Prediction of Burnout. An Artificial Neural Network Approach

Prediction of Burnout An Artificial Neural Network Approach

Contents

List of Figures

List of Tables

1 Burnout

1.1 The Origin of Burnout

1.1.1 The Uncovering of Burnout

1.2 Burnout as a Global Problem

1.3 Why is Burnout increasing?

1.4 Understanding Burnout

1.4.1 Definitions

1.4.2 Possible Symptoms

1.4.3 Burnout vs. Job Stress

1.4.4 Burnout vs. Depression

1.4.5 Burnout vs. Chronic Fatigue

1.5 Assessment and Prevalence

1.5.1 Assessment Tools

1.5.2 Reliability and Validity

1.5.3 Self-report Measures of Burnout

1.5.4 How often does Burnout occur?

1.6 Correlates, Causes and Consequences

1.6.1 Possible Antecedents of Burnout

1.6.2 Possible Consequences of Burnout

1.7 Theoretical Approaches to Explain Burnout

1.7.1 An Integrative Model

1.8 Prevention and Intervention of Burnout

1.8.1 Classification

1.8.2 Individual Level Interventions

1.8.3 Individual/Organizational Level Interventions

1.8.4 Organizational Level Interventions

2 Artificial Neural Networks

2.1 Introduction to Neurocomputing

2.1.1 Biological Motivation

2.1.2 Evolution of Artificial Neural Networks

2.1.3 Categorization of Artificial Neural Networks

2.2 Artificial Neuron Model

2.2.1 Notation and Terminology

2.2.2 Single-Input Neuron

2.3 Basic Transfer Functions

2.3.1 Hard Limit Transfer Function

2.3.2 Linear Transfer Function

2.3.3 Sigmoid Transfer Function

2.3.4 Hyperbolic Tangent Sigmoid Transfer Function

2.3.5 Radial Basis Transfer Function (GaussianFunction)

2.4 Multiple-Input Neuron

2.5 Training Algorithms

2.6 Network Architectures

2.6.1 A Single Layer of Neurons

2.6.2 Multiple Layers of Neurons

2.7 Perceptron

2.7.1 Perceptron Learning Rule

2.7.2 The Perceptron Training Algorithm

2.7.3 Limitations of the Perceptron

2.8 Self-Organizing Map (SOM)

2.8.1 Competitive Learning

2.8.2 Kohonen Training Algorithm

2.8.3 Example of the Kohonen Algorithm

2.8.4 Problems with the Kohonen Algorithm

2.9 Multi-layer Feed-forward Networks

2.9.1 Hidden-Neurons

2.9.2 Back-propagation

2.9.3 Back-propagation Training Algorithm

2.9.4 Problems with Back-propagation

2.10 Radial Basis Function (RBF) Network

2.10.1 Functioning of the Radial Basis Network

2.10.2 The Pseudo Inverse (PI) RBF TrainingAlgorithm

2.10.3 Example of the PI RBF Algorithm

2.10.4 The Hybrid RBF Training Algorithm

2.10.5 Example of the Hybrid RBF Training Algorithm

2.10.6 Problems with Radial Basis Function Networks

3 Application of ANNs toBurnout Data

3.1 Introduction

3.1.1 The Nursing Profession

3.1.2 Burnout in Nurses

3.1.3 Objective

3.2 Data

3.2.1 Participants

3.2.2 Measures

3.2.3 Statistical Data Analysis

3.2.4 Variables used for the Development of the ANNs

3.3 Implementation of the NuBuNet (NursingBurnout Network)

3.3.1 Self-Organizing Map (SOM)

3.3.2 Three-layer Feed-forward Back-propagationNetwork

3.3.3 Radial Basis Function Network

3.4 Processing the Data

3.4.1 Data Preparation (Pre-Processing)

3.4.2 Network Preparation and Training

3.4.3 Post-Processing

3.5 Results

3.5.1 Three-layer Feed-forward Back-propagationNetwork

3.5.2 Radial Basis Function Network (PI Algorithm)

3.5.3 Radial Basis Function Network (HybridAlgorithm)

3.5.4 Comparison of the Results

3.6 Discussion

4 References