Time filter

Source Type

Feng X.,Civil Aviation University of China | Feng X.,Information Technology Research Base of CAAC | Ren Z.-Y.,Civil Aviation University of China
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | Year: 2016

Aircraft ground service is an important part of the airport operation. The series of ground services aircraft accepts during its turnaround time are performed by non-homogeneous service vehicles. Time constraint relationship between refueling services and boarding services is determined through analyzing operational process of airport flight turnaround services. Then collaborative scheduling model of refueling services and boarding services of the apron flights is built. The collaborative scheduling model has two objectives. One is minimizing the total number of fuelling vehicle and ferry vehicle the services need. The other is minimizing the total start time of refueling services and boarding services. Then the solution method for the model based on multi-objective genetic algorithm is given. Experimental results based on actual operation data of Beijing Capital International Airport show that the proposed model could solve the collaborative scheduling problem of fuelling vehicle and ferry vehicle well. A set of Pareto optimal solutions obtained from the experiment could provide decision support for business departments. Copyright © 2016 by Science Press.

Feng X.,Civil Aviation University of China | Feng X.,Information Technology Research Base of CAAC | Chen H.,Civil Aviation University of China | Li Y.,Civil Aviation University of China
Information and Control | Year: 2013

There are some problems in traditional symmetric nonnegative matrix factorization algorithm for discovering community structure in complex networks, such as the instability of result and time consuming of convergence. In view of these, a community discovery method of symmetric nonnegative matrix factorization combined with singular value decomposition (SVD) is proposed. Firstly, based on SVD, the approximations for the rank-Kapproximate matrix of the complex networks feature matrix conduct twice, so as to get effective initial matrix. Then the final matrix factor is calculated using symmetric nonnegative matrix method and network community structure can be found by judging the classification of nodes. Experimental results on computer-generated and real-world networks show that the proposed method is stable and effective and it performs better on the convergence speed and community detection accuracy than traditional symmetric nonnegative matrix factorization method.

Feng X.,Civil Aviation University of China | Feng X.,Information Technology Research Base of CAAC | Zhang C.,Information Technology Research Base of CAAC | Lu M.,Civil Aviation University of China | And 2 more authors.
Energy Education Science and Technology Part A: Energy Science and Research | Year: 2014

Noise exposure arising from air traffic has become the main reason of confliction between airports and nearby communities in most major cities around the world. A reasonable noise annoyance model plays an important role in airport planning and designing, airport noise controlling, and urban planning. In this paper we present a study on a model related to noise annoyance caused by aircrafts. The model is based on fuzzy logic and could be considered as a function of noise level, noise occurring period of day, and noise impact zones. It can describe the noise annoyance caused by aircrafts in a quantitative, visual way, and the crisp value can be more convenient for people to understand. In some way, it provides theoretical support for optimizing aircraft trajectories minimizing population annoyance, and suggests an avenue for further research. With the noise data provided by Beijing Capital International Airport (BCIA), this paper also evaluates the noise annoyance of 13 monitoring sites. © Sila Science. All Rights Reserved.

Zhang Z.,Civil Aviation University of China | Zhang Z.,Information Technology Research Base of CAAC | Feng X.,Civil Aviation University of China | Feng X.,Information Technology Research Base of CAAC
Journal of Computational Information Systems | Year: 2014

Text categorization is an essential task in data mining. In text categorization, the most conventional method for document representation is bag-of-words approach which is an unordered collection of weighted terms that best describe the document. These terms are independently treated in traditional text categorization methods and their semantic relations are ignored. This paper uses corpus-based thesaurus to add semantic background knowledge on documents. Two thesaurus are constructed based on cosine similarity and Pearson's correlation coefficient metric. Two kinds of feature weighting adjustment approaches using thesaurus are also proposed. k-NN algorithm is employed as the classifier. Experimental results on 20-News-Group data show that both of the approaches achieve better performance than traditional ones. Copyright © 2014 Binary Information Press.

Xia F.,Civil Aviation University of China | Xia F.,Information Technology Research Base of CAAC | Bing-Yu X.,Civil Aviation University of China | Min L.,Civil Aviation University of China | And 2 more authors.
Journal of Computational and Theoretical Nanoscience | Year: 2015

For the situation widespread in the civil aviation industry that large numbers of potential high-value passengers was ignored or can not be analysis because of technical reasons by airlines, a potential high-value passengers discovery by random walk on passenger-route heterogeneous network method was been proposed. Simulates the behavior of airline passengers choose routes by building a heterogeneous network of passengers and routes, and random walk between the departure airport and destination airport to discover the potential flight demand of each passenger, and thus evaluate potential value of passengers more effectively. Experiment on the PNR data set of civil aviation reservation systems of China shows: the algorithm we proposed is not only effective for frequent passengers, but also for the common passengers, it can found the passengers that travel by plane infrequently at present, but have great demand and become frequent passengers in the future. Copyright © 2015 American Scientific Publishers.

Discover hidden collaborations