On the adoption of abductive reasoning for time series interpretation

09/19/2016
by   Tomás Teijeiro, et al.
0

Time series interpretation aims to provide an explanation of what is observed in terms of its underlying processes. The present work is based on the assumption that common classification-based approaches to time series interpretation suffer from a set of inherent weaknesses whose ultimate cause lies in the monotonic nature of the deductive reasoning paradigm. In this document we propose a new approach to this problem based on the initial hypothesis that abductive reasoning properly accounts for the human ability to identify and characterize patterns appearing in a time series. The result of the interpretation is a set of conjectures in the form of observations, organized into an abstraction hierarchy, and explaining what has been observed. A knowledge-based framework and a set of algorithms for the interpretation task are provided, implementing a hypothesize-and-test cycle guided by an attentional mechanism. As a promising application domain, the interpretation of the electrocardiogram allows us to highlight the strengths of the present approach in comparison with traditional classification-based approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2020

Construe: a software solution for the explanation-based interpretation of time series

This paper presents a software implementation of a general framework for...
research
05/23/2023

Interpretation of Time-Series Deep Models: A Survey

Deep learning models developed for time-series associated tasks have bec...
research
06/12/2018

A review on distance based time series classification

Time series classification is an increasing research topic due to the va...
research
02/11/2022

InterpretTime: a new approach for the systematic evaluation of neural-network interpretability in time series classification

We present a novel approach to evaluate the performance of interpretabil...
research
06/18/2019

Periphery Plots for Contextualizing Heterogeneous Time-Based Charts

Patterns in temporal data can often be found across different scales, su...
research
03/23/2018

An Incremental Boolean Tensor Factorization approach to model Change Patterns of Objects in Images

Change detection process has recently progressed from a post-classificat...
research
11/09/2018

An Overview of Computational Approaches for Analyzing Interpretation

It is said that beauty is in the eye of the beholder. But how exactly ca...

Please sign up or login with your details

Forgot password? Click here to reset