Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks

By T. T. Um, F. Pfister, Daniel Pichler, S. Endo, Muriel Lang, Sandra Hirche, U. Fietzek, Dana Kulic. International Conference on Multimodal Interaction, 2017

844 citations recorded by the source corpus.

While convolutional neural networks (CNNs) have been successfully applied to many challenging classification applications, they typically require large datasets for training. When the availability of labeled data is limited, data augmentation is a critical preprocessing step for CNNs. However, data augmentation for wearable sensor data has not been deeply investigated yet. In this paper, various data augmentation methods for wearable sensor data are proposed. 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. Appropriate augmentation improves the classification performance from 77.54% to 86.88%.

Subfields: Biomedical Engineering, Neurology

View Paper: https://www.semanticscholar.org/paper/b41de530f4e44926eb4d54f61403011a6d8b3e41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

Citations in the corpus

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security (2018, background): “The key challenge in data augmentation is producing new data samples that preserve the appropriate data distribution for each class, normally necessitating domain knowledge [192, 261].”
Multi-task Self-Supervised Learning for Human Activity Detection (2019, methodology): “In [67] task-specific transformations (such as added noise and rotation) are applied to wearable sensor data to augment and improve the performance of Parkinson’s disease monitoring systems.”
An empirical survey of data augmentation for time series classification with neural networks (2020, methodology): “3) Time Domain Transformations: Similar to Rotation, Permutation had severe detrimental effects on accuracy.”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “In general, using the dataset augmented with synthetic training samples yields higher classification accuracy when compared to using the original dataset [36,56,261,262].”
Time Series Data Augmentation for Deep Learning: A Survey (2020, methodology): “The experiments in [ Um et al. , 2017 ] show that the combination of three basic time-domain methods (permutation, rotation, and time warping) is better than that of a single method and achieves the best performance in time series classiﬁcation.”
Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “This technique was used in [70] where the data was captured from a wearable device to detect if a patient suffers from Parkinson’s disease.”