A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Time Series Clustering For Novelty Detection: An Empirical Approach
2016
Anais do 8. Congresso Brasileiro de Redes Neurais
unpublished
This paper presents some results of DANTE project: Detection of Anomalies and Novelties in Time sEries with self-organizing networks, whose goal is to devise and evaluate self-organizing models for detecting novelties or anomalies in univariate time series. The methodology to detect novelty consists in finding non-parametric confidence intervals, who are computed from the quantization errors obtained at the training phase, used at the testing phase as decision thresholds for classifying data
doi:10.21528/cbrn2007-063
fatcat:27dub2zdeffs7aqoy4b4qjnu3u