DCU-Final-Year-Projects-Booklet-2025

104 216. SmartShade The “SmartShade” project automates curtain operation to enhance convenience and efficiency. It uses an ESP32module, motor drivers, light sensors, and an RTCmodule to control curtains based on light intensity, time, or manual commands via amobile application. The system integrates with Home Assistant using ESPHome, providing smooth connectivity for smart home environments. Users can schedule operations or enable real-time control through the Home Assistant platform. A potential solar panel integration ensures sustainable power usage, making it a versatile and eco-friendly solution tailored for modern living spaces. Student Programme Mechatronic Engineering (Year 4) Project Area Automation, Automotive Technology Project Technology ESPHome Student Name(s) IbrahimMohamed Alabri Email ibrahim.alabri2@mail.dcu.ie Supervisor Dr Brendan Hayes 217. Coaching Buddy The project aims to give Gaelic Football coaches andmanagers an online platform that gives them the tools to fulfil all of their day to day needs. The idea for the project was discovered as an opportunity in the market due to the experiences of the twomembers of the group, confirmed later by both primary and secondary research conducted. This project includes features that are vital to the process of the admin side and the coaching side of a team, including schedule making tools, features vital for tracking and recording game statistics, features enabling users to share video among other users as well as other more specific features to the sport such as a customisable formation tool. Student Programme Computing for Business Project Area Web Application Project Technology CSS, HTML5, JavaScript, Python Student Name(s) LukeMorris  |  Dylan Geraghty Email luke.morris33@mail.dcu.ie  |  dylan.geraghty23@mail.dcu.ie Supervisor Dr SilvanaMacMahon 218. Computer Vision andDeep Learning Based Prediction for Automated ManufacturingQuality Control This project explores the use of neural networks and deep learning for classifying the quality of inkjet- printed electrodes in an automated quality control (QC) station. By integrating image processing technology with neural networks, we improve classification accuracy and reliability. Images of inkjet- printed electrodes were analysed using a convolutional neural network (CNN) and a feedforward neural network, both optimised for maximumaccuracy. This project demonstrates how advanced image processing and neural network optimisation enhance QC automation. By reducingmanual inspection, this approach increases efficiency and ensures consistent product quality in manufacturing lines. Student Programme Mechanical andManufacturing Engineering (Year 5) Project Area Artificial Intelligence, Automation, Computer Vision, Image/Video Processing, LeanManufacturing, Mechanical Design andManufacture, Software Development Project Technology Excel/VB, Python, Machine Learning Student Name(s) Gareth Quinn Email gareth.quinn39@mail.dcu.ie Supervisor Prof Dermot Brabazon