Workplace Flexibility Analysis in Cyberphysical Human Systems Using Cloud-Enabled Deep Autoencoder Networks

Abstract

To examine the correlation between worker safety, workplace interpersonal problems, and individual flexibility within a cyberphysical human system (CPHS), we employed a stacked autoencoder (SAE) approach and a cloud-based computing environment. The study’s statistical population includes construction companies in Mashhad, Iran. To collect data, descriptive surveys and applied research approaches are employed. Thus, data is collected using a cloud-based platform, data processing tools, and information analysis methods. It is our main objective to figure out how to reduce construction accidents and make people safer. Our study used a sample of 200 people to study the entire study population because it is difficult to study the entire study population. There were 151 valid questionnaires collected after the questionnaire distribution. We developed a 28-item questionnaire as part of the study in addition to the Questionnaire on Experience and Evaluation of Work (QEEW). Implementing an optimized SAE network can reduce dangerous situations, physical injuries, supervisor conflict, workplace stress, interpersonal conflict, and colleagues’ involvement. As a consequence of the large amount of data needed for quick analysis and mechanism construction, cloud computing performed admirably. The study of interpersonal conflicts and individual flexibility among construction workers was necessary because only limited research had been conducted on these topics.