Analyses of Diverse Agricultural Worker Data with Explainable Artificial Intelligence: XAI based on SHAP, LIME, and LightGBM

We use recent explainable artificial intelligence (XAI) based on SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Light Gradient Boosting Machine (LightGBM) to analyze diverse physical agricultural (agri-) worker datasets. have developed various promising body-sensing systems enhance agri-technical advancement, training development, security. However, existing methods are not sufficient for in-depth analysis of human motion. Thus, we also wearable sensing (WS) that can capture real-time three-axis acceleration angular velocity data related agri-worker motion by analyzing dynamics statistics in different agri-fields, meadows, gardens. After investigating the obtained time-series using a novel program written Python, discuss our findings recommendations with real agri-workers managers. In this study, XAI visualization experienced inexperienced develop an applied method agri-directors train agri-workers.