Lidé na fakultě
Ing. Martin Scháno, Ph.D.

2025, Neural Network World, 35 (6), p. 101-122), ISSN 2336-4335

Public transport systems face increasing pressure to improve reliability under constrained infrastructure and limited investment capacity. Small-scale bus priority interventions represent a cost-effective tool for improving operational performance, yet their implementation requires reliable identification and prioritisation of delay-generating locations. This paper presents a fully automated method for spatial identification and quantification of delay formation in bus transport systems based exclusively on high-resolution AVL data. The proposed approach reconstructs vehicle trajectories using a high spatial resolution vectorized road network and map-matching, enabling continuous delay estimation along the entire route rather than only at stops. Referential travel times are derived empirically from historical data using a percentile-based approach, allowing delay quantification independently of static timetables and accommodating heterogeneous operating conditions. The method supports aggregation across multiple trips, lines, and corridors, providing a system-wide view of delay accumulation and its infrastructure-related causes. The methodology is demonstrated on regional bus services. An experimental evaluation of machine learning models as substitutes for referential journeys indicates that, given the available data structure, AI-based approaches fail to achieve meaningful predictive performance and cannot reliably replace the proposed statistical reference. The presented method offers a scalable and robust decision-support tool for prioritizing bus priority interventions and improving public transport reliability using operational data already available to most transport authorities.

Článek v periodiku excerpovaném SCI Expanded

2025, Transportation Research Procedia, Amsterdam, Elsevier B.V.), p. 203-210), ISSN 2352-1457

Currently, the most promising path toward long-term sustainable transport — and by extension, a sustainable society — is through public transport (PT). However, many PT systems are experiencing a decline in passenger numbers or stagnating at very low shares of total modal split, requiring substantial public sector support to remain competitive. This lack of competitiveness is determined by a range of factors — particularly the reliability of PT arrival times and the overall uncertainty associated with travel time. These factors are often used as key performance indicators (KPI) to assess the quality of operators and transport systems, to calculate financial losses associated with low popularity of PT, and more. Yet their impact may extend beyond the transport system itself, influencing broader societal outcomes. It is therefore critical that these KPIs accurately reflect the real conditions of PT services. This article presents the results of an exploratory study on the impact of PT unreliability on passenger behavior. It evaluates several alternative definitions of KPIs intended to capture this effect. The findings reveal substantial differences in quality assessment outcomes depending on the KPI used, highlighting the potential for distorted perceptions of service quality. These insights should contribute to a more accurate estimation of the economic consequences of PT unreliability — predominantly pointing to greater impacts than previously assumed — and emphasize the need for urgent action to address the underlying causes of unreliability. In doing so, they provide practical guidance for policymakers and planners seeking to improve PT performance and promote sustainable mobility.

Stať ve sborníku z prestižní konf. (Scopus)

2024, Driver-Car Interaction and Safety Conference 2023, Praha, České vysoké učení technické v Praze), p. 81-93), ISBN 978-80-01-07387-2, ISSN 2336-5382

Understanding the subjective perspectives of drivers is paramount in evaluating the factors affecting driving speed in built-up areas. Building on our previous work, where a wide set of infrastructure attributes was analysed, this paper delves deeper into the realm of driver perception. It seeks to answer how drivers’ observations and awareness of their surroundings influence their speed choices. We reconduct our previous analysis, emphasizing the driver’s subjective viewpoint, contemplating the visible and perceivable elements of the road infrastructure rather than their objective presence. This research aims to garner insights into how these subjective elements impact speed choices. This research has uncovered a number of interesting factors that have not been previously used in the calculation of road vehicle speeds. This more nuanced understanding is expected to lead to enhanced safety and efficiency in road traffic management, ensuring the road design aligns seamlessly with driver perception and behaviour.

Stať ve sborníku z prestižní konf. (Scopus)

2024, Driver-Car Interaction and Safety Conference 2023, Praha, České vysoké učení technické v Praze), p. 94-108), ISBN 978-80-01-07387-2, ISSN 2336-5382

This publication focuses on the development of a regional system for monitoring and evaluating public bus delays in the Ústí nad Labem Region in the Czech Republic. The case study, through a questionnaire survey, addresses the issue of the value of time loss caused by delays in regional public bus transport in the Ústí nad Labem Region from both a societal and individual passenger perspective. The survey includes, in addition to opportunity costs, the necessity to use earlier buses due to uncertainty and the potential real financial loss of passengers, for instance, due to late arrival to work and p otential employer sanctions. Routes for the questionnaire survey were selected based on an analysis of the movement of the bus fleet to represent typical situations applicable to the entire bus transport network. The result is a financial evaluation of the losses caused by bus delays in relation to the number of passengers, the purpose of their journeys, and the value of their time. The findings reveal relatively high costs of time losses, which, when applying a co st benefit approach, allow for the return on larger infrastructure investments aimed at reducing these delays. The research results will contribute to the development of issues evaluating the economic efficiency of investments in transport infrastructure.

Stať ve sborníku z prestižní konf. (Scopus)

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

Carsharing is part of a growing segment of sharing economy. It is often described as a more economically advantageous alternative to owning a car, because in the case of carsharing, some cost items are split between multiple users. On the other hand, it is also necessary to take into account the overhead costs of the carsharing operator and the possible poorer availability of vehicles. This paper presents an analysis of the financial benefits of carsharing in the Czech Republic to estimate the potential of replacing private cars while taking into account other limitations like size of the town and public transport offer. Considering that carsharing tariffs depend not only on the distance driven, but also on the duration of the rental, the financial advantage was assessed for different scenarios of vehicle use. This paper also describes a case study from the Skalka housing estate in Ústí nad Labem, in which, in addition to the potential of replacing private cars with carsharing, the necessary number of shared vehicles was also addressed. This was estimated based on recordings of vehicle stays in the area of the Skalka housing estate. The conclusion is that replacing the user's own car with carsharing is beneficial only for people who use their car only occasionally. If limitations such as the use of public transport and the minimum size of a municipality of 20,000 inhabitants are taken into account, carsharing in the Czech Republic can replace 4-8% of private cars (in larger towns 8-17%). Based on measurements at the Skalka housing estate, one shared car can replace 1.89-3.11 private cars. However, it is necessary to mention that several influences (such as comfort) were not taken into account.

Stať ve sborníku z prestižní konf.

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

Traffic engineers have long sought to understand what encourages drivers to drive fast and to design road infrastructure to induce drivers to behave in a desired way. But what leads drivers to select a particular speed while driving is principally a psychological question. This paper aims to expand the understanding of the factors affecting driving speed in built-up areas of towns and municipalities. We analysed nearly 700,000 vehicles-driving on roads of regional and supra-regional significance near the Bohemian Switzerland National Park-in 20 surveys at 17 locations. A broad set of infrastructure attributes was defined and measured at each site. The collected data were analysed using statistical methods to draw general conclusions about driver behaviour that can be used to improve traffic engineering. Several of the presumed attributes were confirmed to influence driver speed choice, and several new factors were discovered and proposed for implementation in traffic engineering and mathematical modelling tools.

Stať ve sborníku z prestižní konf. (Scopus)

2023, Acta Polytechnica CTU Proceedings, 2023 (41), p. 49-57), ISSN 2336-5382

Vývoj pokročilých asistenčních systémů (ADAS) a autonomních vozidel (AV) na základě strojového učení obecně představuje rozsáhlý a finančně náročný proces. V souvislosti s narůstající komplexností autonomních systémů přichází potřeba rozsáhlého testování a validace. V posledních letech se pro tyto účely využívá počítačových simulací. Provádět realistické simulace především pro účely učení systémů využívajících automatické rozpoznávání obrazu vyžadují vysoce, téměř fotorealistické virtuální prostředí. Tento článek představuje U SMART ZONE, vysoce přesný virtuální model městské části Severní Terasa v Ústí nad Labem, České republice zahrnující více než 7,5 km pojízdných ploch o celkové rozloze téměř 1,4 čtverečních km pro human-in-the-loop a hardware-in-the-loop (HiL) simulace.

Článek v odborném recenzovaném periodiku cizojazyčně