A Benchmark of Data Stream Classification for Human Activity Recognition on Connected Objects

This paper evaluates data stream classifiers from the perspective of connected devices, focusing on the use case of Human Activity Recognition. We measure both the classification performance and resource consumption (runtime, memory, and power) of five usual stream classification algorithms, impleme...

Descripción completa

Detalles Bibliográficos
Autores principales: Khannouz, Martin, Glatard, Tristan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7696887/
https://www.ncbi.nlm.nih.gov/pubmed/33202905
http://dx.doi.org/10.3390/s20226486

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7696887/
https://www.ncbi.nlm.nih.gov/pubmed/33202905
http://dx.doi.org/10.3390/s20226486

Ejemplares similares