Interdisciplinary Methodology for Resource Allocation Problems using Artificial Neural Networks and Software Robots

This study presents an interdisciplinary methodology for the Resource Allocation Problem (RAP) in a textile manufacturing environment, aligned with the principles of Industry 5.0, which emphasizes the convergence of advanced technologies and the human factor. The core of this research lies in the integration of an Artificial Neural Network (ANN) to predict worker performance, coupled with process automation, to optimize the allocation of workers to machines. A key ethical consideration addressed by this methodology is the focus on psychosocial factors and workplace well-being, recognizing their contribution to sustainability and organizational success. The benefits of this interdisciplinary approach to RAP are manifold. By considering psychosocial and productivity factors in the optimization model, the study moves beyond traditional methods that often prioritize efficiency at the expense of human considerations. This human-centered approach leads to a more sustainable and socially responsible production environment. The methodology contributes to the development of new tools for managing production in ways that are not only efficient but also significantly aligned with worker well-being. By embedding human-centered constraints directly into the optimization process, this study offers a pathway to mitigate potential issues such as worker overload and improve overall worker satisfaction. Ultimately, this research underscores the value of interdisciplinarity in operational research and production management by demonstrating a cohesive methodology that balances efficiency with ethical considerations for the workforce.