Publikācijas

729 publikācijas

• 2014

  Wireless Sensor Network Software Design Rules

  STRAZDINS, G., SELAVO, L.

  Kopsavilkums

  <p>STRAZDINS, G., SELAVO, L. 2014. Wireless Sensor Network Software Design Rules, Baltic Journal of Modern Computing, 2(2):84-115</p>
• 2014

  Bayesian Network Approach to Vehicle Mode Monitoring Using Embedded System with 3-axis Accelerometer

  ELSTS, A., MEDNIS, A., SELAVO, L.

  Kopsavilkums

  <p>ELSTS, A., MEDNIS, A., SELAVO, L. 2014. Bayesian Network Approach to Vehicle Mode Monitoring Using Embedded System with 3-axis Accelerometer. International Journal of Imaging and Robotics, 12(1), pp. 67-80.<br /> ABSTRACT</p> <p>Vehicle activity monitoring is an important problem in the transport domain: the activities have impact on the fuel consumption of the vehicle, and therefore its economical feasibility. Activity detection usually is performed using relatively expensive and complicated GNSS receivers. We propose a Bayesian network based algorithm for vehicle mode detection. The algorithm can reliably differentiate between standing and moving modes in a diverse set of test scenarios. It is suitable for a low-cost hardware consisting of low-power microcontroller and uses 3-axis accelerometer as the sole sensor.</p> <p><a href="http://www.researchgate.net/publication/257365996_Bayesian_Network_Approach_to_Vehicle_Mode_Monitoring_Using_Embedded_System_with_3-axis_Accelerometer" target="_blank" rel="noopener noreferrer">PDF</a></p>
• 2014

  Pulse locator and principal component method as means of analysis respiration's parameters

  Vladimir Aristov

  Kopsavilkums

  <p>Pulse locator and principal component method as means of analysis respiration's parameters</p>
• 2014

  The Analysis of Kalman Filtering Algorithm for Land Vehicle Navigation

  Ļevinskis, A

  Kopsavilkums

  <p>Jeralovičs, V., Ļevinskis, A. The Analysis of Kalman Filtering Algorithm for Land Vehicle Navigation. In: Proceedings of the 14th Biennial Baltic Electronics Conference, Estonia, Tallinn, 6-8 October, 2014. Tallinn: Tallinn University of Technology, 2014, pp.53-56. ISBN 978-9949-23-672-5. ISSN 1736-3705.</p>
• 2014

  Distributed Multi-Sensor Real-Time Building Environmental Parameters Monitoring System with Remote Data Access

  BEINARTS, I., GRUNDE, U., JAKOVICS, J.

  Kopsavilkums

  <p>BEINARTS, I., GRUNDE, U., JAKOVICS, J., 2014, Distributed Multi-Sensor Real-Time Building Environmental Parameters Monitoring System with Remote Data Access, The Scientific Journal of Riga Technical University - Electrical, Control and Communication Engineering, 7, pp. 41-46.</p>
• 2014

  Sampling and recovery of angle-modulated signals on the basis of the compressed sensing and event timing techniques.

  RYBAKOV, A.S.

  Kopsavilkums

  <p>RYBAKOV, A.S., 2014. Sampling and recovery of angle-modulated signals on the basis of the compressed sensing and event timing techniques. Automatic Control and Computer Sciences, 48(3), pp. 167-179.<br /> ABSTRACT</p> <p>Informative parameters of angle-modulated signals evaluated by the zero-crossing time instants are studied. Specific features of the compressed sensing technique used to restore modulating signals are considered. It is shown that the standard compressed signal processing techniques based on the minimization do not enable the solution of the problem of the off-the-grid recovery of spectral components. It is proposed to use an iterative method for signal recovery based on successive localization of the spectral peaks between the grid nodes. © 2014 Allerton Press, Inc.</p>
• 2014

  Simplified Classification of Multispectral Image Fragments

  LORENCS, A., MEDNIEKS, I., SINICA-SINAVSKIS, J.

  Kopsavilkums

  <p>LORENCS, A., MEDNIEKS, I., SINICA-SINAVSKIS, J. 2014. Simplified Classification of Multispectral Image Fragments. Electronics and Electrical Engineering. Kaunas: Technologija, 20(6), pp. 136–139.<br /> ABSTRACT</p> <p>A simplified approach to classification of multispectral image fragments by their specific spectral features is presented. Application of this approach to discrimination of vegetation areas occupied by the Giant Hogweed species is described and compared with an approach based on calculation of the Consolidated Covariance Image. The proposed method is based on calculation of mean and standard deviation and successive thresholding within certain spectral bands that are found to be informative for the specific task by analyzing the ground truth data. It is shown that the method provides close to perfect discrimination of Giant Hogweed from other vegetation areas represented in ground truth data (absence of commission errors together with clear identification of Giant Hogweed fragments in corresponding ground truth regions). Simplicity of the method provides for fast processing of multispectral images from large areas. The proposed approach is perspective for analysis of multispectral images in different application fields where it is possible to choose several informative spectral bands, e.g. in biomedical imaging.</p> <p><a href="http://www.researchgate.net/publication/263204778_Simplified_Classification_of_Multispectral_Image_Fragments" target="_blank" rel="noopener noreferrer">PDF</a></p>
• 2014

  Design of FIR Decimation Filters with Low Group Delay for Audio Applications

  SHAVELIS, R., OZOLS, K.

  Kopsavilkums

  <p>SHAVELIS, R., OZOLS, K., 2014. Design of FIR Decimation Filters with Low Group Delay for Audio Applications " The 14th Biennial Baltic Electronics Conference BEC2014, Tallinn, Estonia, Oct. 6-8<br /> ABSTRACT</p> <p>In this paper a design of FIR decimation filters with low group delay (less than 1 millisecond) is investigated. Given an input sampling rate of 192 kHz, linear-phase and minimumphase FIR filters are obtained with decimation factors 16 and 32, respectively. Simulation results and the frequency responses of the minimum-phase filters are provided.</p>
• 2014

  Optimization of Filtering Scheme for Reduction of Loudspeaker Distortions

  SHAVELIS, R., OZOLS, K., GREITANS, M.

  Kopsavilkums

  <p>SHAVELIS, R., OZOLS, K., GREITANS, M., 2014. Optimization of Filtering Scheme for Reduction of Loudspeaker Distortions, The 14th Biennial Baltic Electronics Conference BEC2014, Tallinn, Estonia, Oct. 6-8<br /> ABSTRACT</p> <p>In this paper an investigation is carried out on how to decrease the length of the FIR filter which is used for equalization of the loudspeaker distortions. It is shown that instead of one high-order filter, two FIR filters of lower order can be used by considering that an audio signal is split into two separate frequency bands by a digital crossover network. The expressions of the filters and a comparison of the resources required for implementation of the filtering schemes are provided</p>
• 2014

  Research an Indirect Method of Calculating Complex Antenna Impedance

  GREITANS, M., HERMANIS E., ARISTOVS V., E

  Kopsavilkums

  <p>GREITANS, M., HERMANIS E., ARISTOVS V., E. 2014. Research an Indirect Method of Calculating Complex Antenna Impedance. Automatic Control and Computer Sciences, Vol. 48, No. 6, pp. 375–380.</p>
• 2014

  Rotation-Invariant Object Detection Using Complex Matched Filters and Second Order Vector Fields

  PUDZS, M., GREITANS, M.

  Kopsavilkums

  <p>PUDZS, M., GREITANS, M., 2014 Rotation-Invariant Object Detection Using Complex Matched Filters and Second Order Vector Fields, The 22nd European Signal Processing Conference (EUSIPCO 2014), Sept.</p>
• 2014

  Bimodal palm biometric feature extraction using a single RGB imag

  EGLITIS, T., PUDZS, M., GREITANS, M.

  Kopsavilkums

  <p>EGLITIS, T., PUDZS, M., GREITANS, M., 2014. Bimodal palm biometric feature extraction using a single RGB imag, International Conference of the Biometrics Special Interest Group (BIOSIG 2014),September 2014.</p>
• 2013

  Vehicle detection using non-invasive magnetic wireless sensor network

  Martins Liepins, Aivars Severdaks

  Kopsavilkums

  <p>Martins Liepins, Aivars Severdaks "Vehicle detection using non-invasive magnetic wireless sensor network", 21st Telecommunication Forum TELEFOR 2013, Belgrade, Serbija, November 26-28, 2013, pp 601-604<br /> Abstract</p> <p>This paper describes a method for vehicle counting in intelligent traffic management system using non-invasive wireless magnetic sensor network. Compared to other techniques, magnetic sensors are not affected by weather conditions thus giving more stable and robust data to work with. Sensors can be placed on the side of the road, therefore eliminating the need for inserting them into the road structure. Tests were performed on the road with one lane in each direction and sensors located on each side of the road with real traffic flow. Our proposed approach achieves the accuracy of ~94.8 % detection rate.</p> <p><a href="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&amp;arnumber=6716302&amp;url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6716302" target="_blank" rel="noopener noreferrer">pdf</a></p>
• 2013

  Extended Fourier series for time-varying filtering and reconstruction from level-crossing samples

  M.Greitans and R.Shavelis

  Kopsavilkums

  <p>M.Greitans and R.Shavelis, “Extended Fourier series for time-varying filtering and reconstruction from level-crossing samples”, EUSIPCO 2013, Marrakech, Morocco, 9-13 September, 2013.<br /> Abstract</p> <p>In this paper an extension of the classical Fourier series for<br /> analysis of non-stationary signals with time-varying spectral<br /> content is presented. This, in comparison to the classical series,<br /> allows reducing the number of Fourier coefficients required<br /> to represent the signal. The proposed extended Fourier<br /> series can be used for time-varying filtering, which in turn can<br /> be used for recovery of the signals from level-crossing samples.<br /> This has been demonstrated by numerical simulations</p> <p><a href="http://www.eusipco2013.org/" target="_blank" rel="noopener noreferrer">http://www.eusipco2013.org/</a></p> <p>on different test signals.</p>
• 2013

  Web-Based Real-Time Data Acquisition System as Tool for Energy Efficiency Monitoring

  M. Greitans, U. Grunde, A. Jakovics, S. Gendelis

  Kopsavilkums

  <p>M. Greitans, U. Grunde, A. Jakovics, S. Gendelis. ”Web-Based Real-Time Data Acquisition System as Tool for Energy Efficiency Monitoring”. 21th IEEE Telecommunications Forum (TELFOR 2013), IEEE Catalog Number: CFP1398P-CDR, Belgrade, Serbia, November 2013., Proceedings of Papers, pp.553-556.</p> <p>Abstract</p> <p>A web-based data acquisition system is proposed as a research tool of the energy efficiency monitoring project of the test stands. Basic requirements for the architecture of the data acquisition system are discussed. The architecture of the data acquisition system is proposed to provide the real-time interface with sensors, to acquire and to log data from all sensors with fixed rate, and to deliver logged data through FTP to the end-user.</p> <p><a href="http://ieeexplore.ieee.org/xpl/login.jsp?tp=&amp;arnumber=6716289&amp;url=http%3A%2F%2Fieeexplore.ieee.org%2Fiel7%2F6708582%2F6716151%2F06716289.pdf%3Farnumber%3D6716289" target="_blank" rel="noopener noreferrer">pdf</a></p>
• 2013

  License plate detection algorithm

  Michael Broitman, Yuri Klopovsky, Normunds Silinskis

  Kopsavilkums

  <p>Michael Broitman, Yuri Klopovsky, Normunds Silinskis "Licence plate detection algorithm". The 6th International Conference on Machine Vision (ICMV 2013), London, The United Kingdom, November 16-17, 2013<br /> Abstract</p> <p>A novel algorithm for vehicle license plates localization is proposed. The algorithm is based on pixel intensity transition gradient analysis. Near to 2500 natural-scene gray-level vehicle images of different backgrounds and ambient illumination was tested. The best set of algorithm’s parameters produces detection rate up to 0.94. Taking into account abnormal camera location during our tests and therefore geometrical distortion and troubles from trees this result could be considered as passable. Correlation between source data, such as license Plate dimensions and texture, cameras location and others, and parameters of algorithm were also defined. © (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.</p> <p><a href="http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1795023" target="_blank" rel="noopener noreferrer">pdf</a></p>
• 2013

  A bank of fast matched filters by decomposing the filter kernel

  Mihails Pudzs, Rihards Fuksis, Modris Greitans, Teodors Eglitis

  Kopsavilkums

  <p>Mihails Pudzs, Rihards Fuksis, Modris Greitans, Teodors Eglitis, "A bank of fast matched filters by decomposing the filter kernel" Visual Communications and Image Processing Conference (VCIP), University of Malaya (UM), Kuching, Sarawak, Malaysia, November 12-20, 2013.<br /> Abstract</p> <p>In this paper we introduce a bank of fast matched filters that are designed to extract gradients, edges, lines and various line crossings. Our work is based on previously introduced filtering approaches like conventional Matched Filtering (MF), Complex Matched Filtering (CMF) and Generalized Complex Matched Filtering (GCMF), and is aimed to speed up the image processing. Filter kernel decomposition method is demonstrated for the latter mentioned (GCMF) but can be similarly applied to any other filters (like MF, CMF, Gabor filters, spiculation filters, steerable MF, etc.) as well. By introducing the mask kernel approximation, we show how to substitute the GCMF with several more computationally efficient filters, which reduce the overall computation complexity by over hundred of times. Acquired Fast GCMF retains all of the functionality of GCMF (extracts the desired objects and obtains their angular orientation), losing in accuracy only about +26 dB in terms of PSNR.</p>
• 2013

  Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition

  Olegs Nikisins

  Kopsavilkums

  <p>Olegs Nikisins “Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition”, The 2013 International Conference on Applied Mathematics and Computational Methods, AMCM 2013, Venice, Italia, September 27 – October 1, pp. 76-81<br /> Abstract</p> <p>This paper proposes a novel face recognition methodology, which is based on the combination of the texture operator, namely Multi-scale Local Binary Pattern (MSLBP), face image filtering and discriminative feature weighting algorithms. Presented MSLBP principle enhances the discriminative power of the original Local Binary Pattern operator. The combination of the MSLBP and low-pass filtering improves the stability of the feature vector for different scales of the input face. Proposed mini-batch discriminative feature weighting methodologies are applied to the feature space in the feature and block levels in order to enhance the components more relevant to the recognition process. The observed PCA based data compression algorithm significantly reduced the dimensionality of the feature vector with a minimal loss in the precision of the recognition process. The identification precision exceeded the threshold of 99 % for the frontal subsets of a color FERET database.</p>
• 2013

  A distributed data processing architecture for real time intelligent transport systems

  Krišjānis Nesenbergs, Leo Selavo

  Kopsavilkums

  <p>Krišjānis Nesenbergs, Leo Selavo "A distributed data processing architecture for real time intelligent transport systems", Second International Conference on Informatics and Applications (ICIA2013), Lodz, Poland, 23-25 September, 2013.pp.155-160</p> <p>doi: <a href="http://10.1109/ICoIA.2013.6650248">10.1109/ICoIA.2013.6650248</a></p> <p>All authors: Krisjanis Nesenbergs, Leo Selavo.</p> <p><strong>Abstract:</strong></p> <p>In this paper a new distributed architecture for real-time intelligent transport systems is proposed and implemented in test environment. This architecture provides data gathering, processing and distribution and other services critical for real-time intelligent transport systems, taking special care of reliability in real-time life-critical tasks.</p> <p><a href="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6650248&amp;pageNumber%3D136563" target="_blank" rel="noopener noreferrer">pdf</a></p>
• 2013

  FPGA based palmprint and palm vein biometric system

  Mihails Pudzs, Rihards Fuksis, Rinalds Ruskuls, Teodors Eglitis, Arturs Kadikis, and Modris Greitans

  Kopsavilkums

  <p>Mihails Pudzs, Rihards Fuksis, Rinalds Ruskuls, Teodors Eglitis, Arturs Kadikis, and Modris Greitans “FPGA based palmprint and palm vein biometric system”, 12th International Conference of the Biometrics Special Interest Group, BIOSIG 2013, Darmstadt, Germany, September 4-6, 2013, pp. 321-328<br /> Abstract</p> <p>This paper presents an FPGA based multimodal palm biometric system. System is prototyped on an Altera DE2-115 board from Terasic, using an additional hardware for palm image acquisition in two light spectrums, communication with smart card, and debugging. System captures person’s palmprint and palm vein images, extracts biometric data, encrypts it, and prepares for comparison. The comparison of the biometric data is performed on smart card for additional security. The proposed multimodal palm biometric system achieves a matching accuracy of EER of 16.65 % and a verification processing time of 0.8 seconds.</p> <p>http://fg-biosig.gi.de/biosig-2013/report.html</p>