AmirHossein Dalir - Master of Project Management and Construction: College of Civil and Development Engineering, Hamedan University - PhD student of Construction Engineering Management, Islamic Azad University, Science and Research Branch
Farhad Saeedi - Department of Civil, Islamic Azad University, Science and Research Branch Tehran:Iran
Zahra Pezeshki - Shahrood University of Technology, Faculty of Electrical and Robotics Engineering, Shahrud, Iran

This paper proposes a novel framework for automatic monitoring and controlling of the key success factors of construction projects based on deep learning and machine vision. The paper addresses the research problem of how to improve the efficiency, effectiveness, and performance of construction projects by using these techniques, and what are the benefits and challenges of doing so. The paper presents the design and implementation of the framework, which consists of two types of models: a convolutional neural network (CNN) for monitoring the key success factors, and a reinforcement learning (RL) algorithm for controlling the key success factors. The paper also evaluates the performance and accuracy of the framework using a dataset of images and videos from different construction scenarios, and reports the results using various metrics and criteria. The paper discusses the implications and applications of the work, and compares and contrasts it with the existing literature and state-of-the-art methods. The paper also acknowledges the limitations and challenges of the work, and suggests possible directions for future research and improvement. The paper concludes that the proposed framework can contribute to the advancement of the field of civil engineering and artificial intelligence, and have positive impacts for the construction industry and the society at large.

deep learning, machine vision, construction projects, key success factors, monitoring, controlling