Paleontologists enhance human understanding of the history of life on Earth through the study of fossils, identifying them by examining features such as geometry. However, Southern Adventist University is exploring a faster and more effective method for classifying these ancient remnants.

The university’s Biology and Allied Health Department, together with the School of Computing, has initiated a project that utilizes artificial intelligence (AI) to automatically identify dinosaur teeth. This project employs deep learning, a form of AI that uses artificial neural networks to learn from data and solve complex problems.

The idea for the project was developed by Dr. Harvey Alférez, a professor and director of the Center for Innovation and Research in Computing (CIRC), and Dr. Keith Snyder, chair of the Biology and Allied Health Department, during Fall 2022. They aimed to explore the possibility of using deep learning technology to classify images of dinosaur teeth. The approach involved inputting images into a model for training, enabling it to classify and group the images based on the tooth types recognized.

Jacob Bahn, a graduate student seeking a master’s thesis project, was invited by Alférez to join this endeavor in October 2022. “I was super-intrigued by the project, even though I had never previously worked with deep learning technology,” Bahn said. He worked with a dataset of 487 images from Snyder’s collection of microfossilized Pectinodon bakkeri teeth, which were collected during dinosaur digs in Wyoming.

Bahn organized numerical values based on specific features of the dinosaur teeth into a file, subsequently applying machine learning algorithms to create three distinct groupings. These groupings were then used to train the deep learning model to automatically classify the images. Eighty percent of Snyder’s images were utilized for training, while the remaining 20 percent were employed for validation after a cleaning process.

The deep learning model was trained on a new GPU server in the School of Computing, which was purchased with funds from a research grant provided by the Faith and Science Council of the General Conference of Seventh-day Adventists, along with donations from Southern’s 2022 Giving Day.

Early results from the validation phase are encouraging, showing 71% accuracy, 71% precision, 70.5% recall, and a 70.5% F1-score, which reflect the model's reliability in this context. Alférez, Bahn, and Snyder are currently working to refine Bahn’s original thesis with the goal of having it peer-reviewed and published in an academic journal.

Bahn, who now works as a software engineer for the Tennessee Valley Authority, expressed enthusiasm about the project: “It’s a fun talking point in my career. I’ve always been a bit of a geek when it comes to technology, and why not throw dinosaurs into the mix?”

Both Alférez and Snyder emphasized that this project represents a significant collaboration between the two departments at Southern. “The nature of this project requires lots of data, which is something that the biology team can provide,” Alférez noted. “Then, processing that data is our side—the computing side—of things.”

Snyder added, “For a project like this, it is essential to have the expertise in both fields to reach the goal.”

According to Alférez and Snyder, this collaborative initiative has opened the door for the School of Computing and the Biology and Allied Health Department to pursue additional projects aimed at providing more learning opportunities for students. “We live in the era of AI,” Alférez stated. “Through these projects, students are able to generate new knowledge and gain the necessary preparation for jobs in which AI is highly sought after.”

The original article was published on the Southern University website.