Title | ||
---|---|---|
Post Hoc Explainability for Time Series Classification: Toward a signal processing perspective |
Abstract | ||
---|---|---|
Time series data correspond to observations of phenomena that are recorded over time
<xref ref-type="bibr" rid="ref1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[1]</xref>
. Such data are encountered regularly in a wide range of applications, such as speech and music recognition, monitoring health and medical diagnosis, financial analysis, motion tracking, and shape identification, to name a few. With such a diversity of applications and the large variations in their characteristics, time series classification is a complex and challenging task. One of the fundamental steps in the design of time series classifiers is that of defining or constructing the
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">discriminant features</i>
that help differentiate between classes. This is typically achieved by designing novel
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">representation techniques</i>
<xref ref-type="bibr" rid="ref2" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[2]</xref>
that transform the raw time series data to a new data domain, where subsequently a classifier is trained on the transformed data, such as one-nearest neighbors
<xref ref-type="bibr" rid="ref3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[3]</xref>
or random forests
<xref ref-type="bibr" rid="ref4" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[4]</xref>
. In recent time series classification approaches, deep neural network models have been employed that are able to jointly learn a representation of time series and perform classification
<xref ref-type="bibr" rid="ref5" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[5]</xref>
. In many of these sophisticated approaches, the discriminant features tend to be complicated to analyze and interpret, given the high degree of nonlinearity. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/MSP.2022.3155955 | IEEE Signal Processing Magazine |
Keywords | DocType | Volume |
post hoc explainability,signal processing perspective,music recognition,medical diagnosis,time series classifiers,discriminant features,raw time series data,data domain,transformed data,recent time series classification approaches | Journal | 39 |
Issue | ISSN | Citations |
4 | 1053-5888 | 0 |
PageRank | References | Authors |
0.34 | 16 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rami Mochaourab | 1 | 0 | 0.34 |
Arun Venkitaraman | 2 | 0 | 0.34 |
Isak Samsten | 3 | 0 | 0.34 |
Panagiotis Papapetrou | 4 | 452 | 43.51 |
Cristian R. Rojas | 5 | 252 | 43.97 |