Construe: a software solution for the explanation-based interpretation of time series
Published in
arXiv.org(2020)External Links:
TL
TL;DR
A comprehensive knowledge base for the electrocardiogram (ECG) domain is provided, so it can be used directly as a tool for ECG analysis and has been successfully validated in several noteworthy problems, such as heartbeat classification or atrial fibrillation detection.
Abstract
This paper presents a software implementation of a general framework for time series interpretation based on abductive reasoning. The software provides a data model and a set of algorithms to make inference to the best explanation of a time series, resulting in a description in multiple abstraction levels of the processes underlying the time series. As a proof of concept, a comprehensive knowledge base for the electrocardiogram (ECG) domain is provided, so it can be used directly as a tool for ECG analysis. This tool has been successfully validated in several noteworthy problems, such as heartbeat classification or atrial fibrillation detection.
References13 items
1
The genetic makeup of the electrocardiogram
2
Heart Rate Recovery 10 Seconds After Cessation of Exercise Predicts Death
3
Heartbeat Classification Using Abstract Features From the Abductive Interpretation of the ECG
4
Abductive reasoning as a basis to reproduce expert criteria in ECG atrial fibrillation identification
5