Averaged one-dependence estimators on edge devices for smart pregnancy data analysis. (July 2019)

• Record Type: Journal Article
• Authors: Moreira, Mário W.L.; Rodrigues, Joel J.P.C.; Furtado, Vasco; Kumar, Neeraj; Korotaev, Valery V.
• Is Part Of: Computers & electrical engineering. Volume 77(2019)
• Page Start: 435
• Page End: 444
• Publication Date: 2019-07
• Subjects: Edge computing -- Internet of things -- Machine learning -- Hypertensive disorders -- Pregnancy -- Healthcare; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.07.041
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Review of edge network architectures, applications, and trends in IoT-based healthcare solutions. Study of algorithms based on machine learning (ML) techniques and their use in conjunction with edge devices for high-risk pregnancy monitoring. Classification mechanism to predict childbirth outcome in pregnancy: Averaged one-dependence estimators. Performance evaluation using a real dataset from the Maternity School Assis Chateaubriand through a 10-fold cross-validation method. Abstract: The development of edge computing has allowed the Internet of Things (IoT) to reach higher levels of operational efficiency, knowledge generation, and decision-making through a better relationship between applications and their users. The principal idea is the processing of large amounts of data close to the network edge, where these data are generated. Hence, in this paper, the use of a machine learning technique, known as averaged one-dependence estimators, is proposed for real-time pregnancy data analysis from IoT devices and gateways. This statistical technique is useful for decentralized pre-processing of data and its intermediate storage, reducing the amount of data to be transferred to the cloud and ensuring operability, even in an event of network failure. The results show that this technique presents accurate results with a low computational cost and could be a useful tool to better take advantage of the potential of IoT solutions in healthcare.