발간년도 : [2023]
| 논문정보 |
|
| 논문명(한글) |
[Vol.18, No.6] A Study on Artificial Intelligent-based Trajectory Pattern Mining for Smart Vehicular Traffic |
|
| 논문투고자 |
Jinhong Kim, Chulbum Ahn |
|
| 논문내용 |
Recently, with the rapid growth and widespread use of GPS devices, RFID sensors using Internet ofThings, wireless communication, and artificial intelligent, it has become possible to track various movingobjects in real-world. In addition, an increasing number of trajectories are being collected and stored indatabases, often containing valuable knowledge that requires urgent analysis. As the adoption of locationacquisition technologies increases, here is a growing opportunity to collect large-scale spatio-temporaldatasets and discover actionable knowledge about moving behaviors, fostering the development of newapplications and services. The main functionalities and modules of activity pattern discovery systeminclude trajectory preprocessing, trajectory clustering, periodic pattern discovery, and an extensiblevisualization module for parameter interaction and result presentation. In the experimental part, wevalidate the accuracy and efficiency of activity pattern discovery system using taxi trajectory data fromKorea. In this paper, we develop an extension of the sequential pattern mining paradigm to analyzetrajectories of moving objects in this direction. In addition, we introduce trajectory patterns as concisedescriptions of frequent behaviors in terms of space and time. In this setting, we propose a generalformalization for the novel mining problem and then study several different instances of varyingcomplexities. Fianlly, we empirically evaluate different approaches on real-world data and syntheticbenchmarks to compare their strengths and weaknesses. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
