hrcak mascot   Srce   HID

Pregledni rad
https://doi.org/10.17559/TV-20150616163905

Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection

Bin Sun ; Kunming University of Science and Technology, Kunming 650093, China / Blekinge Institute of Technology, Karlskrona 37179, Sweden
Wei Cheng ; Kunming University of Science and Technology, Kunming 650093, China / Blekinge Institute of Technology, Karlskrona 37179, Sweden
Guohua Bai ; Kunming University of Science and Technology, Kunming 650093, China / Blekinge Institute of Technology, Karlskrona 37179, Sweden
Prashant Goswami ; Kunming University of Science and Technology, Kunming 650093, China / Blekinge Institute of Technology, Karlskrona 37179, Sweden

Puni tekst: engleski, pdf (3 MB) str. 1597-1607 preuzimanja: 156* citiraj
APA 6th Edition
Sun, B., Cheng, W., Bai, G. i Goswami, P. (2017). Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection. Tehnički vjesnik, 24 (5), 1597-1607. https://doi.org/10.17559/TV-20150616163905
MLA 8th Edition
Sun, Bin, et al. "Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection." Tehnički vjesnik, vol. 24, br. 5, 2017, str. 1597-1607. https://doi.org/10.17559/TV-20150616163905. Citirano 21.10.2020.
Chicago 17th Edition
Sun, Bin, Wei Cheng, Guohua Bai i Prashant Goswami. "Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection." Tehnički vjesnik 24, br. 5 (2017): 1597-1607. https://doi.org/10.17559/TV-20150616163905
Harvard
Sun, B., et al. (2017). 'Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection', Tehnički vjesnik, 24(5), str. 1597-1607. https://doi.org/10.17559/TV-20150616163905
Vancouver
Sun B, Cheng W, Bai G, Goswami P. Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection. Tehnički vjesnik [Internet]. 2017 [pristupljeno 21.10.2020.];24(5):1597-1607. https://doi.org/10.17559/TV-20150616163905
IEEE
B. Sun, W. Cheng, G. Bai i P. Goswami, "Correcting and complementing freeway traffic accident data using Mahalanobis distance based outlier detection", Tehnički vjesnik, vol.24, br. 5, str. 1597-1607, 2017. [Online]. https://doi.org/10.17559/TV-20150616163905
Puni tekst: hrvatski, pdf (3 MB) str. 1597-1607 preuzimanja: 318* citiraj
APA 6th Edition
Sun, B., Cheng, W., Bai, G. i Goswami, P. (2017). Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti. Tehnički vjesnik, 24 (5), 1597-1607. https://doi.org/10.17559/TV-20150616163905
MLA 8th Edition
Sun, Bin, et al. "Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti." Tehnički vjesnik, vol. 24, br. 5, 2017, str. 1597-1607. https://doi.org/10.17559/TV-20150616163905. Citirano 21.10.2020.
Chicago 17th Edition
Sun, Bin, Wei Cheng, Guohua Bai i Prashant Goswami. "Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti." Tehnički vjesnik 24, br. 5 (2017): 1597-1607. https://doi.org/10.17559/TV-20150616163905
Harvard
Sun, B., et al. (2017). 'Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti', Tehnički vjesnik, 24(5), str. 1597-1607. https://doi.org/10.17559/TV-20150616163905
Vancouver
Sun B, Cheng W, Bai G, Goswami P. Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti. Tehnički vjesnik [Internet]. 2017 [pristupljeno 21.10.2020.];24(5):1597-1607. https://doi.org/10.17559/TV-20150616163905
IEEE
B. Sun, W. Cheng, G. Bai i P. Goswami, "Ispravljanje i nadopunjavanje podataja o prometnim nesrećama na autocesti putem Mahalanobis udaljenosti na temelju otkrivanja netipičnih vrijednosti", Tehnički vjesnik, vol.24, br. 5, str. 1597-1607, 2017. [Online]. https://doi.org/10.17559/TV-20150616163905

Sažetak
A huge amount of traffic data is archived which can be used in data mining especially supervised learning. However, it is not being fully used due to lack of accurate accident information (labels). In this study, we improve a Mahalanobis distance based algorithm to be able to handle differential data to estimate flow fluctuations and detect accidents and use it to support correcting and complementing accident information. The outlier detection algorithm provides accurate suggestions for accident occurring time, duration and direction. We also develop a system with interactive user interface to realize this procedure. There are three contributions for data handling. Firstly, we propose to use multi-metric traffic data instead of single metric for traffic outlier detection. Secondly, we present a practical method to organise traffic data and to evaluate the organisation for Mahalanobis distance. Thirdly, we describe a general method to modify Mahalanobis distance algorithms to be updatable.

Ključne riječi
accident data; data labelling; differential distance; Mahalanobis distance; outlier detection; traffic data; updatable algorithm

Hrčak ID: 188258

URI
https://hrcak.srce.hr/188258

[hrvatski]

Posjeta: 735 *