Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Autonomous Control And Signal Acquisition System, Rion Cadell Krampe
Autonomous Control And Signal Acquisition System, Rion Cadell Krampe
Honors College Theses
Our goal is to continue a previous teams project to build a NDE autonomous control and signal acquisition system that is more precise, more customizable with both code and mechanical parts, and cheaper than a similar system bought by the school. This goal has two stages to it. First, to repair the system from considerable damage it received during transportation. Secondly, to continue designing and developing the system to make considerable progress towards the goal of a fully functional NDE system. Along with making progress we must consider the team after us and create an easy stepping off point for …
Automated Bottling Station - Packaging System, Lauren Nicole Zinzilieta
Automated Bottling Station - Packaging System, Lauren Nicole Zinzilieta
Honors College Theses
This report focuses on the packaging system used at the end of the FESTO bottling station that is located in EP 2355. The system will be made up of an x-y 300 mm x 300 mm gantry system, an Arduino, two micro-stepping stepper drivers, and two 152.4 mm (6 in) single acting cylinders with a 3D printed bracket attached to both. The gantry system will be located at the end of the conveyor belt and will be programmed to pick up three bottles at a time and then will move a specified number of steps in both the x and …
Pneumonia Radiograph Diagnosis Utilizing Deep Learning Network, Wesley O'Quinn
Pneumonia Radiograph Diagnosis Utilizing Deep Learning Network, Wesley O'Quinn
Honors College Theses
Pneumonia is a life-threatening respiratory disease caused by bacterial infection. The goal of this study is to develop an algorithm using Convolutional Neural Networks (CNNs) to detect visual signals for pneumonia in medical images and make a diagnosis. Although Pneumonia is prevalent, detection and diagnosis are challenging. The deep learning network AlexNet was utilized through transfer learning. A dataset consisting of 11,318 images was used for training, and a preliminary diagnosis accuracy of 72% was achieved.