A Conceptual Approach of an Integrated Multi Criteria Decision Making Techniques and Deep Learning for Construction Project Managers Selection Problem.

The success of a construction project depends on several critical success factors in such a hazardous scenario characterized by COVID-19 and its consequent stress. One important factor is supervision by a competent project manager with higher emotional intelligence (EI) skills especially in these pandemic times of uncertainty. The selection of this kind of project manager is, by nature, one of the most important and, at the same time, most complicated decisions to be made due to a multi-criteria decision-making (MCDM) problem. Based on previous studies, the human emotion element is often overlooked in the decision-making process. Modern evaluation would require a multimodal dataset to evaluate a competent candidate for the position. In addition, it is identified that classical MCDM is static and unable to quantify real-time human emotion. Hence, in this study, our approach uses an integrated techniques for MCDM and deep learning to address the managers' selection problem. Accordingly, a number of techniques, such as convolutional neural networks and other variations of algorithms, will be tested and compared. The emotion in our facial emotion recognition intensities value will be forwarded to MCDM as part of the input and eventually yield a non-bias and quality decision. It is anticipated that this study will enable employers to simplify and implement an effective decision-making process by embedding EI into the decision-making process to improve the quality of their hires and source the perfect candidate for construction project managers. Therefore, this study is aligned with the national construction agenda under the Construction 4.0 Strategic Plan (2021-2025), which requires changes to be made within the construction industry in tandem with the rapid development of technology and smarter systems. It emphasizes the utilization of digital technology as well as skills and knowledge enhancement. [ABSTRACT FROM AUTHOR]