Improved Boosted Decision Tree Algorithms by Adaptive Apriori and Post-Pruning for Predicting Obstructive Sleep Apnea

Sim, Doreen Ying Ying; Teh, Chee Siong; Ismail, Ahmad Izuanuddin

doi:10.1166/asl.2018.11136

Cited by 13 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We shall focus on the nonparametric algorithms and more specifically, nearest neighbors, support vector machines, decision trees and random forests. These algorithms have been extensively studied on diverse datasets [1], [2], [3]. We attempt to contribute to the comparative literature by studying the algorithms performance on a medical insurance dataset.…”

Section: Introductionmentioning

confidence: 99%

Estimating the Time-Lapse Between Medical Insurance Reimbursement with Non-parametric Regression Models

Akinyemi

Yinka-Banjo

Ugot

et al. 2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Nonparametric supervised learning algorithms represent a succinct class of supervised learning algorithms where the learning parameters are highly flexible and whose values are directly dependent on the size of the training data. In this paper, we comparatively study the properties of four nonparametric algorithms, K-Nearest Neighbours (KNNs), Support Vector Machines (SVMs), Decision trees and Random forests. The supervised learning task is a regression estimate of the time lapse in medical insurance reimbursement. Our study is concerned precisely with how well each of the nonparametric regression models fits the training data. We quantify the goodness of fit using the R-squared metric. The results are presented with a focus on the effect of the size of the training data, the feature space dimension and hyperparameter optimization. The findings suggest k-NN's and SVM's algorithms as better models in predicting welldefined output labels (i.e, Time lapse in days). However, overall, the decision tree model performs better because it makes a better prediction on new data points than the ballpark estimates made from likelihood models-SVM's and k-NN's.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimating the Time-Lapse Between Medical Insurance Reimbursement with Non-parametric Regression Models

Akinyemi

Yinka-Banjo

Ugot

et al. 2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…But, interesting rules are often not being supported by frequent itemsets. Hence, mining frequent itemsets and using association rules to construct a prediction system for Obstructive Sleep Apnea (OSA) based on the raw data collected in Malaysia is still yet to be researched upon [1][2][3][4]. Pruning techniques applied in this research mainly involve in the association rules, especially those augmented by Adaptive Apriori (AA), applied.…”

Section: Introductionmentioning

confidence: 99%

Pushing Constraints by Rule-Driven Pruning Techniques in Non-Uniform Minimum Support for Predicting Obstructive Sleep Apnea

Sim

Teh

Ismail³

2019

AMM

Self Cite

View full text Add to dashboard Cite

Boosted Association-Ruled Pruned Decision Tree (ARP-DT), the improved version of the Boosted Decision Tree algorithm, was developed by using association-ruled pre-and post-pruning techniques with referring to the pushed minimum support and minimum confidence constraints as well as the association rules applied. The novelty of the Association-Ruled pruning techniques applied mainly embark on the pre-pruning techniques through researching on the maximum number of decision tree splitting, as well as the post-pruning techniques involving subtree replacement and subtree raising. The applied association rules (ARs) augment the mining of frequent itemset (s) or interesting itemset (s) such that appropriate pre-pruning or subtree pruning techniques can be applied before AdaBoost ensemble is implemented. The ARs applied involve the Adaptive Apriori (AA) augmented rule definitions and theorem as stated in this research focuses on the characteristics of the datasets accessed so as to streamline the rule-driven pruning techniques on the Boosting algorithms developed for predicting Obstructive Sleep Apnea (OSA). There is a significant improvement in the prediction accuracies when comparing the classical boosting algorithms and Boosted ARP-DT being applied to the OSA datasets and those online databases from University of California Irvine (UCI) data repositories.

show abstract

“…This research adopts visualization techniques using PCA and/or PCVG algorithms embarking on schema enumerated trees (i.e. SETs) after investigating the data features and characteristics in the datasets [1,[3][4][5] before applying AdaBoost ensemble. AdaBoost is one of the most popular ensemble methods to be used for further improving certain weak classifiers such as decision trees [1,4,13,[14][15][16].…”

mentioning

confidence: 99%

Pushing Visualization Effects into Pushed Schema Enumerated Tree-Based Support Constraints

Sim

Teh

Ismail³

2019

AMM

Self Cite

View full text Add to dashboard Cite

Based on the datasets from UCI and Obstructive Sleep Apnea, a disparate methodology of uncovering the visualization effects into the pushed support constraints of schema enumerated tree-based classification techniques is proposed and presented in this paper. This is to actively ‘wipe out’ the redundant growing effects of decision trees through itemset generation when visualization techniques are applied using Principal Component Analysis (PCA) and/or Principal Component Variable Grouping (PCVG) algorithms. Enumeration specification is based on the schema enumerated tree (SET) drawn after sorting out the features and characteristics on each dataset applied. The linchpin is to streamline the pre-tree classification effects for post-tree classification by using visualization techniques, i.e. PCA and/or PCVG, which are applied during the SET development. The over-fitting effects done during the SET development by the pushed support constraints can be counter-corrected by fewer PCA and/or PCVG imposed during visualization processes. The under-fitting effects done by the imprecise ‘early stopping’ of the SET development can be counter-corrected by greater PCA and/or PCVG imposed during the post-tree classification techniques through pushed SET support constraint learning. Research outcome on all the investigated datasets showed that the prediction accuracies have been profoundly improved after applying visualization of PCA and/or PCVG algorithms into the pushed SET-based or SET-based support constraints.

show abstract

Improved Boosted Decision Tree Algorithms by Adaptive Apriori and Post-Pruning for Predicting Obstructive Sleep Apnea

Cited by 13 publications

References 0 publications

Estimating the Time-Lapse Between Medical Insurance Reimbursement with Non-parametric Regression Models

Estimating the Time-Lapse Between Medical Insurance Reimbursement with Non-parametric Regression Models

Pushing Constraints by Rule-Driven Pruning Techniques in Non-Uniform Minimum Support for Predicting Obstructive Sleep Apnea

Pushing Visualization Effects into Pushed Schema Enumerated Tree-Based Support Constraints

Contact Info

Product

Resources

About