Generalizing to unseen domains: A survey on domain generalization

J Wang, C Lan, C Liu, Y Ouyang, T Qin… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Fedclip: Fast generalization and personalization for clip in federated learning

W Lu, X Hu, J Wang, X Xie - arXiv preprint arXiv:2302.13485, 2023 - arxiv.org
Federated learning (FL) has emerged as a new paradigm for privacy-preserving
computation in recent years. Unfortunately, FL faces two critical challenges that hinder its …

Metafed: Federated learning among federations with cyclic knowledge distillation for personalized healthcare

Y Chen, W Lu, X Qin, J Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Federated learning (FL) has attracted increasing attention to building models without
accessing raw user data, especially in healthcare. In real applications, different federations …

Personalized federated learning with adaptive batchnorm for healthcare

W Lu, J Wang, Y Chen, X Qin, R Xu… - … Transactions on Big …, 2022 - ieeexplore.ieee.org
There is a growing interest in applying machine learning techniques to healthcare. Recently,
federated machine learning (FL) is gaining popularity since it allows researchers to train …

Generalizable low-resource activity recognition with diverse and discriminative representation learning

X Qin, J Wang, S Ma, W Lu, Y Zhu, X Xie… - Proceedings of the 29th …, 2023 - dl.acm.org
Human activity recognition (HAR) is a time series classification task that focuses on
identifying the motion patterns from human sensor readings. Adequate data is essential but …

Machine Learning Techniques for Sensor-based Human Activity Recognition with Data Heterogeneity--A Review

X Ye, K Sakurai, N Nair, KIK Wang - arXiv preprint arXiv:2403.15422, 2024 - arxiv.org
Sensor-based Human Activity Recognition (HAR) is crucial in ubiquitous computing,
analysing behaviours through multi-dimensional observations. Despite research progress …

Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition

S Wang, J Wang, H Xi, B Zhang, L Zhang… - Proceedings of the ACM …, 2024 - dl.acm.org
Human Activity Recognition (HAR) models often suffer from performance degradation in real-
world applications due to distribution shifts in activity patterns across individuals. Test-Time …

Cross-person activity recognition method using snapshot ensemble learning

S Xu, Z He, W Shi, Y Wang, T Ohtsuki… - 2022 IEEE 96th …, 2022 - ieeexplore.ieee.org
Human activity recognition (HAR) is one of the most promising technologies in the smart
home, especially radio frequency (RF-based) method, which has the advantages of low cost …

[HTML][HTML] Non-Contact Cross-Person Activity Recognition by Deep Metric Ensemble Learning

C Ye, S Xu, Z He, Y Yin, T Ohtsuki, G Gui - Bioengineering, 2024 - mdpi.com
In elderly monitoring or indoor intrusion detection, the recognition of human activity is a key
task. Owing to several strengths of Wi-Fi-based devices, including their non-contact and …

STFNet: Enhanced and Lightweight Spatiotemporal Fusion Network for Wearable Human Activity Recognition

H Zou, Z Chen, C Zhang, A Yuan, B Wang… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
Human activity recognition using sensor data has become a research hotspot in the field of
ubiquitous computing and has a wide range of application scenarios in real life. Effectively …