Csi-based human activity recognition using multi-input multi-output autoencoder and fine-tuning

HIGHLIGHTS

• who: Mahnaz Chahoushi et al. from the Beheshti University, Tehran , Iran have published the paper: CSI-Based Human Activity Recognition Using Multi-Input Multi-Output Autoencoder and Fine-Tuning, in the Journal: Sensors
• what: The focus of this study is on data reconstruction, with an emphasis on the outcomes of hyperparameter optimization. In this research, to relieve the problem of HAR data gathering, which is a timeconsuming and costly task and may include some privacy invasion, a method based on multi-input multi-output convolutional autoencoder (MIMO-AE) and fine-tuning is proposed, which improves . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.