Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks

Abstract

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\%.

ICMI2017 (oral session)

Cited by in corpus (26)

• Data Augmentation techniques in time series domain: A survey and taxonomy
• Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data
• SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
• SleepPoseNet: Multi-View Learning for Sleep Postural Transition Recognition Using UWB
• Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and Challenges
• A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network
• IMU Based Deep Stride Length Estimation With Self-Supervised Learning
• Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
• Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks
• ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition
• A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning
• Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition
• MLGaze: Machine Learning-Based Analysis of Gaze Error Patterns in Consumer Eye Tracking Systems
• Data augmentation on-the-fly and active learning in data stream classification
• Transportation mode recognition based on low-rate acceleration and location signals with an attention-based multiple-instance learning network
• Data Augmentation Methods of Dynamic Model Identification for Harbor Maneuvers using Feedforward Neural Network
• Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments
• Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
• SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach
• Estimating Motor Symptom Presence and Severity in Parkinson's Disease from Wrist Accelerometer Time Series using ROCKET and InceptionTime
• Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial Networks
• Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
• On Neural Inertial Classification Networks for Pedestrian Activity Recognition
• Graph Structure Based Data Augmentation Method
• Deep Learning-Based Detection of Cognitive Impairment from Passive Smartphone Sensing with Routine-Aware Augmentation and Demographic Personalization