Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition

1 Dec 2023  ·  Duc-Anh Nguyen, Cuong Pham, Nhien-An Le-Khac ·

Various types of sensors can be used for Human Activity Recognition (HAR), and each of them has different strengths and weaknesses. Sometimes a single sensor cannot fully observe the user's motions from its perspective, which causes wrong predictions. While sensor fusion provides more information for HAR, it comes with many inherent drawbacks like user privacy and acceptance, costly set-up, operation, and maintenance. To deal with this problem, we propose Virtual Fusion - a new method that takes advantage of unlabeled data from multiple time-synchronized sensors during training, but only needs one sensor for inference. Contrastive learning is adopted to exploit the correlation among sensors. Virtual Fusion gives significantly better accuracy than training with the same single sensor, and in some cases, it even surpasses actual fusion using multiple sensors at test time. We also extend this method to a more general version called Actual Fusion within Virtual Fusion (AFVF), which uses a subset of training sensors during inference. Our method achieves state-of-the-art accuracy and F1-score on UCI-HAR and PAMAP2 benchmark datasets. Implementation is available upon request.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Human Activity Recognition on PAMAP2 (Accuracy metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human Activity Recognition HAR AFVF Accuracy 0.9861 # 1
Macro-F1 0.9865 # 1
Human Activity Recognition PAMAP2 AFVF Accuracy 0.9672 # 1
Macro F1 0.9665 # 1

Methods