RT-RK is a R&D company and national research institute that delivers development services and own products in the arena of real time embedded systems, with strong focus on consumer electronics and automotive. Headquartered in Novi Sad, with offices in Belgrade , Banja Luka and Osijek with over 500 engineers, RT-RK is one of the biggest development houses in Southeast Europe.RT-RK is professionally engaged in embedded system design, TV software development, automotive software development, Digital Signal Processing , UI/UX design, product development including small scale production, testing of Set-Top Box and multimedia devices, and FPGA rapid prototyping. Wikipedia.
Vekic M.S.,University of Novi Sad |
Grabic S.U.,University of Novi Sad |
Majstorovic D.P.,University of Novi Sad |
Majstorovic D.P.,RT - RK Computer Based Systems LLC |
And 4 more authors.
IEEE Transactions on Power Electronics | Year: 2012
Prototyping and verification of complex power electronics (PE) systems and control algorithms is a laborious and time-consuming process. Even when a low-power hardware model is assembled, it enables only a limited insight into the large number of operating points; changes in system parameters regularly demand hardware modifications and always there is the risk of hardware damage. The ultralow-latency Hardware-In-the-Loop (HIL) platform proposed in this paper combines the flexibility, accuracy, and ease of use of state-of-the-art- simulation packages, with the response speed of small power-hardware models. In this way, PE systems-optimization, code-development, and laboratory-testing can be combined into one step, which dramatically accelerates the pace of product prototyping. Low-power hardware-models also suffer from nonscalability, because some parameters such as electrical machine inertia cannot be properly scaled. However, HIL enables control prototyping that covers all operational conditions. In order to demonstrate HIL-based rapid development, the verification of an active damping algorithm for a permanent magnet synchronous generator (PMSG) cascade is performed. Two goals are set in this paper: to verify the developed HIL platform by means of comparison with a low-power hardware setup and then to emulate the real, high-power system in order to test the active damping algorithm. © 2012 IEEE.
Todorovic B.M.,RT - RK Computer Based Systems LLC |
Samardzija D.,University of Novi Sad
Energy Efficiency | Year: 2016
An intelligent wireless sensor network that is designed to save road lighting energy, while maintaining traffic safety, is presented. It consists of an array of nodes that may be installed on both sides of the road, being mutually separated by a few tens to a few hundreds of meters. Each node consists of (i) vehicle detection subsystem, (ii) wireless communications and control subsystem for message exchange between the neighboring nodes, and (iii) lighting subsystem. During the day, nodes are inactive, while during the night, they turn to an active mode enabling detection of passing vehicles and timely activation of road lighting. Upon detection of a passing vehicle, the node generates a wireless message. Neighboring nodes that receive the wireless message will turn on their road lighting. In order to prevent driver distraction, each lamp will be turned on at a safe distance ahead of the moving vehicle. In order to improve energy efficiency, the lights will be dimmed or turned off behind the passing vehicle. The proposed road lighting energy-saving (RLES) system, which combines advanced sensor and wireless communication technologies, is suitable for implementation both with existing high-intensity discharge (HID) lamps and new light-emitting diode (LED) lamps. Our analysis shows that the RLES system will pay off in less than a year when used with HID lamps, while pay-back period is less than two and a half years when used with LEDs. © 2016 Springer Science+Business Media Dordrecht
Marijan D.,University of Novi Sad |
Zlokolica V.,University of Novi Sad |
Teslic N.,University of Novi Sad |
Pekovic V.,RT - RK Computer Based Systems LLC
IEEE Transactions on Consumer Electronics | Year: 2010
Enormous technological innovation in recent years has put a great challenge upon manufacturers in consumer electronics industry: how to efficiently and accurately verify the functionality of a product handed to a customer. To address this problem, we propose a fully automated system for functional failure detection in TV sets. In the proposed framework, the automatic assessment of TV set functionality is performed by processing captured images of the TV set under inspection and the captured images from the reference TV set (which is considered to be with no functional failures). A new algorithm for image similarity is proposed and incorporated in the system for evaluating the difference between the tested image and the reference one, in respect to specific degradations that can occur in TV sets. The similarity detection algorithm is a full-reference intra-frame video quality assessment scheme, which is based on spatiallylocal mean square error and variance between the reference and the tested image. Based on the similarity detection, an acceptance decision for the TV set functionality is made. The proposed embedded system for automatic TV functional failure detection includes (i) central control unit through which the testing methodology is carried out: The TV set under inspection is fed by the test video signals defined by the (ii) specified test-case-scenario, while the picture is simultaneously captured from the tested TV set and compared by the (iii) proposed similarity detection algorithm to the reference one, for the same type of TV set. Finally, the results are stored in the (iv) data base for TV set debugging purposes. The usability and effectiveness of the proposed methodology has been experimentally evaluated and detailed analysis of the results has been reported. The proposed similarity detection algorithm has shown to be superior to the other state-of-the-art image quality assessment algorithms in terms of detecting TV picture degradations (such as picture misalignment, illumination change, aliasing, blurring, etc.) in captured images from TV set, under the methodology which incorporates defined test-case-scenario1. © 2006 IEEE.
Tadic J.M.,Carnegie Institution for Science |
Ilic V.,RT - RK Computer Based Systems LLC |
Biraud S.,Lawrence Berkeley National Laboratory
Atmospheric Environment | Year: 2015
Selecting which interpolation method to use significantly affects the results of atmospheric studies. The goal of this study is to examine the performance of several interpolation techniques under typical atmospheric conditions. Several types of kriging and artificial neural networks used as spatial interpolators are here compared and evaluated against ordinary kriging, using real airborne CO2 mixing-ratio data and synthetic data. The real data were measured (on December 26, 2012) between Billings and Lamont, near Oklahoma City, Oklahoma, within and above the planetary boundary layer (PBL). Predictions were made all along the flight trajectory within a total volume of 5000km3 of atmospheric air (27×33×5.6km). We evaluated (a) universal kriging, (b) ensemble neural networks, (c) universal kriging with ensemble neural network outputs used as covariates, and (d) ensemble neural networks with ordinary kriging of the residuals as interpolation tools. We found that in certain cases, when the weaknesses of ordinary kriging interpolation schemes (based on an omnidirectional isotropic variogram presumption) became apparent, more sophisticated interpolation methods were in order. In this study, preservation of the potentially nonlinear relationship between the trend and coordinates (by using neural kriging output as a covariate in a universal kriging scheme) was attempted, with varying degrees of success (it was best performer in 4 out of 8 cases). The study confirmed the necessity of selecting an interpolation approach that includes a combination of expert understanding and appropriate interpolation tools. The error analysis showed that uncertainty representations generated by the kriging methods are superior to neural networks, but that the actual error varies from case to case. © 2015 Elsevier Ltd.
Saric Z.M.,RT - RK Computer Based Systems LLC |
Kukolj D.D.,University of Novi Sad |
Teslic N.D.,University of Novi Sad
Circuits, Systems, and Signal Processing | Year: 2010
In this paper, we consider the problem of acoustic source localization in a wireless sensor network based on different measured signal quantities, such as the received signal strength (RSS), the angle of arrival (AOA) and the time of arrival (TOA). For each of these quantities, an appropriate weighted least squares criterion function is developed to be used for sound source localization. The weights of each criterion function take into account the decrease in the signal-to-noise ratio (SNR) with distance from the source. In addition, RSS localization algorithm proposed in this paper provides improvement of the localization accuracy for low SNR. Finally, separate criterion functions for RSS, TOA and AOA are used together to obtain minimal localization error and maximal reliability of the acoustic source localization. Simulation analysis confirms improved performance of the proposed localization algorithm. © Springer Science+Business Media, LLC 2010.