Semantic-discriminative mixup for generalizable sensor-based cross-domain activity recognition

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 distribution...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu, Wang, Wang, Jindong, Chen, Yiqiang, Pan, Sinno Jialin, Hu, Chunyu, Qin, Xin
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/164234
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English