Urban Fietzek

TL;DR: The proposed methods and CNNs are applied to the classification of the motor state of Parkinson’s Disease patients, which is challenging due to small dataset size, noisy labels, and large intra-class variability.

TL;DR: In this article, various data augmentation methods for wearable sensor data are proposed and applied to the classification of the motor state of Parkinson's disease patients, which is challenging due to small dataset size, noisy labels, and large intra-class variability Appropriate augmentation improves the classification performance from 7754% to 8688%

TL;DR: The feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU is demonstrated using a single wrist-worn IMU sensor recording in unscripted environments.

TL;DR: A variety of statistical models to detect the motor state of patients with Parkinson's disease based on sensor data from a wearable device are developed and it is found that deep learning models consistently outperform a classical machine learning model applied on hand-crafted features in this time series classification task.

TL;DR: An automatic PD motor-state assessment in free-living conditions is proposed using an accelerometer in a wrist-worn wearable sensor and an ensemble of convolutional neural networks is applied to capture the large variability of daily-living activities and overcome the dissimilarity between training and test patients due to the inter-patient variability.