Szczegóły publikacji
Opis bibliograficzny
Effective car collision detection with mobile phone only / Mateusz PACIOREK, Adrian KŁUSEK, Piotr WAWRYKA, Michał Kosowski, Andrzej Piechowicz, Julia Plewa, Marek Powroźnik, Wojciech Wach, Bartosz Rakoczy, Aleksander BYRSKI, Marcin KURDZIEL, Wojciech TUREK // W: Computational Science – ICCS 2021 : 21st International Conference : Krakow, Poland, June 16–18, 2021 : proceedings, Pt. 6 / eds. Maciej Paszyński, [et al.]. — Cham : Springer Nature Switzerland, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12747. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-030-77979-5; e-ISBN: 978-3-030-77980-1. — S. 303–317. — Bibliogr., Abstr. — Publikacja dostępna online od: 2021-06-09
Autorzy (12)
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 134761 |
---|---|
Data dodania do BaDAP | 2021-07-14 |
DOI | 10.1007/978-3-030-77980-1_24 |
Rok publikacji | 2021 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Konferencja | 21st International Conference on Computational Science |
Czasopisma/serie | Lecture Notes in Computer Science, Theoretical Computer Science and General Issues |
Abstract
Despite fast progress in the automotive industry, the number of deaths in car accidents is constantly growing. One of the most important challenges in this area, besides crash prevention, is immediate and precise notification of rescue services. Automatic crash detection systems go a long way towards improving these notifications, and new cars currently sold in developed countries often come with such systems factory installed. However, the majority of life threatening accidents occur in low-income countries, where these novel and expensive solutions will not become common anytime soon. This paper presents a method for detecting car collisions, which requires a mobile phone only, and therefore can be used in any type of car. The method was developed and evaluated using data from real crash tests. It integrates data series from various sensors using an optimized decision tree. The evaluation results show that it can successfully detect even minor collisions while keeping the number of false positives at an acceptable level.