 There will be one, but this one presentation will be given by two people. So Chris will start and I'll continue. Good morning everyone. I will give the presentation on the fact sheets of classes of decision analysis together with Professor Dimitriyev. First, this is outline of this presentation. There are many three parts. The first is general overview, which includes the scope of the fact sheets, the application areas, the critical appraisal. And the second is the basic theory parts, which consists of the decision tree, the decision based on the prior information. That is the prior analysis and decision based on the additional information, that is the posterior analysis. And the decision based on the unknown information, that is the preposterior analysis. And finally, the value of information is defined. The first, about the scope of these fact sheets, these fact sheets is mainly focused on three different classes of decision analysis. The first, the prior analysis, the posterior analysis, and the preposterior analysis. Among which, the last one, the preposterior analysis will be considered in detail and will be presented later by Professor Dimitriyev. And also, the value of information is defined in this fact sheets about the application areas of the decision analysis. Since the Bayesian decision analysis is for optimizing the collection of information, which leads to a better decision process, its application in civil engineering field laid the basis for the computation of the value of information for optimizing the inspections and SHM in the deteriorating structures. And also, it is widely applied to other fields such as the transportation infrastructure management, geotechnical engineering, natural hazards, and so on. Detail about these applications can refer to the fact sheets about the critical appraisal. The advantage of using the posterior and preposterior analysis, it takes into account the uncertainties in the decision making process. And this will give a well considered and structured way for making the optimal decisions and their uncertainty. But also, it has some drawbacks. For example, it sometimes requires significant computational efforts and statistical modeling. And this can be cumbersome if we want to apply this methodology to practical applications. The second part is the basic theory. First, the definition of the decision tree. The decision tree, as indicated in this feature, it is a decision as part two that uses the tree-like graph to make the decision and their consequences. And it mainly consists of five parts. The first, the inspection decisions. It is the set of possible inspection actions. For example, the inspection date, type of inspection, location, and so on. And the second note is that it is the inspection outcomes, which followed by the inspection decisions. And it consists of the set of inspection outcomes, which provide information on the actual structural states. And after knowing the inspection or inspection outcomes, certain actions can be made. For example, do nothing, repair or replace some part of this structure. And finally, set is structural states. It is a set of structural states representing different levels of damages. Of course, these are usually time-dependent. And the combination of the first four notes gives the value, use, or utility of the paths that followed. So this utility is what we call the value of information. And based on this decision tree, we can do the prior analysis. That is, the decision made based on the prior information. And the prior analysis is a situation when decision is to be made based on the previously available, often generic information. And using this information, probabilities are assigned to the different conditions of the structure. And this can be represented by the P prime set J. It is the prior probabilities. And after setting utilities of these possible action-state combinations, the expected utility corresponding to the different actions can be calculated. And you can see from this figure, it is a reduced decision tree. Since there is only a generic information and no inspection outcomes, so this decision tree starts with the action, a set of possible actions A, and followed by the possible condition, structural conditions set J. And if the associated utilities are assigned, then we can use this formula to calculate the expected utility of the action AI. And where this E prime set denotes the expectation operation with respect to the prior probabilities P prime set. And consequently, the decision analysis consists of the truth in the action A, which results in the largest expected utility U. And this can be represented with these two formulas. Okay, next. Professor.