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 (2018). On the adoption of abductive reasoning for time series interpretation. Artificial Intelligence, 262, 163–188. https://doi.org/10.1016/j.artint.2018.06.005

[2]: T. Teijeiro, P. Felix, J. Presedo and D. Castro (2018). Heartbeat Classification Using Abstract Features from the Abductive Interpretation of the ECG. IEEE Journal of Biomedical and Health Informatics, 22(2), 409–420. https://doi.org/10.1109/JBHI.2016.2631247

[3]: T. Teijeiro, C. A. García, D. Castro, and P. Félix (2018). Abductive reasoning as the basis to reproduce expert criteria in ECG Atrial Fibrillation identification. Physiological Measurement, 39(8), 084006. https://doi.org/10.1088/1361-6579/aad7e4

[4]: T. Teijeiro, C. A. García, D. Castro, and P. Félix (2017). Arrhythmia classification from the abductive interpretation of short single-lead ECG records. In Computing in Cardiology (Vol. 44). https://doi.org/10.22489/CinC.2017.166-054

[5]: T. Teijeiro, P. Félix and J. Presedo (2014). Using Temporal Abduction for Biosignal Interpretation: A Case Study on QRS Detection. In 2014 IEEE International Conference on Healthcare Informatics (pp. 334–339). IEEE. https://doi.org/10.1109/ICHI.2014.52