We are thrilled to announce that IEEE ICDE 2024 demo paper entitled “ADecimo: Model Selection for Time Series Anomaly Detection” by P. Boniol, E. Sylligardos, J. Paparizos, P. Trahanias, T. Palpanas, has been honored with the “Best Runner Up Demo” Award!
Predictive Maintenance in dynamic environments poses significant challenges, including data and concept drifts, lack of labeled data, and the constraints of streaming environments. To address these, our approach leverages unsupervised anomaly detection techniques to monitor asset states, eliminating the dependency on labeled datasets. Auto-configurable solutions ensure robustness against data drifts and enhance usability for end-users. Additionally, context-aware methods are employed to provide explainability and improve decision-making processes. All solutions are designed for online deployment, enabling real-time analytics and swift responses.
Stream DaQ is an open-source framework developed by members of the Data and Web Science Lab (DATALAB) with a strong expertise in data streaming, anomaly detection and time series analytics. Stream DaQ is developed to keep an eye on your data stream, letting you know the moment when travelling data do not meet the expected quality in real time, so that you can take timely, informed actions. Acknowledging that every data-centric application is different, Stream DaQ comes with a comprehensive built-in suite of 60+ state-of-the-art data quality measures, so that
