PL
 |
EN
Preferencje help
Polish version English version Język
Widoczny [Schowaj] Abstrakt
Liczba wyników
Powiadomienia systemowe
  • Sesja wygasła!

Znaleziono wyników: 10

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
Content available Design and development of a road traffic redirection system
Bazan M., Janiczek T., Halawa K., Dudek R., Rudawski Ł.
Archives of Transport System Telematics
|
2017
|
Vol. 10, iss. 1
3--8
EN
Nowadays, the crucial issue of guidance systems based on a GPS signal is that they are not able to redirect road users, taking into account the current state of traffic (and the predicted state within the time of the travel) in the city. In this paper we present a three layer architecture of a computer system capable of redirecting users of an urban road system via routes with a lighter traffic load in order to reach their declared destination in the city. A basic layer is a multiprocessor calculation server running Dijkstra path search tasks, the middle layer - the one which is visible to the road user - is a replicable proxy server that collects route requests from road users. The third layer is a mobile application. The prototype of such a system was developed by the ArsNumerica Group. The crucial feature of the system is feedback from road users that allows us to adjust the whole Intelligent Transportation System in the city to changes in traffic flow at various road links introduced by the redirection process applied to many users. The performance test strategy to prove the efficiency of the architecture was carried out for the city of Wrocław.
2
Content available A new method to estimate dimensions of vehicle using a single camera
Bazan M., Janiczek T., Halawa K., Wykrzykowski A., Łabuda P.
Archives of Transport System Telematics
|
2017
|
Vol. 10, iss. 3
3--7
EN
The capability of a telematic vision system of estimating dimensions of vehicles is used for such tasks as vehicle classification or preselection of vehicles that violate local vehicle size limitations. Also in some European countries dimensions of heavy vehicles must obey some global regulations. Furthermore, vehicle size estimation allows us to determine the structure of traffic and can be very useful for advanced traffic flow control. Many existing Intelligent Transportation Systems consist of a large number of video cameras located in various places e.g., the ITS in Wrocław uses more than 1400 cameras. In this paper we propose a new method developed by the ArsNumerica Group and CyberTech Scientific Circle for the precise estimation of vehicle sizes using a single camera. The method does not require the entering of measurements such as the distance between lane lines or the height of the camera above the roadway. Only one vehicle’s dimensions are used for calibration. The proposed method is easy to implement and may be applied with the OpenCV library which is free both for academic and commercial use. The method is tested on real-world video streams. The obtained results are shown and analyzed in the paper.
3
Content available Multithreaded enhancements of the Dijkstra algorithm for route optimization in urban networks
Bazan M., Ciskowski P., Dudek R., Halawa K., Janiczek T., Kozaczewski P., Rusiecki A.
Archives of Transport System Telematics
|
2016
|
Vol. 9, iss. 2
3--7
EN
In this paper, we present a case study, showing step by step, how to speed up Dijkstra’s method by parallelizing its computation and using different data structures. We compare basic algorithm with its bidirectional version and investigate two-and-multi-thread implementations based on Fibonacci heaps and regular priority queues. Experimental results obtained for artificially generated graphs as well as real-world road network data are presented and described.
4
Content available Green wave optimization
Bazan M., Ciskowski B., Halawa K., Janiczek T., Madej Ł., Rusiecki A.
Archives of Transport System Telematics
|
2016
|
Vol. 9, iss. 3
3--8
EN
In this paper we present the results of global optimization of green wave parameters (offsets, opening times, speed limit) for the main artery in the city of Wrocław (Poland). The optimization process was performed in ArsNumerica Execution Environment [1] and involved two different objective functions: the average waiting time and the average queue length. Both approaches were compared by calculating the number of vehicles that pssed the artery in a prescribed time.
5
Content available Detection of vehicles moving in wrong direction
Bazan M., Ciskowski P., Halawa K., Janiczek T., Rusiecki A., Śmigowski M.
Archives of Transport System Telematics
|
2016
|
Vol. 9, iss. 1
3--9
EN
In this paper we describe a method for detecting situations where a vehicle moves along a highway in the wrong direction. The first step of the algorithm is to build a pattern using Gaussian mixture model based on the optical flow calculated with the Lucas-Kanade method. The second stage concerns the detection of objects as a potential road hazard. The optical flow calculated on-line during the second stage is compared with the traffic pattern used in the first stage. Then the difference in movement direction is detected using predefined thresholds.
6
Content available Some aspects of Intelligent Transport System auditing
Bazan M., Bożek M., Ciskowski P., Halawa K., Janiczek T., Kozaczewski P., Rusiecki A.
Archives of Transport System Telematics
|
2015
|
Vol. 8, iss. 3
3--8
EN
Nowadays, in urbanized areas one of the most important matters is to determine a priori the time of driving from one zone of the city to another at various times of the day. The problem of travel time prediction is crucial in Intelligent Transportation Systems. The solution to this problem is a foundation of any route guidance system that will redirect drivers to their target destination via routes that have a lighter traffic load and thus higher travel velocity. In this paper is present a concept of a statistical methodology, developed by the ArsNumerica Group, that enables a quantity audit a travel time prediction algorithm. The methodology assumes that we are given database records of vehicles recognized by their unique identifier as well as duration times for which the messages with the predicted travel time are displayed VMS. the second aspect of ITS auditing considered in this paper is a placement of video cameras to measure vehicle stream velocity. Inappropriate camera location results in the fact that the stream velocity measured by them has a low usefulness for travel time prediction.
7
Content available Intelligent Transport System auditing using road traffic micro-simulation
Bazan M., Ciskowski P., Halawa K., Janiczek T., Kozaczewski P., Madej Ł., Rusiecki A.
Archives of Transport System Telematics
|
2015
|
Vol. 8, iss. 4
3--8
EN
ITS systems have been deployed for last one and a half decades. Their aim is to increase a traffic flow rate in a road network of an urbanized area, to improve the comfort of driving as well as to decrease the pollution. A lot of commercial software are is available to simulate road traffic in urbanized areas. Some of them are suitable to perform traffic simulations of intelligent transportation systems via traffic modeling. A process of traffic modeling exploiting numerical simulations for an urban area where an ITS is deployed requires provision of digital maps, traffic demand amongst city zones, traffic signalization micro-programs being executed in the environment that can imitate a dynamic behavior of traffic lights at intersections in the ITS. In this paper an execution environment, developed by the Ars Numerica Group, that launches a road traffic micro-simulation is used to audit a performance of intersections’ signalization micro-programs on one of the main arteries in the city of Wrocław (Poland).
8
Content available remote Optymalizacja procesu uczenia fourierowskich sieci neuronowych przy wykorzystaniu algorytmu najszybszego spadku
Halawa K.
Przegląd Elektrotechniczny
|
2008
|
R. 84, nr 6
128-130
PL
W artykule zaproponowano metody pozwalające zmniejszyć liczbę obliczeń wykonywanych podczas treningu fourierowskich sieci neuronowych algorytmem najszybszego spadku. Uczenie tych sieci za pomocą tego algorytmu przebiega bardzo szybko. Przedstawiono sposób określania współczynnika uczenia zapewniającego stabilność procesu uczenia. Podano maksymalne jego wartości dla kilku popularnych funkcji celu.
EN
In this paper some methods which reduce the number of calculations carried out during learning Fourier series neural networks with the gradient descent algorithm are proposed. These networks learn with this algorithm very quickly. The way of determining such learning rate so as to ensure learning process stability is presented. Maximum values of the learning rate for several common cost functions are also given.
9
Content available remote Determining the weights of a Fourier series neural network on the basis of the multidimensional discrete Fourier transform
Halawa K.
International Journal of Applied Mathematics and Computer Science
|
2008
|
Vol. 18, no 3
369-375
EN
This paper presents a method for training a Fourier series neural network on the basis of the multidimensional discrete Fourier transform. The proposed method is characterized by low computational complexity. The article shows how the method can be used for modelling dynamic systems.
10
Uwagi o wyznaczaniu parametrów regulatorów za pomocą bloku NCD Simulinka
Halawa K.
Elektronika : konstrukcje, technologie, zastosowania
|
2007
|
Vol. 48, nr 1
45-47
PL
Artykuł dotyczy symulacyjnego wyznaczania parametrów regulatorów typu Pl i PID za pomocą bloku NCD Simulinka. Zaproponowano obliczanie przybliżeń początkowych metodą reduktów. Wyniki badań symulacyjnych modeli w postaci wykresów odpowiedzi skokowych potwierdzają przydatność metody.
EN
Determination of controller setting is still an actual issue, especially for construction of self-tuning controllers. What we are striving to attain are step responses of closed control system which are non-oscillatory as far as possible and which are reaching steady state as soon as possible. When automatic determination of type PI and PID controllers' settings is made with Simulink NCD unit for some models of controlled systems given by transfer functions, no successful results can be reached now and then. Initial approximations close to the results being calculated are necessary.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.