This paper discussed the limitation of current disaster manage system by hand,and by the aided decision making requirement of managing to abrupt disaster urgently,studied and designed the basic structure and main pro- cedures of aided decision making system,mainly researched specific model and matching algorithm,and figured out matching and reasoning problem of task framework and manpower framework by the arithmetic,provided deci- sion maker and organization for basis to assign manpower reasonably,and pointed out universal application of aided decision making system at last.
Abstract In big data environments,utilizing a parallel Support Vector Machine (SVM) can significantly expedite the training process. However, prior efforts have faced challenges due to the excessive deviation of subset distribution, inadequate performance of parallel training, and poor filtering ability of non-support vector. To tackle these obstacles, this paper proposes a novel approach called SVM algorithm based on MapReduce (PSVM-MR). Firstly, a data partition method based on relative entropy (DP-RE) calculates relative entropy to prevent excessive deviation of subset distribution introduced. Secondly, it presents a redundancy level-removing method based on cosine similarity (RLR-CS) that addresses the inadequate performance of parallel training by eliminating the redundancy levels in the cascade structure. Finally, a non-support vector filtering method (NSVF) that enhances the ability of non-support vector filtering by combining rough identification and singular vector identification is proposed. The proposed algorithm demonstrates higher parallel efficiency and lower training costs compared to the general parallel SVM algorithm.
Traditional methods including algebra and category theory have some deficiencies in analyzing semantics properties and describing inductive rules of inductive data types, we present a method based on Fibrations theory aiming at those questions above. We systematically analyze some basic logical structures of inductive data types about a fibration such as re-indexing functor, truth functor and comprehension functor, make semantics models of non-indexed fibration, single-sorted indexed fibration and many-sorted indexed fibration respectively. On this basis, we thoroughly discuss semantics properties of fibred, single-sorted indexed and many-sorted indexed inductive data types, and abstractly describe their inductive rules with universality. Furthermore, we briefly introduce applications of the three inductive dana types for analyzing semantics properties and describing inductive rules based on Fibrations theory via some examples. Compared with traditional methods, our works have the following three advantages. Firstly, brief descriptions and flexible expansibility of Fibrations theory can analyze semantics properties of inductive data types accurately, whose semantics are computed automatically. Secondly, superior abstractness of Fibrations theory does not rely on particular computing environments to depict inductive rules of inductive data types with universality. Thirdly, its rigorousness and consistence provide sound basis for testing and maintenance of software development. ACM CCS (2012) Classification : Theory of computation→Logic→Constraint and logic programming *To cite this article: D. Miao et al ., "Inductive Data Types Based on Fibrations Theory in Programming", CIT. Journal of Computing and Information Technology , vol. 24, no. 1, pp. 1-16, 2016.
This paper discussed the important status of DSS during the course of MIS development,and by the decision support requirement of modem enterprise management,studied and designed the basic structure of decision information model.Then Data Mining technology of this model and its arithmetic is discussed.Potential information pattern providing knowledge of subsystem model can be excavated.The accuracy and catholicity of the arithmetic was pointed out finally.
Temporal data model is the mainline of trends in temporal database technology, and it is the core and basis of temporal database system development. Existing temporal data models focus on specific implementation among different abstract levels, the lack of unified concepts and systematic formal descriptions, especially the deficiency of solid theoretical foundation for universality, flexibility and extensibility etc., leads to some difficulties to meet actual needs of the temporal database systems development. This paper presented FTDM (Formal Temporal Data Model) at higher abstract level in accordance with the status of quo of temporal data models, proposed the definition of data model reuse by the thinking of software reuse, and further made temporal data models family Mi based on FTDM. By the methods of category theory this paper also demonstrated some categorical properties of Mi, and analyzed the inherent relationship between temporal data models in Mi, which provided an efficient and convenient formalization theory framework for studying temporal data model, also provided solid theoretical foundations for development and design of temporal database system.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)