DCU-Final-Year-Projects-Booklet-2025

86 162. Human Presence Sensing for Smart Home Applications Using mmWave Radar Sensors This project explores the development of an IoT-based human presence sensing system usingmmWave radar technology to enhance smart home automation and safety. Traditional motion sensors often struggle to detect subtle movements and differentiate between motion states, leading to false positives andmissed detections. To address these limitations, a DFRobot C1001mmWave radar sensor is integrated with an ESP32microcontroller, enabling precise detection of presence, movement, and falls. The sensor data is processed in real-time and transmitted via theMQTT protocol to Home Assistant, where it triggers smart home automation tasks. The project aims to develop a functional prototype that improves energy efficiency, automation reliability, and safety in smart home environments. Student Programme Electronic and Computer Engineering (Year 4) Project Area Arduino, Automation, Internet of Things, Sensor Data, Sensor Technology Project Technology C/C++, Digital Signal Processing, MQTT Student Name(s) JakubWojtowicz Email jakub.wojtowicz2@mail.dcu.ie Supervisor Prof DerekMolloy 163. Codipy Codipy is a cloud-based coding challenge platform that provides a visual scripting version of Python. It features an interface where users drag, drop, and connect blocks representing Python constructs, drawing on concepts from visual scripting environments such as Scratch and UE’s Blueprint. These blocks are parsed into executable code, and run within secure, isolated containers. Codipy supports incremental learning, allowing educators to design structured challenge sets that help learners visualise Python concepts and progressively build their Python skills. The platform is built on a scalable architecture, leveraging Kubernetes for deployment, Express and React for the web application, a PostgreSQL database, and FastAPI for Python-related tasks such as code generation and validation. Student Programme Computer Science Project Area Cloud Computing, Distributed Systems, Educational, Software Development, Web Application, Visual Programming Project Technology Docker, Python, React.js, Typescript, Postgres, Kubernetes, Postman, Selenium Student Name(s) Michael Regan  |  Jordan Tallon Email michael.regan25@mail.dcu.ie   |  jordan.tallon3@mail.dcu.ie Supervisor Dr David Sinclair 164. Mitigating Privacy Risks in Retrieval-Augmented Generation (RAG) Systems This project addresses privacy challenges in Retrieval-Augmented Generation (RAG) systems, which enhance Large LanguageModels (LLMs) by retrieving external knowledge to generate accurate, contextually enriched responses. While RAG systems improve factual accuracy and reliability, they often process sensitive data, such as personal or proprietary information, which can lead to significant privacy vulnerabilities. This project develops a privacy-preserving pipeline that integrates Differential Privacy (DP) techniques with Low-Rank Adaptation (LoRA) to fine-tune a T5-small model. The goal is to generate synthetic query-document pairs that maintain semantic fidelity while minimising the risk of exposing sensitive information. Student Programme Electronic and Computer Engineering (Year 4) Project Area Artificial Intelligence, Data Analytics, Natural Language Processing, Security, Software Development, Machine Learning Project Technology Python, Machine Learning Student Name(s) Joseph O’Reilly Email joseph.oreilly58@mail.dcu.ie Supervisor Dr Conor McArdle