488
Q. Xu et al.
Many researchers in the field of ATM focus on information management and
efficient use methods in the operation of air traffic control.
Some researchers [8,9] introduce the concept of System Wide Information
Management (SWIM). As an information switch platform based on network
technology, it has been shown that relevant data can be safely, effectively, and
timely shared and exchanged between different units and information systems.
Medina et al. [10] describe a usability analysis tool which computes estimate
of trials-to-mastery and the probability of failure-to-complete for each task. The
information required to complete a task on the automation under development
is entered into the Web-based tool via a form. Yang et al. [11] look ahead the
concept of intellectualized air traffic management technology, represented by
deep learning, emphasizes that judgment and decision-making based on a large
number of prior knowledges, which is consistent with the decision-making process
of ATM.
However, most of the proposed methods put much emphasize on the breadth
while not depth of information that system can handle, and thus leading to the
failure to solve the depth-related problems. For example, is there relationship
between flight CCA4228 and CES2471? If yes, what is the relationship? Is Shanghai Pudong Airport related to Beijing Capital Airport? If so, how is it related?
Inspired by the research idea of applying knowledge graph in social network,
which can represent the breadth of a person’s social relationship and analyze the
depth of the relationship between any two people, we propose an information
fusion and correlation analysis method based on ATM knowledge graph [12].
The main contributions of this paper are outlined as follows.
(1) Using ATM knowledge graph to reorganize the information flexibly and manage the fusion process dynamically.
(2) Based on the ATM knowledge graph, a breadth-first and depth-first searchbased correlation analysis method is proposed to get all related feature
instances on breadth and get relative path on depth.
Experimental results show that, compared with the traditional fusion and
search method, the proposed method can find more deeper correlation and
improve the searching efficiency.
The structure of the paper is organized as follows. Section 2 describes the
problem definition. Section 3 shows the ATM knowledge graph-based information
fusion and correlation analysis method. Section 4 shows the experimental results,
and at last conclusions are made at Sect. 5.
2 Problem Definition
The ATM feature types commonly used in ATM information system include airports, runways, routes, airspace, flights, airlines, route points, control units, etc.
Most of these commonly used information uses object-oriented design method,
that is, to design a type template for each kind of feature, and mainly uses
tables in entity-relationship databases for storage, which finally convert each
data entity into a row of records.
Q. Xu et al.
Many researchers in the field of ATM focus on information management and
efficient use methods in the operation of air traffic control.
Some researchers [8,9] introduce the concept of System Wide Information
Management (SWIM). As an information switch platform based on network
technology, it has been shown that relevant data can be safely, effectively, and
timely shared and exchanged between different units and information systems.
Medina et al. [10] describe a usability analysis tool which computes estimate
of trials-to-mastery and the probability of failure-to-complete for each task. The
information required to complete a task on the automation under development
is entered into the Web-based tool via a form. Yang et al. [11] look ahead the
concept of intellectualized air traffic management technology, represented by
deep learning, emphasizes that judgment and decision-making based on a large
number of prior knowledges, which is consistent with the decision-making process
of ATM.
However, most of the proposed methods put much emphasize on the breadth
while not depth of information that system can handle, and thus leading to the
failure to solve the depth-related problems. For example, is there relationship
between flight CCA4228 and CES2471? If yes, what is the relationship? Is Shanghai Pudong Airport related to Beijing Capital Airport? If so, how is it related?
Inspired by the research idea of applying knowledge graph in social network,
which can represent the breadth of a person’s social relationship and analyze the
depth of the relationship between any two people, we propose an information
fusion and correlation analysis method based on ATM knowledge graph [12].
The main contributions of this paper are outlined as follows.
(1) Using ATM knowledge graph to reorganize the information flexibly and manage the fusion process dynamically.
(2) Based on the ATM knowledge graph, a breadth-first and depth-first searchbased correlation analysis method is proposed to get all related feature
instances on breadth and get relative path on depth.
Experimental results show that, compared with the traditional fusion and
search method, the proposed method can find more deeper correlation and
improve the searching efficiency.
The structure of the paper is organized as follows. Section 2 describes the
problem definition. Section 3 shows the ATM knowledge graph-based information
fusion and correlation analysis method. Section 4 shows the experimental results,
and at last conclusions are made at Sect. 5.
2 Problem Definition
The ATM feature types commonly used in ATM information system include airports, runways, routes, airspace, flights, airlines, route points, control units, etc.
Most of these commonly used information uses object-oriented design method,
that is, to design a type template for each kind of feature, and mainly uses
tables in entity-relationship databases for storage, which finally convert each
data entity into a row of records.