What is it about?
Human Activity Recognition (HAR) is the most popular research area in the pervasive computing field in recent years. Sensor data plays a vital role in identifying several human actions. Deep CNN requires huge datasets and models which increases the computational complexity. In this paper, we have proposed the idea of transforming the raw accelerometer and gyroscope sensor data into the visual domain by using our novel activity image creation method (NAICM). Pre-trained CNN (AlexNet) has been used on the converted image domain information.
Featured Image
Photo by Jorge Ramirez on Unsplash
Why is it important?
We have proposed a novel activity image creation method (NAICM) to transform IMU sensor data into an image to make it compatible to use with transfer learning.
Perspectives
Read the Original
This page is a summary of: Deep transfer learning based human activity recognition by transforming IMU data to image domain using novel activity image creation method, Journal of Intelligent & Fuzzy Systems, July 2022, IOS Press,
DOI: 10.3233/jifs-213174.
You can read the full text:
Contributors
The following have contributed to this page