Weakly-supervised sensor-based activity segmentation and recognition via learning from distributions
Sensor-based activity recognition aims to recognize users' activities from multi-dimensional streams of sensor readings received from ubiquitous sensors. It has been shown that data segmentation and feature extraction are two crucial steps in developing machine learning-based models for sensor-...
Saved in:
Main Authors: | Qian, Hangwei, Pan, Sinno Jialin, Miao, Chunyan |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/159353 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Sensor-based activity recognition via learning from distributions
by: Qian, Hangwei, et al.
Published: (2018) -
Distribution-based semi-supervised learning for activity recognition
by: Qian, Hangwei, et al.
Published: (2019) -
A novel distribution-embedded neural network for sensor-based activity recognition
by: Qian, Hangwei, et al.
Published: (2020) -
Latent independent excitation for generalizable sensor-based cross-person activity recognition
by: Qian, Hangwei, et al.
Published: (2021) -
Weakly-supervised cross-domain road scene segmentation via multi-level curriculum adaptation
by: Lv, Fengmao, et al.
Published: (2022)