Szczegóły publikacji
Opis bibliograficzny
Driver profiling by using LSTM networks with Kalman filtering / Adrian KŁUSEK, Marcin KURDZIEL, Mateusz PACIOREK, Piotr WAWRYKA, Wojciech TUREK // W: IV' 18 [Dokument elektroniczny] : the 2018 29th IEEE Intelligent Vehicles symposium : June 26-30, 2018, Suzhou, China. — Wersja do Windows. — Dane tekstowe. — [Piscataway : IEEE], [2018]. — Dysk Flash. — (IEEE Intelligent Vehicles Symposium ; ISSN 1931-0587). — e-ISBN: 978-1-5386-4451-5. — S. 1983–1988. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 1988, Abstr. — Toż w: https://ieeexplore-1ieee-1org-10000476j011b.wbg2.bg.agh.edu.pl/stamp/stamp.jsp?tp=&arnumber=8500715 [15-04-2019]
Autorzy (5)
Dane bibliometryczne
| ID BaDAP | 115574 |
|---|---|
| Data dodania do BaDAP | 2018-08-08 |
| DOI | 10.1109/IVS.2018.8500715 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | 29th IEEE Intelligent Vehicles Symposium |
| Czasopismo/seria | IEEE Intelligent Vehicles Symposium |
Abstract
Nowadays, the most common way to model the driver behavior is to create, under some assumptions, a model of common patterns in driver maneuvers. These patterns are often modeled with averaged driver model. While this idea is very simple and intuitive in the context of driver classification by his/her patterns of maneuvers, our previous works demonstrated that assumptions underlying such models are often inaccurate and not applicable in general settings. In fact, it is very hard to express driving patterns with simple models. In this article we present a new way of modeling drivers: we employ Long-Short Term Memory networks to learn driver models from telematics data. In particular, our neural network models learn to predict driving-related signals, such as speed or acceleration, given the evolution of these signals up to the point of prediction. Solving this prediction task allows us to capture the behavioral model of the driver. We tested our models on several drivers, by predicting their future decisions. By learning our models on one driver and then evaluating them on another driver, we demonstrate that LSTM models are a powerful tool for driver profiling and detection of abnormal situations. We also evaluate the influence of data preprocessing on the quality of predictions. In this context we use Kalman filtering, which can remove noise from uncertain dynamic measurements, in effect giving the best linearly estimated data.