Papers by Keyword: Rough Set

Abstract: In order to reduce the false alarm rate in coal mine fire warning system, we apply information fusion technology to the system and propose a fire forecast algorithm based on Rough Set Support Vector Machine ( RS-SVM ). Firstly, we map the feature description of coal mine fires to the knowledge representation system described by rough set; Secondly, we discrete the continuous attributes and eliminate the redundant information for attribute reduction to form a rule set of this knowledge representation system; At last, we use the above rule set as the training sample to optimize the parameters for the fire warning support vector machine. The experimental results show that the accuracy of the algorithm is very high. It can make timely and accurate prediction of coal mine fire.

Abstract: During the analysis of stability heat conduction in the composite pipes, firstly, when the heat equation contained fuzzy and random uncertain parameters, interval equations of the heat conduction are presented in the rough set. Secondly, the error expecting of heat conduction equation is presented. Finally, with upper (lower) approximation in rough set, a new method of the rough set analysis to deal with the stability heat conduction is presented.

Abstract: Rough set theory is a popular mathematical knowledge to resolve problems which are vagueness and uncertainly. And it has been used of solving the redundancy of attribute and data. Decision tree has been widely used in data mining techniques, because it is efficient, fast and easy to be understood in terms of data classification. There are many approaches have been used to generate a decision tree. In this paper, a novel and effective algorithm is introduced for decision tree. This algorithm is based on the core of discernibility matrix on rough set theory and the degree of consistent dependence. This algorithm is to improve the decision tree on node selection. This approach reduces the time complexity of the decision tree production and space complexity compared with ID3.In the end of the article, there is an example of the algorithm can exhibit superiority.

Abstract: A new classified real-time flood forecasting framework was presented. Firstly, the historical floods were classified by K-means cluster, according to the hydrological factors. Then rough set was used to extract operation rules for flood forecasting. Following, the conceptual hydrological model was constructed and Genetic Algorithm (GA) was used to calibrate the hydrological model parameters. In simulation, River A is taken as study example. The categories of parameters are selected in operation according to flood information and rules. The result is compared with traditional flood forecasting. It demonstrates the performance of classified framework is improved in terms of accuracy and reliability.

Abstract: In order to intensively study the stability influencing factors of rockfill dam slope in tailing pond, it was simplified to the common rock slope. And the data of 45 groups of circular failure slope was collected, based on the discrete normalization, the condition attributes of influencing stability were reduced by Rough Set theory (RS), at the same time, the stability influencing factors were simplified by Principal Component Analysis (PCA). Combining the two results through the above two methods, the main affecting factors of the rockfill dam slope’s stability are: rock density, slope angle and the angle of internal friction. The study conclusion can provide the decision-making basis for the rockfill dam design and safety management, and also be used as the foundation for other intelligent algorithm to predict the dam safety coefficient.

Abstract: Concrete mixing station location occupies a very important position in the supply chain of the commercial concrete, location not only affects the cost, but the level of quality of concrete delivery service. In view of the traditonal location model only pursuing the cost minimization and neglecting serive level, the reliability is introduced into location model as a standard of concrete delivery service, to establish a multi-objective model which uses the cost minimization and reliability maximization as the objective function. Finally, the effectiveness of the model was confirmed by a numerical example.

Abstract: The attribute reduction algorithm of radix sort to integer digit sequence table is not ideal. In this paper, based on how integers is stored in computer memory, low and high storage mode is designed for the solving algorithm of U/C chain structure of a new reasonable optimization. The time complexity of the algorithm from O (K|C| |U|) is reduced to O (K|C| |U| log (|M|)). The efficiency of the algorithm is improved by 3.8%.

Abstract: This paper tries to find a more feasible method to achieve core and reduction. Against concepts "distinguishable relation of attribute set" and "distinguishable unit set of attribute set", it defines a concept "important index", and proposes an effective and quick approach for important index. After drawn out the involved theory and equivalent proposition, also presents algorithms for core and reduction upon the important index. The heuristic reduction algorithm adopts the bottom-up design, and gets reduction based on the heuristic information "important index of attribute set". The complexity of the algorithm in space is O(m), and the complexity in time is O(mn²). The theoretical analysis and results show that the ways proposed here simplify the relevant operations and are suitable to deal with the huge volume of data.

Abstract: In this paper,the basic idea is to use fuzzy conversion principle,through membership degree theory to qualitative evaluation into quantitative evaluation,and consider all relevant factors, from the lowest level of each factor level comprehensive evaluation, followed up until the highest target layer, thus subject to many factors thing or object to make a relatively objective, accurate, realistic assessment. Then solve practical problems with fuzzy nature. It has the result of clear, systematic and strong features can solve vague, difficult to quantify the problem, suitable for solving a variety of non-deterministic problem.

Abstract: This paper proposes a rough set model with to tolerance relation based on conditional prior probability. The new model can effectively improve classification reasonability, which base on the statistics of property values in incomplete decision system. It takes into account both the different conditions with the same attribute value and the correlation between different attributes. The model is practical for the system with significant correlation among attributes and fewer unknown attribute values