No clue how this will help towards 100% recovery. To me all assessment research is useless since there is never any followup that solves the problems that the assessment points out.
A GMAF is a novel technique to encode time series data into images, it employs the polar-coordinates representation of the data written in a matrix form called the Gramian matrix where each element is either the summation (GASF) of the cosines of the angles or difference (GADF).
Improving the activity recognition using GMAF and transfer learning in post-stroke rehabilitation assessment
Issam Boukhennoufa, Xiaojun Zhai*,Klaus D. McDonald-Maier
School of Computer Science and Electronic Engineering
University of Essex
Colchester, United Kingdom
xzhai@essex.ac.uk
Victor Utti, Jo Jackson
School of Sport, Rehabilitation and Exercise Sciences
University of Essex
Colchester, United Kingdom
School of Computer Science and Electronic Engineering
University of Essex
Colchester, United Kingdom
xzhai@essex.ac.uk
Victor Utti, Jo Jackson
School of Sport, Rehabilitation and Exercise Sciences
University of Essex
Colchester, United Kingdom
Abstract
—An important part of developing a performant
assessment algorithm for post-stroke rehabilitation is to achieve
a high-precision activity recognition. Convolutional Neural Networks (CNN) are known to give very accurate results, however
they require the data to be of a specific structure that differs
from the sequential time-series format typically collected from
wearable sensors. In this paper, we describe models to improve
the activity recognition using the CNN classifier. At first by
modifying the Gramian angular field algorithm by encoding all
the sensors’ channels from a single time window into a single
2D image allows to map the maximum activity characteristics.
Feeding the resulting images to a simple 1D CNN classifier
improves the accuracy of the test data from 94% for the
traditional segmentation approach to 97.06%. Subsequently, we
convert the 2D images into the RGB format and use a 2D CNN
classifier. This results in increasing the test data accuracy to
97.52%. Finally, we employ transfer learning with the popular
VGG 16 model to the RGB images, which yields to improving
the accuracy further more to reach 98.53%.
Index Terms—Stroke, GMAF, CNN, Activity recognition,
Transfer learning.
assessment algorithm for post-stroke rehabilitation is to achieve
a high-precision activity recognition. Convolutional Neural Networks (CNN) are known to give very accurate results, however
they require the data to be of a specific structure that differs
from the sequential time-series format typically collected from
wearable sensors. In this paper, we describe models to improve
the activity recognition using the CNN classifier. At first by
modifying the Gramian angular field algorithm by encoding all
the sensors’ channels from a single time window into a single
2D image allows to map the maximum activity characteristics.
Feeding the resulting images to a simple 1D CNN classifier
improves the accuracy of the test data from 94% for the
traditional segmentation approach to 97.06%. Subsequently, we
convert the 2D images into the RGB format and use a 2D CNN
classifier. This results in increasing the test data accuracy to
97.52%. Finally, we employ transfer learning with the popular
VGG 16 model to the RGB images, which yields to improving
the accuracy further more to reach 98.53%.
Index Terms—Stroke, GMAF, CNN, Activity recognition,
Transfer learning.
No comments:
Post a Comment