RT Conference Proceedings
T1 Adaptive compressed sensing at the fingertip of Internet-of-Things sensors: An ultra-low power activity recognition
A1 Fallahzadeh, Ramin
A1 Pagán Ortiz, Josué
A1 Ghasemzadeh, Hassan
AB With the proliferation of wearable devices in the Internet-of-Things applications, designing highly power-efficient solutions for continuous operation of these technologies in life-critical settings emerges. We propose a novel ultra-low power framework for adaptive compressed sensing in activity recognition. The proposed design uses a coarse-grained activity recognition module to adaptively tune the compressed sensing module for minimized sensing/transmission costs. We pose an optimization problem to minimize activity-specific sensing rates and introduce a polynomial time approximation algorithm using a novel heuristic dynamic optimization tree. Our evaluations on real-world data shows that the proposed autonomous framework is capable of generating feedback with -80% confidence and improves power reduction performance of the state-of-the-art approach by a factor of two.
YR 2017
FD 2017
LK https://hdl.handle.net/20.500.14352/94862
UL https://hdl.handle.net/20.500.14352/94862
LA eng
NO R. Fallahzadeh, J. P. Ortiz and H. Ghasemzadeh, "Adaptive compressed sensing at the fingertip of Internet-of-Things sensors: An ultra-low power activity recognition," Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017, Lausanne, Switzerland, 2017, pp. 996-1001, doi: 10.23919/DATE.2017.7927136.
DS Docta Complutense
RD 13 abr 2025