Improving Cross-Subject Activity Recognition via Adversarial Learning
Authors:
- Clayton Frederick Souza LeiteCLClayton Frederick Souza Leite
- Yu XiaoYXYu Xiao
Open Access
- 11 May 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 90542-90554
Abstract
Deep learning has been widely used for implementing human activity recognition from wearable sensors like inertial measurement units. The performance of deep activity recognition is heavily affected by the amount and variability of the labeled data available for training the deep learning models. On the other hand, it is costly and time-consuming to collect and label data. Given limited training data, it is hard to maintain high performance across a wide range of subjects, due to the differences in the underlying data distribution of the training and the testing sets. In this work, we develop a novel solution that applies adversarial learning to improve cross-subject performance by generating training data that mimic artificial subjects - i.e. through data augmentation - and enforcing the activity classifier to ignore subject-dependent information. Contrary to domain adaptation methods, our solution does not utilize any data from subjects of the test set (or target domain). Furthermore, our solution is versatile as it can be utilized together with any deep neural network as the classifier. Considering the open dataset PAMAP2, nearly 10% higher crosssubject performance in terms of F1-score can be achieved when training a CNN-LSTM-based classifier with our solution. A performance gain of 5% is also observed when our solution is applied to a state-of-the-art HAR classifier composed of a combination of inception neural network and recurrent neural network. We also investigate different influencing factors of classification performance (i.e. selection of sensor modalities, sampling rates and the number of subjects in the training data), and summarize a practical guideline for implementing deep learning solutions for sensor-based human activity recognition.Keywords
Funding Information
- Business Finland (1660/31/2018)
- European Union’s Horizon 2020 Research and Innovation Programme (777222)
This publication has 34 references indexed in Scilit:
- A Comprehensive Survey on Domain Adaptation for Visual Applications2017
- Recognition of multiple overlapping activities using compositional CNN-LSTM model2017
- CNN-based sensor fusion techniques for multimodal human activity recognition2017
- Ensembles of Deep LSTM Learners for Activity Recognition using WearablesProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017
- Device-Free Human Activity Recognition Using Commercial WiFi DevicesIEEE Journal on Selected Areas in Communications, 2017
- Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity RecognitionSensors, 2016
- A recognition method for combined activities with accelerometers2014
- The Opportunity challenge: A benchmark database for on-body sensor-based activity recognitionPattern Recognition Letters, 2013
- Introducing a New Benchmarked Dataset for Activity Monitoring2012
- Wearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait SymptomIEEE Transactions on Information Technology in Biomedicine, 2009