Three undergraduate students from the Department of Electrical and Computer Engineering presented their work at last week’s JHU DREAMS 2021 Virtual Presentation Event. Formerly Undergraduate Research Day, this event is now known as “Day of Undergraduate Research in Engineering, the Arts & Humanities, Medicine and the Sciences“.
See below to find out more about the three ECE projects that were presented.
Title: Automated neuron segmentation and connectivity analysis for investigating connectome-constrained subneuron computation
Abstract: In neuroscience and deep learning, the fundamental computational unit in the brain is often analyzed at the level of the individual neuron. However, the firing of the neuron is determined in part by its geometry and how current flows through individual branches. Recent synapse-level connectome data holds promise for investigating the principles of subneuron computation in more detail at the level of an entire neural circuit. Simulating the activation of each neuron using an entire skeleton with tens of thousands of segments each is computationally burdensome at the network level and yields challenges for interpretability of information processing at the subneuron level. We have developed methodologies to automate segmenting neuron skeletons into several functional compartments to simulate a network at the subneuron level, while still being computationally efficient. We demonstrate the neuron segmentation and subneuron connectivity analysis in the Navigation center of the fruit fly, Drosophila melanogaster.
Abstract: Knolist is a research tool designed to simplify the process of gathering information, making it easier to be organized and visualize that information, and improving our users’ ability to generate new and insightful ideas. With Knolist, you can track your research progress and view all your gathered information non-linearly. This will help you to stay organized and have greater insights into your research projects in an easy and efficient way. As you do online research, you can use our chrome extension to add pages, highlights, and notes directly to your project. Then, in your project, you can move items around in 2D space, even making clusters and sub-clusters to give your project the structure it needs. You can also use our search feature to quickly find anything you need in your project. Now that you can truly organize your information the way you want it to be structured, it’ll be easier to see connections and have new ideas. We also help actively inspire new ideas with our minigame feature, which uses the information you’ve inputted as an object in small minigames like find the odd-one-out or say what these items have in common. Finally, Knolist works for group projects as well by allowing you to easily share your project with your group members so that everyone’s research is in one place.
Why do you pursue this research?
VL: I’ve been working on Knolist with some friends for a little over a year now. This project started in the Computer Science Innovation & Entrepreneurship class, but we decided to keep working on it after the class was over because we wanted to try building a product from scratch and creating a startup around it, and we believed that we had a good idea for a product. I’m very passionate about entrepreneurship and product development, so this experience has been great; I’ve learned things that I probably wouldn’t have learned in class, things that can only come from practice.
Our app can be found by clicking here.
Title: Assessing the Accuracy of Smart Stents for Monitoring Coronary Artery Restenosis
Abstract: Coronary heart disease, one of the leading causes of death globally, is characterized by the buildup of plaque in the coronary arteries. A common treatment for this is stent placement, however the plaque can return, or form restenosis, on the stent. Thus, researchers developed smart stents, or stents that can measure the pressure inside the coronary artery and inform patients as well as doctors of restenosis. However, measurement and accuracy of in-stent pressure were documented in previous literature as a major challenge. Therefore, this study was set to develop a test for the accuracy of smart stents, investigate the effects of sensor redundancy, and develop a novel method for measuring in-stent restenosis. Based upon Clarke’s error grid analysis, a method for testing smart stent accuracy was developed. After simulating coronary artery in-stent restenosis and testing the smart stent models, the accuracy of in-stent restenosis measurement was found to decrease with plaque buildup as well as heart rate and increase with the number of sensors. Thus, a novel method for measuring in-stent restenosis for coronary heart disease patients was developed and validated successfully.
Why did you pursue this research?
EL: I originally pursued this research due to my interest in helping treat as large a problem as possible. Thus, I found heart disease, the number one cause of death, and looked for ways I could help advance developing treatments for the disease. I enjoyed this project because not only was I on the forefront of medical research, but also, I believe the methods I used could be applied to pretty much any sensor an electrical engineer can build.