Toward ultra-low-power remote health monitoring: An optimal and adaptive compressed sensing framework for activity recognition

Pagán Ortiz, Josué and Fallahzadeh, Ramin and Pedram, Mahdi and Risco Martín, José Luis and Moya Fernández, José Manuel and Ayala Rodrigo, José Luis and Ghasemzadeh, Hassan (2019). Toward ultra-low-power remote health monitoring: An optimal and adaptive compressed sensing framework for activity recognition. "IEEE Transactions on mobile computing", v. 18 (n. 3); pp. 658-673. ISSN 1536-1233. https://doi.org/10.1109/TMC.2018.2843373.

Description

Title: Toward ultra-low-power remote health monitoring: An optimal and adaptive compressed sensing framework for activity recognition
Author/s:
  • Pagán Ortiz, Josué
  • Fallahzadeh, Ramin
  • Pedram, Mahdi
  • Risco Martín, José Luis
  • Moya Fernández, José Manuel
  • Ayala Rodrigo, José Luis
  • Ghasemzadeh, Hassan
Item Type: Article
Journal/Publication Title: IEEE Transactions on mobile computing
Date: March 2019
ISSN: 1536-1233
Volume: 18
Subjects:
Freetext Keywords: Compressed sensing; activity recognition; feature selection; energy efficiency; ultra-low power; optimization; adaptive
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (6MB) | Preview

Abstract

Activity recognition, as an important component of behavioral monitoring and intervention, has attracted enormous attention, especially in Mobile Cloud Computing (MCC) and Remote Health Monitoring (RHM) paradigms. While recently resource constrained wearable devices have been gaining popularity, their battery life is limited and constrained by the frequent wireless transmission of data to more computationally powerful back-ends. This paper proposes an ultra-low power activity recognition system using a novel adaptive compressed sensing technique that aims to minimize transmission costs. Coarse-grained on-body sensor localization and unsupervised clustering modules are devised to autonomously reconfigure the compressed sensing module for further power saving. We perform a thorough heuristic optimization using Grammatical Evolution (GE) to ensure minimal computation overhead of the proposed methodology. Our evaluation on a real-world dataset and a low power wearable sensing node demonstrates that our approach can reduce the energy consumption of the wireless data transmission up to 81.2 and 61.5 percent, with up to 60.6 and 35.0 percent overall power savings in comparison with baseline and a naive state-of-the-art approaches, respectively. These solutions lead to an average activity recognition accuracy of 89.0 percent-only 4.8 percent less than the baseline accuracy-while having a negligible energy overhead of on-node computation.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainTIN2015-65277-RCOPHERNICOUnspecifiedEfficient heterogeneous computing: from the processor to the datacenter
Government of SpainTEC2012-33892UnspecifiedUnspecifiedTecnologías HW/SW para la eficiencia energética en sistemas de computación distribuidos

More information

Item ID: 67002
DC Identifier: http://oa.upm.es/67002/
OAI Identifier: oai:oa.upm.es:67002
DOI: 10.1109/TMC.2018.2843373
Official URL: https://ieeexplore.ieee.org/document/8371282
Deposited by: Memoria Investigacion
Deposited on: 18 May 2021 14:21
Last Modified: 18 May 2021 14:21
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM