2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2016
DOI: 10.1109/icassp.2016.7471786
|View full text |Cite
|
Sign up to set email alerts
|

An energy-efficient compressive sensing framework incorporating online dictionary learning for long-term wireless health monitoring

Abstract: Wireless body area network (WBAN) is emerging in the mobile healthcare area to replace the traditional wire-connected monitoring devices. As wireless data transmission dominates power cost of sensor nodes, it is beneficial to reduce the data size without much information loss. Compressive sensing (CS) is a perfect candidate to achieve this goal compared to existing compression techniques. In this paper, we proposed a general framework that utilize CS and online dictionary learning (ODL) together. The learned d… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
6
1
1

Relationship

2
6

Authors

Journals

citations
Cited by 18 publications
(8 citation statements)
references
References 17 publications
0
8
0
Order By: Relevance
“…This technique computes a small number of compressed samples before transmission by linear projection of a sparse or compressible signal with a random sensing matrix. ECG signals, like most biological signals, are not sparse in the time domain, so they can be made sparse like the work done by [20] and authors previous work [21] or using a deterministic or Adaptive Dictionary(AD) to sparsify the signals [22,23]. The wavelet basis or Gaussian dictionaries are examples of deterministic sparsifying matrices.…”
Section: Related Workmentioning
confidence: 99%
“…This technique computes a small number of compressed samples before transmission by linear projection of a sparse or compressible signal with a random sensing matrix. ECG signals, like most biological signals, are not sparse in the time domain, so they can be made sparse like the work done by [20] and authors previous work [21] or using a deterministic or Adaptive Dictionary(AD) to sparsify the signals [22,23]. The wavelet basis or Gaussian dictionaries are examples of deterministic sparsifying matrices.…”
Section: Related Workmentioning
confidence: 99%
“…The proposed design also offloads pre-processing from sensor nodes to the server node, resulting in even significant reductions in hardware costs prior to dictionary learning. Because it is data-driven, the paradigm that has been proposed has the potential to be applied to a broad range of physiological indicators" [50]. In conclusion, based on the literature review, we can infer that much research has been undertaken and/or is currently being conducted in an effort to develop WBSNs that are flexible; reliable; secure; real-time; and energy-efficient, with the goal of using them in healthcare applications.…”
Section: Literature Surveymentioning
confidence: 99%
“…And Morell et al (2016) applied the principal component analysis method to the WSNs data collection process to construct the sparse representation matrix, and at the same time gave a method for updating the sparse representation matrix. Xu et al (2016) proposed a method of using dictionary learning to construct sparse representation bases, which can effectively enhance the sparseness of the converted signal and improve the accuracy of sensor data reconstruction. The dictionary learning form can be expressed as follows: …”
Section: Proposed Algorithmmentioning
confidence: 99%