Tampere University of Technology

TUTCRIS Research Portal

A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems

Research output: Contribution to journalArticleScientificpeer-review

Standard

A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems. / Said, Ahmed Ben; Al-Sa'D, Mohamed Fathi; Tlili, Mounira; Abdellatif, Alaa Awad; Mohamed, Amr; Elfouly, Tarek; Harras, Khaled; O'Connor, Mark Dennis.

In: IEEE Access, Vol. 6, 05.06.2018, p. 33727-33739.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Said, AB, Al-Sa'D, MF, Tlili, M, Abdellatif, AA, Mohamed, A, Elfouly, T, Harras, K & O'Connor, MD 2018, 'A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems', IEEE Access, vol. 6, pp. 33727-33739. https://doi.org/10.1109/ACCESS.2018.2844308

APA

Said, A. B., Al-Sa'D, M. F., Tlili, M., Abdellatif, A. A., Mohamed, A., Elfouly, T., ... O'Connor, M. D. (2018). A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems. IEEE Access, 6, 33727-33739. https://doi.org/10.1109/ACCESS.2018.2844308

Vancouver

Author

Said, Ahmed Ben ; Al-Sa'D, Mohamed Fathi ; Tlili, Mounira ; Abdellatif, Alaa Awad ; Mohamed, Amr ; Elfouly, Tarek ; Harras, Khaled ; O'Connor, Mark Dennis. / A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems. In: IEEE Access. 2018 ; Vol. 6. pp. 33727-33739.

Bibtex - Download

@article{1ab64d707c3644b69c63763d3700b903,
title = "A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems",
abstract = "Due to the increasing number of chronic disease patients, continuous health monitoring has become the top priority for health-care providers and has posed a major stimulus for the development of scalable and energy efficient mobile health systems. Collected data in such systems are highly critical and can be affected by wireless network conditions, which in return, motivates the need for a preprocessing stage that optimizes data delivery in an adaptive manner with respect to network dynamics. We present in this paper adaptive single and multiple modality data compression schemes based on deep learning approach, which consider acquired data characteristics and network dynamics for providing energy efficient data delivery. Results indicate that: 1) the proposed adaptive single modality compression scheme outperforms conventional compression methods by 13.24{\%} and 43.75{\%} reductions in distortion and processing time, respectively; 2) the proposed adaptive multiple modality compression further decreases the distortion by 3.71{\%} and 72.37{\%} when compared with the proposed single modality scheme and conventional methods through leveraging inter-modality correlations; and 3) adaptive multiple modality compression demonstrates its efficiency in terms of energy consumption, computational complexity, and responding to different network states. Hence, our approach is suitable for mobile health applications (mHealth), where the smart preprocessing of vital signs can enhance energy consumption, reduce storage, and cut down transmission delays to the mHealth cloud.",
keywords = "compression, cross-layer optimization, deep learning, multiple modality data, WBASN",
author = "Said, {Ahmed Ben} and Al-Sa'D, {Mohamed Fathi} and Mounira Tlili and Abdellatif, {Alaa Awad} and Amr Mohamed and Tarek Elfouly and Khaled Harras and O'Connor, {Mark Dennis}",
year = "2018",
month = "6",
day = "5",
doi = "10.1109/ACCESS.2018.2844308",
language = "English",
volume = "6",
pages = "33727--33739",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A Deep Learning Approach for Vital Signs Compression and Energy Efficient Delivery in mhealth Systems

AU - Said, Ahmed Ben

AU - Al-Sa'D, Mohamed Fathi

AU - Tlili, Mounira

AU - Abdellatif, Alaa Awad

AU - Mohamed, Amr

AU - Elfouly, Tarek

AU - Harras, Khaled

AU - O'Connor, Mark Dennis

PY - 2018/6/5

Y1 - 2018/6/5

N2 - Due to the increasing number of chronic disease patients, continuous health monitoring has become the top priority for health-care providers and has posed a major stimulus for the development of scalable and energy efficient mobile health systems. Collected data in such systems are highly critical and can be affected by wireless network conditions, which in return, motivates the need for a preprocessing stage that optimizes data delivery in an adaptive manner with respect to network dynamics. We present in this paper adaptive single and multiple modality data compression schemes based on deep learning approach, which consider acquired data characteristics and network dynamics for providing energy efficient data delivery. Results indicate that: 1) the proposed adaptive single modality compression scheme outperforms conventional compression methods by 13.24% and 43.75% reductions in distortion and processing time, respectively; 2) the proposed adaptive multiple modality compression further decreases the distortion by 3.71% and 72.37% when compared with the proposed single modality scheme and conventional methods through leveraging inter-modality correlations; and 3) adaptive multiple modality compression demonstrates its efficiency in terms of energy consumption, computational complexity, and responding to different network states. Hence, our approach is suitable for mobile health applications (mHealth), where the smart preprocessing of vital signs can enhance energy consumption, reduce storage, and cut down transmission delays to the mHealth cloud.

AB - Due to the increasing number of chronic disease patients, continuous health monitoring has become the top priority for health-care providers and has posed a major stimulus for the development of scalable and energy efficient mobile health systems. Collected data in such systems are highly critical and can be affected by wireless network conditions, which in return, motivates the need for a preprocessing stage that optimizes data delivery in an adaptive manner with respect to network dynamics. We present in this paper adaptive single and multiple modality data compression schemes based on deep learning approach, which consider acquired data characteristics and network dynamics for providing energy efficient data delivery. Results indicate that: 1) the proposed adaptive single modality compression scheme outperforms conventional compression methods by 13.24% and 43.75% reductions in distortion and processing time, respectively; 2) the proposed adaptive multiple modality compression further decreases the distortion by 3.71% and 72.37% when compared with the proposed single modality scheme and conventional methods through leveraging inter-modality correlations; and 3) adaptive multiple modality compression demonstrates its efficiency in terms of energy consumption, computational complexity, and responding to different network states. Hence, our approach is suitable for mobile health applications (mHealth), where the smart preprocessing of vital signs can enhance energy consumption, reduce storage, and cut down transmission delays to the mHealth cloud.

KW - compression

KW - cross-layer optimization

KW - deep learning

KW - multiple modality data

KW - WBASN

U2 - 10.1109/ACCESS.2018.2844308

DO - 10.1109/ACCESS.2018.2844308

M3 - Article

VL - 6

SP - 33727

EP - 33739

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -