Efficient training set use for blood pressure prediction in a large scale learning classifier system

Abstract

We define a machine learning problem to forecast arterial blood pressure. Our goal is to solve this problem with a large scale learning classifier system. Because learning classifiers systems are extremely computationally intensive and this problem's eventually large training set will be very costly to execute, we address how to use less of the training set while not negatively impacting learning accuracy. Our approach is to allow competition among solutions which have not been evaluated on the entire training set. The best of these solutions are then evaluated on more of the training set while their offspring start off being evaluated on less of the training set. To keep selection fair, we divide competing solutions according to how many training examples they have been tested on.

Hyperparameter Selection

“…Although we restricted our study to the use of MSE and HR alone, it would be interesting to integrate and combine other disease characteristics and physiological signals. For example, [10] used Bayesian optimization to find the Fig. 29.4 The impact of the MSE parameters on the outcome prediction AUROC most optimal wavelet parameters to predict acute hypotensive episodes.…”

Characterising the Influence of Rule-Based Knowledge Representations in Biological Knowledge Extraction from Transcriptomics Data

“…In the majority of cases [23, 4-6, 10, 22, 9, 24, 13] as supervised (classification) learning, but sometimes also applied to unsupervised learning in the form of association rules [16] or bi-clustering [15]. Moreover, they have been applied to a variety of biological data, such as transcriptomics [16,6,10,15], SNPs [23,24], proteomics [22], lipidomics [9], protein structure [4,5] or clinical measurements [13]. Often, these methods are used for the core machine learning task of performing predictions, but in some cases also to extract knowledge from the data, as identifying and ranking important variables (biomarkers) [23,24], generating minimal sets of biomarkers [22], or inferring networks of interactions from data [16,6,23].…”