Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2020 Dec 7;10:21370. doi: 10.1038/s41598-020-78418-8

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2020

Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Visualization of bag instances that receive the highest and lowest attention weights by the proposed model. Figures were drawn using Inkscape v1.0 https://inkscape.org/. (a) View of the tri-axial (x-axis: blue, y-axis:orange, z-axis: green) accelerometer segments corresponding to the two highest (top row) and two lowest (bottom row) attention weights assigned by the model, for a PD subject that exhibits tremor. As we can see, the model assigns larger attention weights ak to the acceleration segments that contain sinusoidal components in the PD tremor frequency band of 3–8Hz (top row) and low weights to segments that lack such patterns (bottom left) or whose frequency content is outside the target frequency band (bottom right). (b) View of the hold and flight time histograms (smoothed for visualization purposes via a kernel-density estimator) corresponding to the two highest (top row) and two lowest (bottom row) attention weights for a PD subject that exhibits FMI. Notice how the model assigns large attention weights to typing sessions in which the hold and flight time distributions are multi-modal and shifted towards regions of slower typing, in contrast to the sessions that receive little attention and in which the distributions are unimodal and located at regions of faster typing.