The opportunity to do undergraduate research is one of the reasons Avi Devy Mohan decided to transfer to the University of Wisconsin-Eau Claire from a university in his native Malaysia.
Still, Blugold – now majoring in computer science and applied mathematics – didn’t expect his research to include collaborations with professors in three university departments as well as doctors in one of the world’s largest healthcare systems. respected in the world.
More surprisingly, his research ranges from biomedical technology to recreational mathematics, helping him understand the many ways researchers can influence everything from healthcare to wallpaper.
“Participating in the research has been a great learning experience,” says Mohan. “I learned so much about deep learning and how it can be used in different areas. “
Seize research opportunities
Mohan is part of a UW-Eau Claire computer research team working with physicians at the Mayo Clinic Health System, a project to create a deep learning model capable of detecting inferior vena cava filters ( IVC) in the analyzes.
Deep learning is a subset of machine learning that derives its operating logic from the functioning of the brain. Due to its high precision, deep learning finds application in things such as self-driving cars that process high-resolution images on the fly as well as in biomedical technology.
For the deep learning research project with the Mayo Clinic Health System, Mohan is helping develop ideas that can improve basic architecture. She also participates in literature reviews for future articles and presentations.
In addition, Mohan is part of a research team involving geography teachers and students, again using deep learning techniques but, in this project, focusing on techniques applicable to remote sensing. She helps develop different deep learning models and data processing for the models, as well as participating in tasks such as literature reviews.
“In both research projects, we try to apply deep learning techniques to problems in a way that has never been done before,” Mohan explains, explaining why and how the projects interest him and challenge her.
Mohan was also involved in a very different research project, which she describes as “great fun to work with” and which involves working with math teachers. This project, she said, fell into the realm of “recreational math” and involved creating knitted versions of different wallpaper group patterns.
“In a broader sense, these combined research projects opened my eyes to the many possibilities that can be realized through technology in different fields,” says Mohan.
An exceptional student, researcher
Mohan’s intelligence and curiosity make her a valuable student to work in her research lab, says Dr. Rahul Gomes, assistant professor of computer science and one of Mohan’s research mentors over the past year .
“She is very motivated and keen to learn more about machine learning, especially deep learning and how it can be used in image classification and segmentation,” Gomes said of her assistant. of research.
Recently, Mohan has started exploring unsupervised deep learning algorithms to reduce the need to use tagged images during training. This branch of the research will reduce the reliance of deep learning algorithms on labeled images and training masks, as creating them can be a tedious process, says Gomes.
“His research focuses on modifying the underlying framework of deep learning by using experimental layers of TensorFlow instead of using models readily available on the Internet,” Gomes explains. “For example, in our Mayo Clinic research project on CVI filter detection, Avi is exploring custom image filters in the deep learning model that could potentially improve CVI filters in CT scans based on their shape. and their reflectance. “
The main task of this filter is to break up blood clots and prevent them from getting to the heart and lungs. The research team’s goal is to automate the detection of these filters when a patient has a CT scan, Gomes explains, adding that they are using deep learning to achieve their goal.
Mohan’s contributions to this project and others are invaluable, Gomes says.
“She is an expert at performing parallel tasks at the Blugold Center for High-Performance Computing,” explains Gomes. “It’s great to have her as a research assistant. “
Find a potential career path
Mohan came to UW-Eau Claire knowing that she would pursue her passions for computer science and mathematics, two academic fields that have long interested her.
“I’ve been interested in computers since I was in college, especially the problem-solving aspects involved in programming,” says Mohan. “I decided to take an additional math major because I really enjoyed the math classes I was in, and they had great applications in some areas of computer science. “
It is through her research, however, that Mohan learns about biomedical technology and the increasingly important and critical role it plays in healthcare.
“Before, I had very little knowledge of the medical field and the technology used,” says Mohan, who will be graduating in May 2022. “Working with Mayo allowed me to acquire this knowledge through our collaboration. In fact, doing research has shown me that this is something I would love to do as a career. “
Mohan’s plans now include earning a PhD, which would set her on the path to a career in machine learning research.
The research she does as a Blugold will help her achieve these goals, says Mohan, noting that her research experience will strengthen her candidacy when she applies to graduate programs.
“More importantly, it taught me how to conduct research and be an independent learner,” Mohan says. “It will help me throughout my graduate studies and beyond.
“With technology being a constantly evolving field, I’ll be able to cope with change easily and stay relevant in my field, especially because research teaches you to think outside the box. Other little things I have learned, such as working with others, working outside my comfort zone, and dealing with “failures” will also help me in the long run. “
While her research experience has strengthened her understanding of deep learning and related concepts, it also helps her develop other skills that will help her flourish in her life as well as her career.
“On a more personal level, research has taught me that some things take time,” Mohan says. “As a perfectionist, I like being able to complete my task as soon as possible, and as perfectly as possible. This is not always the case in research. Sometimes it takes weeks or days to get to where you need to be. Sometimes you hunt for rabbit holes that end nowhere or methods that don’t work as well as you think. It’s still something I struggle with, but I’m getting better with time.
“And, of course, research is always a collaborative effort, so it has improved my communication skills and my ability to work with others. “