A ceiling panel system is developed that comprises a ceiling panel having a face portion with four corner areas and a skirt portion extending rearward from the face portion. The method includes nominating a set of allowed dialog actions and a set of contextual features at each turn in a dialog, and selecting an optimal action from the set of nominated allowed dialog actions using a machine learning algorithm. The data are used for determining the position of the at least one object. This allows a much wider range of uses and higher level of feed stream contaminants than prior art catalysts.