- Browse Repository
- School of Engineering
- Machine learning (x)
- Department of Computer & Data Sciences
Department of Computer & Data Sciences
Show more3D Printing, or additive manufacturing, is a novel approach to manufacturing simple and complex structures. 3D printing uses digital models and g-code to build these parts layer by layer. This method can allow for more freedom of part design with regard to complexity of shape, and can reduce material waste compared to other manufacturing methods. This project explores the 3D printability of common caulking materials, cements, adhesives, and other pastes. These materials are low-cost and present high printability. Experiments are underway to determine the thermomechanical properties of these 3D printed materials and the effects of nanomaterial additives in low loading (1% by weight or less) in these materials. The additives being tested are carbon nanotubes, graphene oxide, and silica nanoparticles. They have the potential to improve the thermal and electrical conductivity of these materials as well as the thermomechanical properties. Aging studies using high temperature, pressure and moisture are being utilized to test the long term viability of these materials as well.
Show less
Show moreDespite the popularity, we noticed that it is rather hard to verify a NLP/text-mining like stock prediction model's performance due to the amount of "groundwork" needed. It is very typical a researcher will have to gather the plain text data, the company info, the stock market data, and categorize them in a way that is communicable with each other and the model; then the researcher will need to build a virtual trading platform that keeps track of all the trading signals generated by the model, log the activities in a certain way, then do some kinds of visualization for evaluations. To implement all these steps from ground up, it is required for a researcher to have certain level of proficiency on skills which are, from a research stand-point, fairly deviated from the nature of the NLP/text-mining model itself (like scraping a website and understanding the fundamental mechanism of trading in stock market). Thus, we like to build a set of lightweight tools that may automate such process to a certain degree.
Show less
Show moreSimulation education for medical and health professional training bridges classroom learning and training in a clinical environment. Its use has been increasing over the past two decades. Guidance to avoid in-person contact due to SARS-CoV-2 has further increased demand. Pure-tone audiometry is part of an audiometric test battery used to evaluate the auditory system. At Case Western Reserve University, students typically learn to conduct audiometry in COSI 370: Introduction to Audiology. Under current pandemic circumstances, students are unable to gain in-person experience using standard hardware (an audiometer and calibrated headphones). AvatarAudiometer solves this problem via an interactive online tool that mimics a real audiometer and simulates patient responses. The system consists of a simulation of pure-tone audiometry and a tool for graphing results on a standard audiogram interface. AvatarAudiometer allows students to measure unmasked air- and bone-conduction thresholds for each ear at octave and interoctave frequencies, 250-8000 Hz. The virtual patients' responses to tones are based on their individual hearing level thresholds. Because real humans are inconsistent in their responding, AvatarAudiometer patients differ from one another in their frequency of false positive/negative responses, range of reaction times, and duration of holding down the virtual response button. Two sources of patient audiometric profiles are included: 1) curated audiograms simulating specific types, configurations, and severities of hearing loss, along with a description of each virtual patient’s case history, and 2) a sample of 5470 audiograms representative of the United States’ population by age and sex selected from the CDC’s NHANES database. AvatarAudiometer includes a tutorial that demonstrates functions and settings of a standard audiometer. Students can complete numerous pure-tone audiometric exams and screen large cohorts of virtual patients to simulate a hearing-screening protocol. After testing is complete, an interface for plotting, editing, and downloading corresponding pure-tone audiometric results on an audiogram is shown. A professor may have students self-grade their audiograms by comparing the student-measured audiograms with those of the patient's "true" simulated pure-tone thresholds.
Show less