Accountable capability improvement based on interpretable capability evaluation using belief rule base

A new approach is proposed in this study for accountable capability improvement based on interpretable capability evaluation using the belief rule base(BRB).Firstly,a capability evaluation model is constructed and optimized.Then,the key sub-capabilities are identified by quantitatively calculating the contributions made by each sub-capability to the overall capability.Finally,the overall capability is improved by optimizing the identified key sub-capabilities.The theoretical contributions of the proposed approach are as follows.(i)An interpretable capability evaluation model is constructed by employing BRB which can provide complete access to decision-makers.(ii)Key sub-capabilities are identified according to the quantitative contribution analysis results.(iii)Accountable capability improvement is carried out by only optimizing the identified key sub-capabilities.Case study results show that“Surveillance”,“Positioning”,and“Identification”are identified as key sub-capabilities with a summed contribution of 75.55%in an analytical and deducible fashion based on the interpretable capability evaluation model.As a result,the overall capability is improved by optimizing only the identified key sub-capabilities.The overall capability can be greatly improved from 59.20%to 81.80%with a minimum cost of 397.Furthermore,this paper also investigates how optimizing the BRB with more collected data would affect the evaluation results:only optimizing“Surveillance”and“Positioning”can also improve the overall capability to 81.34%with a cost of 370,which thus validates the efficiency of the proposed approach.

A study on improving anti-interference capability of inversion method reconstructing layered sea bottom parameters

The remote measurement of the vertical distribution of acoustical parameters of the sea bottom is an inverse method in acoustics. The existing methods can be divided into two types: the wave method and the ray method. The former usually does not apply to cases with discontinuity in acoustical parameter profiles[1] , whereas the latter usually ignores the contributions made by multiple reflections, resulting in the appearance of pseudo interfaces. However, under certain practical circumstances, the ray method can produce satisfactory results[2,3]. In this paper, at first we use the conception of equitime layer thickness to obtain the pulse response iteration method. The anti-interference capability of this method is poor. In order to improve this capability, we develope the sample iteration method and the sample-averaging iteration method. The sample-averaging iteration method introduces a way of statistical averaging, which can further improve the anti-interference capability.