Page 86 - Read Online

Shu et al. Intell Robot 2024;4(1):74-86 Intelligence & Robotics
DOI: 10.20517/ir.2024.05

Research Article Open Access

A small-sample time-series signal augmentation and

analysis method for quantitative assessment of bradyki-
nesia in Parkinson’s disease

5
5
5
Zhilin Shu 1,2 , Peipei Liu 3,4 , Yuanyuan Cheng , Jinrui Liu 1,2 , Yuxin Feng 1,2 , Zhizhong Zhu , Yang Yu , Jianda
Han 1,2,6 , Jialing Wu 3,4 , Ningbo Yu 1,2,6
1 College of Artificial Intelligence, Nankai University, Tianjin 300350, China.
2 Engineering Research Center of Trusted Behavior Intelligence, Ministry of Education, Nankai University, Tianjin 300350, China .
3 Department of Neurology, Tianjin Huanhu Hospital, Tianjin 300350, China.
4 Tianjin Key Laboratory of Cerebral Vascular and Neurodegenerative Diseases, Tianjin Neurosurgical Institute, Tianjin 300350,
China.
5 Department of Rehabilitation Medicine, Tianjin Huanhu Hospital, Tianjin 300350, China.
6 Institute of Intelligence Technology and Robotic Systems, Shenzhen Research Institute of Nankai University, Shenzhen 518083,
Guangdong, China.

Correspondence to: Prof. Jianda Han, Prof. Ningbo Yu, College of Artificial Intelligence, Nankai University, 38 Tongyan Road, Jinnan
District, Tianjin 300350, China. E-mail: hanjianda@nankai.edu.cn; nyu@nankai.edu.cn; Dr. Jialing Wu, Department of Neurology,
Tianjin Huanhu Hospital, 6 Jizhao Road, Jinnan District, Tianjin 300350, China. E-mail: wywjl2009@hotmail.com

How to cite this article: Shu Z, Liu P, Cheng Y, Liu J, Feng Y, Zhu Z, Yu Y, Han J, Wu J, Yu N. A small-sample time-series signal
augmentation and analysis method for quantitative assessment of bradykinesia in Parkinson’s disease. Intell Robot 2024;4(1):74-
86. http://dx.doi.org/10.20517/ir.2024.05

Received: 30 Nov 2023 First Decision: 24 Jan 2024 Revised: 20 Feb 2024 Accepted: 4 Mar 2024 Published: 11 Mar 2024
Academic Editor: Simon X. Yang Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract

Patients with Parkinson’s disease (PD) usually have varying degrees of bradykinesia, and the current clinical assess-
ment is mainly based on the Movement Disorder Society Unified PD Rating Scale, which can hardly meet the needs
of objectivity and accuracy. Therefore, this paper proposed a small-sample time series classification method (DTW-
TapNet) based on dynamic time warping (DTW) data augmentation and attentional prototype network. Firstly, for
the problem of small sample sizes of clinical data, a DTW-based data merge method is used to achieve data augmen-
tation. Then, the time series are dimensionally reorganized using random grouping, and convolutional operations are
performed to learn features from multivariate time series. Further, attention mechanism and prototype learning are in-
troduced to optimize the distance of the class prototype to which each time series belongs to train a low-dimensional
feature representation of the time series, thus reducing the dependency on data volume. Clinical experiments were
conducted to collect motion capture data of upper and lower limb movements from 36 patients with PD and eight
healthy controls. For the upper limb movement data, the proposed method improved the classification accuracy,

© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, shar-
ing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you
give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate
if changes were made.

www.oaepublish.com/ir