부산대학교 도서관

Using a wearable sensor group mounted to the worker, we can obtain data of the movement and position of workers. We propose a method to predict the worker activity by combining the sensor data and information on workplaces in working environment and teams of workers. We will describe the method extracting several types of feature information related to worker activity and integrating them for prediction using a probability model. We also describe the results of the experiment using the data on workers working in warehouse operations.