Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrea Kocianova has a total of 11 co-authors. Here are the top co-authors by number of shared publications:

  • Michal Hodoň

    Department of Technical Cybernetics, Faculty of Management Science and Informatics, University of Žilina, Univerzitná 8215/1, 010 26 Žilina, Slovakia

    3 shared publications
  • Eva Pitlova

    Department of Highway Engineering, Faculty of Civil Engineering, University of Zilina, Univerzitna 8215/1, Zilina, 010 26, Slovakia

    2 shared publications
  • Lukas Formanek

    Department of Technical Cybernetics, Faculty of Management Science and Informatics, University of Žilina, Univerzitná 8215/1, 010 26 Žilina, Slovakia

    2 shared publications
  • Peter Sarafin

    Department of Technical Cybernetics, Faculty of Management Science and Informatics, University of Žilina, Univerzitná 8215/1, 010 26 Žilina, Slovakia

    2 shared publications
  • Adam Kníž

    Department of Highway and Environmental Engineering, Faculty of Civil Engineering , University of Žilina , Žilina , Slovakia

    1 shared publication
  • Eva Pitlova

    Department of Highway Engineering Faculty of Civil Engineering University of Zilina Univerzitna 8215/1 010 26 Zilina Slovakia

    1 shared publication

Latest Publications

  • Open Access

    Design and Evaluation of an Edge AI-Enabled Low-Power Magnetic Sensor for Real-Time Road Traffic Monitoring

    by Michal Hodoň, Peter Šarafín, Lukáš Formanek, Andrea Kociánová

    Road traffic surveys require sensing systems that can be deployed rapidly without modifying the road surface or requiring a permanent power connection. This paper presents the design, embedded implementation, and evaluation of a low-power roadside magnetic sensor that performs vehicle-event detection and classification directly at the edge. The sensing node integrates two RM3100 three-axis magnetometers (PNI Sensor, Santa Rosa, CA, USA) with an NXP MK22FN512VLH12 microcontroller (NXP Semiconductors N.V., Eindhoven, The Netherlands) based on a 120 MHz Arm Cortex-M4F core with 512 kB Flash and 128 kB SRAM. Magnetic-field data are acquired at 250 Hz and processed locally using baseline removal, low-pass filtering, signal-energy calculation, and peak-based event detection. Detected magnetic signatures are classified using an integer-quantised one-dimensional convolutional neural network implemented directly on the microcontroller. The model processes four synchronised 512-sample channels representing the three magnetic-field axes and their combined signal energy. Model development was supported by approximately 50,000 annotated events obtained from 36 h of real-world traffic measurements at eight locations. The selected model achieved an overall classification accuracy of 91.1% for the considered operational categories. The implemented network requires 288,128 multiply–accumulate operations per inference, while its quantised weights and biases occupy approximately 23 kB of Flash memory. Complete three-axis event signatures are stored locally for subsequent verification, whereas only the timestamp and predicted vehicle category are transmitted through the wireless interface. Based on the capacity of the applied LiFePO4 battery and the estimated consumption of the implemented hardware, the expected autonomous operating period is approximately 41 days. The results demonstrate the feasibility of integrating magnetic sensing, embedded signal processing, and Edge AI on a conventional resource-constrained Cortex-M4 platform for non-invasive road traffic monitoring.

  • Open Access

    Efficient Dataset Creation for MEMS-Based Magnetic Sensor Systems in Intelligent Transportation Applications

    by Michal Hodoň, Peter Šarafín, Lukáš Formanek, Andrea Kociánová

    This article describes the innovative use of an advanced annotation tool designed specifically for creating datasets tailored to MEMS (Micro-Electro-Mechanical Systems) sensor systems for the intelligent transportation domain. By optimizing the data annotation process, this tool significantly enhances the efficiency and accuracy of dataset development, which is critical for the optimal performance and reliability of MEMS-based applications. The tool was tested with a specialized sensor system based on magnetometers for traffic flow monitoring, demonstrating its practical applications and effectiveness in real-world scenarios. The proposed approach offered a clear improvement over manual labelling by reducing the time needed per event and increasing the number of events that could be processed, without compromising the consistency of the assigned labels. The discussion includes a detailed overview of the tool’s features, its integration into existing workflows, as well as the benefits it offers engineers and researchers in the field of sensor technology.

  • Open Access

    Comparative Analysis of Traffic Speed Data on Two-Lane Rural Road Segments: Radar Technology, Google Maps API, and License Plate Recognition

    by Andrea Kociánová, Adam Kníž, Peter Pisca

    This paper presents a comparative analysis of traffic speed data on two-lane rural road segments using three different methods: radar technology measuring spot speeds, Google Maps API, and License Plate Recognition (LPR) providing space-mean speed estimates. The study employs a two-stage validation approach with LPR as the reference method, followed by direct comparison between Google Maps and radar speed data. Analysis of five road segments with varying geometry, traffic volumes, mobile signal quality, and radar placement reveals that no single method is universally superior. The findings show that Google Maps API offers a scalable, cost-effective solution with reasonable performance (MAE 5.5-8.8 km/h) under optimal conditions, but becomes unreliable in areas with weak mobile signal coverage and tends to smooth speed variations. When properly positioned, radar measurements provide high-resolution speed data with sensitivity to traffic changes (MAE 3.7-9.8 km/h against LPR), but their point-based nature creates significant dependency on sensor placement. Both methods exhibit reduced accuracy during low-speed conditions, as indicated by elevated MAPE values. Mobile network signal quality emerges as critical for Google Maps reliability, while road segment geometry and sensor positioning are paramount for radar reliability.


  • Open Access

    Which Digital-Output MEMS Magnetometer Meets the Requirements of Modern Road Traffic Survey?

    by Michal Hodoň, Ondrej Karpiš, Peter Ševčík, Andrea Kociánová

    Present systems for road traffic surveillance largely utilize MEMS magnetometers for the purpose of vehicle detection and classification. Magnetoresistive sensing or LR oscillation circuitry are technologies providing the sensors with the competitive advantage which lies in the energy efficiency and low price. There are several chip suppliers on the market who specialize in the development of these sensors. The aim of this paper is to compare available sensors from the viewpoint of their suitability for traffic measurements. A summary of the achieved results is given in the form of the score for each sensor. The introduced sensor chart should provide the audience with knowledge about pros and cons of sensors, especially if intended for the purposes of road traffic surveillance. The authors in this research focused on the specific situation of road traffic monitoring with magnetometers placed at the roadside.


  • Open Access

    Sustainability obstacles of free bike-sharing model

    by A Kocianova, L Slebodnik

    Cycling is one of the options for sustainable urban mobility. Although this transport mode is not so widely used in Slovak cities, the bike-sharing project in Žilina with 80 thousand inhabitants has been remarkably successful. The system comprises of 120 shared bikes and 20 bike stations located mainly in the city core and wider centre to cover important transport destinations. During the first-year usage, a great interest of citizens has been recorded also thanks to the one-hour-free-of-charge service. That leads to an average rental number of 35 thousand bicycles per month (with a maximum of 47 thousand) and a high usage rate of the system (on average, 9.5 rides per bike per day). A more detailed analysis, including the Covid-19 pandemic’s impact on reducing bicycle rental, is presented in the article. In addition to the positive experience with the bike-sharing system, the disadvantages of the one-hour-free service model are discussed. In addition to the reduced service availability for citizens with real transport needs or higher users’ disrespect to the system, the technical operation costs are about 40 % higher due to an excessive wear system, poorer technical condition, and shorter lifespan of bicycles, or increase in a certain form of vandalism due to the bicycle joyriding. Ultimately, the overall loss is much higher because of no income, which threatens the sustainability of this system.

  • Open Access

    Specifics of Bending Priority Road at Unsignalized Intersections

    by Andrea Kocianova, Eva Pitlova

    Unsignalized intersections with a bending priority road are common in Slovakia’s road network. Various specifics are associated with these type of intersections compared to conventional intersections with a straight priority road. There are different priority ranks for traffic streams, more complicated traffic situation, different traffic flow characteristics and driver behaviour. The problem is that only a few studies to date have addressed to this type of intersections and their specifics. Therefore, some traffic flow characteristics such as the speed of major-stream vehicles; and driver behaviour such as compliance with traffic rules, influences of potentially conflicting traffic streams on minor-stream drivers, and the driver gap-acceptance characteristics (critical gaps) at unsignalized four-leg intersection with a bending priority road in Zilina were surveyed. The results show vehicles moving along the bending major street about 40% slower than the city speed limit of 50 kilometres per hour. About 16% to 25% of drivers turning right from the major street did not signal the change of direction. About 16% of priority rule violations were recorded at the least priority minor approach during peak hours and long delays. There are two times more potentially conflicting traffic streams compared to intersection with the straight priority road and the effect of these potentially conflicting streams has ranged between 20% and 60%. The paper demonstrate that the values of critical gaps for the same movements more significant differ according to major/minor street and rank of priority, and critical gap values for straight traffic streams of third and fourth priority rank were determined to be about 0.4 to 0.9 second higher in comparison to the values for conventional rural unsignalized intersections. This new findings cause reduction of minor stream potential capacity and traffic safety.

  • Open Access

    Critical Gaps at Unsignalized Intersections with Bending Right-of-Way

    by Andrea Kocianova, Eva Pitlova

    The capacity calculation procedure for unsignalized intersections is based on the gap-acceptance theory in most of existing capacity regulations and it relies on one of the important parameters - critical gap. However, the capacity calculation...


  • Open Access

    Influence of roundabout capacity enhancement on emission production

    by Andrea Kocianova, Marek Drliciak, Eva Pitlova

    Secondary effects of intersections insufficient capacity in urban areas are negative impacts on environment out of acceleration and deceleration of vehicles moving in long queues. The positive influence of increased intersection performance to reduce delays and queues, as well as negative impacts on the atmosphere is presented in this paper. The case study includes two single-lane roundabouts located close to each other in Žilina. Both roundabouts do not comply with the current traffic loads. This results in long queues and delays lasting not just during the peak hours. The solution to this problem is a new type of roundabout-turbo-roundabout. Capacity characteristics of both the current and new state are determined by microsimulation using PTV Vissim software. Obtained main characteristics of traffic flows are used as inputs to establish emission productions of NOx, CO and HC at the roundabout entries. The paper shows that proposed basic turbo-roundabout provides significant higher capacity performance compared with current state. Waiting times and queue lengths decrease about ten times. Due to this reduction, emission productions decrease about 50-60%.