Entity

Time filter

Source Type


Xu T.,Civil Aviation University of China | Xu T.,Information Technology Research Base | Ding X.,Civil Aviation University of China | Li J.,Civil Aviation University of China
Journal of Software | Year: 2013

With the rapid development of high-speed railway and the changes of the tourists' requirement, it is imperative to the integrate advantages of aviation and rail. This paper constructs the air-rail integration model based on the current development situation and characteristics of Chinese railways. In allusion to the search problem of connecting path in air-rail integration network, a constrained Yen* algorithm is proposed to solve the problem in this paper. The constrained Yen* algorithm is set up by using the heuristic strategy of A* algorithm and two certain constraints by reducing running time to generate candidate paths. The experimental results show that the search problem of connecting path in air-rail integration network can be obtained fast by the constrained Yen* algorithm. Therefore, constrained Yen* algorithm is more efficient than constrained Yen algorithm in application. © 2013 ACADEMY PUBLISHER. Source


Huang J.,Beijing University of Technology | Ding J.,Civil Aviation University of China | Ding J.,Information Technology Research Base
Shuju Caiji Yu Chuli/Journal of Data Acquisition and Processing | Year: 2011

Risk evaluation is the base of the risk management of information system. It integrates expert oriented weight and factual data with math planning model to modify the fuzzy integral evaluation method for the risk evaluation of information system. The demonstration research with 30 firms proves the integrated weight fuzzy integral method is effectively. Source


Xie J.,Civil Aviation University of China | Xie J.,Information Technology Research Base | Xu T.,Civil Aviation University of China | Xu T.,Information Technology Research Base | Yang G.,Information Technology Research Base
Sensors and Transducers | Year: 2014

Mining the distribution pattern and evolution of the airport noise from the airport noise data and the geographic information of the monitoring points is of great significance for the scientific and rational governance of airport noise pollution problem. However, most of the traditional clustering methods are based on the closeness of space location or the similarity of non-spatial features, which split the duality of space elements, resulting in that the clustering result has difficult in satisfying both the closeness of space location and the similarity of non-spatial features. This paper, therefore, proposes a spatial clustering algorithm based on dual-distance. This algorithm uses a distance function as the similarity measure function in which spatial features and non-spatial features are combined. The experimental results show that the proposed algorithm can discover the noise distribution pattern around the airport effectively. © 2014 IFSA Publishing, S. L Source


Xu T.,Civil Aviation University of China | Xu T.,Information Technology Research Base | Yang Q.,Civil Aviation University of China | Lv Z.,Civil Aviation University of China | Lv Z.,Information Technology Research Base
Sensors and Transducers | Year: 2014

Using monitoring history data to build and to train a prediction model for airport noise is a normal method in recent years. However, the single model built in different ways has various performances in the storage, efficiency and accuracy. In order to predict the noise accurately in some complex environment around airport, this paper presents a prediction method based on hybrid ensemble learning. The proposed method ensembles three algorithms: artificial neural network as an active learner, nearest neighbor as a passive leaner and nonlinear regression as a synthesized learner. The experimental results show that the three learners can meet forecast demands respectively in on-line, near-line and off-line. And the accuracy of prediction is improved by integrating these three learners’ results. © 2014 IFSA Publishing, S. L. Source

Discover hidden collaborations