KIT | KIT-Bibliothek | Impressum | Datenschutz

TinyHAR: A Lightweight Deep Learning Model Designed for Human Activity Recognition

Zhou, Yexu 1; Zhao, Haibin ORCID iD icon 1; Huang, Yiran ORCID iD icon 1; Hefenbrock, Michael 1; Riedel, Till ORCID iD icon 1; Beigl, Michael 1
1 Institut für Telematik (TM), Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

Deep learning models have shown excellent performance in human activity recognition tasks. However, these models typically require large amounts of computational resources, which makes them inefficient to deploy on edge devices. Furthermore, the superior performance of deep learning models relies heavily on the availability of large datasets to avoid over-fitting. However, the expensive efforts for labeling limits the amount of datasets. We address both challenges by designing a more lightweight model, called TinyHAR. TinyHAR is designed specifically for human activity recognition employing different saliency of multi modalities, multimodal collaboration, and temporal information extraction. Initial experimental results show that TinyHAR is several times smaller and often meets or even surpasses the performance of DeepConvLSTM, a state-of-the-art human activity recognition model.

Postprint §
DOI: 10.5445/IR/1000150216/post
Veröffentlicht am 12.09.2023
Preprint §
DOI: 10.5445/IR/1000150216
Veröffentlicht am 05.09.2022
DOI: 10.1145/3544794.3558467
Zitationen: 7
Zitationen: 10
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Telematik (TM)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 11.09.2022
Sprache Englisch
Identifikator ISBN: 978-1-4503-9424-6
KITopen-ID: 1000150216
Erschienen in International Symposium on Wearable Computers (ISWC'22) , Atlanta, GA and Cambridge, UK, September 11-15, 2022
Veranstaltung International Symposium on Wearable Computers (ISWC 2022), Cambridge, Vereinigtes Königreich, 11.09.2022 – 15.09.2022
Verlag Association for Computing Machinery (ACM)
Seiten 89-93
Projektinformation JuBot (ZEISS-STFG, JuBot)
CC-KING (WM_BW, 3-4332.62-FhG/38)
SDI-C (BMBF, 01IS19030A)
Schlagwörter human activity recognition, time series processing, lightweight deep learning model
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page