Detection and description of traffic events using floating car and social media data

Download

index.pdf

Date

2022-9-12

Author

Ünsal, Ahmet Dündar

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

213
views

198
downloads

Detection and verification of traffic events, in traffic management, can be performed traditionally using roadside sensor data. More recently wide coverage travel time information obtained from floating car data (FCD) is also used, despite its limitations to describe the event characteristics and requires verification. Social media, widely adopted in our daily lives, hosts a sheer amount of data which can be analyzed to identify incidents and events using information retrieval methods. In this study, a framework is proposed to detect and describe traffic events in real-time using two independent data sources, FCD and Social Media Data (SMD). Traffic event related tweets in SMD are classified using a language model which is tailored to handle agglutinative nature of Turkish language. Detected traffic event tweets are geolocated using a custom named-entity recognition (NER) integrated, knowledge-based geocoding approach, which achieves a median positional error of 379.2 meters. In FCD, proposed detection tasks identified non-recurrent congestions (NRCs) with their spatiotemporal impact areas. Matching experiments using spatiotemporal information showed that 64.1% of traffic event reporting tweets can be verified by an NRC, whereas only 33% of the large-scale NRCs are verified by a tweet.

Subject Keywords

Traffic Event Detection, Intelligent Transportation Systems, Floating Car Data, Social Media

URI

https://hdl.handle.net/11511/99672

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Detection of urban traffic patterns from Floating Car Data (FCD) ALTINTAŞI, ORUÇ; Tüydeş Yaman, Hediye; Tuncay, Kağan (Elsevier BV; 2016-09-07) Real time data collection in traffic engineering is crucial for better traffic corridor control and management. In the literature, many data collection methods have been used such as; magnetic loops, road tube counters, piezo sensors, radars, Bluetooth etc. to estimate the link occupancy, average speed or density of a corridor. More recently, Floating Car Data (FCD) has become another important traffic data source and has an increasing usage due to its lower cost and higher coverage despite its reliability ...
Monitoring urban traffic from floating car data (fcd): using speed or a los-based state measure Altıntaşı, Oruç; Tüydeş Yaman, Hediye; Tuncay, Kağan (Springer, Cham, 2019-01-01) Floating Car Data (FCD) has an important traffic data source due to its lower cost and higher coverage despite its reliability problems. FCD obtained from GPS equipped vehicles can provide speed data for many segments in real-time, as provided by Be-Mobile for urban regions in Turkey. Though only providing speed per consecutive road segments, FCD is a great data source to visualize urban traffic state, in the absence of any other traffic data source, which is the focus of this study. After evaluation of var...
Characteristics of cloverleaf interchange in Turkey Yalçın, Esra Gözde; Tüydeş Yaman, Hediye; Department of Civil Engineering (2018) Level of Service (LOS) is a qualitative key attribute for monitoring traffic performance of road infrastructure. As interchanges are major but rather limited designs in road networks, providing uninterrupted flow with high capacities, there is a no LOS concept developed for them. However, data collection capability via Bluetooth (BT) readers located at interchange approaches make it possible to collect continuous speed and travel time data for all possible movements, which can lead to a measure for LOS for ...
Detecting queue length on urban arterials using floating car data (FCD) Altıntaşı, Oruç; Tüydeş Yaman, Hediye; Tuncay, Kağan; Department of Civil Engineering (2018) Accurate estimation of queue lengths whether in the approach of a signalized intersection or near a bottleneck location along an uninterrupted urban arterial is essential for better traffic management. This requires reliable traffic data, which is traditionally obtained from loop detectors, video cameras, etc. More recently, Floating Car Data (FCD) is being increasingly used as an alternative traffic data source due to its lower cost and high coverage area. Commercially available FCD is obtained from GPS eq...
Analysis of comprehension of traffic signs: a pilot study in Ankara, Turkey Kırmızıoğlu, Erkut; Tüydeş Yaman, Hediye; Department of Civil Engineering (2010) Traffic signs, which are extremely important for traffic safety, aims to regulate traffic by providing information about the characteristics of road and road environment for drivers. The success of traffic signs mainly rely on the easy comprehensibility of its meaning in a short time. Further more, today’s global economies and transportation systems emphasize the need for more universial traffic signs which was the main motivation of two main treaties on traffic signs; Vienna Convetion in 1968 and European ...

Citation Formats

A. D. Ünsal, “Detection and description of traffic events using floating car and social media data,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.