Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition
Open Access
Abstract
The study of human activity recognition concentrates on classifying human activities and the inference of human behavior using modern sensing technology. However, the issue of domain adaptation for inertial sensing-based human activity recognition (HAR) is still burdensome. The existing requirement of labeled training data for adapting such classifiers to every new person, device, or on-body location is a significant barrier to the widespread adoption of HAR-based applications, making this a challenge of high practical importance. We propose the semi-supervised HAR method to improve reconstruction and generation. It executes proper adaptation with unlabeled data without changes to a pre-trained HAR classifier. Our approach decouples VAE with adversarial learning to ensure robust classifier operation, without newly labeled training data, under changes to the individual activity and the on-body sensor position. Our proposed framework shows the empirical results using the publicly available benchmark dataset compared to state-of-art baselines, achieving competitive improvement for handling new and unlabeled activity. The result demonstrates SAA has achieved a 5% improvement in classification score compared to the existing HAR platform.Keywords
Funding Information
- Basic Science Research Program through the National Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2020R1C1008728)
This publication has 46 references indexed in Scilit:
- Active learning enabled activity recognition2016
- Recognition of Human Activities Using Continuous Autoencoders with Wearable SensorsSensors, 2016
- Two-Layer Hidden Markov Model for Human Activity Recognition in Home EnvironmentsInternational Journal of Distributed Sensor Networks, 2016
- Activity Recognition Using a Single Accelerometer Placed at the Wrist or AnkleMedicine & Science in Sports & Exercise, 2013
- Transfer learning for activity recognition: a surveyKnowledge and Information Systems, 2013
- A Survey on Human Activity Recognition using Wearable SensorsIEEE Communications Surveys & Tutorials, 2012
- Multimodal recognition of reading activity in transit using body-worn sensorsACM Transactions on Applied Perception, 2012
- Domain Transfer Multiple Kernel LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- An activity monitoring system for elderly care using generative and discriminative modelsPersonal and Ubiquitous Computing, 2010
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999