Automated workflow analysis in vegetable grafting using an Ultra-Wide Band based real-time indoor location tracking system

Traditional workflow analysis requires intensive manual processes to extract meaningful information from raw sensory data. A novel framework for workflow analysis is developed based on a real-time indoor location tracking system utilizing Ultra-Wide Band technology. The proposed framework is applied to identify worker and task associations in a labor-intensive horticultural plant production process for grafted vegetable seedlings, based on location data. It involves binary segmentation of different distance measures calculated from location data to detect the plant tray's movements and worker association in the vegetable grafting operation. An iterative overlap time removal algorithm is then implemented to ensure that no worker is assigned to overlapping processes, and no task is processed by multiple workers simultaneously. Key workflow metrices such as flow time, processing time, and waiting times are automatically calculated. Automatically generated Gantt charts and bar plots provide valuable insights into the workflow for management and help them identify improvement opportunities. Validation of results with video data show that the proposed workflow analysis is 90.5% accurate.