Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning

Iman Azimi, Janne Takalo-Mattila, Arman Anzanpour, Amir Rahmani, Juha-Pekka Soininen, Pasi Liljeberg

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

4 Citations (Scopus)

Abstract

Remote health monitoring is a powerful tool to provide preventive care and early intervention for populations-at-risk. Such monitoring systems are becoming available nowadays due to recent advancements in Internet-of-Things (IoT) paradigms, enabling ubiquitous monitoring. These systems require a high level of quality in attributes such as availability and accuracy due to patients critical conditions in the monitoring. Deep learning methods are very promising in such health applications to obtain a satisfactory performance, where a considerable amount of data is available. These methods are perfectly positioned in the cloud servers in a centralized cloud-based IoT system. However, the response time and availability of these systems highly depend on the quality of Internet connection. On the other hand, smart gateway devices are unable to implement deep learning methods (such as training models) due to their limited computational capacities. In our previous work, we proposed a hierarchical computing architecture (HiCH), where both edge and cloud computing resources were efficiently exploited, allocating heavy tasks of a conventional machine learning method to the cloud servers and outsourcing the hypothesis function to the edge. Due to this local decision making, the availability of the system was highly improved. In this paper, we investigate the feasibility of deploying the Convolutional Neural Network (CNN) based classification model as an example of deep learning methods in this architecture. Therefore, the system benefits from the features of the HiCH and the CNN, ensuring a high-level availability and accuracy. We demonstrate a real-time health monitoring for a case study on ECG classifications and evaluate the performance of the system in terms of response time and accuracy.
Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/ACM International Conference on Connected Health
Subtitle of host publicationApplications, Systems and Engineering Technologies, CHASE 2018
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages63-68
Number of pages6
ISBN (Electronic)978-1-5386-7206-8
ISBN (Print)978-1-5386-7207-5
Publication statusPublished - 21 Feb 2019
MoE publication typeA4 Article in a conference publication
EventThe Third IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018 - Washington, United States
Duration: 26 Sep 201828 Sep 2018
Conference number: 3

Conference

ConferenceThe Third IEEE/ACM International Conference on Connected Health
Abbreviated titleCHASE 2018
CountryUnited States
CityWashington
Period26/09/1828/09/18

Fingerprint

Availability
Monitoring
Health
Servers
Neural networks
Gateways (computer networks)
Outsourcing
Cloud computing
Electrocardiography
Learning systems
Decision making
Internet of things
Deep learning
Internet

Keywords

  • Internet of Things
  • Hierarchical Computing
  • Electrocardiogram
  • Health Monitoring
  • Deep Learning
  • Convolutional neural networks (CNN)
  • Convolutional Neural Networks

Cite this

Azimi, I., Takalo-Mattila, J., Anzanpour, A., Rahmani, A., Soininen, J-P., & Liljeberg, P. (2019). Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning. In Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018 (pp. 63-68). Institute of Electrical and Electronic Engineers IEEE.
Azimi, Iman ; Takalo-Mattila, Janne ; Anzanpour, Arman ; Rahmani, Amir ; Soininen, Juha-Pekka ; Liljeberg, Pasi. / Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning. Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronic Engineers IEEE, 2019. pp. 63-68
@inproceedings{795fe9a014594c4b998da79d21af47d0,
title = "Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning",
abstract = "Remote health monitoring is a powerful tool to provide preventive care and early intervention for populations-at-risk. Such monitoring systems are becoming available nowadays due to recent advancements in Internet-of-Things (IoT) paradigms, enabling ubiquitous monitoring. These systems require a high level of quality in attributes such as availability and accuracy due to patients critical conditions in the monitoring. Deep learning methods are very promising in such health applications to obtain a satisfactory performance, where a considerable amount of data is available. These methods are perfectly positioned in the cloud servers in a centralized cloud-based IoT system. However, the response time and availability of these systems highly depend on the quality of Internet connection. On the other hand, smart gateway devices are unable to implement deep learning methods (such as training models) due to their limited computational capacities. In our previous work, we proposed a hierarchical computing architecture (HiCH), where both edge and cloud computing resources were efficiently exploited, allocating heavy tasks of a conventional machine learning method to the cloud servers and outsourcing the hypothesis function to the edge. Due to this local decision making, the availability of the system was highly improved. In this paper, we investigate the feasibility of deploying the Convolutional Neural Network (CNN) based classification model as an example of deep learning methods in this architecture. Therefore, the system benefits from the features of the HiCH and the CNN, ensuring a high-level availability and accuracy. We demonstrate a real-time health monitoring for a case study on ECG classifications and evaluate the performance of the system in terms of response time and accuracy.",
keywords = "Internet of Things, Hierarchical Computing, Electrocardiogram, Health Monitoring, Deep Learning, Convolutional neural networks (CNN), Convolutional Neural Networks",
author = "Iman Azimi and Janne Takalo-Mattila and Arman Anzanpour and Amir Rahmani and Juha-Pekka Soininen and Pasi Liljeberg",
year = "2019",
month = "2",
day = "21",
language = "English",
isbn = "978-1-5386-7207-5",
pages = "63--68",
booktitle = "Proceedings - 2018 IEEE/ACM International Conference on Connected Health",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Azimi, I, Takalo-Mattila, J, Anzanpour, A, Rahmani, A, Soininen, J-P & Liljeberg, P 2019, Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning. in Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronic Engineers IEEE, pp. 63-68, The Third IEEE/ACM International Conference on Connected Health, Washington, United States, 26/09/18.

Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning. / Azimi, Iman; Takalo-Mattila, Janne; Anzanpour, Arman; Rahmani, Amir; Soininen, Juha-Pekka; Liljeberg, Pasi.

Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronic Engineers IEEE, 2019. p. 63-68.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning

AU - Azimi, Iman

AU - Takalo-Mattila, Janne

AU - Anzanpour, Arman

AU - Rahmani, Amir

AU - Soininen, Juha-Pekka

AU - Liljeberg, Pasi

PY - 2019/2/21

Y1 - 2019/2/21

N2 - Remote health monitoring is a powerful tool to provide preventive care and early intervention for populations-at-risk. Such monitoring systems are becoming available nowadays due to recent advancements in Internet-of-Things (IoT) paradigms, enabling ubiquitous monitoring. These systems require a high level of quality in attributes such as availability and accuracy due to patients critical conditions in the monitoring. Deep learning methods are very promising in such health applications to obtain a satisfactory performance, where a considerable amount of data is available. These methods are perfectly positioned in the cloud servers in a centralized cloud-based IoT system. However, the response time and availability of these systems highly depend on the quality of Internet connection. On the other hand, smart gateway devices are unable to implement deep learning methods (such as training models) due to their limited computational capacities. In our previous work, we proposed a hierarchical computing architecture (HiCH), where both edge and cloud computing resources were efficiently exploited, allocating heavy tasks of a conventional machine learning method to the cloud servers and outsourcing the hypothesis function to the edge. Due to this local decision making, the availability of the system was highly improved. In this paper, we investigate the feasibility of deploying the Convolutional Neural Network (CNN) based classification model as an example of deep learning methods in this architecture. Therefore, the system benefits from the features of the HiCH and the CNN, ensuring a high-level availability and accuracy. We demonstrate a real-time health monitoring for a case study on ECG classifications and evaluate the performance of the system in terms of response time and accuracy.

AB - Remote health monitoring is a powerful tool to provide preventive care and early intervention for populations-at-risk. Such monitoring systems are becoming available nowadays due to recent advancements in Internet-of-Things (IoT) paradigms, enabling ubiquitous monitoring. These systems require a high level of quality in attributes such as availability and accuracy due to patients critical conditions in the monitoring. Deep learning methods are very promising in such health applications to obtain a satisfactory performance, where a considerable amount of data is available. These methods are perfectly positioned in the cloud servers in a centralized cloud-based IoT system. However, the response time and availability of these systems highly depend on the quality of Internet connection. On the other hand, smart gateway devices are unable to implement deep learning methods (such as training models) due to their limited computational capacities. In our previous work, we proposed a hierarchical computing architecture (HiCH), where both edge and cloud computing resources were efficiently exploited, allocating heavy tasks of a conventional machine learning method to the cloud servers and outsourcing the hypothesis function to the edge. Due to this local decision making, the availability of the system was highly improved. In this paper, we investigate the feasibility of deploying the Convolutional Neural Network (CNN) based classification model as an example of deep learning methods in this architecture. Therefore, the system benefits from the features of the HiCH and the CNN, ensuring a high-level availability and accuracy. We demonstrate a real-time health monitoring for a case study on ECG classifications and evaluate the performance of the system in terms of response time and accuracy.

KW - Internet of Things

KW - Hierarchical Computing

KW - Electrocardiogram

KW - Health Monitoring

KW - Deep Learning

KW - Convolutional neural networks (CNN)

KW - Convolutional Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85063253016&partnerID=8YFLogxK

M3 - Conference article in proceedings

SN - 978-1-5386-7207-5

SP - 63

EP - 68

BT - Proceedings - 2018 IEEE/ACM International Conference on Connected Health

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Azimi I, Takalo-Mattila J, Anzanpour A, Rahmani A, Soininen J-P, Liljeberg P. Empowering Healthcare IoT Systems with Hierarchical Edge-Based Deep Learning. In Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronic Engineers IEEE. 2019. p. 63-68