Prioritizing Health Promotion Plans with k-Bayesian Network Classifier

Abstract

Recently, Bayesian Network Classifiers (BNCs) have attracted many researchers because they can produce classification models with dependencies among attributes. From the application viewpoint, however, BNCs sometimes produce models too complicated to interpret easily. In this paper, we propose k-Bayesian Network Classifier (k-BNC), which is a new method to reconstruct the attribute-dependency relationship from data for health promotion planning. From the health promotion viewpoint, it would be highly advantageous if occupational physicians could make effective plans for employees, and if employees could carry out the plans easily. Therefore, we focus on the attribute dependencies in classification models represented as a Directed Acyclic Graph (DAG), and find the effective attributes by measuring the standardized Kullback-Leibler divergence from parent attributes to their children. In experimental evaluation, we firstly compare the accuracy of k-BNC with that of Naive Bayes Classifiers, and other wellknown Bayesian Networks and structure learning methods (k2 algorithm etc.) on some public datasets. We show that our proposed k-BNC method successfully produces classification models for the prioritization of health promotion plans on our health checkup data.

Data mining in occupational safety and health: a systematic mapping and roadmap

“…The steel industry also presents relevant research for systematic mapping (Krishna et al, 2015;Sarkar et al, 2017Sarkar et al, , 2018Sarkar et al, , 2019aShirali et al, 2018), as well as applications in the area of healthcare (Di Noia et al, 2019;Kao et al, 2018;Olsen et al, 2009;Saâdaoui et al, 2015;Ueno et al, 2008), mining (Luo et al, 2016;Qu, 2009;Sanmiquel et al, 2015Sanmiquel et al, , 2018 and petrochemical (Bevilacqua et al, 2008;Cheng et al, 2013;Sanchez-Pi et al, 2014;Waghmare & Pai, 2013).…”

“…As for the types of data that can go through the mining process, this sample includes research studies that use images (Rubaiyat et al, 2016;Siddula et al, 2016) and videos (Paliyawan et al, 2014;Ueno et al, 2008), being directly associated with the concept of machine learning and automation in the worker's environment. Other studies present textual data sets in formats of injuries (Tixier et al, 2017) and accidents reports (Liao & Perng, 2008;Sarkar et al, 2016) and medical examinations (Bonneterre et al, 2012).…”

Modelo de simulación y minería de datos para identificar y predecir cambios presupuestales en la atención de pacientes con hipertensión arterial

“…Se encontró una población de 247 pacientes de los cuales se disponían 1 692 registros. Experimentado con clasificadores de tipo Bayesiano (17), meta-clasificadores tipo Bagging y diferentes árboles de decisión, se seleccionó un predictor tipo RepTree tipo árbol de decisión, con un porcentaje de clasificaciones correctas de 84,2 %. Los resultados de la clasificación se describen en la Tabla 2.…”

A self-growing Bayesian network classifier for online learning of human motion patterns

“…When an instance described by a set of attributes is classified, a Bayesian network classifier considers the conditional dependences between attributes. As a result, Bayesian network classifier has been used in a wide range of applications [5][6][7][8]. Despite an improved idea and a better classification performance, Bayesian network classifier has a number of limitations.…”