Poster
Explainable Sensor Data-Driven Anomaly Detection in Internet of Things Systems
IEEE/ACM IoTDI 2022.
Project Overview
Uses LSTM autoencoders with surrogate models and SHAP explanations to interpret anomaly detection decisions on IoT sensor data.
The project trains LSTM autoencoders on the SWaT dataset, then explains detected anomalies via random-forest surrogate models and SHAP visualisations. A dashboard answers when, how, what, and why questions for different personas.
Team
Moaz Hussain
Charith Perera