Pētniecība

Publikācijas

729 publikācijas

2018
Nonparametric Classification of Satellite Images

Romans Dinuls, Ints Mednieks

Kopsavilkums

Romans Dinuls, Ints Mednieks. (2018). Nonparametric Classification of Satellite Images.ICoMS 2018 Proceedings of the 2018 International Conference on Mathematics and Statistics Pages 64-68, Porto, Portugal — July 15 - 17, 2018 Abstract: The task of classifying the objects on a satellite image into predefined categories is the topic of the article. The problems arising while designing a practicable classifier are discussed. The general conditions for robustness of a classifier are provided. To solve the problems mentioned, a robust classification approach is proposed aiming at completely nonparametric unsupervised clustering with consequent association of the clusters with target categories using multiple sources of the testing and training data. The nonparametric clustering used is primarily based on ranking and grouping. Completely nonparametric cluster union and cleaning procedures are presented; theoretical basics for other parts of the approach are provided. The software implementation and complexity of the methodology are discussed. The approach aims at getting the highest possible classification accuracy under real conditions for images with more than 100 million pixels.
2018
The Use Of The Karhunen Loeve Transformation To Form The Speech Data For Their Subsequent Wiring To Sound By Probing Sound Source By An Ultra-Wideband Pulse Locator

V. Aristov. T.Laimina

Kopsavilkums

V. Aristov. T.Laimina “ The Use Of The Karhunen Loeve Transformation To Form The Speech Data For Their Subsequent Wiring To Sound By Probing Sound Source By An Ultra-Wideband Pulse Locator” , Žurnāls Austria-science, № 17/ 2018, pp.22-28. The possibility of applying the first principal component of the Karunen-Loeve transformation is developed to form the speech data for their subsequent wiring to sound when a sound source (speaking person) is probed with an ultrawideband pulse locator. http://austria-science.info/2018/08/10/austria-science-17-iyun-2018/
2018
Integration of Computervision and Artificial Intelligence Subsystems with Robot Operating System Based Motion Planning for Industrial Robots

Jānis Ārents, Ričards Cacurs, Modris Greitans

Kopsavilkums

Jānis Ārents, Ričards Cacurs, Modris Greitans, "Integration of Computervision and Artificial Intelligence Subsystems with Robot Operating System Based Motion Planning for Industrial Robots", Automatic Control and Computer Sciences Journal, Volume 52, Issue 5, 2018
2018
Performance of Adaptive Filters for Predicting the Future Values of the Vehicle Sideslip Angle

R.Shavelis, K.Ozols, M.Greitans, V.Fescenko

Kopsavilkums

R.Shavelis, K.Ozols, M.Greitans, V.Fescenko, "Performance of Adaptive Filters for Predicting the Future Values of the Vehicle Sideslip Angle", The 16th Biennial Baltic Electronics Conference BEC2018, Tallinn, Estonia, Oct. 8-10, 2018. Abstract: In this paper a performance of conventional adaptive finite impulse response filters and a feedforward multi-layer neural network is examined for predicting the future values of the slip angle of a vehicle. The obtained results depending on a number of inputs and a prediction horizon are compared in terms of prediction error and a required number of operations for executing the algorithms.
2018
FPGA Master-based on chip communications architecture for Cyclone V SoC running Linux

R. Novickis, M. Greitāns

Kopsavilkums

R. Novickis, M. Greitāns, "FPGA Master based on chip communications architecture for Cyclone V SoC running Linux", IEEE-2018 International Conference on Control, Decision and Information Technologies (CoDIT), Thessaloniki, Greeze 2018
2018
“Specific Signal Representation for Transmission and Processing based on Precise Event Timing

I.Mednieks, I.Bilinskis, E.Boole

Kopsavilkums

I.Mednieks, I.Bilinskis, E.Boole “Specific Signal Representation for Transmission and Processing based on Precise Event Timing”, 16th Biennial Baltic Electronics Conference (BEC2018), Oct 8, 2018 - Oct 10, 2018 Tallinn, Estonia Abstract: Method for signal representation based on using the signal phase at the time instant of the signal and reference function crossing events is proposed and described. Combination of the signal compressive transmission and digital processing, performed before recovery of the input signals, is described. Focus is on application of this method for avoiding multiple multiplications of two digital variables at digital processing the signals according to the widely used algorithms. Using the described approach to signal representation and digital processing provides for significant increasing the operational speed at the involved calculations.
2018
Demodulation of Frequency-Modulated Signals by Pseudorandomly Selected Zero-Crossing Instants

A. S. Rybakov.

Kopsavilkums

A. S. Rybakov. Demodulation of Frequency-Modulated Signals by Pseudorandomly Selected Zero-Crossing Instants. // Automatic Control and Computer Sciences, 2018, Vol. 52, No. 2, pp. 77–88.
2018
Human skin as data transmission medium for improved privacy and usability in wearable electronics

J. Ormanis, K. Nesenbergs.

Kopsavilkums

J. Ormanis, K. Nesenbergs. “Human skin as data transmission medium for improved privacy and usability in wearable electronics”, In Medical Measurements and Applications (MeMeA), 2018 IEEE International Symposium on, pages 1–6. IEEE.
2017
Measurement of current consumption in a wireless sensor network TestBed

Didzis Lapsa, Rihards Balass, Janis Judvaitis, Krisjanis Nesenbergs

Kopsavilkums

Didzis Lapsa, Rihards Balass, Janis Judvaitis, Krisjanis Nesenbergs. Measurement of current consumption in a wireless sensor network TestBed. Published in: 2017 25th Telecommunication Forum (TELFOR) <div class="u-pb-1 stats-document-abstract-doi">DOI: <a href="https://doi.org/10.1109/TELFOR.2017.8249408" target="_blank" rel="noopener noreferrer">10.1109/TELFOR.2017.8249408</a></div> Abstract: <div>To accurately determine current consumption of a device under test in a wireless sensor network testbed, the accuracy of the measurement device must be assessed. The implementation and operation of current measurement circuit of testbed and evaluate errors and possible improvements to reduce these errors have been described in this paper.</div>
2017
Power Consumption Measurement of Tested Units in the WSN TestBed

D. Lapsa, R. Balass, J. Judvaitis, K. Nesenbergs and A. Skageris

Kopsavilkums

D. Lapsa, R. Balass, J. Judvaitis, K. Nesenbergs and A. Skageris. “Power Consumption Measurement of Tested Units in the WSN TestBed”. TELFOR, 2017
2017
Mobile wireless sensor network TestBed

A. Salmins, J. Judvaitis, R. Balass and K. Nesenbergs.

Kopsavilkums

A. Salmins, J. Judvaitis, R. Balass and K. Nesenbergs. “Mobile wireless sensor network TestBed”. TELFOR, 2017 <div id="gtx-trans" style="position: absolute; left: -7px; top: 48px;"> <div class="gtx-trans-icon"></div> </div>
2017
Vehicle type and licence plate localisation and segmentation using FCN and LSTM

N. Dorbe, R. Kadikis, K. Nesenbergs

Kopsavilkums

<img class="wp-image-6930 aligncenter" src="/storage/wp/2019/07/license_plate_recognition_architecture-300x54.png" alt="" width="594" height="107" /> We propose an end-to-end vehicle type and licence plate localisation and recognition system, based on a combination of existing methods, modifications to neural network architecture and improvements in the training process, resulting in high accuracy licence plate localization and recognition with minimal post-processing. The proposed system was trained and tested on a custom data set of 17000 manually labeled images, containing in total 19000 license plates, 18300 motorcars, 1414 trucks, 722 ambulances, 492 motorbikes, 45 trailers, 26 police motorcars, 15 firetrucks and 6 other operative cars. Additional transformations such as added noise, zoom and rotation were used to generate more images. The methods and tools used include FCN, transfer learning, Feature Extraction Maxout CNN, Recurrent LSTM networks, Tensorflow etc. The resulting system is capable of localizing multiple types of vehicles (including motorcycles) as well as their licence plates. The achieved precision of the localisation is 99.5%. The whole number recognition accuracy is 96.7% and character level recognition accuracy is 98.8%. An end-to-end test for a single image took 0.2 seconds on a GPU and 8 seconds on a single core CPU.   N. Dorbe, R. Kadikis, K. Nesenbergs. “Vehicle type and licence plate localisation and segmentation using FCN and LSTM”, Proceedings of New Challenges of Economic and Business Development 2017, Riga, Latvia, May 18-20, 2017, pp. 143-151 <a href="https://makonis.edi.lv/s/BSejTsLYrZkfBHE">pdf</a>
2017
pEGFP transfection into murine skeletal muscle by electrosonoporation

M. Tamosiunas, D. Jakovels, U. Rubins, R. Kadiķis, R. Petrovska, S. Satkauskas

Kopsavilkums

In this study, we aimed to determine whether the combination of electroporation (EP) and ultrasound (US) waves (sonoporation) can affect the plasmid DNA transfection to mice tibialis cranialis muscle. Multispectral imaging technique combined with fluorescence spectroscopy point measurements has been used for the transcutaneous detection of enhanced green fluorescent protein (EGFP) fluorescence, providing information on location and duration of EGFP expression. We found that electrosonoporation, commonly enhancing pDNA transfection in vitro, had no positive effect on EGFP transfection efficiency increase in vivo with respect to electroporation alone. We presume that this may be associated with decreased viability of transfected fibers. <a href="https://spie.org/Publications/Proceedings/Paper/10.1117/12.2297222?SSO=1">Tamošiūnas, M., Jakovels, D., Rubins, U., Kadikis, R., Petrovska, R., & Šatkauskas, S. (2017, December). pEGFP transfection into murine skeletal muscle by electrosonoporation. In Biophotonics—Riga 2017 (Vol. 10592, p. 105920L). International Society for Optics and Photonics.</a>
2017
Inertial sensors and muscle electrical signals in human-computer interaction

A. Ancans, A. Rozentals, K. Nesenbergs, M. Greitans.

Kopsavilkums

A. Ancans, A. Rozentals, K. Nesenbergs, M. Greitans. “Inertial sensors and muscle electrical signals in human-computer interaction”, 6th International Conference on Information and Communication Technology and Accessibility ICTA 2017
2017
Efficient determination of a finite set of states for an up-and-down process possesing a practical closure

A. Lorencs, V. Plocins

Kopsavilkums

A. Lorencs, V. Plocins. Efficient determination of a finite set of states for an up-and-down process possesing a practical closure. AC&CS, issue 4, 2017, Pages 224-232
2017
Prospects of improving the self-driving car development pipeline: transfer of algorithms from virtual to physical environment

N. Dorbe, I. Ribners, K. Nesenbergs

Kopsavilkums

N. Dorbe, I. Ribners, K. Nesenbergs. "Prospects of improving the self-driving car development pipeline: transfer of algorithms from virtual to physical environment", 2017 The 10th International Conference on Machine Vision (ICMV 2017), November 13-15, 2017, Vienna, Austria
2017
LoPy as a Building Block for Internet of Things in Coastal Marine Applications

U.Grunde, D.Zagars

Kopsavilkums

U.Grunde, D.Zagars, “LoPy as a Building Block for Internet of Things in Coastal Marine Applications”, IEEE 2017 25th TELECOMMUNICATIONS FORUM, Proceedings of Papers, IEEE Catalog Number CFP1798P-CDR, ISBN: 978-1-5386-3072-3
2017
On improving gait analysis data: heel induced force plate noise removal and cut-off frequency selection for Butterworth filter

V. Abolins, K. Nesenbers, E. Bernans

Kopsavilkums

V. Abolins, K. Nesenbers, E. Bernans. “On improving gait analysis data: heel induced force plate noise removal and cut-off frequency selection for Butterworth filter”, ICSPS 2017
2017
Response to CBRNE and Human-Caused Accidents by Using Land and Air Robots

A.Baums

Kopsavilkums

A.Baums, Response to CBRNE and Human-Caused Accidents by Using Land and Air Robots1 ISSN 0146-4116, Automatic Control and Computer Sciences, 2017, Vol. 51, No. 6, pp. 410–416. © Allerton Press, Inc., 2017.
2017
Combination of Periodic and Alias-free Non-uniform Signal Sampling for Wideband Signal Digitizing and Compressed Transmitting Based on Picosecond Resolution Event Timing

I.Bilinskis, E.Boole, K.Sudars

Kopsavilkums

I.Bilinskis, E.Boole, K.Sudars, Combination of Periodic and Alias-free Non-uniform Signal Sampling for Wideband Signal Digitizing and Compressed Transmitting Based on Picosecond Resolution Event Timing, Proceeding of Signal Processing Symposium 2017

Nonparametric Classification of Satellite Images

The Use Of The Karhunen Loeve Transformation To Form The Speech Data For Their Subsequent Wiring To Sound By Probing Sound Source By An Ultra-Wideband Pulse Locator

Integration of Computervision and Artificial Intelligence Subsystems with Robot Operating System Based Motion Planning for Industrial Robots

Performance of Adaptive Filters for Predicting the Future Values of the Vehicle Sideslip Angle

FPGA Master-based on chip communications architecture for Cyclone V SoC running Linux

“Specific Signal Representation for Transmission and Processing based on Precise Event Timing

Demodulation of Frequency-Modulated Signals by Pseudorandomly Selected Zero-Crossing Instants

Human skin as data transmission medium for improved privacy and usability in wearable electronics

Measurement of current consumption in a wireless sensor network TestBed

Power Consumption Measurement of Tested Units in the WSN TestBed

Mobile wireless sensor network TestBed

Vehicle type and licence plate localisation and segmentation using FCN and LSTM

pEGFP transfection into murine skeletal muscle by electrosonoporation

Inertial sensors and muscle electrical signals in human-computer interaction

Efficient determination of a finite set of states for an up-and-down process possesing a practical closure

Prospects of improving the self-driving car development pipeline: transfer of algorithms from virtual to physical environment

LoPy as a Building Block for Internet of Things in Coastal Marine Applications

On improving gait analysis data: heel induced force plate noise removal and cut-off frequency selection for Butterworth filter

Response to CBRNE and Human-Caused Accidents by Using Land and Air Robots

Combination of Periodic and Alias-free Non-uniform Signal Sampling for Wideband Signal Digitizing and Compressed Transmitting Based on Picosecond Resolution Event Timing