Transformer-based models to deal with heterogeneous environments in Human Activity Recognition

Ek, Sannara; Portet, François; Lalanda, Philippe

doi:10.1007/s00779-023-01776-3

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article3

Other1

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Fish feeding behavior recognition using time-domain and frequency-domain signals fusion from six-axis inertial sensors

Ma,

Yang,

et al. 2024

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Fish feeding behavior recognition using time-domain and frequency-domain signals fusion from six-axis inertial sensors

Ma,

Yang,

et al. 2024

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

DNN Model Comparison for Sensor Location Robustness

Enokibori,

Sato,

Mase

2024

Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing

View full text Add to dashboard Cite

rTsfNet: A DNN Model with Multi-head 3D Rotation and Time Series Feature Extraction for IMU-based Human Activity Recognition

Enokibori

2024

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Many deep learning (DL) models have been proposed for the IMU (inertial measurement unit) based HAR (human activity recognition) domain. However, combinations of manually designed time series features (TSFs) and traditional machine learning (ML) often continue to perform well. It is not rare that combinations among TSFs and DL show better performance than the DL-only approaches. Those facts mean that TSFs have the potential to outperform automatically generated features using deep neural networks (DNNs). However, TSFs have a problem: their performances are only good if appropriate 3D bases are selected. Fortunately, DL's strengths include capturing the features of input data and adaptively deriving parameters automatically. Thus, as a new DNN model for an IMU-based HAR, this paper proposes rTsfNet, a DNN model with Multi-head 3D Rotation and Time Series Feature Extraction. rTsfNet automatically selects multiple 3D bases from which features should be derived by extracting 3D rotation parameters within the DNN. Then, TSFs are derived to achieve HAR results using multilayer perceptrons (MLPs). With this combination, rTsfNet showed higher performance than existing models under well-managed benchmark conditions and multiple datasets: UCI HAR, PAMAP2, Daphnet, and OPPORTUNITY, all of which target different activities.

show abstract

Transformer-based models to deal with heterogeneous environments in Human Activity Recognition

Cited by 4 publications

References 26 publications

Fish feeding behavior recognition using time-domain and frequency-domain signals fusion from six-axis inertial sensors

Fish feeding behavior recognition using time-domain and frequency-domain signals fusion from six-axis inertial sensors

DNN Model Comparison for Sensor Location Robustness

rTsfNet: A DNN Model with Multi-head 3D Rotation and Time Series Feature Extraction for IMU-based Human Activity Recognition

Contact Info

Product

Resources

About