Cargando…
Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition
Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individ...
Autores principales: | Ding, Renjie, Li, Xue, Nie, Lanshun, Li, Jiazhen, Si, Xiandong, Chu, Dianhui, Liu, Guozhong, Zhan, Dechen |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6339185/ https://www.ncbi.nlm.nih.gov/pubmed/30586875 http://dx.doi.org/10.3390/s19010057 |
Ejemplares similares
-
Ensembles of Deep Learning Models and Transfer Learning for Ear Recognition
por: Alshazly, Hammam, et al.
Publicado: (2019) -
Transfer learning based cascaded deep learning network and mask recognition for COVID-19
por: Li, Fengyin, et al.
Publicado: (2023) -
Deep Transfer Learning for Ni-Based Superalloys Microstructure Recognition on γ′ Phase
por: Li, Wenyi, et al.
Publicado: (2022) -
Recognition of Rare Microfossils Using Transfer Learning and Deep Residual Networks
por: Wang, Bin, et al.
Publicado: (2022) -
Transfer Learning for Toxoplasma gondii Recognition
por: Li, Sen, et al.
Publicado: (2020)