Fully Connected Generative Adversarial Network for Human Activity Recognition

Fully Connected Generative Adversarial Network for Human Activity Recognition

Conditional Generative Adversarial Networks (CGAN) have shown great promise in generating synthetic data for sensor-based activity recognition. However, one key issue concerning existing CGAN is the design of the network architecture that affects sample quality. This study proposes an effective CGAN...

Full description

Bibliographic Details
Main Authors: Ali Olow Jimale, Mohd Halim Mohd Noor
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Activity recognition
deep learning
generative adversarial network
Online Access:https://ieeexplore.ieee.org/document/9893100/

Internet

https://ieeexplore.ieee.org/document/9893100/

Similar Items