, other urgent analyzes require computer processing. powerful. For example, surveillance drones with applications in search and rescue, defense, and smart cities require roaming large areas and analyzing high-definition imagery and video to quickly identify their targets (such as an injured person or a missing child). These devices must also be able to assess the condition of their target for important information such as signs of cardiac events, risk of heat-related injury, and threats of airborne contamination.

“This type of multi-access edge computing allows Internet of Things devices to offload their delay-sensitive resource-intensive tasks. As we or these devices move, our connection to these computing resources will change. , but the devices should experience no downtime,” she said. “I plan to explore how to proactively manage mobility challenges and deliver stable IT services.”

The problem here is much more impactful than just fixing loading lag while trying to upload photos or videos to social media.

“Nowadays and in the years to come, everything will be connected,” said Chien-Chung Shen, a professor in the Department of Computing and Information Science who chaired the recruitment committee when Mashayekhy was hired. . “There is a lot of treatment to be done. You want to minimize delay, even though all of these decisions are subject to real-time constraints. All of this requires very advanced resource planning.

The Internet of Things is leading us towards a much more digitally dependent future. By using multi-access edge computing, which allows necessary data to be processed closer to user devices, Mashayekhy and his team of researchers hope to improve the quality of connections and computing services in the rapidly changing mobile world. in which we live today.

“A lot of these problems have been formulated as optimization problems,” Shen said, noting that Mashayekhy is a highly respected expert in this field of study. “The impact will provide critical information and solutions that will help carriers – Verizon, for example – deploy their edge devices.”

The proposed project focuses on mobility challenges from three different angles. Mashayekhy and his lab will first assess how the movement of users creates challenges and how these issues could be addressed.

Next, they will tackle the challenges caused by infrastructure mobility, where an edge device would be mobile instead of stationary. For example, a larger drone could provide the localized computing power needed by research drones while they do their important work.

Finally, the project will explore user incentive programs that could help balance the load of an entire digital system. For example, when electricity companies advise people to “beat the peak” and reduce high energy consumption during the hottest parts of the day in summer, there are also benefits to spreading the demand from digital users. This could apply to offering incentives to users of self-driving vehicles to take a different route than the most popular busiest, for example.

“In this project, we will study all aspects of mobility in multi-access edge computing,” she said. “This project also examines how we can generate insights from deep learning, game theory and physics, such as Newton’s center of gravity and law of universal gravitation, rules that impact about maintaining balance and adjusting cutting-edge drone-based devices in response to a dynamic and uncertain Internet of Things device mobility.

The NSF CAREER awards combine research and education, and Mashayekhy’s project will recruit two doctoral students to help with the research. She said there will also be opportunities for undergraduate students to participate in research during the five-year project.

The project will also support an integrated educational program and outreach activities for K-12 students, their families, and the wider community to broaden exposure to this research while enabling more innovative applications that are not yet possible today.

“This recognition by the NSF is recognition not only of her strong and exciting research program, but also of her exceptional record as a strong and dedicated teacher and mentor who can pass on the enthusiasm of this research to others” , said Kathleen McCoy, professor. and former chair of the Department of Computing and Information Science. “His research fills a critical area of ​​computer systems – a very important research focus in the department – ​​and it is also important to many interdisciplinary research efforts within the College of Engineering and the University of Delaware, such than the computational effort required for Autonomous Vehicles.”


Comments are closed.