Trajectory classification based on machine-learning techniques over tracking data

Jesus García; Oscar Pérez Concha; José M. Molina; Gonzalo De Miguel

doi:10.1109/ICIF.2006.301629

Trajectory classification based on machine-learning techniques over tracking data

Jesus García^*, Oscar Pérez Concha, José M. Molina, Gonzalo De Miguel

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

17 Citations (Scopus)

Abstract

This work addresses the application of a machine-learning approach to classify ATC trajectory segments from recorded opportunity traffic. It is based on the mode probabilities estimated by an IMM tracking filter operating forward and backward over available data. A learning algorithm creates a rule base for classification from these data, once they have been properly prepared. Performance of this data-driven classification system is compared with a more conventional approach based on transition detection on simulated and real data of representative situations. The offline processing of real data allows an accurate classification of manoeuvring segments, with the possibility of synthesizing ground truth lines for performance evaluation.

Original language	English
Title of host publication	2006 9th International Conference on Information Fusion, FUSION
Place of Publication	Florence
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-8
Number of pages	8
ISBN (Print)	1424409535, 9781424409532, 0972184465
DOIs	https://doi.org/10.1109/ICIF.2006.301629
Publication status	Published - 2006
Externally published	Yes
Event	2006 9th International Conference on Information Fusion, FUSION - Florence, Italy Duration: 10 Jul 2006 → 13 Jul 2006

Other

Other	2006 9th International Conference on Information Fusion, FUSION
Country/Territory	Italy
City	Florence
Period	10/07/06 → 13/07/06

Keywords

Artificial intelligence
Data mining
Trajectory classification and reconstruction

Access to Document

10.1109/ICIF.2006.301629

Cite this

@inproceedings{2959d5edfac841e28b57224305b08bc5,

title = "Trajectory classification based on machine-learning techniques over tracking data",

abstract = "This work addresses the application of a machine-learning approach to classify ATC trajectory segments from recorded opportunity traffic. It is based on the mode probabilities estimated by an IMM tracking filter operating forward and backward over available data. A learning algorithm creates a rule base for classification from these data, once they have been properly prepared. Performance of this data-driven classification system is compared with a more conventional approach based on transition detection on simulated and real data of representative situations. The offline processing of real data allows an accurate classification of manoeuvring segments, with the possibility of synthesizing ground truth lines for performance evaluation.",

keywords = "Artificial intelligence, Data mining, Trajectory classification and reconstruction",

author = "Jesus Garc{\'i}a and Concha, \{Oscar P{\'e}rez\} and Molina, \{Jos{\'e} M.\} and \{De Miguel\}, Gonzalo",

year = "2006",

doi = "10.1109/ICIF.2006.301629",

language = "English",

isbn = "1424409535",

pages = "1--8",

booktitle = "2006 9th International Conference on Information Fusion, FUSION",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2006 9th International Conference on Information Fusion, FUSION ; Conference date: 10-07-2006 Through 13-07-2006",

}

García, J, Concha, OP, Molina, JM & De Miguel, G 2006, Trajectory classification based on machine-learning techniques over tracking data. in 2006 9th International Conference on Information Fusion, FUSION., 4085915, Institute of Electrical and Electronics Engineers (IEEE), Florence, pp. 1-8, 2006 9th International Conference on Information Fusion, FUSION, Florence, Italy, 10/07/06. https://doi.org/10.1109/ICIF.2006.301629

Trajectory classification based on machine-learning techniques over tracking data. / García, Jesus; Concha, Oscar Pérez; Molina, José M. et al.
2006 9th International Conference on Information Fusion, FUSION. Florence: Institute of Electrical and Electronics Engineers (IEEE), 2006. p. 1-8 4085915.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Trajectory classification based on machine-learning techniques over tracking data

AU - García, Jesus

AU - Concha, Oscar Pérez

AU - Molina, José M.

AU - De Miguel, Gonzalo

PY - 2006

Y1 - 2006

N2 - This work addresses the application of a machine-learning approach to classify ATC trajectory segments from recorded opportunity traffic. It is based on the mode probabilities estimated by an IMM tracking filter operating forward and backward over available data. A learning algorithm creates a rule base for classification from these data, once they have been properly prepared. Performance of this data-driven classification system is compared with a more conventional approach based on transition detection on simulated and real data of representative situations. The offline processing of real data allows an accurate classification of manoeuvring segments, with the possibility of synthesizing ground truth lines for performance evaluation.

AB - This work addresses the application of a machine-learning approach to classify ATC trajectory segments from recorded opportunity traffic. It is based on the mode probabilities estimated by an IMM tracking filter operating forward and backward over available data. A learning algorithm creates a rule base for classification from these data, once they have been properly prepared. Performance of this data-driven classification system is compared with a more conventional approach based on transition detection on simulated and real data of representative situations. The offline processing of real data allows an accurate classification of manoeuvring segments, with the possibility of synthesizing ground truth lines for performance evaluation.

KW - Artificial intelligence

KW - Data mining

KW - Trajectory classification and reconstruction

UR - https://www.scopus.com/pages/publications/50149110922

U2 - 10.1109/ICIF.2006.301629

DO - 10.1109/ICIF.2006.301629

M3 - Conference proceeding contribution

AN - SCOPUS:50149110922

SN - 1424409535

SN - 9781424409532

SN - 0972184465

SP - 1

EP - 8

BT - 2006 9th International Conference on Information Fusion, FUSION

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Florence

T2 - 2006 9th International Conference on Information Fusion, FUSION

Y2 - 10 July 2006 through 13 July 2006

ER -

Trajectory classification based on machine-learning techniques over tracking data

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this