This thesis investigates how reliably Large Language Model (LLM)-generated data can be used to train deep learning-based Intrusion Detection Systems (IDS) beyond traditional, real-traffic datasets. In the context of a small distributed environmental measurement application, application-layer sensor data (temperature, humidity, and particulate matter) and corresponding HTTP Network Traffic Telemetry (NTT) were collected over one week using Raspberry Pi measurement stations and Zeek. Two Long-Short-Term Memory (LSTM) models were trained: an Application Model (AM) for sensor anomalies and a Network Traffic Model (NTM) for network anomalies, combined in a voting-based IDS that outputs a trust score per source. Using a structured prompting strategy, a publicly available LLM was then employed to generate synthetic AM and NTT datasets. The similarity between real and synthetic data distributions was quantified using the Wasserstein distance, after which two experiment series were conducted: (1) progressively replacing real samples with synthetic ones while keeping training set size fixed, and (2) augmenting the real data with increasing fractions of synthetic samples. Results show that replacing more than roughly 10% of the AM training data degrades detection performance, whereas the NTM remains robust until real data is nearly fully replaced. In contrast, augmenting (rather than replacing) real data preserves, and in some cases modestly improves, IDS performance. Overall, the findings indicate that LLM-generated data can effectively complement—but not fully replace—real measurements when carefully integrated into IDS training pipelines. ... Read more

This thesis describes the design and implementation of a subsystem within a larger medical monitoring system. This subsystem will make bidirectional audio communication possible between a patient and their caregivers or family members. The patient in question can be premature babies that have to stay inside of incubators and elderly people that need to be monitored for their health.
The designed subsystem is tasked with creating an audio stream that goes bidirectionally between a speaker with a handsfree functionality and the front end via a server. On the server the audio from the patient should be stored on a hard drive. Whether the audio communication should be stopped or started and whether the audio should be stored will be controlled by the front-end user. Initially the goal was to implement the solution on a Pine singleboard computer (SBC), but due to unforeseen delays of the delivery of the necessary Pine SBC, it was decided that a proof of concept would be developed. The future work in this thesis will discuss the portability of the solution to the Pine SBC. ... Read more