Pētniecība
Publikācijas
729 publikācijas
- 2022
Automated delineation of microstands in hemiboreal mixed forests using stereo GeoEye-1 data(atveras jaunā logā)
Linda Gulbe, Juris Zarins, Ints Mednieks
MPDI Open Access Journals, Sēj. 14 (6), lpp. https://www.mdpi.com/2072-4292/14/6/1471, MDPI
Kopsavilkums
A microstand is a small forest area with a homogeneous tree species, height, and density composition. High-spatial-resolution GeoEye-1 multispectral (MS) images and GeoEye-1-based canopy height models (CHMs) allow delineating microstands automatically. This paper studied the potential benefits of two microstand segmentation workflows: (1) our modification of JSEG and (2) generic region merging (GRM) of the Orfeo Toolbox, both intended for the microstand border refinement and automated stand volume estimation in hemiboreal forests. Our modification of JSEG uses a CHM as the primary data source for segmentation by refining the results using MS data. Meanwhile, the CHM and multispectral data fusion were achieved as multiband segmentation for the GRM workflow. The accuracy was evaluated using several sets of metrics (unsupervised, supervised direct assessment, and system-level assessment). Metrics were calculated for a regular segment grid to check the benefits compared with the simple image patches. The metrics showed very similar results for both workflows. The most successful combinations in the workflow parameters retrieved over 75 % of the boundaries selected by a human interpreter. However, the impact of data fusion and parameter combinations on stand volume estimation accuracy was minimal, causing variations of the RMSE within approximately 7 m3/ha.
Scopus procentile: 91 · SNIP: 1.546
- 2021
Impact of Base-to-Height Ratio on Canopy Height Estimation Accuracy of Hemiboreal Forest Tree Species by Using Satellite and Airborne Stereo Imagery(atveras jaunā logā)
G. Goldbergs
Remote Sensing, Sēj. 13 (15), lpp. 2941, MDPI
Kopsavilkums
The present study assessed the large-format airborne (UltraCam) and satellite (GeoEye1 and Pleiades1B) image-based digital surface model (DSM) performance for canopy height estimation in predominantly mature, closed-canopy Latvian hemiboreal forestland. The research performed the direct comparison of calculated image-based DSM models with canopy peaks heights extracted from reference LiDAR data. The study confirmed the tendency for canopy height underestimation for all satellite-based models. The obtained accuracy of the canopy height estimation GeoEye1-based models varied as follows: for a pine (−1.49 median error, 1.52 m normalised median absolute deviation (NMAD)), spruce (−0.94 median, 1.97 m NMAD), birch (−0.26 median, 1.96 m NMAD), and black alder (−0.31 median, 1.52 m NMAD). The canopy detection rates (completeness) using GeoEye1 stereo imagery varied from 98% (pine) to >99% for spruce and deciduous tree species. This research has shown that determining the optimum base-to-height (B/H) ratio is critical for canopy height estimation efficiency and completeness using image-based DSMs. This study found that stereo imagery with a B/H ratio range of 0.2–0.3 (or convergence angle range 10–15◦) is optimal for image-based DSMs in closed-canopy hemiboreal forest areas.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.708
- 2021
Impact of Base-to-Height Ratio on Canopy Height Estimation Accuracy of Hemiboreal Forest Tree Species by Using Satellite and Airborne Stereo Imagery(atveras jaunā logā)
G. Goldbergs
Remote Sensing, Sēj. 13 (15), lpp. 2941, MDPI
Kopsavilkums
The present study assessed the large-format airborne (UltraCam) and satellite (GeoEye1 and Pleiades1B) image-based digital surface model (DSM) performance for canopy height estimation in predominantly mature, closed-canopy Latvian hemiboreal forestland. The research performed the direct comparison of calculated image-based DSM models with canopy peaks heights extracted from reference LiDAR data. The study confirmed the tendency for canopy height underestimation for all satellite-based models. The obtained accuracy of the canopy height estimation GeoEye1-based models varied as follows: for a pine (−1.49 median error, 1.52 m normalised median absolute deviation (NMAD)), spruce (−0.94 median, 1.97 m NMAD), birch (−0.26 median, 1.96 m NMAD), and black alder (−0.31 median, 1.52 m NMAD). The canopy detection rates (completeness) using GeoEye1 stereo imagery varied from 98% (pine) to >99% for spruce and deciduous tree species. This research has shown that determining the optimum base-to-height (B/H) ratio is critical for canopy height estimation efficiency and completeness using image-based DSMs. This study found that stereo imagery with a B/H ratio range of 0.2–0.3 (or convergence angle range 10–15◦) is optimal for image-based DSMs in closed-canopy hemiboreal forest areas. © 2021 by the author. Licensee MDPI, Basel, Switzerland.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · Scopus procentile: 91 · SNIP: 1.708
- 2021
Programmable Systems for Intelligence in Automobiles (PRYSTINE): Final results after Year 3(atveras jaunā logā)
Norbert Druml, Anna Ryabokon, Rupert Schorn, Jochen Koszescha, Kaspars Ozols, Aleksandrs Levinskis, Rihards Novickis
2021 24th Euromicro Conference on Digital System Design (DSD), IEEE
Kopsavilkums
Autonomous driving is disrupting the automotive industry as we know it today. For this, fail-operational behavior is essential in the sense, plan, and act stages of the automation chain in order to handle safety-critical situations on its own, which currently is not reached with state-of-the-art approaches.The European ECSEL research project PRYSTINE realizes Fail-operational Urban Surround perceptION (FUSION) based on robust Radar and LiDAR sensor fusion and control functions in order to enable safe automated driving in urban and rural environments. This paper showcases some of the key exploitable results (e.g., novel Radar sensors, innovative embedded control and E/E architectures, pioneering sensor fusion approaches, AI-controlled vehicle demonstrators) achieved until its final year 3.
Indeksēts Scopus / WoS
- 2021
Pushing Mechatronic Applications to the Limits via Smart Motion Control(atveras jaunā logā)
Čech Martin, Arend-Jan Beltman, Kaspars Ozols
Applied Sciences, Sēj. 11 (18), lpp. 8337, MDPI
Kopsavilkums
Modern machines strive to run at limit performance and dependability while their operational area and size are getting restricted. To achieve those objectives, often swift integration of custom-made subsystems is required, either actuators, sensors, electronic, or SW modules. Such a diverse suite of elements needs specific approaches and tools for fast optimization and adjustment following model-based system engineering (MBSE) and digital twinning principles. The large-scale I-MECH project was an industry-driven initiative striving to give a scientific response to those demands. The intermediate results were summarized in the authors’ previous work. The purpose of this paper is to report on final project results, namely specific performance achievements and figures based on measurable KPIs. After a brief description of key technologies, special focus is given to industrial printing technology based on a generic substrate carrier. However, it is shown that similar and consistent methodology can be applicable in many other industrial domains, such as semiconductors, healthcare robotics, machining, packaging, etc. Thus, the main merit of this survey is a holistic approach to motion control design.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.068
- 2021
Demo: Large Scale Wireless Network Simulations with TSCH-Sim(atveras jaunā logā)
Atis Elsts
The 2021 International Conference on Embedded Wireless Systems and Networks (EWSN), lpp. 181-182, ACM
Kopsavilkums
Simulators capable of handling large networks are increasingly necessary. To this end, this demo abstract presents TSCH-Sim, a scalable simulator for TSCH and 6TiSCH networks. The experimental results presented in this demo abstract include both performance of the simulated networks, as well as the speed of the simulator itself. The results demonstrate the benefits from developing new, custom solutions for networks above a certain size.
Indeksēts Scopus / WoS
- 2021
Hand-Washing Video Dataset Annotated According to the World Health Organization’s Hand-Washing Guidelines(atveras jaunā logā)
Lulla M., Rutkovskis A., Slavinska A., Vilde A., Gromova A., Ivanovs M., Skadins A., Kadikis R., Elsts A.
Data, Sēj. 6 (4), lpp. 38, MDPI
Kopsavilkums
Washing hands is one of the most important ways to prevent infectious diseases, including COVID-19. The World Health Organization (WHO) has published hand-washing guidelines. This paper presents a large real-world dataset with videos recording medical staff washing their hands as part of their normal job duties in the Pauls Stradins Clinical University Hospital. There are 3185 hand-washing episodes in total, each of which is annotated by up to seven different persons. The annotations classify the washing movements according to the WHO guidelines by marking each frame in each video with a certain movement code. The intention of this “in-the-wild” dataset is two-fold: to serve as a basis for training machine-learning classifiers for automated hand-washing movement recognition and quality control, and to allow to investigation of the real-world quality of washing performed by working medical staff. We demonstrate how the data can be used to train a machine-learning classifier that achieves classification accuracy of 0.7511 on a test dataset.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.086
- 2021
Ultra-Wideband Pulse Radar with Discrete Stroboscopic Receiver for Detection of Small Targets Behind Dielectric Obstacles(atveras jaunā logā)
V.Aristovs, G.Gaigals, G.Supols, E.Lobanovs, V.Riekstins, V.Zujs
Transport and Telecommunication Journal, Sēj. 22 (2), lpp. 196 - 206, Sciendo
Kopsavilkums
Increasing requirements in the field of security, in particular in the transport sector, the rescue work, the inviolability of private property and others urged to research work in the field of radar monitoring people, vehicles or other objects in the environment that not allow make so using the most popular and available technology for production and analysis of video images. These conditions of poor visibility, or even lack thereof, are darkness, bad weather, smoke, dust, wall (roof) buildings and the vehicle body. Existing instruments and special equipment occupy a certain niche in this area, mainly for counter-terrorism operations. However, such equipment is not readily available and extremely high price. In the paper presented research is development of the group's existing radar technology in the field of location through opaque obstacles.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 0.646
- 2021
Ultra-Wideband Pulse Radar with Discrete Stroboscopic Receiver for Detection of Small Targets Behind Dielectric Obstacles(atveras jaunā logā)
V. Aristovs, G. Gaigals, G. Supols, E. Lobanovs, V. Riekstins, V. Zujs
Transport and Telecommunication, Sēj. 22 (2), lpp. 196 - 206, Sciendo
Kopsavilkums
Increasing requirements in the field of security, in particular in the transport sector, the rescue work, the inviolability of private property and others urged to research work in the field of radar monitoring people, vehicles or other objects in the environment that not allow make so using the most popular and available technology for production and analysis of video images. These conditions of poor visibility, or even lack thereof, are darkness, bad weather, smoke, dust, wall (roof) buildings and the vehicle body. Existing instruments and special equipment occupy a certain niche in this area, mainly for counter-terrorism operations. However, such equipment is not readily available and extremely high price. In the paper presented research is development of the group's existing radar technology in the field of location through opaque obstacles. © 2021 Vladimir Aristov et al., published by Sciendo 2021.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 0.646
- 2021
Perturbation-based methods for explaining deep neural networks: A survey(atveras jaunā logā)
Maksims Ivanovs, Roberts Kadiķis, Kaspars Ozols
Pattern Recognition Letters, Sēj. 150, lpp. 228 - 234, Elsevier
Kopsavilkums
Deep neural networks (DNNs) have achieved state-of-the-art results in a broad range of tasks, in particular the ones dealing with the perceptual data. However, full-scale application of DNNs in safety-critical areas is hindered by their black box-like nature, which makes their inner workings nontransparent. As a response to the black box problem, the field of explainable artificial intelligence (XAI) has recently emerged and is currently rapidly growing. The present survey is concerned with perturbation-based XAI methods, which allow to explore DNN models by perturbing their input and observing changes in the output. We present an overview of the most recent research focusing on the differences and similarities in the applications of perturbation-based methods to different data types, from extensively studied perturbations of images to the just emerging research on perturbations of video, natural language, software code, and reinforcement learning entities.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.739
- 2021
Wearable Sensor Clothing for Body Movement Measurement during Physical Activities in Healthcare(atveras jaunā logā)
A. Ancans, M. Greitans, R. Cacurs, B. Banga, A. Rozentals
Sensors, Sēj. 21 (6), lpp. 2068, MDPI
Kopsavilkums
This paper presents a wearable wireless system for measuring human body activities, consisting of small inertial sensor nodes and the main hub for data transmission via Bluetooth for further analysis. Unlike optical and ultrasonic technologies, the proposed solution has no movement restrictions, such as the requirement to stay in the line of sight, and it provides information on the dynamics of the human body’s poses regardless of its location. The problem of the correct placement of sensors on the body is considered, a simplified architecture of the wearable clothing is described, an experimental set-up is developed and tests are performed. The system has been tested by performing several physical exercises and comparing the performance with the commercially available BTS Bioengineering SMART DX motion capture system. The results show that our solution is more suitable for complex exercises as the system based on digital cameras tends to lose some markers. The proposed wearable sensor clothing can be used as a multi-purpose data acquisition device for application-specific data analysis, thus providing an automated tool for scientists and doctors to measure patient’s body movements.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.555
- 2021
Use of Augmented and Virtual Reality in Remote Higher Education: A Systematic Umbrella Review(atveras jaunā logā)
Krisjanis Nesenbergs, Valters Abolins, Juris Ormanis, Artis Mednis
Education Sciences, Sēj. 11 (1), lpp. 1 - 12, MDPI AG
Kopsavilkums
In this systematic umbrella review we aggregate the current knowledge of how virtual and augmented reality technologies are applicable to and impact remote learning in higher education; specifically, how they impact such learning outcomes as performance and engagement in all stages of higher education from course preparation to student evaluation and grading. This review was done as part of a state wide research effort of Latvia, to mitigate the impact of COVID-19 and specifically to provide a framework for a technological transformation of education in this context. In this work we search the Scopus and Web of Science databases for articles describing the use of virtual and/or augmented reality technologies in remote learning for higher education and their impact on learning outcomes. We identified 68 articles from which, after multiple screening and eligibility phases, nine review articles were left for extraction phase in which 30 structural elements with corresponding interventions and measured effects were extracted. Of these, 24 interventions had a measured effect on student performance (11 positive, seven negative, six no impact) and six interventions had a measured effect on student engagement (all six positive). © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.204
- 2021
Use of Augmented and Virtual Reality in Remote Higher Education: A Systematic Umbrella Review
Krisjanis Nesenbergs, Valters Abolins, Juris Ormanis, Artis Mednis
Kopsavilkums
<p>Use of Augmented and Virtual Reality in Remote Higher Education: A Systematic Umbrella Review, 2021</p> <p><a href="https://doi.org/10.3390/educsci11010008">https://doi.org/10.3390/educsci11010008</a></p> <p>All authors:</p> <p>Krisjanis Nesenbergs, Valters Abolins, Juris Ormanis and Artis Mednis</p> <p><strong>Abstract:</strong></p> <p>In this systematic umbrella review we aggregate the current knowledge of how virtual and augmented reality technologies are applicable to and impact remote learning in higher education; specifically, how they impact such learning outcomes as performance and engagement in all stages of higher education from course preparation to student evaluation and grading. This review was done as part of a state wide research effort of Latvia, to mitigate the impact of COVID-19 and specifically to provide a framework for a technological transformation of education in this context. In this work we search the Scopus and Web of Science databases for articles describing the use of virtual and/or augmented reality technologies in remote learning for higher education and their impact on learning outcomes. We identified 68 articles from which, after multiple screening and eligibility phases, nine review articles were left for extraction phase in which 30 structural elements with corresponding interventions and measured effects were extracted. Of these, 24 interventions had a measured effect on student performance (11 positive, seven negative, six no impact) and six interventions had a measured effect on student engagement (all six positive).</p>
- 2021
A Wearable Low-Power Sensing Platform for Environmental and Health Monitoring: The Convergence Project(atveras jaunā logā)
Elise Saoutieff, Tiziana Polichetti, Laurent Jouanet, Adrien Faucon, Audrey Vidal, Alexandre Pereira, Sébastien Boisseau, Thomas Ernst, Maria Lucia Miglietta, Brigida Alfano, Ettore Massera, Saverio De Vito, Do Hanh Ngan Bui, Philippe Benech, Tan-Phu Vuong, Carmen Moldovan, Yann Danlee, Thomas Walewyns, Sylvain Petre, Denis Flandre, Armands Ancans, Modris Greitans, Adrian M. Ionescu
Sensors, Sēj. 21 (5), lpp. 1802, MDPI
Kopsavilkums
The low-power sensing platform proposed by the Convergence project is foreseen as a wireless, low-power and multifunctional wearable system empowered by energy-efficient technologies. This will allow meeting the strict demands of life-style and healthcare applications in terms of autonomy for quasi-continuous collection of data for early-detection strategies. The system is compatible with different kinds of sensors, able to monitor not only health indicators of individual person (physical activity, core body temperature and biomarkers) but also the environment with chemical composition of the ambient air (NOx, COx, NHx particles) returning meaningful information on his/her exposure to dangerous (safety) or pollutant agents. In this article, we introduce the specifications and the design of the low-power sensing platform and the different sensors developed in the project, with a particular focus on pollutant sensing capabilities and specifically on NO2 sensor based on graphene and CO sensor based on polyaniline ink.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.555
- 2021
Wearable Sensor Clothing for Body Movement Measurement during Physical Activities in Healthcare(atveras jaunā logā)
A. Ancāns, M.Greitāns, R. Cacurs, B. Banga, A. Rozentāls
Sensors, Sēj. 21 (6), lpp. 1 - 16, MDPI AG
Kopsavilkums
This paper presents a wearable wireless system for measuring human body activities, consisting of small inertial sensor nodes and the main hub for data transmission via Bluetooth for further analysis. Unlike optical and ultrasonic technologies, the proposed solution has no movement restrictions, such as the requirement to stay in the line of sight, and it provides information on the dynamics of the human body’s poses regardless of its location. The problem of the correct placement of sensors on the body is considered, a simplified architecture of the wearable clothing is described, an experimental set-up is developed and tests are performed. The system has been tested by performing several physical exercises and comparing the performance with the commercially available BTS Bioengineering SMART DX motion capture system. The results show that our solution is more suitable for complex exercises as the system based on digital cameras tends to lose some markers. The proposed wearable sensor clothing can be used as a multi-purpose data acquisition device for application-specific data analysis, thus providing an automated tool for scientists and doctors to measure patient’s body movements. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.555
- 2021
Survey of Low-Power Wireless Network Technologies for the Internet of Things(atveras jaunā logā)
Niklavs Barkovskis, Kaspars Ozols, Atis Elsts
Automatic Control and Computer Sciences, Sēj. 55 (2), lpp. 177 - 194, Pleiades Publishing
Kopsavilkums
A large number of different low-power wireless network technologies exist, including IEEE 802.15.4, Bluetooth Low Energy, multiple protocol standards of WiFi (IEEE 802.11), Near Field Communication (NFC), and LoRa. Given this number of competing technologies, the selection of the best one for a new project is not trivial. This paper aims to help Internet of Things (IoT) practitioners in this task. To this end, we illuminate the underlying technical differences between these state-of-the-art wireless solutions through their assessment and brief analysis. We quantify and compare their latency, throughput and overhead, as well as overview their main characteristics such as frequency bands, bandwidth, medium access methods, and packet sizes.
Indeksēts Scopus / WoS · SNIP: 0.676
- 2021
Human–Robot Collaboration Trends and Safety Aspects: A Systematic Review(atveras jaunā logā)
Janis Arents, Valters Abolins, Janis Judvaitis, Oskars Vismanis, Aly Oraby, Kaspars Ozols
Journal of Sensor and Actuator Networks, Sēj. 10 (3), lpp. 48, MDPI
Kopsavilkums
Smart manufacturing and smart factories depend on automation and robotics, whereas human–robot collaboration (HRC) contributes to increasing the effectiveness and productivity of today’s and future factories. Industrial robots especially in HRC settings can be hazardous if safety is not addressed properly. In this review, we look at the collaboration levels of HRC and what safety actions have been used to address safety. One hundred and ninety-three articles were identified from which, after screening and eligibility stages, 46 articles were used for the extraction stage. Predefined parameters such as: devices, algorithms, collaboration level, safety action, and standards used for HRC were extracted. Despite close human and robot collaboration, 25% of all reviewed studies did not use any safety actions, and more than 50% did not use any standard to address safety issues. This review shows HRC trends and what kind of functionalities are lacking in today’s HRC systems. HRC systems can be a tremendously complex process; therefore, proper safety mechanisms must be addressed at an early stage of development.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 1.329
- 2021
The Nature of Finger Enslaving: New Results and Their Implications(atveras jaunā logā)
V. Abolins, M.L. Latash
Motor Control, Sēj. 25 (4), lpp. 680–703, Human Kinetics Journals
Kopsavilkums
We present a review on the phenomenon of unintentional finger action seen when other fingers of the hand act intentionally. This phenomenon (enslaving) has been viewed as a consequence of both peripheral (e.g., connective tissue links and multifinger muscles) and neural (e.g., projections of corticospinal pathways) factors. Recent studies have shown relatively large and fast drifts in enslaving toward higher magnitudes, which are not perceived by subjects. These and other results emphasize the defining role of neural factors in enslaving. We analyze enslaving within the framework of the theory of motor control with spatial referent coordinates. This analysis suggests that unintentional finger force changes result from drifts of referent coordinates, possibly reflecting the spread of cortical excitation.
Indeksēts Scopus / WoS · Q1/Q2 žurnāls · SNIP: 0.692
- 2021
Ultra-Wideband Pulse Radar Mounted on an Unmanned Aerial Vehicle for the Monitoring of Moving Objects(atveras jaunā logā)
V.Aristov, E.Lobanovs, R.Maliks, M.Celitans, J.Simanovichs, S.Bondars, R.Gailis
Automatic Control and Computer Sciences, Sēj. 54 (4), lpp. 396 - 405, Pleiades Publishing
Kopsavilkums
This article describes a classic ground-penetrating radar, which includes a transmitter on two step-recovery diodes for the shock excitation of an ultra-wideband Vivaldi antenna, a discrete sampling receiver with data transmission via Ethernet mounted on a six-blade unmanned aerial vehicle, experiments and processing results of the obtained signals for detecting the movement of small objects both in open space and behind a wall, as well as calculations to determine the thickness of the sounded walls in the case of a single measurement scenario.
Indeksēts Scopus / WoS · SNIP: 0.676
- 2021
Integrated circuit of clocked comparator for ultra-wideband radar(atveras jaunā logā)
R. Maliks, G. Supols, E. Lobanovs, M. Greitans
2021 IEEE Microwave Theory and Techniques in Wireless Communications (MTTW), lpp. 46-51, IEEE
Kopsavilkums
In this paper, the complete technological process of designing the integrated circuit (IC) from an idea to the working clocked comparator for the ultra-wideband (UWB) impulse radar device is proposed. Several IC technologies are investigated and the favourable is determined to design the radar receiver's clocked comparator. The clocked comparator circuit and its methodology are proposed to evaluate the performance within the simulation software. The IC layout is designed with pre and post-layout simulations. During the post-layout simulation, parasitics have been extracted to validate the performance of the device prior to manufacturing. An experimental setup is created to implement the IC into the UWB impulse radar for testing and measurements. The clocked comparator provides 9.1 GHz frequency bandwidth in pre-layout simulation and 5.6 GHz in post-layout simulation, while the manufactured prototype within the experimental setup provides 4 GHz bandwidth. The achieved results demonstrate that chosen technology allowed to design clocked comparator for the UWB impulse radar. Post-layout simulations empower the technology choice before manufacturing to reduce the costs of implementing other UWB radar blocks in one package, which would also reduce the overall size and improve the device parameters.