Knowledge building

Wright State computer scientist Cogan Shimizu has a key role in designing a federally funded Open Knowledge Network

Cogan Shimizu, assistant professor of computer science at Wright State, and four collaborators received a $1.499 million grant from the National Science Foundation to create educational materials and tools to access the Prototype Open Knowledge Network. (Photo by Erin Pence)

Cogan Shimizu, Ph.D., an assistant professor of computer science at Wright State University, will play a key role in providing access to a new network of data designed to help solve a broad set of societal and economic challenges.

Shimizu and four collaborators received a $1.499 million grant from the National Science Foundation to create the Education Gateway, a set of educational materials and tools for people and organizations interested in engaging with the Prototype Open Knowledge Network.

The Education Gateway — or EduGate — will serve as the entry point to the network, a publicly accessible, interconnected set of data repositories and knowledge graphs that will enable data-driven, artificial intelligence-based solutions.

“We are the first point of contact for understanding why anyone should ever use the Open Knowledge Network, how to use it and in what ways can you use it,” Shimizu said. “We’re the entry point or the gateway that shows this is how you use the tools, these are the tools you can expect, the concepts you will need to know in order to use this.”

Shimizu is collaborating with four co-principal investigators: Pascal Hitzler, Ph.D., the Lloyd T. Smith Creativity in Engineering Chair in the Department of Computer Science at Kansas State University; Florence Hudson, executive director of the Northeast Big Data Innovation Hub at Columbia University; Hande McGinty, Ph.D., assistant professor of computer science at Kansas State; and Francois Scharffe, co-founder of the Knowledge Graph Conference.

The Prototype Open Knowledge Network (Proto-OKN) is a joint project of the National Science Foundation, NASA, the National Institutes of Health, the National Institute of Justice, the National Oceanic and Atmospheric Administration and the U.S. Geological Survey.

Fifteen use cases were selected to be part of the Proto-OKN, which will feature knowledge graphs, or nodes, that provide data-centric solutions to various societal challenges. These challenges include equitable water distribution, social care, justice, carbon capture, the environment, health communications, supply chains, wildlife management, agriculture and homelessness.

“The goal is to bring together different researchers in their important domain problems and connect together their data and their results in a human-meaningful way,” Shimizu said.

The network will connect the projects and ensure they are understandable and accessible to other researchers, academics, teachers, students, industry and government leaders and members of the public.

Shimizu said the network can help bridge concepts and fields of study that over time have unintentionally become siloed. Creating an open and transparent network can help introduce researchers to tools they may not be aware of and ensure their projects are aligned.

He said that some of the projects and technologies in the network are important and powerful but also niche and not well-known. The EduGate will introduce users to these niche technologies.

“Making sure we have a common vocabulary and a common way of exchanging information is extremely important,” Shimizu said. “What that does is gives us a mechanism by which we can have extremely rich and extremely interconnected learning materials.”

The EduGate will serve as the portal through which users will learn how to use and access the Proto-OKN and, eventually, the Open Knowledge Network. The platform will feature tutorials that Shimizu and his colleagues will create to help users navigate the network.

“We want to provide a seamless educational onboarding to people who then come to learn about the individual projects,” Shimizu said.

Portions of the Prototype Open Knowledge Network will initially be available publicly in 2024 when researchers will begin collecting feedback from users. The network will be fully operational in 2026.

Shimizu was drawn to the Open Knowledge Network project because it involves one of his research and teaching interests — knowledge graphs. A knowledge graph represents a network of real-world objects, events, situations or concepts and illustrates the relationships between them.

“Knowledge graphs are a way to connect all of that together in a way that’s human meaningful,” Shimizu said.

Shimizu’s doctoral dissertation, which he completed at Kansas State, focused on designing an effective and easily teachable way of creating knowledge graphs.

“We were able to come up with a core methodology and some tools to support it, and that showed that our approach was superior to other approaches out there,” he said.

After receiving his Ph.D. in computer science, he remained at Kansas State as a postdoctoral researcher working on a project called KnowhereGraph. A predecessor to the Open Knowledge Network, KnowhereGraph is believed to be the largest geospatial knowledge graph in the world and is designed to help solve many critical problems that rely on geospatial data.

He also participated in the Innovation Sprint conducted by the National Science Foundation and the White House Office of Science and Technology Policy in 2022 that helped draw the roadmap for the Prototype Open Knowledge Network.

Shimizu considers himself a generalist interested in a variety of topics, and knowledge graphs are a way of enabling that.

“By doing knowledge engineering with knowledge graphs,” he said, “I can interact with every other field of science because everybody has a data problem, everybody needs to manage their data to understand what sort of data they have, and that’s what I help with.”

When Shimizu joined the faculty in the Wright State College of Engineering and Computer Science in 2022, it was a homecoming for him.

He received his bachelor’s degree and master’s degree in computer science from Wright State. As a graduate student at Wright State, he served as a fellow in what was previously known as the Dayton Area Graduate Studies Institute.

Comments are closed.