Salvato in:
Dettagli Bibliografici
Autori principali: Barboza, Eduardo V. L., de Almeida, Paulo R. Lisboa, Britto Jr, Alceu de Souza, Cruz, Rafael M. O.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2307.00106
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914426041401344
author Barboza, Eduardo V. L.
de Almeida, Paulo R. Lisboa
Britto Jr, Alceu de Souza
Cruz, Rafael M. O.
author_facet Barboza, Eduardo V. L.
de Almeida, Paulo R. Lisboa
Britto Jr, Alceu de Souza
Cruz, Rafael M. O.
contents Data normalization is an essential task when modeling a classification system. When dealing with data streams, data normalization becomes especially challenging since we may not know in advance the properties of the features, such as their minimum/maximum values, and these properties may change over time. We compare the accuracies generated by eight well-known distance functions in data streams without normalization, normalized considering the statistics of the first batch of data received, and considering the previous batch received. We argue that experimental protocols for streams that consider the full stream as normalized are unrealistic and can lead to biased and poor results. Our results indicate that using the original data stream without applying normalization, and the Canberra distance, can be a good combination when no information about the data stream is known beforehand.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00106
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Distance Functions and Normalization Under Stream Scenarios
Barboza, Eduardo V. L.
de Almeida, Paulo R. Lisboa
Britto Jr, Alceu de Souza
Cruz, Rafael M. O.
Machine Learning
Data normalization is an essential task when modeling a classification system. When dealing with data streams, data normalization becomes especially challenging since we may not know in advance the properties of the features, such as their minimum/maximum values, and these properties may change over time. We compare the accuracies generated by eight well-known distance functions in data streams without normalization, normalized considering the statistics of the first batch of data received, and considering the previous batch received. We argue that experimental protocols for streams that consider the full stream as normalized are unrealistic and can lead to biased and poor results. Our results indicate that using the original data stream without applying normalization, and the Canberra distance, can be a good combination when no information about the data stream is known beforehand.
title Distance Functions and Normalization Under Stream Scenarios
topic Machine Learning
url https://arxiv.org/abs/2307.00106