Investigation of machine learning techniques in forecasting of blood pressure time series data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

143 Downloads (Pure)

Abstract

The aim of this paper is to investigate different machine learning based forecasting techniques for forecasting of blood pressure and heart rate. Forecasting of blood pressure could potentially help a clinician to take preventative steps even before dangerous medical situations occur. This paper examines forecasting blood pressure 30 minutes in advance. Univariate and multivariate forecast models are considered. Different forecast strategies are also considered. To compare different forecast strategies, LSTM and BI-LSTM machine learning algorithms were included. Then univariate and multivariate LSTM, BI-LSTM and CNN machine learning algorithms were compared using the two best forecasting strategies. Comparative analysis between forecasting strategies suggest that MIMO and DIRMO forecast strategies provide the best accuracy in forecasting physiological time series data. Results also appear to show that multivariate forecast models for blood pressure and heart rate are more reliable compared to blood pressure alone. Comparative analysis between MIMO and DIRMO forecasting strategies appear to show that DIRMO is more reliable for both univariate and multivariate cases. Results also appear to show that the forecast model that uses BI-LSTM with the DIRMO strategy is the best overall.
Original languageEnglish
Title of host publicationSGAI 2019: Artificial Intelligence XXXVI. Thirty-ninth SGAI International Conference on Artificial Intelligence
Subtitle of host publicationInternational Conference on Innovative Techniques and Applications of Artificial Intelligence
EditorsMax Bramer, Miltos Petridis
PublisherSpringer
Chapter21
Pages269-282
Number of pages14
Volume11927
ISBN (Electronic)978-3-030-34885-4
ISBN (Print)978-3-030-34884-7
DOIs
Publication statusPublished - 19 Nov 2019
EventAI-2019 Thirty-ninth SGAI International Conference on Artificial Intelligence - Cambridge, United Kingdom
Duration: 17 Dec 201919 Dec 2019
Conference number: 39
http://www.bcs-sgai.org/ai2019/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743
NameLecture Notes in Artificial Intelligence
PublisherSpringer
ISSN (Print)0302-9743

Conference

ConferenceAI-2019 Thirty-ninth SGAI International Conference on Artificial Intelligence
Abbreviated titleSGAI
CountryUnited Kingdom
CityCambridge
Period17/12/1919/12/19
Internet address

Keywords

  • Time series forecasting
  • Univariate data
  • Multivariate data
  • Forecast strategies
  • LSTM
  • BI-LSTM
  • CNN
  • Blood pressure
  • Heart rate

Fingerprint

Dive into the research topics of 'Investigation of machine learning techniques in forecasting of blood pressure time series data'. Together they form a unique fingerprint.

Cite this