• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • 1
  • Tagged with
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Generative Adversarial Networks for Vehicle Trajectory Generation / Generativa Motståndarnätverk för Generering av Fordonsbana

Bajarunas, Kristupas January 2022 (has links)
Deep learning models heavily rely on an abundance of data, and their performance is directly affected by data availability. In mobility pattern modeling, problems, such as next location prediction or flow prediction, are commonly solved using deep learning approaches. Despite advances in modeling techniques, complications arise when acquiring mobility data is limited by geographic factors and data protection laws. Generating highquality synthetic data is one of the solutions to get around at times when information is scarce. Trajectory generation is concerned with generating trajectories that can reproduce the spatial and temporal characteristics of the underlying original mobility patterns. The task of this project was to evaluate Generative Adversarial Network (GAN) capabilities to generate synthetic vehicle trajectory data. We extend the methodology of previous research on trajectory generation by introducing conditional trajectory duration labels and a model pretraining mechanism. The evaluation of generated trajectories consisted of a two-fold analysis. We perform qualitative analysis by visually inspecting generated trajectories and quantitative analysis by calculating the statistical distance between synthetic and original data distributions. The results indicate that extending the previous GAN methodology allows the novel model to generate trajectories statistically closer to the original data distribution. Nevertheless, a statistical base model has the best generative performance and is the only model to generate visually plausible results. We accredit the superior performance of the statistical base model to the highly predictive nature of vehicle trajectories, which must follow the road network and have the tendency to follow minimum distance routes. This research considered only one type of GAN-based model, and further research should explore other architecture alternatives to understand the potential of GAN-based models fully / Modeller för djupinlärning är starkt beroende av ett överflöd av data, och derasprestanda påverkas direkt av datatillgänglighet. I mobilitetsmönstermodellering löses problem, såsom nästa platsförutsägelse eller flödesprediktion,vanligtvis med hjälp av djupinlärningsmetoder. Trots framsteg inommodelleringsteknik uppstår komplikationer när inhämtning av mobilitetsdatabegränsas av geografiska faktorer och dataskyddslagar. Att generera syntetiskdata av hög kvalitet är en av lösningarna för att ta sig runt i tider dåinformationen är knapp. Bangenerering handlar om att generera banorsom kan reproducera de rumsliga och tidsmässiga egenskaperna hos deunderliggande ursprungliga rörlighetsmönstren. Uppgiften för detta projektvar att utvärdera GAN-kapaciteten för att generera syntetiska fordonsbanor. Viutökar metodiken för tidigare forskning om banagenerering genom att introducera villkorliga etiketter för banalängd och en modellförträningsmekanism.Utvärderingen av genererade banor bestod av en tvåfaldig analys. Viutför kvalitativ analys genom att visuellt inspektera genererade banor ochkvantitativ analys genom att beräkna det statistiska avståndet mellan syntetiskaoch ursprungliga datafördelningar. Resultaten indikerar att en utvidgningav den tidigare GAN-metoden tillåter den nya modellen att generera banorstatistiskt närmare den ursprungliga datadistributionen. Ändå har en statistiskbasmodell den bästa generativa prestandan och är den enda modellen somgenererar visuellt rimliga resultat. Vi ackrediterar den statistiska basmodellensöverlägsna prestanda till den mycket prediktiva karaktären hos fordonsbanor,som måste följa vägnätet och ha en tendens att följa minimiavståndsrutter.Denna forskning övervägde endast en typ av GAN-baserad modell, ochytterligare forskning bör utforska andra arkitekturalternativ för att förståpotentialen hos GAN-baserade modeller fullt ut
2

Capteurs de position innovants : application aux Systèmes de Transport Intelligents dans le cadre d'un observatoire de trajectoires de véhicules / New position sensors : application to Intelligent Transport Systems within the context of estimation of vehicule trajectories

Aubin, Sébastien 12 December 2009 (has links)
Améliorer la sécurité routière passe par une meilleure compréhension des causes d'accidents. Il est donc nécessaire de développer des observatoires discrets pour étudier la manière de conduire de tous les automobilistes. Une partie de cette analyse implique l'utilisation de capteurs mesurant les trajectoires des véhicules sur une portion de route. Deux capteurs innovants ont été crées pour pallier au manque de capteurs suffisamment précis pour ces travaux de recherche : le premier est un capteur à fibres optiques présentant une succession de réseaux de Bragg et le second, protégé par un brevet, est fondé sur une technologie résistive. Le premier repère la déformation locale de fibres optiques noyées à moins d'un centimètre sous la surface de la chaussée. Il utilise la variation de longueurs d'onde engendré par l'extension de la fibre à la zone de contact roue - sol. En utilisant un algorithme adéquat, il est insensible à la température. Le second est constitué de deux conducteurs dont un est résistif. Le poids du véhicule engendre un contact électrique entre les deux conducteurs, transformant la résistance électrique de l'ensemble. Les modèles développés, électrique ainsi que de variation thermique, permettent sa meilleure utilisation. Ils ont été soumis à une expérimentation sur une route départementale. Le capteur optique s'avère plus performant mais coûteux. Le deuxième n'est pas assez robuste mais présente des perspectives intéressantes. / This action stake is not technology for itself. It is a great help the development of new safety functions, e.g. the estimation of driver’s behaviour based uponthe vehicle’s trajectory. This trajectory is determined via two sensors we developed. This system must not disturb the driver and should therefore remain invisible to him. The first one is a fiber Bragg grating (FBG) sensor. It detects local strain due to the vehicle weight. The fiber is embedded in the road thanks to resin used in other traffic sensors. The vehicle location is spotted according to the variations of Bragg wavelengths. The fiber extension located under the ground - wheel contact zone changes the step of the Bragg grating. The second one is based upon two conductors. One of them has a grater electrical resistance. The vehicle’s weight creates a link between the two conductors. The resulting electrical resistance provides a lateral position estimation of the vehicle. Electrical and thermic models and simulation even increase the sensor reliability. A caveat is lodged. Both of them were tested on a secondary road. To put in a nutshell, the FBG sensor gives better results but is very expensive (sensors and interrogator too). The resistance sensor is not much raw nevertheless it has interesting perspectives.

Page generated in 0.0645 seconds