| Proj No. | A3255-251 |
| Title | LLM-Powered Heartbeat Anomaly Detection and Diagnostic Reporting |
| Summary | Objective This project aims to use LLMs for heartbeat anomaly detection by analyzing ECG (electrocardiogram) signals and providing AI-generated diagnostic reports for medical assistance. Scope Use public ECG datasets (e.g., MIT-BIH Arrhythmia Database) for training and testing. Apply signal preprocessing to convert raw ECG waveforms into LLM-readable descriptions. Implement IoT-LLM reasoning to classify normal vs. abnormal heartbeats and generate explainable diagnostic reports. Develop an LLM-powered chatbot that allows doctors to query about patient conditions using natural language. Required Skills Python, SciPy, and signal processing techniques (Fourier Transform, filtering). Experience with ECG classification using deep learning models. Familiarity with LLM-based medical report generation and query answering. |
| Supervisor | Ast/P Yang Jianfei (Loc:School of Mechanical and Aerospace Engineering (MAE), Ext: ?) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Internet of Things Laboratory (Loc: S1-B4c-14, ext: 5470/5475) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |