DCU Expo 2023 Final Year Projects

48 66. ExhibitAce: Third-Level Project Expo App ExhibitAce is amobile application designed for exhibitions and events in third-level institutions. It allows attendees to navigate the exhibition with ease using a digital map of the event, and quickly find projects of interest with the help of search and filter functions. Class Enterprise Computing Project Area Android, Mobile App, Software Development Project Technology Java, NoSQL, XML Student Name(s) Amy Donovan  |  Luke O’Callaghan Smith Email amy.donovan8@mail.dcu.ie   |  luke.ocallaghansmith22@mail.dcu.ie Supervisor Dr Jennifer Foster 67. Open Source Event Management Suite A software suite consisting of an Android App, Management API, and Analytics API. Its goal is to provide an all-in-one suite for hosting, managing, analysing events if you’re an organizer. As well as a single place for keeping up to date with and participating in the latest social events. The project demonstrates how a feature full event management application can be developed usingmultiple APIs. The application can be forked and adapted to fit general or more specific use cases. Class Computer Applications Project Area Android, Cloud Computing, Data Analytics, Databases, Distributed Systems, GPS/GIS, Information Retrieval, Mobile App, Network Applications, Social Networking, Software Development, Statistical Analysis, Web Application, Recommender System Project Technology CSS, HTML5, Java, JavaScript, MongoDB, Nodejs, Python, REST, XML, Machine Learning Student Name(s) Armands Dunskis  |  Sebastian Pluta Email armands.dunskis2@mail.dcu.ie   |  sebastian.pluta2@mail.dcu.ie Supervisor Dr Darragh O’Brien 68. Prediction of Kidney Transplant Graft Survival Using a Cluster-Then-Predict Framework A kidney transplant is a life-changing surgery that adds decades to a recipient’s lifespan however supply does not meet demand. This project’s objective is to predict kidney transplant outcomes (how long a kidney transplant survives in a patient) in order to improve the kidney allocation system. The estimated Glomerular Filtration Rate (eGFR) rate (ameasure of kidney function) is predicted at 1 year and 5 years post-transplant using a cluster-then-predict framework. Clustering analysis is performed on the donor and recipient data to understand any underlying phenotypes. A regression model is applied to each cluster and the predictions are combined. Finally, an evaluation and comparison of the proposed framework to a standalone traditional statistical regression model are carried out. Class Data Science Project Area Artificial Intelligence, Data Analytics, DataMining, Statistical Analysis, Medicine, Phenotyping Project Technology Python, R Student Name(s) Diarmuid Brady  |  AoifeMcDaid Email diarmuid.brady35@mail.dcu.ie   |  aoife.mcdaid3@mail.dcu.ie Supervisor Prof TomasWard