Lidé na fakultě
Ing. Zuzana Purkrábková

2024, Transportation Research Procedia, Amsterdam, Elsevier B.V.), p. 619-626), ISSN 2352-1465

This paper presents a method for assessing the quality of floating car data and estimating emissions of the road network. The authors use a fundamental diagram from real probe vehicles to determine the categorization of the road network. These data are complemented by the widely used emission factors of the COPERT model to investigate the quality of the floating vehicle data to use them for the determination of emissions on individual road classes with a detailed spatiotemporal resolution. From the same data, an estimate of the emission rate of the categories is determined and it is assessed whether similar differences are exhibited. The hypothesis is that the quality of data is quite sufficient on highways and high-class roads, but unusable and insufficient on low-class roads. The results show that differences in emission estimates can be observed for the road categories of the highway network and low-class road network. For some pollutants, the urban network can also be identified. The offered categorization could lead to further possibilities of using floating vehicle data, such as the assumption of the possibility to detect atypical traffic phenomena (traffic jams, accidents, or impassable roads due to bad weather conditions).

Stať ve sborníku z prestižní konf. (Scopus)

2024, Neural Network World, 34 (4), p. 203-218), ISSN 1210-0552

The primary objective of the presented research is to enhance an existing data quality control application by integrating advanced anomaly detection mechanisms based on generalized additive models. This approach targets time- series traffic data, where traditional methods may fall short in identifying complex, non-linear patterns of anomalies. In collaboration with Simplity s.r.o., we are extending their current data quality assessment tool to incorporate generalized additive models, providing a more robust and dynamic solution for monitoring and ensuring the reliability of traffic datasets. The integration of these models aims to improve the accuracy of anomaly detection, leading to more effective data management in transport systems and contributing to higher standards of data quality in the field of traffic informatics.

Článek v periodiku excerpovaném SCI Expanded

2024

Zpráva o činnosti ČVUT FD v roce 2023 při řešení projektu Nástroje kvality dat pro zabezpečení systémové spolehlivosti dopravně informačních center.

Výzkumná zpráva v češtině

2024, 2024 Smart City Symposium Prague - IEEE PROCEEDINGS, New York, IEEE Press), ISBN 979-8-3503-6096-7, ISSN 2831-5618

Within the activities of planning, organizing, or regulating traffic, a considerable amount of various traffic data is actively used. For responsible data-based decision-making, the quality of the utilized data is crucial. However, defining the specifics of this quality and establishing procedures for its control is often ambiguous. The primary objective of the research was to review methods for ensuring or managing data quality within the transportation environment. Building on the collected information, a practical data governance approach was delineated to be applied to specific transportation data. Simultaneously, data from detectors and floating vehicles on the highway network in the Czech Republic were analyzed for the same reason. The results show that the chosen data governance approaches are applicable to transportation data, even in the task of evaluating data quality in the detail of individual dimensions. In the context of semantic data quality control, it is necessary to explore additional suitable tools, such as the use of statistical models, to reliably distinguish real errors or otherwise reduced data quality from genuinely truthful values, such as traffic conditions.

Stať ve sborníku z prestižní konf.

2023, European Transport (93), ISSN 1825-3997

Data from floating vehicles is a modern technology and can be another source of data. There is a free data source available in the Czech Republic, which is relatively new. The addressed source of data from floating vehicles covers the whole Czech Republic, which is a promising source for future use e.g. in transport planning in logistics, estimation of travel times and other related issues. For this reason, it is appropriate to examine the qualitative parameters of the data to see if they characterize the traffic stream. The present paper deals with the size of the processed data. Furthermore, the paper compares the data quality and coverage. January data for four subsequent years was used. The period of the COVID19 pandemic, when traffic declined, was included. Finally, data from selected highways are compared and the period covered is evaluated.

Článek v periodiku excerpovaném databází Scopus

2023, 2023 Smart City Symposium Prague, New York, IEEE Press), ISBN 979-8-3503-2162-3, ISSN 2691-3666

Floating car data (FCD) is a beneficial consequence of the modern telematics technologies in the logistics and automotive industry, and can thus be an additional source of transportation data about current traffic flows on the road network. There is a state-provided free source of this data available in the Czech Republic, which is relatively new and gradually being introduced for use by the public and private sectors. This data source appears to be very promising for nationwide coverage; however, due to its novelty, it is necessary and advisable to investigate its qualitative parameters and assess whether it actually adequately characterizes vehicle traffic flows. The present paper deals with the characteristics and quality of processed FCD outputs before and during the covid-19 pandemic, for the possibility of capturing and comparing significant changes in the behaviour of road users. The paper describes the impact of the associated pandemic measures on traffic in the country in general, which can be detected during FCD processing, as well as the impact on the quality of FCDs as such. It also tests the hypothesis that although the quality of the data has been reduced as a result of the pandemic, the data still have sufficient predictive value. The paper describes the specifics of the data in the spatial and temporal domain analyzed and makes recommendations for future work for use in models and predictions.

Stať ve sborníku z prestižní konf. (Scopus)

2023, 2023 Smart City Symposium Prague, New York, IEEE Press), ISBN 979-8-3503-2162-3, ISSN 2691-3666

As part of the implementation of the Smart City concept in cities, there is an effort to use efficient, economical and sustainable solutions that should contribute to increasing the quality of life in cities. LoRaWAnis one of the IoT technologies that offers a solution for wireless data transmission, when the main goal is low energy consumption at low acquisition costs. Cities are currently building this network, but they often do not have a clear purpose in advance for its versatile use. The aim of this review paper is mapping the possibilities of using the LoRaWAnnetwork for (not only) Czech cities. First, it analyzes and describes the current state of knowledge in the field of LoRaWantechnology, then, based on examples of good practice from various cities across the several countries, it defines the areas of use of the LoRaWannetwork for streamlining processes in cities, and then gives specific examples of elements - sensors that can be used in the LoRaWannetwork. Finally, we propose specific recommendations on the example of a case study for Hradec Králové, which is a medium-sized city in the Czech Republic that currently has a LoRaWannetwork built. All the recommendations are in line with the concept of sustainable mobility and the SMART Hradec Králové project.

Stať ve sborníku z mezinár. konf.

2023, 2023 Smart City Symposium Prague, New York, IEEE Press), ISBN 979-8-3503-2162-3, ISSN 2691-3666

Protected nature parks are important areas that often arouse the greater interest of visitors for their natural beauty and landscape. Paradoxically, these visitors and their need for transport across the territory endanger these areas. To find the balance between transport needs and environmental protection, it is necessary to apply suitable measures that will regulate and improve traffic and movement in these areas. The article aims to present possible solutions to influencing traffic in protected areas. Applied research was a part of the study, where the transport system in protected areas was proposed as a soft system. The method used is based on a detailed analysis of data sources for a complex system and their subsequent integration, which leads to the design of a new architecture. The proposal is shown in the case study in the Czech Republic.

Stať ve sborníku z mezinár. konf.

2023, SUSTAINABILITY, 15 (17), ISSN 2071-1050

In the context of nature protection, there is an effort to regulate individual car traffic in protected areas. In the framework of the research, a pilot testing of a vehicle detection and identification system in the Krkonoše National Park was carried out using two selected technologies (license plate recognition and Bluetooth token detection). The research was carried out under conditions of poorer availability of mobile signal for transmission of measured data, lack of electrical power supply, and in challenging climatic conditions in the mountains. The main objective was to verify the applicability and limits of the mentioned technologies under these difficult conditions. For this purpose, two test sites were built: a fixed and a mobile point. Testing at both points was carried out using two basic methods, namely online through continuous data collection from the detectors and on-site through a local survey during the summer of 2022. The parameters evaluated were the reliability of the vehicle identification itself and the reliability of the operation of the individual detection subsystems and the tested system as a whole. The results show that the license plate recognition system using two cameras for the checkpoint shows a high recognition reliability, but it is reduced for some types of vehicles (especially motorcycles and four-wheelers). At the same time, this technology is demanding on energy resources. Detection using a Bluetooth scanner has proven to be highly reliable up to 50 km/h. A reliable power supply is necessary to achieve high reliability, which was a problem at the mobile point. Evaluation of images from cameras with motion detection showed the limits of this technology, which increased with increasing vehicle speed. The system can be used to detect traffic in protected areas, taking into account the limits specified in this article.

Článek v periodiku excerpovaném SCI Expanded

2022

Výzkum se zabývá detekcí objízdných tras při nehodě na hlavním dopravním tahu na základě dat z plovoucích vozidel. Na základě těchto dat lze sledovat chování uživatelů při mimořádných událostech. Výsledkem jsou reálně využívané objízdné trasy vybrané při omezení na hlavní komunikaci a dopady těchto tras na jejich okolí.

Výzkumná zpráva v češtině

2022, Proceedings of the 11th Euro American Conference on Telematics and Information Systems, New York, Association for Computing Machinery), ISBN 9781450397384

In this article we demonstrate a particular use of ontologies based on the European specifications of the DATEX II UML model with Safety Related Traffic Information (SRTI) version 3 scope. These specifications are designed and developed as an exchange of traffic data and mechanisms for sending information by a working group to establish and standardize the interface between traffic control and information centers. It is the standard reference for sending and receiving traffic information between applications developed by different countries in Europe. This specification of DATEX II XML/UML describes concepts and data structures related to traffic, but the description is only syntactic, not semantic. Therefore, the objective to be achieved in this part of the research has been to develop a semantic description of the contents based on the UML data model and to link the data of the new general ontology with other vocabularies or related ontologies already developed and available on the internet.

Stať ve sborníku z prestižní konf. (Scopus)

2021, 2021 Smart City Symposium Prague, Piscataway, IEEE Signal Processing Society), p. 1-6), ISBN 9780738131580

Modern telematics systems are based on data collected from real operation. The article works with a new source of traffic data, which is freely available to the public. Linking traffic data with spatio-temporal significance also allows us to examine data from the perspective of user behavior. From the principle of data collection, the data already have their specific assumed behaviors, which are described in the article. It is desirable to further investigate these behaviors, to what extent they are affected and whether they can be considered as parameters of the entire traffic flow

Stať ve sborníku z prestižní konf. (Scopus)

2021, 27th ITS World Congress, Brussels, ERTICO - ITS Europe), p. 1702-1713)

In the Czech Republic, there is a new, freely available source of data on the speeds of traffic flows on the road network, based on the movement of floating vehicles. This opens up new possibilities for community and commercial use, as well as research, especially in assessing the qualitative characteristics of this resource and the possibilities and areas of application of its use. It is a unique source of traffic data covering the entire country and it is necessary to examine its reliability in time and space resolution. In the future, this source could be used directly to influence and manage the optimization of the transport network operation, so it is necessary to subject it to a detailed qualitative examination. In addition to these qualitative analyzes, the paper also deals with similar research and the presentation of the user interface. Finally, possible uses and other directions of research are discussed.

Stať ve sborníku z mezinár. konf.

2021, 2021 The 9th International Conference on Information Technology: IoT and Smart City (ICIT 2021), New York, ACM), ISBN 978-1-4503-8497-1

Today, traffic management is based on traffic data, which must be high quality and reliable. The article deals with a new data source that is available in the Czech Republic. Thanks to this dataset, it is possible to get an overview of a wide road network throughout the whole area of the country. The authors use a broader view of the road network to study the behavior of drivers of floating vehicles in an accident on the main road. The high data coverage promises the ability to monitor traffic spills in the event of an emergency. These data can be used in the future to improve the overview of the current state of traffic and road management.

Stať ve sborníku z prestižní konf. (Scopus)

2021, Neural Network World, 31 (05/21), p. 343-353), ISSN 1210-0552

The article deals with the current issue of traffic accident risk classification in urban area. In connection with the increase in traffic in the Czech Republic, a higher probability of risks of traffic excesses can be expected in the future. If there is a traffic excess in the city, the aim is to propose a meaningful traffic management solution to minimize the social losses. The main needs are the early identification and classification of the cause of the traffic excess, finding a suitable alternative solution, quick application of that solution, and the rapid ability to resume operations in the area of congestion. Traffic prediction is one of the tools for the early identification of traffic excess. The article describes extensive research focused on the classification and prediction of the output variable of accident risk based on own programmed neural networks. The research outputs will be subsequently used for the creation of a traffic application for a selected urban area in the Czech Republic

Článek v periodiku excerpovaném SCI Expanded

2021, Prostorové služby pro Smart City a Smart Region, Ostrava, VYSOKÁ ŠKOLA BÁŇSKÁ-TECHNICKÁ UNIVERZITA OSTRAVA), ISBN 978-80-248-4508-1, ISSN 1213-239X

The modern trend in the "Smart" areas is the collection of data to influence, control, optimize or predict general processes, including transport. In the Czech Republic, model data on the speed of road traffic flow based on the movement of floating vehicles, as it is called, have been available since last year. It is a new source of data on the traffic situation with nationwide coverage. These data are therefore published not only on traditional main roads but also on roads that have not been and are not equipped with any detection technology. Thanks to this model, it is possible to monitor and analyze the speed of the traffic flow and its development over time for a large part of the transport network throughout the Czech Republic. The article deals with the use of this data, their spatial significance, and processing in GIS.

Stať ve sborníku z mezinár. konf. cizojazyčně

2020, GARI INTERNATIONAL JOURNAL OF MULTIDISCIPLINARY RESEARCH, Colombo, GARI Publisher), p. 86-93), ISBN 978-955-7153-00-1, ISSN 2659-2193

Progress in the option of transport data collection allows users to collect data using floating vehicles. This data provides real-time information about the road network. In the Czech Republic, these data were published in a pilot project last year. The article uses this new data source. Data can be spatially displayed using GIS software. Analysis options can be used and drivers' choice when the main road is closed can be detected.

Stať ve sborníku z mezinár. konf.

2020

Výzkumná zpráva v češtině

2020

Výzkumná zpráva v češtině

2020, 2020 Smart City Symposium Prague, New York, IEEE Press), ISBN 978-1-7281-6821-0

The prediction of traffic excesses (traffic congestions and traffic accidents) is become a very important topic for many cities and regions. The number of cars in cities and the total traffic volumes in cities are increasing over time, and solutions will be needed to eliminate traffic accidents and prevent secondary excesses. This will ideally lead to time savings for transport users and, above all, to an increase in the safety, fluidity and environmental performance of the transport itself. The article deals with a research activity that aims to develop a separate module in the form of a traffic application that will be able to predict traffic excesses. The neural networks were the main tool for the development of traffic applications for prediction, namely multilayer neural networks with activation function sigmoidou. With regard to the focus of the conference Smart City, the article does not focus on extensive development and testing of neural network, but primarily on the description of the functionalities of the result, including a critical commentary on the problems of the current state of the application. The transport application is developed in collaboration with the scientific and commercial spheres and its future integration into the management platform for smart city management is expected.

Stať ve sborníku z prestižní konf.

2020, Young Transportation Engineers Conference 2020, Praha, Fakulta dopravní), p. 119-125), ISBN 978-80-01-06793-2

Digitization of the transport environment and the use of new data sources is a much-discussed topic today. FCD (Floating Car Data) systems, so-called floating vehicles, make it possible to obtain data of traffic parameters directly from the road network without the need to install stationary sensors. The article deals with the use of this new data source in the Czech Republic, financed from public sources, and made available by the Directorate of Roads and Motorways. This data can be displayed in the road network model using geographic information programs and further analyzed.

Stať ve sborníku z mezinár. konf. cizojazyčně

2020

Výzkum se zabývá vznikem alternativních tras na základě dat odvozených z plovoucích vozidel. Na základě získaných dat lze určit dobu jízdy mezi vybranými uzlovými body v síti a jejich možné alternativní trasy. Výsledkem jsou reálně používané hlavní a alternativní trasy mezi jednotlivými uzly, vlivy vzniku a dopady tvorby těchto alternativních tras.

Výzkumná zpráva v češtině

2019

Studie „Vyhodnocení obrátkovosti, obsazenosti parkování v Uherském Hradišti – II etapa“ je hlavním výstupem dopravního průzkumu, který byl ve městě realizován v termínu od 11. 06. – 12. 06. 2019. Jedná se o komplexní dopravní průzkum parkování ve městě na vymezených parkovištích Palackého náměstí – sever, Palackého náměstí – jih, Stojanova, Nádražní, Komenského náměstí. Průzkum byl proveden zejména s ohledem na následné ověření funkčnosti nově nasazovaných parkovacích technologií na těchto parkovištích a dále z důvodu získání dopravně-inženýrských dat z parkování.

Výzkumná zpráva v češtině

2018

Výzkumná zpráva cizojazyčně