AI-Driven Labor Time Studies: Harnessing Deep Action Recognition for Workforce Productivity

Abstract

The integration of artificial intelligence and computer vision technologies in warehouse operations has emerged as a critical factor for enhancing operational efficiency and workforce management. This research presents a novel approach to labor time study through action-aware deep learning systems that leverage action recognition algorithms for optimized workforce management in smart warehouses. Our proposed framework combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to automatically recognize, classify, and analyze worker actions in real-time warehouse environments. The system demonstrates significant improvements in labor productivity assessment, with 94.2% accuracy in action recognition and 23% reduction in time study overhead. The implementation of this action-aware system resulted in optimized task allocation, reduced idle time by 18%, and improved overall warehouse throughput by 15.7%. This study contributes to the growing body of knowledge in AI-driven warehouse automation and provides a scalable solution for modern supply chain optimization.