Applied Mechanics and Materials Vols. 635-637

Abstract: Aimed at the Liquor-making with the characteristic of huge consumption of raw materials and energy,this paper presents a predictive method of Liquor-making energy consumption based on GA-BP Neural Net.Genetic algorithm of mixed coding was used to optimize the structure and initial values,and then BP algorithm adjusted weight and thresholding accurately.Construct the B-P model by using the neural networks toolbox of MATLAB. Optimize calculation based on MATLAB genetic algorithm toolbox using the real data of water consumption,electricity consumptionand steam consumption.The prediction results agrees well with the real data.Finally factual data are used to validate the validity and the rationality of the designed result .Liquor-making energy consumption mainly is water consumption,electricity consumption and steam consumption.Results in some extent can reflect the liquor enterprise energy consumption.Experiment shows that the method is effective for the liquor enterprise energy consumption.prediction.

Abstract: Some problems of decision support systems in computer aided agriculture are discussed. The main focus is made on collaborative model development, including model decomposition issues and implementation of generic frameworks for polyvariant model use. A current state and prospective ideas for improvement of modeling infrastructure suitable to perform multi-factor computer experiments with existing crop simulation models are presented.

Abstract: Some drawbacks of existing binary search algorithm has been improved to reduce the number of paging through improved reader in this paper to reduce the number of bytes for each tag and reader communication transmission, thereby reducing the improved algorithm of recognition time. At the same time, an improved binary anti-collision algorithm, and by Matlab simulation results show the advantages of the improved algorithm compared to other improved binary search algorithm.

Abstract: Grey model GM(1,1) is applied to forecast flight training time. The discreteness of originality data is overcome and the high-precise predicted result is received under the condition of a small amount of data. This paper takes a short-term forecast flight training time of Civil Aviation Flight University of China (CAFUC) by using grey system theory. With a comparison of the actual data to the forecast result, it is proved that using grey system theory to forecast the flight training time of Civil Aviation Flight University of China is feasible with relatively high prediction accuracy.

Abstract: Many methods are proposed to solve a system of linear equations (SLE), some are relatively efficient, in this study we use one type of Evolutionary Algorithms to solve a System of Linear Equation, the famous one: Genetic Algorithm (GA), we compare the efficiency of Genetic Algorithm and the determinant method (DM) in solving the system of linear equations, our experiences show that GA outperforms DM in almost all the cases.

Abstract: The purpose of this paper is to compare a mixed integer programming (MIP) model, and heuristic rules based on their practical efficiency and the accuracy of results to tackle the minimum lateness single machine scheduling problem with release and due date constraints. Extensive numerical experiments are carried out on randomly generated testing instances in order to evaluate the performance of the MIP model and heuristic rules.

Abstract: The three-dimensional GIS network as a new tourist information platform for the development of tourism provides a new opportunity to network with an intuitive three-dimensional GIS, real, easy to operate features, compared to the previous two-dimensional GIS to better showcase the beautiful tour scenic landscape view, therefore, the network will become three-dimensional GIS platform development of the tourism industry on the basis of the supporting platform. This paper focuses on the design and implementation of tourism services platform to illustrate the three-dimensional GIS used in the travel industry network inevitability.

Abstract: A noveol neural network of Elman is typically dynamic recurrent neural network. A novel method of flow regime identification based on Elman neural network and wavelet packet decomposition is proposed in this paper. Above all, the collected pressure-difference fluctuation signals are decomposed by the four-layer wavelet packet, and the decomposed signals in various frequency bands are obtained within the frequency domain. Then the wavelet packet energy eigenvectors of flow regimes are established. At last the wavelet packet energy eigenvectors are input into Elman neural network and flow regime intelligent identification can be performed.

Abstract: The purpose of this study is to investigate the performance of mathematics reading based on fuzzy clustering. Mathematics reading proficiency is an importance issue which is related to the reading comprehension, mathematics achievement and mathematics literacy. Theoretical foundation of mathematics reading consists of three components, which are general reading comprehension, prior knowledge of mathematics and specific skills of mathematics. The subject is sixth graders. The researchers develop internet system of mathematics assessment and adopt fuzzy clustering to appropriately classify students. Results show that three clusters are the best and there exist characteristics and differences among clusters. Based on the findings, some recommendations and suggestions for future research are provided.

Abstract: Local outliers detection is an important issue in data mining. By analyzing the limitations of the existing outlier detection algorthms, a local outlier detection algorthm based on coefficient of variation is introduced. This algorthms applies K-means which is strong in outliers searching, divides data set into sections, puts outliers and their nearing clusters into a local neighbourhood, then figures out the local deviation factor of each local neighbourhood by coefficient of variation, as a result, local outliers can more likely be found.The heoretic analysis and experimental results indicate that the method is ef fective and efficient.