Student Projects

Students: Willy Brandes ‘21, Devon Harris 19, Alex Haug ‘19, Charlie Peeke ‘19, John Spirk ‘19, Daniel Stocker ‘19, Nick Zambelli ‘19
Faculty Mentor: Ben Coleman

Regulations.gov was created by the federal government to allow citizens to search for regulatory materials and to submit comments on proposed regulations. The data contained on this site is valuable to researchers, but the API severely limits the rate at which it can be obtained - it would take a single user over one year to download all the data. The goal of the mirrulations project is to coordinate the efforts of multiple volunteers to download the data in a distributed fashion. Using a client/server architecture, each client is assigned records to obtain, which it uploads to the server once they are obtained from regulations.gov. All data is hosted by Docgraph, our partner in this project.

Images: system diagram, logos (regulations.gov, DocGraph, Merck)
URL: https://github.com/MoravianCollege/mirrulations

Students: Andrew Carr ‘19, John Polich ‘19
Faculty Mentor: Ben Coleman

Philips Hue lights are a popular in Smart Home applications, allowing users to create dynamic lighting environments for various rooms. The goal of this project was to allow the public to use SMS (text) messages to change the color of a light on display in the computer science research lab. The system uses a Flask webserver running on a Raspberry Pi to receive and send SMS messages via Twilio. A database of colors is stored on the Raspberry Pi, and the system also track how often various colors are requested by users.

Images: System Diagram
URL: https://github.com/MoravianCollege/hue_sms

Students: Megan Biernat ‘17, Jason Boccuti ‘15, Lewis Cooper ‘15, Myes Barros ‘14, David Cariello ‘14, Justin Dilts ‘14, Michael Eckhart ‘14, Nicholas Forouraghi ‘14, Alec Gerhart ‘17, Karli Gnehm ‘14, Rachel Johnson ‘14, Charlie McDonald ‘17, James Perry ‘14, Vincent Pillinger ‘16, Allison Samson ‘14, Alek Szilagyi ‘14
Faculty Mentor: Ben Coleman

OpenMRS is an open source EMR used in more than 23 countries throughout the world, including 400+ installations in Nigeria. Providing efficient access to this data would allow researchers to more effectively answer important questions about population health. The goal of this project was to create an add-on module for OpenMRS to provide aggregate, anonymized data through a REST interface.

Images: System Diagram, Triangle of Logos, bar graph
URL: http://moraviancollege.github.io/OpenMRS/openMRS.html

Students: Megan Biernat ‘17, Jason Boccuti ‘15, Steve Chakif ‘15, William Collins ‘17, Lewis Cooper ‘15, Jon Diehl ‘15, Alec Gerhart ‘17, Hansen Huang ‘15, Anna Lamoureux ‘17, Steve MacDonald ‘18, Charlie McDonald ‘17, Martin Nesbitt ‘18, Andrew Reed ‘17, Josh Russett ‘17, Michael Turnbach ‘17, Michael Vitone ‘15, John Vonelli ‘18
Faculty Mentor: Ben Coleman

The HA1C blood test provides a way to see the average blood sugar levels of a patient during the two to three months prior to the test, and doctors recommend that the test be administered four times per year for diabetes patience. The goal of this project was to determine whether compliance to this recommendation can be seen in the 2012 medicare doctor billing and referral data. The project focused on visualizing this dataset simultaneously with other datasets on an interactive web-based map.

Images: Screenshot, team picture
URL: http://moraviancollege.github.io/MorningStar/morningstar.html

Students: Chris Angelico ‘16, Nick Cicchetti ‘16, Spenser Diernbach ‘16, Khristian Morel ‘16, Vincent Pillinger ‘16, Derek Raines ‘16
Faculty Mentor: Ben Coleman

The goal of interoperability is for patients to be able to seamlessly share their medical records between doctors - even if those doctors are using different EMR systems. Fast Healthcare Interoperability Resources is a standard created by Health Level 7 that describes data formats to achieve this goal. In this project, students created a program to translate medicare billing data into the FHIR format.

Images: Logo, State Diagram
URL: None

Students: Megan Biernat ‘17, Bill Collins ‘17, Gabe Fournier, Alec Gerhart ‘17, Anna Lamoureux ‘17, Martin Nesbitt ‘18, Andrew Reed ‘17, Josh Russett ‘17, Michael Turnbach ‘17, John Vonelli ‘18, Nicholas Zambelli ‘19 
Faculty Mentor: Ben Coleman

Joining multiple datasets together can result in significant insights, but for this to be possible, researchers must know about what datasets are available. Hydra provides Merck employees with an easy-to-use tool to catalog and search datasets, and a version of the tool was given to DocGraph (called Linea) prior to completion. The goal of this project was to incorporate features of the final version of Hydra into Linea and to add features required by the DocGraph community.

Images: Students presenting, screenshot
URL: None

Students: Bill Collins ‘17, Alec Gerhart ‘17
Faculty Mentor: Ben Coleman

The data sets available from the Centers for Medicare and Medicaid Services (CMS) offer researchers a wealth of information. The goal of this project was to explore the accuracy of doctor classification in the Medicare billing datasets. Using the k-means algorithm to cluster by billing patterns, doctors who fell outside the most prevalent groups were flagged as potentially mis-classified.

Images: None
URL: None

Student: Alec Gerhart ‘17
Faculty Mentor: Ben Coleman

The Affordable Care Act (ACA) introduced the concept of an Accountable Care Organization (ACO), and it is believed that doctors in ACOs will have lower referral rates. The goal of this project was to determine whether changes to referral rates could be seen in the six years of Medicare billing data available from CMS.

Images: None
URL: None

Students: Megan Biernat ‘17, Bill Collins ‘17, Gabe Fournier, Alec Gerhart ‘17, Anna Lamoureux ‘17, Martin Nesbitt ‘18, Andrew Reed ‘17, Josh Russett ‘17, Michael Turnbach ‘17, John Vonelli ‘18, Nicholas Zambelli ‘19
Faculty Mentor: Ben Coleman

Medical professionals make decisions based on available data, so an increased frequency of measurement enables physicians to provide more informed diagnoses. The goal of this project was to develop an application for patients to collect blood pressure and blood oxygen data using low-cost sensors connected to a Raspberry Pi. That data was automatically uploaded to a server via a REST interface, and doctors could access that data to monitor their patients.

Images: Usage, hardware, use case
URL: https://github.com/MoravianCollege/HomeHealthKit

Students: Tyler Bialoblocki ‘17, Megan Biernat ‘17, William Collins ‘17, Alec Gerhart ‘17, Devon Harris ‘19, Adam Howard ‘18, Daniel Howard ‘17, Anna Lamoureux ‘17, Charles McDonald ‘17, Martin Nesbitt ‘18, Charles Peeke ‘19, Andrew Reed ‘17, Joshua Russett ‘17, Christopher Sheehan ‘17, John Spirk ‘19, Michael Turnbach ‘17, John Vonelli ‘18, Nicholas Zambelli ‘19
Faculty Mentor: Ben Coleman

The widespread usage of smartphones, fitness trackers, and home automation provides an opportunity to improve patient care. The goal of this project was to explore how the Internet of Things (IoT) could be used to improve Alzheimer’s care by collecting data on the patient, providing reminders, and allowing caregivers to remotely determine the wellness of the patient.

Images: system diagram, use case diagrams
URL: https://github.com/MoravianCollege/AlzheimersIoT

Students: John Spirk ‘19
Faculty Mentor: Ben Coleman

The Moravian University firewall blocks between 10 and 15 incoming connections per second. The goal of this project is the create a visual display of the geographic region from which these connections originate. Log entries are streamed from the Moravian University log server to a dedicated system that geo-locates the IP address and archives the data. This system also provides a REST API that provides access to a sliding window of the data. A simple visualization client retrieves the data and displays it on map of the world.

URL: https://github.com/MoravianCollege/BlockedTrafficVisualization
Images: Screenshot?

Student: David Durski ‘19
Faculty Mentor: Ben Coleman

The Moravian University 3D-Print Team maintains two Ultimaker 3 printers. The goal of this project is to create a dashboard showing the status of each printer. The display shows the name of the current print job, a wire-frame rendering of the final result, the percent progress and elapsed time of the print job, and current temperature readings from both print heads and the print bed.

Students: Ben Anderson ‘20, Caelin McCool ‘20
Faculty Mentor: Ben Coleman

The Computer Science Research Laboratory is located in a different building from the offices of the computer science faculty. The goal of this project is to create a display that shows whether each faculty member's door is open or closed. The system uses magnetic door sensors that communicate using the Zigbee protocol with a instance of OpenHabian running on a Raspberry Pi. The Pi provides the data to a client via a REST API implemented using Flask. Finally, the client implements a visual display of the status of each door using the Python GUI library, TKinter.

Students: Adam Howard ‘18, Steve MacDonald ‘18, Jose Meono ‘18, Martin Nesbitt ‘18, Andrew O’Brien ‘18, Mario Sobrino ‘18, John Vonelli ‘18
Faculty Mentor: Ben Coleman

This project focused on process. and the team committed engage in TDD, CI, and Clean Code. The project was to create a collection of services around the inventory of a local beer distributor. One service scraped the data from the company's website and stored it into a data store. Another service provides a REST API that allows users to query the current inventory with various filters. A web service allows users to register beer-style preferences, and a final service periodically checks the inventory and informs users via SMS if a new beer matches the user's preferences.

Student: John Vonelli ‘18
Faculty Mentors: Thyago Mota, Brenna Curley

The purpose of this research project was to investigate how songs lyrically and musically influence popularity and emotional responses throughout contemporary history. We built a dataset of 27,346 songs that are listed on the Billboard “Hot 100” list from 1958 to 2017. We then used Spotify’s song metrics, together with a weighted sampling function, to evaluate how music changed over time. Our analysis showed that popular music is becoming louder, more energetic, and lyrically dense. Acoustic and instrumental popular songs have severely declined since the 1960s while danceability, tempo, and liveness of the analyzed songs remained consistent over the years. Duration reached a maximum value around 1993, after which it started to decline.

URL: http://www.ncurproceedings.org/ojs/index.php/NCUR2018/article/view/2631/1418

Student: Zachary Balga ‘19
Faculty Mentor: Thyago Mota

Twitter uses one-way relationships between followers and followed to build its social network. Two-way relationships (also called friendship) happen when users simultaneously follow one another. The main motivation of this research project was to sample Twitter’s friendship network in an efficient way. We proposed a parallel implementation of the BFS (Breadth-first Search) algorithm to speed up the sampling process, a very time-consuming process because of the rate-limits imposed by Twitter’s API.

Image: CCSC Poster (under the “Twitter Friendship” folder)

Student: William Brandes ‘21
Faculty Mentor: Thyago Mota

In this project we demonstrated how to turn a device essential to many homeowners, a garage door opener, into a smart device connected to the Internet and controlled by a smartphone. To be able to effectively control the device from a distance, our implementation uses a Raspberry Pi computer, together with a relay interface module. The small single-board computer is also used to collect basic usage stats such as door opening and closing times, number of invalid requests, etc. The system is operated from an Android app designed to use short-range bluetooth communication to control the garage door safely within eyesight. A version of the Challenge-Handshake Authentication Protocol (CHAP) was implemented to allow opening and closing the garage door in a secure way.

Image: CCSC Poster (under the “Garage Door” folder)

Student: John Vonelli ‘18
Faculty Mentor: Thyago Mota

A computer cluster is a group of independent computers working together with the goal to provide a computational resource with a higher degree of availability. Compared to a single machine, a cluster offers more processing power, data storage, and the ability to run distributed applications. In this project, we were interested in creating a computational resource to support current and future research for the Mathematics and Computer Science Department at Moravian University. Likewise, this computational resource can be used as an important teaching aid to assist students in learning important CS topics, such as operating systems, networking, and security.

Image: CCSC Poster (under the “Cluster” folder)

Student: Anna Lamoureux ‘17
Faculty Mentor: Thyago Mota

The overall goal of this project was to develop an app (named “ServeTracker”) that could help a tennis coach to collect players' serve statistics. The app's initial screen allows the user to enter the required parameters for a typical serve practice session, including the player's name, the serve side (Deuce or AD), the target area, and the number of serves. Depending on whether a Deuce or AD serve side is chosen, "ServeTracker" shows an appropriate screen that matches the coach’s view of the tennis court. The coach can then touch any of the tennis court labeled areas to collect statistics for the practice session. At the end of the session "ServeTracker" presents all collected statistics using percentages. The statistics could then be shared for further analysis.

Images: app screens (under the “Tennis Serve Tracker” folder)