Visual Analysis for Civil Aviation Passenger Reservation Data Characteristics Based on Uncertainty Measurement
Aviation data analysis can help airlines to understand passenger needs, so as to provide passengers with more sophisticated and better services. How to explore the implicit message and analyze contained features from large amounts of data has become an im
- PDF / 5,544,208 Bytes
- 11 Pages / 439.37 x 666.14 pts Page_size
- 28 Downloads / 172 Views
)
Department of Computer Science and Technology, Civil Aviation University of China, Tianjin, China [email protected]
Abstract. Aviation data analysis can help airlines to understand passenger needs, so as to provide passengers with more sophisticated and better services. How to explore the implicit message and analyze contained features from large amounts of data has become an important issue in the civil aviation passenger data analysis process. The uncertainty analysis and visualization methods of data record and property measurement are offered in this paper, based on the visual analysis and uncertainty measure theory combined with parallel coordinates, radar chart, histogram, pixel chart and good interaction. At the same time, the data source expression clearly shows the uncertainty and hidden information as an information base for passengers’ service recommendations. Keywords: Civil aviation passenger data · Uncertainty · Visual analysis
1
Introduction
With China’s social progress and economic development, its civil aviation passenger constitute in the domestic market has undergone great changes, which have an important impact on the demand characteristics of travelers and are gradually changing the pattern of the future society transport market. Currently, the scale of civil aviation passenger data records becomes increasing, which can provide good suggestions for improving the business by passenger travel behavior-depth analysis. At the same time it needs to be aware that the travel choice randomness exists in passenger travel due to the impact of various events, such as weather, travel location, personal preferences, etc., namely uncertainty. The degree of personal uncertainty largely determines the future evolution of travel. The uncertainty analysis applied to the passenger data in recommender system can help researchers analyze the transfer degree of historical preference for users, which can provide passengers with personalized service and create value. Aviation passenger reservation data is a typical of high-dimensional dataset, including the user’s age, gender, travel records and other properties. A simple and fast way to reflect the characteristics of these properties is required, and visualization techniques can display multi-dimensional data in a low-dimensional space intuitively, effectively and interactively, which also explore data patterns and models to uncover the relationship between each property [1]. At present, the basic methods of multi-dimensional data © Springer Science+Business Media Singapore 2016 W. Chen et al. (Eds.): BDTA 2015, CCIS 590, pp. 15–25, 2016. DOI: 10.1007/978-981-10-0457-5_3
16
H. He et al.
visualization: space mapping, icons and pixel-based visualization methods, such as parallel coordinates, scatter, Chernoff Faces, radar chart, pixel chart. Parallel coordinates is a common method for multidimensional data, but the overlapping will affect the judge‐ ment for how much the value of the shaft, therefore the histograms is introduced in parallel coordinates to displ
Data Loading...
