Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164234
Title: Semantic-discriminative mixup for generalizable sensor-based cross-domain activity recognition
Authors: Lu, Wang
Wang, Jindong
Chen, Yiqiang
Pan, Sinno Jialin
Hu, Chunyu
Qin, Xin
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Lu, W., Wang, J., Chen, Y., Pan, S. J., Hu, C. & Qin, X. (2022). Semantic-discriminative mixup for generalizable sensor-based cross-domain activity recognition. Proceedings of the ACM On Interactive, Mobile, Wearable and Ubiquitous Technologies, 6(2), 65:1-65:19. https://dx.doi.org/10.1145/3534589
Journal: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Abstract: It is expensive and time-consuming to collect sufficient labeled data to build human activity recognition (HAR) models. Training on existing data often makes the model biased towards the distribution of the training data, thus the model might perform terribly on test data with different distributions. Although existing efforts on transfer learning and domain adaptation try to solve the above problem, they still need access to unlabeled data on the target domain, which may not be possible in real scenarios. Few works pay attention to training a model that can generalize well to unseen target domains for HAR. In this paper, we propose a novel method called Semantic-Discriminative Mixup (SDMix) for generalizable cross-domain HAR. Firstly, we introduce semantic-Aware Mixup that considers the activity semantic ranges to overcome the semantic inconsistency brought by domain differences. Secondly, we introduce the large margin loss to enhance the discrimination of Mixup to prevent misclassification brought by noisy virtual labels. Comprehensive generalization experiments on five public datasets demonstrate that our SDMix substantially outperforms the state-of-The-Art approaches with 6% average accuracy improvement on cross-person, cross-dataset, and cross-position HAR.
URI: https://hdl.handle.net/10356/164234
ISSN: 2474-9567
DOI: 10.1145/3534589
Schools: School of Computer Science and Engineering 
Rights: © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 50

8
Updated on Feb 21, 2024

Web of ScienceTM
Citations 50

2
Updated on Oct 24, 2023

Page view(s)

71
Updated on Feb 24, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.