We present a unique approach to defining assistance systems that utilize information fusion to combine various sources of information and provide an assessment. The main contribution of this study is the development of a comprehensive framework for fusing multiple information sources using the evidence theory. This fusion process enhances prediction accuracy and also generates a measure of uncertainty, which can be utilized to evaluate the likelihood of the prediction. Additionally, we introduce a methodology for fusing information from two primary sources: a machine data-based ensemble classifier and an expert-centered model. To illustrate the information fusion approach, we apply it to data from an industrial setting, thus demonstrating its practical application. Moreover, we tackle the issue of data drift by proposing a methodology to update the data-based models using an evidence theory approach. To validate our approach, we employ the Benchmark Tennessee Eastman dataset and conduct an ablation study on the model update parameters.
A Study on Information Fusion for Production Assessment in Assistance Systems (arXiv:2309.00157v1 [cs.LG])
