2013
DOI: 10.1016/j.engappai.2012.09.019
|View full text |Cite
|
Sign up to set email alerts
|

Time series classification for the prediction of dialysis in critically ill patients using echo statenetworks

Abstract: Objective: Time series often appear in medical databases, but only few machine learning methods exist that process this kind of data properly. Most modeling techniques have been designed with a static data model in mind and are not suitable for coping with the dynamic nature of time series. Recurrent Neural Networks (RNN) are often used to process time series, but only a few training algorithms exist for RNNs which are complex and often yield poor results. Therefore, researchers often turn to traditional machi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
10
0

Year Published

2013
2013
2020
2020

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 18 publications
(10 citation statements)
references
References 32 publications
0
10
0
Order By: Relevance
“…The minimum of the criterion function is found by changing the values of the weights matrix W out , which is determined by Eqs. (5), (6), (9) and (10). The basic echo state neural networks model consists of one input layer within 96 neurons, (SI1(t), .…”
Section: Echo State Neural Network Mod-ellingmentioning
confidence: 99%
See 1 more Smart Citation
“…The minimum of the criterion function is found by changing the values of the weights matrix W out , which is determined by Eqs. (5), (6), (9) and (10). The basic echo state neural networks model consists of one input layer within 96 neurons, (SI1(t), .…”
Section: Echo State Neural Network Mod-ellingmentioning
confidence: 99%
“…is defined as follows: The key idea in reservoir computing [10], [14] is to feed time series to a reservoir by modelling the dynamics of the system which generates the time series. The reservoir is then read by a readout function in order to make predictions using the constructed model.…”
Section: Echo State Neural Networkmentioning
confidence: 99%
“…The ESN application domains are various. They can be founded in medical [15], economic [16] and optical applications [17].…”
Section: A Backgrounds Of Esnmentioning
confidence: 99%
“…There are quite a wide range of machine learning algorithms. This includes Naive Bayes [25], Support Vector Machines [34], Support Vector Regression [40], Gradient Boosted Regression Tree [11], Factorisation Machine [35] and Multilayer Perceptrons. They can be applied to time series forecasting of blood pres-sure but they are not specifically designed to deal with temporal data.…”
Section: Introductionmentioning
confidence: 99%