Improving Resource Efficiency of Deep Activity Recognition via Redundancy Reduction

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

Abstrakti

Compression methods for deep learning have been recently used to port deep neural networks into resource-constrained devices - such as digital gloves and smartwatches - for human activity recognition (HAR). While the results have been in favor of utilizing compressed models, we envision that the current paradigm of long and fixed-size overlapping sliding windows that permeate the literature of HAR contributes negatively toward the goal of more resource-efficient systems, as it induces redundancies in memory and computation. In this work, we provide a different perspective by demonstrating that memory footprint, computational expense, and possibly energy consumption can be dramatically spared by modifying the architecture of the neural networks and their training. It is achieved by enabling non-overlapping short sliding windows and skipping fine-grained features in favor of rough ones on certain occasions, thus reducing the demand for more powerful hardware. Compared with the state-of-the-art, our method is able to achieve comparable performance far more efficiently in terms of resource use.
AlkuperäiskieliEnglanti
OtsikkoHotMobile 2020 - Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications3 March 2020
KustantajaACM
Sivut33-38
Sivumäärä6
ISBN (elektroninen)9781450371162
DOI - pysyväislinkit
TilaJulkaistu - 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Workshop on Mobile Computing Systems and Applications - Austin, Yhdysvallat
Kesto: 3 maaliskuuta 20204 maaliskuuta 2020
Konferenssinumero: 21
http://www.hotmobile.org/2020/

Workshop

WorkshopInternational Workshop on Mobile Computing Systems and Applications
LyhennettäHotMobile
MaaYhdysvallat
KaupunkiAustin
Ajanjakso03/03/202004/03/2020
www-osoite

Sormenjälki Sukella tutkimusaiheisiin 'Improving Resource Efficiency of Deep Activity Recognition via Redundancy Reduction'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Projektit

    DEBARE: Deep-learning Based Activity Recognition on the Edge

    Xiao, Y., Parviainen, A., Pouta, E. & Guridi Sotomayor, S.

    20/05/201931/12/2020

    Projekti: EU: Framework programmes funding

    CEAMA: CEAMA Cognitive Engine for Assembly and Maintenance Automation

    Xiao, Y., Lee, J., Byvshev, P., Pham, T., Nyman, P., Souza Leite, C., Pouta, E. & Wirtanen, S.

    01/08/201830/06/2020

    Projekti: Business Finland: New business from research ideas (TUTLI)

    Siteeraa tätä

    Souza Leite, C., & Xiao, Y. (2020). Improving Resource Efficiency of Deep Activity Recognition via Redundancy Reduction. teoksessa HotMobile 2020 - Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications3 March 2020 (Sivut 33-38). ACM. https://doi.org/10.1145/3376897.3377859