English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Data series classification is an important and challenging problem in datascience. Explaining the classification decisions by finding the discriminantparts of the input that led the algorithm to some decisions is a real need inmany applications. Convolutional neural networks perform well for the dataseries classification task; though, the explanations provided by this type ofalgorithm are poor for the specific case of multivariate data series.Addressing this important limitation is a significant challenge. In this paper,we propose a novel method that solves this problem by highlighting both thetemporal and dimensional discriminant information. Our contribution istwo-fold: we first describe a convolutional architecture that enables thecomparison of dimensions; then, we propose a method that returns dCAM, aDimension-wise Class Activation Map specifically designed for multivariate timeseries (and CNN-based models). Experiments with several synthetic and realdatasets demonstrate that dCAM is not only more accurate than previousapproaches, but the only viable solution for discriminant feature discovery andclassification explanation in multivariate time series. This paper has appearedin SIGMOD'22.

dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification