Home

Construe is a knowledge-based framework for time series interpretation. It follows the principles of abductive reasoning, inspired by how humans describe the behavior of processes underlying a set of temporal observations, identifying and characterizing recurrent patterns. This approach tries to overcome some limitations of common classification-based strategies, being specially suitable in noisy and poor controlled scenarios. A full description of the framework is published in [1]

At this moment, the framework has been succesfully applied to the electrocardiogram (ECG) interpretation problem, and provides a set of tools for the interpretation of ECG signals and heartbeat classification.

Tutorials

How to define abstraction models

References

^{[1]: T. Teijeiro and P. Félix: On the adoption of abductive reasoning for time series interpretation, 2016, arXiv:1609.05632.}

^{[2]: T. Teijeiro, P. Félix, J.Presedo and D. Castro: Heartbeat classification using abstract features from the abductive interpretation of the ECG}

^{[3]: T. Teijeiro, P. Felix, and J. Presedo. Using Temporal Abduction for Biosignal Interpretation: A Case Study on QRS Detection. In 2014 IEEE International Conference on Healthcare Informatics, pages 334–339. September 2014.}