There exists widely incomplete knowledge all over the world, but incomplete knowledge still cannot be dealt with in the process of ontology construction. Hence, a method for fuzzy ontology construction based on incomp...There exists widely incomplete knowledge all over the world, but incomplete knowledge still cannot be dealt with in the process of ontology construction. Hence, a method for fuzzy ontology construction based on incomplete knowledge is proposed. First, the calculation principle of the attribute weight of the ontology concept is presented, and the calculation function of the attribute weight is derived through experiments. Then, the membership degree of the incomplete individual to the concept is computed. Finally, the incomplete individual is classified according to the principle of the variable precision rough set model. The experimental results show that the average precision of the classification of the incomplete individuals is 81.7% when the common attributes are omitted and that it is difficult to classify the incomplete individuals correctly when the private attributes are omitted. This method is significant for handling incomplete knowledge in the process of ontology construction.展开更多
Up to now, no satisfactory theory has been established for formalizing incomplete knowledge in incomplete databases. In this paper, we clarify why existing closed world approaches, such as the CWA, the GCWA, the ECWA,...Up to now, no satisfactory theory has been established for formalizing incomplete knowledge in incomplete databases. In this paper, we clarify why existing closed world approaches, such as the CWA, the GCWA, the ECWA, circumscription, predicate completion and the PWA, fail to do so, and propose a new method. The method is an augmentation of both the ECWA and circumscrip- tion with the mechanism to discriminate implicitly expressed positive knowledge, negative knowledge and truly unknown knowledge.展开更多
In this paper, firstly the current analysis methods of uncertainties in seismic hazard assessment (SHA) are systematically reviewed, and the existing problems are pointed out. At the same time, it is proposed that the...In this paper, firstly the current analysis methods of uncertainties in seismic hazard assessment (SHA) are systematically reviewed, and the existing problems are pointed out. At the same time, it is proposed that the uncertainties can be divided into three kinds, namely, randomness, fuzziness and incompleteness of knowledge, and they can be treated in a unified way. Then, based on marked point process theory, a general equation for SHA is obtained, and a general equation for uncertainty analysis is also given on the basis of total probability theorem. Finally, the relationship between the proposed analysis method with those currently used both at home and abroad is discussed. The analysis shows that they are just the special case of the proposed method.展开更多
基金supported by the Beijing Natural Science Foundation under Grant No.4123094 the Science and Technology Project of Beijing Municipal Commission of Education under Grants No.KM201110028020,No. KM201010028019 Beijing Key Construction Discipline“Computer Application Technology”
文摘There exists widely incomplete knowledge all over the world, but incomplete knowledge still cannot be dealt with in the process of ontology construction. Hence, a method for fuzzy ontology construction based on incomplete knowledge is proposed. First, the calculation principle of the attribute weight of the ontology concept is presented, and the calculation function of the attribute weight is derived through experiments. Then, the membership degree of the incomplete individual to the concept is computed. Finally, the incomplete individual is classified according to the principle of the variable precision rough set model. The experimental results show that the average precision of the classification of the incomplete individuals is 81.7% when the common attributes are omitted and that it is difficult to classify the incomplete individuals correctly when the private attributes are omitted. This method is significant for handling incomplete knowledge in the process of ontology construction.
文摘Up to now, no satisfactory theory has been established for formalizing incomplete knowledge in incomplete databases. In this paper, we clarify why existing closed world approaches, such as the CWA, the GCWA, the ECWA, circumscription, predicate completion and the PWA, fail to do so, and propose a new method. The method is an augmentation of both the ECWA and circumscrip- tion with the mechanism to discriminate implicitly expressed positive knowledge, negative knowledge and truly unknown knowledge.
文摘In this paper, firstly the current analysis methods of uncertainties in seismic hazard assessment (SHA) are systematically reviewed, and the existing problems are pointed out. At the same time, it is proposed that the uncertainties can be divided into three kinds, namely, randomness, fuzziness and incompleteness of knowledge, and they can be treated in a unified way. Then, based on marked point process theory, a general equation for SHA is obtained, and a general equation for uncertainty analysis is also given on the basis of total probability theorem. Finally, the relationship between the proposed analysis method with those currently used both at home and abroad is discussed. The analysis shows that they are just the special case of the proposed method.
