期刊
SENSORS
卷 21, 期 22, 页码 -出版社
MDPI
DOI: 10.3390/s21227628
关键词
balance assessment; data augmentation; gated recurrent unit; human activity recognition; inertial measurement unit; one-dimensional convolutional neural network
资金
- INHA UNIVERSITY Research Grant
- National Research Foundation of Korea [NRF-2020R1A2C2004624]
This study utilized wearable technology and deep learning algorithms to improve the evaluation performance of the Berg Balance Scale, finding the optimal model combination through testing different structures.
In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据