Applied Mechanics and Materials Vols. 687-691

Abstract: This paper studies on the data mining technology based on association rules, and analyzes on important algorithm in association rules - the advantages and disadvantages of Apriori algorithm and puts forward an improved Apriori-mapping algorithm based on address mapping. This algorithm adopts the way of horizontal deposit transaction, establishes candidate item identification list of corresponding candidate project transaction and length value of transaction list. And shorten the pruning operation time by address mapping, and compress the frequent item sets number of operation connected operation with large amplitude.The system efficiency is improved, and the performance of the algorithm has been improved by experiment.

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

Abstract: This paper describes the simulated annealing algorithm and TSP problems, analyze the applicability of simulated annealing algorithm to solve TSP problem, and takes China urban travel questions as an examples to vertified the validity of the model, the results showed that when the number of iterations reached at 4000,it will obtain the optimal solution.

Abstract: The topic tree-based topic structure model is proposed using five-tuple and probability theory of ontology. Vocabularies in the glossary are presented with leaf nodes of the topic tree. The results of simulation experiment on real news corpus eventually show that the topic similarity of sym-KL divergence could construct a topic tree more accurately and dig the potential semantic topic characteristics of time and space more deeply in the text stream compared with other flat topic structure models.

Abstract: This paper presents a topic ontology tree based hierarchical HMM (hHMM), and the generation of topic property based life cycle curve is studied. Compared with the traditional methods, this model can describe the hierarchy relations of topics.

Abstract: Aiming at the widely used differential equation in engineering practice, solution method based on recursion is proposed in this paper, and the theoretic proof of the local truncation error in the method ensures the calculation precision, meanwhile, the computational example verifies the correctness of the method. In all, a new way to the Variable Coefficients Differential Equation or the system of equations is offered in this paper.

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: In the retail enterprises, it is an important problem to choose goods group through their sales record.We should consider not only the direct benefits of product, but also the benefits bring by the cross selling. On the base of the mutual promotion in cross selling, in this paper we propose a new method to generate the optimal selected model. Firstly we use Apriori algorithm to obtain the frequent item sets and analyses the association rules sets between products.And then we analyses the above results to generate the optimal products mixes and recommend relationship in cross selling. The experimental result shows the proposed method has some practical value to the decisions of cross selling.

Abstract: With the rapid advance of data collection and storage technique, it is easy to acquire tens of millions or even billions of data sets. How to explore and exploit the useful or interesting information for human beings from these data sets has become an urgent issue. Traditional k-means clustering algorithm has been widely used in data mining community. First, randomly initialize k clustering centres. Then, all instances are classified into k different classes according to their distances to clustering centres. Lastly, update the clustering centres by the mean of its corresponding constituent instances. This whole process will be iterated until convergence. Obviously, at each iteration, distance matrix from all instances to k clustering centres must be calculated which will cost so much time when encounter large scale data sets. To address this issue, in this paper, we proposed a fast optimization algorithm based on stochastic gradient descent (SGD). At each iteration, randomly choose an instance, search its corresponding clustering centre and then update it immediately. Experimental results show that our proposed method achieves a competitive clustering results with less time cost.

Abstract: The scaling and corrosion of circulating cooling water have been a major concern in industry circulating cooling water system, severely affecting the production operation of the circulating cooling water system. In this paper, the circulating cooling water quality is investigated and analyzed. In addition, based on the water quality analysis of Petrochemical Industries Co, it is indicated that part of water quality parameters have great influence on the adhesion rate. In order to further forecast the adhesion rate, a NARX neural network prediction model is developed. Finally, the actual data sets are utilized to demonstrate the feasibility of proposed model.