Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models.
Milagros Jaén-VargasKarla Miriam Reyes LeivaFrancisco FernandesSérgio Barroso GonçalvesMiguel Tavares SilvaDaniel Simões LopesJosé Javier Serrano OlmedoPublished in: PeerJ Comput. Sci. (2022)
Keyphrases
- sliding window
- learning models
- human activities
- data streams
- sensor data
- activity recognition
- machine learning
- loss function
- fixed size
- learning algorithm
- semi supervised learning
- learning tasks
- window size
- conditional random fields
- stream data
- machine learning algorithms
- human computer interaction
- classification models
- learning problems
- collaborative filtering
- semi supervised
- information retrieval