Pētniecība
Publikācijas
729 publikācijas
- 2021
Development and Experimental Validation of High Performance Embedded Intelligence and Fail-Operational Urban Surround Perception Solutions of the PRYSTINE Project(atveras jaunā logā)
Rihards Novickis, Aleksandrs Levinskis, Vitalijs Fescenko, Roberts Kadikis, Kaspars Ozols, Anna Ryabokon, Rupert Schorn, Jochen Koszescha, Selim Solmaz, Georg Stettinger, Akwasi Adu-Kyere, Lauri Halla-aho, Ethiopia Nigussie, Jouni Isoaho
Applied Sciences, Sēj. 12 (1), lpp. 168, MDPI
Kopsavilkums
Automated Driving Systems (ADSs) commend a substantial reduction of human-caused road accidents while simultaneously lowering emissions, mitigating congestion, decreasing energy consumption and increasing overall productivity. However, achieving higher SAE levels of driving automation and complying with ISO26262 C and D Automotive Safety Integrity Levels (ASILs) is a multi-disciplinary challenge that requires insights into safety-critical architectures, multi-modal perception and real-time control. This paper presents an assorted effort carried out in the European H2020 ECSEL project—PRYSTINE. In this paper, we (1) investigate Simplex, 1oo2d and hybrid fail-operational computing architectures, (2) devise a multi-modal perception system with fail-safety mechanisms, (3) present a passenger vehicle-based demonstrator for low-speed autonomy and (4) suggest a trust-based fusion approach validated on a heavy-duty truck.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.068
- 2021
AI in Industrial Machinery(atveras jaunā logā)
Urlini Giulio, Janis Arents, and Antonio Latella
Artificial Intelligence for Digitising Industry, River Publishers
Kopsavilkums
This introductory article opens the section on “Advancing Artificial Intelligence in Industrial Machinery Applications”. It gives an overview of the state-of-the-art AI technologies in industrial machinery and the current AI development in efficiency improvement, personnel safety, automation, and human-machine interaction. It also presents future potential and opportunities for AI in the sector, covering trends of using AI, IIoT technologies, and advanced actuation and sensing techniques, safety/quality, maintenance, waste reduction, and environmental sustainability. Finally, the article introduces the four contributions to this section.
- 2021
Construction of a Smart Vision-Guided Robot System for Manipulation in a Dynamic Environment(atveras jaunā logā)
Janis Arents, Modris Greitans, Bernd Lesser
Artificial Intelligence for Digitising Industry, River Publishers
Kopsavilkums
This article outlines the construction of universal, user-friendly smart robot system for manipulation in a dynamic environment through AI-based vision system which incorporates processing on the edge. To successfully perform complex tasks in changing conditions, robots require both intelligence for adaptive decision-making and the ability to accurately perceive the environment and interface with it. The proposed system is built in a way that maximizes the modularity of the system. And thus, improves the ease at which the system can be modified to other specific goals after it has been operationalized. In this work, these characteristics are achieved by the use of synthetically generated data and Robot Operating System (ROS) as a middleware software. The first results prove the feasibility of training object detection networks on synthetically generated data sets. And also a combination of a 3D camera and industrial robot provides a convenient way for adding new objects to the database.
- 2021
Multispectral Data Classification with Deep CNN for Plastic Bottle Sorting(atveras jaunā logā)
Romans Maliks, Roberts Kadikis
2021 6th International Conference on Mechanical Engineering and Robotics Research (ICMERR), IEEE
Kopsavilkums
Current global trends and green policies indicate the importance of smart waste sorting. Polymer type identification plays a key role in the circular economy model, where high precision is vital to reduce the impurities of recycled plastic flakes. In this paper, we present a robust, high-accuracy plastic bottle polymer type classification using Convolutional Neural Network (CNN). Near-infrared (NIR) absorbance spectroscopy is used to gather polypropylene (PP), polyethene terephthalate (PET), high-density polyethene (HDPE), and low-density polyethene (LDPE) spectra in a dry and wet state. We propose a data augmentation method that generates additional training examples, and we experimentally determine the impact of the ratio of real and generated samples on the accuracy of the classification. In addition, we compare this classification approach with Support Vector Machine (SVM), Principal Component Analysis (PCA) and t-distributed Stochastic Neighbour Embedding (t-SNE) classification methods and also provide data-preprocessing steps for these methods. Finally, we combine pre-processing, component analysis, and CNN to achieve 98.4% accuracy rate while reducing the sizes of CNN input feature vectors and the CNN model itself.
- 2021
Multi-static UWB radar for classification of objects from different materials(atveras jaunā logā)
K. Greitans, M. Greitans
Proceedings of 2021 IEEE Workshop on Microwave Theory and Techniques in Wireless Communications, IEEE
Kopsavilkums
This paper evaluates the advantages of Multi-static Ultra-wide band (UWB) radar architecture for the classification of objects from different materials comparing single-static and bistatic UWB radar cases. In this research single transmitting and four receiving Vivaldi antennas are used. Antennas are connected to the UWB impulse radio radar that is configured to sample 1023 points with a sampling time of 20 ps per point. For the classification of objects, a hybrid artificial neural network model is used. The model consists of 4 channel single convolution layer blocks for feature recognition that are combined and processed by two extra deep layers. The networks were trained on data obtained from several objects from different materials - metal cans, regular PET bottles, crushed PET bottles, and glass bottles. The impact of the additional antennas of UWB radar are evaluated on PET material involved into two classes - regular and crushed bottles. This takes into account the impact of the different structures of objects. The results show 6 times increase of correctly classified objects with the multi-static approach in comparison with a single-channel case. The Multi-static architecture reaches 98.4% accuracy but a single channel evaluation accuracy varies from 91% to 95.1%. © 2021 IEEE.
- 2021
Conformance analysis of model for material properties determination using simulation of ultra-wideband pulse radar(atveras jaunā logā)
G. Gaigals, V. Aristov, M. Greitans
Proceedings of 2021 IEEE Workshop on Microwave Theory and Techniques in Wireless Communications, IEEE
Kopsavilkums
This paper describes compliance analysis of the proposed mathematical model for determination of materials relative permittivity and dielectric losses. The novelty of the proposed model is in non-contact measurement using ultra-wideband impulse radar. The study was concentrated on compliance analysis using simulated data before establishment of the experimental test-bench. Paper includes a short description of proposed measurement method and detailed description of the evaluation of the model using finite-difference time-domain method for simulation of the electromagnetic wave propagation used to obtain electromagnetic field distribution within simulated scene in order to find the conformation of the proposed model to the data obtained during simulations. Study includes description of the conformation analysis steps of the proposed model for determination of the relative permittivity and dielectric losses. Results show practical applicability of the proposed method for quite narrow spectrum of material dielectric properties. Further research directions are shown in order to improve the conformity of the proposed model and results from simulated data. © 2021 IEEE.
- 2021
Determination of the Electrophysical Parameters of Dielectric Objects via the Processing of Ultra-Wideband Pulse Radar Signals(atveras jaunā logā)
V. Aristov, M. Greitans
Automatic Control and Computer Sciences, Sēj. 55 (6), lpp. 577–587, Allerton Press
Kopsavilkums
The article proposes and studies a mathematical model for the determination of the basic electrophysical properties of a dielectric object presented as a single layer with ground-penetrating radar signals. The model algorithm uses the values of reflection amplitudes from the front and rear edges of the object, their ratio, and the mutual time shift as the main initial physical data to find the relative permittivity of the studied object and the loss tangent.
Indeksēts Scopus / WoS · Scopus procentile: 25 · SNIP: 0.676
- 2021
Mobile iot-edge-cloud continuum based and devops enabled software framework(atveras jaunā logā)
J. Judvaitis, R. Balass, M. Greitans
Journal of Sensor and Actuator Networks, Sēj. 10 (4), lpp. 62, MDPI
Kopsavilkums
This research aims to provide a high-level software framework for IoT-Edge-Cloud computational continuum-based applications with support for mobile IoT and DevOps integration utilizing the Edge computing paradigms. This is achieved by dividing the system in a modular fashion and providing a loosely coupled service and module descriptions for usage in the respective system layers for flexible and yet trustworthy implementation. The article describes the software architecture for a DevOps-enabled Edge computing solution in the IoT-Edge-Cloud computational continuum with the support for flexible and mobile IoT solutions. The proposed framework is validated on an intelligent transport system use case in the rolling stock domain and showcases the improvements gained by using the proposed IoT-Edge-Cloud continuum framework. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.329
- 2021
Feasibilty Study in Energy Community Business Model Development for Latvia(atveras jaunā logā)
R. Lazdins, A. Mutule and E. Kairisa
2021 IEEE 62nd International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON), Riga, Latvia, lpp. 1-5
- 2021
Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition?(atveras jaunā logā)
Atis Elsts, Ryan McConville
Electronics, Sēj. 9 (21), lpp. 2640, MDPI
Kopsavilkums
The last decade has seen exponential growth in the field of deep learning with deep learning on microcontrollers a new frontier for this research area. This paper presents a case study about machine learning on microcontrollers, with a focus on human activity recognition using accelerometer data. We build machine learning classifiers suitable for execution on modern microcontrollers and evaluate their performance. Specifically, we compare Random Forests (RF), a classical machine learning technique, with Convolutional Neural Networks (CNN), in terms of classification accuracy and inference speed. The results show that RF classifiers achieve similar levels of classification accuracy while being several times faster than a small custom CNN model designed for the task. The RF and the custom CNN are also several orders of magnitude faster than state-of-the-art deep learning models. On the one hand, these findings confirm the feasibility of using deep learning on modern microcontrollers. On the other hand, they cast doubt on whether deep learning is the best approach for this application, especially if high inference speed and, thus, low energy consumption is the key objective. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Q1/Q2 žurnāls · Scopus procentile: 61 · SNIP: 0.985
- 2021
An efficient FPGA-based co-processor for feature point detection and tracking(atveras jaunā logā)
T. Stūrmanis, R. Novickis
Proceedings - 2021 24th Euromicro Conference on Digital System Design, IEEE
Kopsavilkums
The use of mobile agents is propagating throughout various industries. Nevertheless, the success of novel applications relies on the utilization of novel computing platforms and algorithms, including acceleration technology and onboard localization. We propose an FPGA-based sparse optical flow computing accelerator based on the FAST feature detection and BRIEF feature descriptor. The correspondences are found by splitting the image into static regions, where for each region, the feature points are tracked in-between the frames. The accelerator is fully pipelined and achieves a performance of 300 fps with VGA resolution images. The experimentation with the default configuration of the accelerator shows to support a reliable measurement of frame-to-frame image plane rotation of 9 degrees and translation of 24 pixels, with the total error below 0.4 degrees and 0.16 pixels.
Indeksēts Scopus / WoS
- 2021
Feasibility and physics potential of detecting 8B solar neutrinos at JUNO(atveras jaunā logā)
Angel Abusleme, Joao Pedro Athayde Marcondes de Andre, Andrej Babic, Anatael Cabrera, Christophe De La Taille, Timo Enqvist, Andrea Fabbri, Haonan Gan, Paul Hackspacher, Antonio Insolia, Kuo-Lun Jen, Leonidas Kalousis, Tobias Lachenmaier, Ints Mednieks, Massimiliano Nastasi, Lothar Oberauer, Hsiao-Ru Pan, Fazhi Qi, Muhammad Rajput, Andrey Sadovsky, Stefan van Waasen, Pablo Walker, Yufei Xi, Baojun Yan, Noman Zafar, others
Chinese Physics C, Sēj. 45 (2), lpp. 023004, IOP Publishing Ltd
Kopsavilkums
The Jiangmen Underground Neutrino Observatory (JUNO) features a 20 kt multi-purpose underground liquid scintillator sphere as its main detector. Some of JUNO's features make it an excellent location for 8B solar neutrino measurements, such as its low-energy threshold, high energy resolution compared with water Cherenkov detectors, and much larger target mass compared with previous liquid scintillator detectors. In this paper, we present a comprehensive assessment of JUNO's potential for detecting 8B solar neutrinos via the neutrino-electron elastic scattering process. A reduced 2 MeV threshold for the recoil electron energy is found to be achievable, assuming that the intrinsic radioactive background 238U and 232Th in the liquid scintillator can be controlled to 10-17g/g. With ten years of data acquisition, approximately 60,000 signal and 30,000 background events are expected. This large sample will enable an examination of the distortion of the recoil electron spectrum that is dominated by the neutrino flavor transformation in the dense solar matter, which will shed new light on the inconsistency between the measured electron spectra and the predictions of the standard three-flavor neutrino oscillation framework. If Δm221= 4.8 × 10-5(7.5 × 10-5) eV, JUNO can provide evidence of neutrino oscillation in the Earth at approximately the 3σ (2σ) level by measuring the non-zero signal rate variation with respect to the solar zenith angle. Moreover, JUNO can simultaneously measure Δm221using 8B solar neutrinos to a precision of 20% or better, depending on the central value, and to sub-percent precision using reactor antineutrinos. A comparison of these two measurements from the same detector will help understand the current mild inconsistency between the value of Δm221reported by solar neutrino experiments and the KamLAND experiment. © 2021 Institute of Physics Publishing. All rights reserved.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.019
- 2021
Calibration strategy of the JUNO experiment(atveras jaunā logā)
Angel Abusleme, Andrej Babic, Anatael Cabrera, Selma Conforti Di Lorenzo, Timo Enqvist, Andrea Fabbri, Haonan Gan, Paul Hackspacher, Antonio Insolia, Beatrice Jelmini, Leonidas Kalousis, Tobias Lachenmaier, Qiumei Ma, Massimiliano Nastasi, Lothar Oberauer, Hsiao-Ru Pan, Fazhi Qi, Muhammad Rajput, Andrey Sadovsky, Jian Tang, Stefan van Waasen, Pablo Walker, Yufei Xi, Baojun Yan, Noman Zafar, Ints Mednieks
Journal of High Energy Physics, Sēj. 2021 (3), lpp. 4, Springer Science and Business Media Deutschland GmbH
Kopsavilkums
We present the calibration strategy for the 20 kton liquid scintillator central detector of the Jiangmen Underground Neutrino Observatory (JUNO). By utilizing a comprehensive multiple-source and multiple-positional calibration program, in combination with a novel dual calorimetry technique exploiting two independent photosensors and readout systems, we demonstrate that the JUNO central detector can achieve a better than 1% energy linearity and a 3% effective energy resolution, required by the neutrino mass ordering determination. © 2021, The Author(s).
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.175
- 2021
Radioactivity control strategy for the JUNO detector(atveras jaunā logā)
Angel Abusleme, Joao Pedro Athayde Marcondes de Andre, Andrej Babic, Natael Cabrera, Timo Enqvist, Andrea Fabbri, Haonan Gan, Paul Hackspacher, Ara Ioannisian, Beatrice Jelmini, Leonidas Kalousis, Tobias Lachenmaier, Bangzheng Ma, Massimiliano Nastasi, Lothar Oberauer, Juan PedroOchoa-Ricoux, Fazhi Qi, Muhammad Usman Rajput, Andrey Sadovsky, Jian Tang, Nikita Ushakov, Johannes vanden Boom, Pablo Walker, Yufei Xi, Baojun Yan, Noman Zafar, Ints Mednieks
Journal of High Energy Physics, Sēj. 2021 (11), lpp. 102, Springer Science and Business Media Deutschland GmbH
Kopsavilkums
JUNO is a massive liquid scintillator detector with a primary scientific goal of determining the neutrino mass ordering by studying the oscillated anti-neutrino flux coming from two nuclear power plants at 53 km distance. The expected signal anti-neutrino interaction rate is only 60 counts per day (cpd), therefore a careful control of the background sources due to radioactivity is critical. In particular, natural radioactivity present in all materials and in the environment represents a serious issue that could impair the sensitivity of the experiment if appropriate countermeasures were not foreseen. In this paper we discuss the background reduction strategies undertaken by the JUNO collaboration to reduce at minimum the impact of natural radioactivity. We describe our efforts for an optimized experimental design, a careful material screening and accurate detector production handling, and a constant control of the expected results through a meticulous Monte Carlo simulation program. We show that all these actions should allow us to keep the background count rate safely below the target value of 10 Hz (i.e. ∼1 cpd accidental background) in the default fiducial volume, above an energy threshold of 0.7 MeV.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.175
- 2021
PV Energy Communities—Challenges and Barriers from a Consumer Perspective: A Literature Review(atveras jaunā logā)
R. Lazdins, A. Mutule and D. Zalostiba
Energies, Sēj. 14
- 2021
Optimization of the JUNO liquid scintillator composition using a Daya Bay antineutrino detector(atveras jaunā logā)
A. Abusleme, J. P. A. M. de Andre, A. Babic, A. Cabrera, T. Enqvist, A. Fabbri, J. P. Gallo, M. Haacke, A. Insolia, D. E. Jaffe, L. Kalousis, B. Lachacinski, Q. M. Ma, J. Napolitano, L. Oberauer, H. R. Pan, L. F. Pineres Rico, F. Z. Qi, A. Sadovsky, J. Tang, S. van Waasen, P. Walker, Y. F. Xi, B. J. Yan, N. Zafar, Ints Mednieks
Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Sēj. 988, lpp. 164823, Elsevier B.V.
Kopsavilkums
To maximize the light yield of the liquid scintillator (LS) for the Jiangmen Underground Neutrino Observatory (JUNO), a 20 t LS sample was produced in a pilot plant at Daya Bay. The optical properties of the new LS in various compositions were studied by replacing the gadolinium-loaded LS in one antineutrino detector. The concentrations of the fluor, PPO, and the wavelength shifter, bis-MSB, were increased in 12 steps from 0.5 g/L and <0.01 mg/L to 4 g/L and 13 mg/L, respectively. The numbers of total detected photoelectrons suggest that, with the optically purified solvent, the bis-MSB concentration does not need to be more than 4 mg/L. To bridge the one order of magnitude in the detector size difference between Daya Bay and JUNO, the Daya Bay data were used to tune the parameters of a newly developed optical model. Then, the model and tuned parameters were used in the JUNO simulation. This enabled to determine the optimal composition for the JUNO LS: purified solvent LAB with 2.5 g/L PPO, and 1 to 4 mg/L bis-MSB. © 2020 Elsevier B.V.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.227
- 2021
JUNO sensitivity to low energy atmospheric neutrino spectra(atveras jaunā logā)
Angel Abusleme, Joao Pedro Athayde Marcondes de Andre, Andrej Babic, Anatael Cabrera, Timo Enqvist, Andrea Fabbri, Haonan Gan, Paul Hackspacher, Antonio Insolia, Beatrice Jelmini, Leonidas Kalousis, Tobias Lachenmaier, Bangzheng Ma, Massimiliano Nastasi, Lothar Oberauer, Hsiao-Ru Pan, Luis Felipe Pineres Rico, Fazhi Qi, Andrey Sadovsky, Jian Tang, Nikita Ushakov, Johannes van den Boom, Pablo Walker, Yufei Xi, Baojun Yan, Noman Zafar, Ints Mednieks
European Physical Journal C, Sēj. 81 (10), lpp. 887, Springer Science and Business Media Deutschland GmbH
Kopsavilkums
Atmospheric neutrinos are one of the most relevant natural neutrino sources that can be exploited to infer properties about cosmic rays and neutrino oscillations. The Jiangmen Underground Neutrino Observatory (JUNO) experiment, a 20 kton liquid scintillator detector with excellent energy resolution is currently under construction in China. JUNO will be able to detect several atmospheric neutrinos per day given the large volume. A study on the JUNO detection and reconstruction capabilities of atmospheric νe and νμ fluxes is presented in this paper. In this study, a sample of atmospheric neutrino Monte Carlo events has been generated, starting from theoretical models, and then processed by the detector simulation. The excellent timing resolution of the 3” PMT light detection system of JUNO detector and the much higher light yield for scintillation over Cherenkov allow to measure the time structure of the scintillation light with very high precision. Since νe and νμ interactions produce a slightly different light pattern, the different time evolution of light allows to discriminate the flavor of primary neutrinos. A probabilistic unfolding method has been used, in order to infer the primary neutrino energy spectrum from the detector experimental observables. The simulated spectrum has been reconstructed between 100 MeV and 10 GeV, showing a great potential of the detector in the atmospheric low energy region. © 2021, The Author(s).
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.339
- 2021
The design and sensitivity of JUNO’s scintillator radiopurity pre-detector OSIRIS(atveras jaunā logā)
Angel Abusleme, Joao Pedro Athayde Marcondes de Andre, Andrej Babic, Anatael Cabrera, Timo Enqvist, Andrea Fabbri, Haonan Gan, Paul Hackspacher, Ara Ioannisian, Beatrice Jelmini, Leonidas Kalousis, Tobias Lachenmaier, Bangzheng Ma, Massimiliano Nastasi, Lothar Oberauer, Hsiao-Ru Pan, Luis Felipe Pineres Rico, Fazhi Qi, Andrey Sadovsky, Jian Tang, Nikita Ushakov, Johannes van den Boom, Pablo Walker, Yufei Xi, Baojun Yan, Noman Zafar, Ints Mednieks, J. Miller, P. Montini, A. Müller
European Physical Journal C, Sēj. 81 (11), lpp. 973, Springer Science and Business Media Deutschland GmbH
Kopsavilkums
The OSIRIS detector is a subsystem of the liquid scintillator filling chain of the JUNO reactor neutrino experiment. Its purpose is to validate the radiopurity of the scintillator to assure that all components of the JUNO scintillator system work to specifications and only neutrino-grade scintillator is filled into the JUNO Central Detector. The aspired sensitivity level of 10-16g/g of 238U and 232Th requires a large (∼20m3) detection volume and ultralow background levels. The present paper reports on the design and major components of the OSIRIS detector, the detector simulation as well as the measuring strategies foreseen and the sensitivity levels to U/Th that can be reached in this setup. © 2021, The Author(s)
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.339
- 2021
Determination of the Electrophysical Parameters of Dielectric Objects via the Processing of Ultra-Wideband Pulse Radar Signals(atveras jaunā logā)
Vladimir Aristov, Modris Greitans
Automatic Control and Computer Sciences, Sēj. 55 (6), lpp. 577 - 587, Allerton Press
Kopsavilkums
For the classical peak detector circuit, built on a modern element base and designed to measure the amplitude of pulses of nanosecond duration, mathematically, using the Laplace transform, an equivalent circuit is described, which additionally includes parasitic capacitors and inductances. Based on the results of the analysis of the characteristics of the equivalent circuit, recommendations are made to increase the measurement accuracy when it is possible to reduce the limit of the duration of the measured pulses.
Scopus procentile: 32 · SNIP: 0.657
- 2021
Metamodel-based Optimisation of Synchronous Reluctance Motor Rotor
Orlova S., Pugachov V., Auzins J., Rassolkin A.
2021 28th International Workshop on Electric Drives: Improving Reliability of Electric Drives