Human activity recognition plays an increasingly important role not only in our daily lives, but also in the medical and rehabilitation fields. The development of deep learning has also contributed to the advancement of human activity recognition, but the large amount of data annotation work required to train deep learning models is a major obstacle to the development of human activity recognition. Contrastive learning has started to be used in the field of sensor-based human activity recognition due to its ability to avoid the cost of labeling large datasets and its ability to better distinguish between sample representations of different instances. Among them, data augmentation, an important part of contrast learning, has a significant impact on model effectiveness, but current data augmentation methods do not perform too successfully in contrast learning frameworks for wearable sensor-based activity recognition. To optimize the effect of contrast learning models, in this paper, we investigate the sampling frequency of sensors and propose a resampling data augmentation method. In addition, we also propose a contrast learning framework based on human activity recognition and apply the resampling augmentation method to the data augmentation phase of contrast learning. The experimental results show that the resampling augmentation method outperforms supervised learning by 9.88% on UCI HAR and 7.69% on Motion Sensor in the fine-tuning evaluation of contrast learning with a small amount of labeled data, and also reveal that not all data augmentation methods will have positive effects in the contrast learning framework. Finally, we explored the influence of the combination of different augmentation methods on contrastive learning, and the experimental results showed that the effect of most combination augmentation methods was better than that of single augmentation.
تحميل البحث