Design an Artificial Neural Network by MLP Method; Analysis of the Relationship between Demographic Variables, Resilience, COVID-19 and Burnout
  • Chao-Hsi Huang1, Tsung-Shun Hsieh2,3, Hsiao-Ting Chien4, Ehsan Eftekhari-Zadeh5,*, Saba Amiri6
1 Office of Research and Development, Tunghai University, Taichung, 407224, Taiwan
2 Nanyang Institute of Management, The Central 059817, Singapore
3 Krirk University, Thanon Ram Intra, Khwaeng Anusawari, Khet Bang Khen, Krung Thep Maha Nakhon, 10220, Thailand
4 National Taiwan Normal University, Graduate Institute of Information and Computer Education, Taipei, 10610, Taiwan
5 Institute of Optics and Quantum Electronics, Friedrich Schiller University Jena, Jena, 07743, Germany
6 Managamenet and Entrepreneurship Department, Razi University, Kermanshah, 67146, Iran
* Corresponding Author: Ehsan Eftekhari-Zadeh. Email: e.eftekharizadeh@uni-jena.de
Received 11 January 2022; Accepted 01 July 2022 ; Published online 02 August 2022
Abstract
In addition to the effect that the COVID-19 pandemic has had on the physical and mental health of individuals, it has also led to a change in the mental and emotional state of many employees. Especially among businesses and private companies, which faced many restrictions due to the special conditions of the pandemic. Therefore, the present study aimed to design an artificial neural network with MLP technique to analyze the relationship between demographic variables, resilience, COVID-19 and burnout in start-ups in Iran. The research method was quantitative. Managers and employees of start-ups formed the statistical population of the study, based on the statistical sample size of the unlimited community, 384 of them were tested. For data gathering, standard questionnaires include of MBI-GS and BRCS and researcher-made questionnaire of stress caused by COVID-19 were used. The validity of the questionnaires was confirmed by a panel of experts and their reliability was confirmed by Cronbach’s alpha coefficient. The number of neurons in the input layer was equal to 10, the number of neurons in the 1st hidden layer was equal to 7, the number of neurons in the output layer was equal to 1, and the number of epochs was equal to 500. 70% of the data were used for training and 30% for testing. In the designed artificial neural network, all experiment data except one were correctly predicted and the obtained MAE error was less than 0.012%. Finally, he precision and correction of the presented model was confirmed by the obtained results.
Keywords
Burnout; artificial neural network; multi-layer perceptron; COVID-19; resilience