Publications

729 publications

• 2024

  Electrodes for bio-electrical impedance and body-coupled communication

  Juris Ormanis, Anastasija Sevcenko, Vladislavs Medvedevs, Krisjanis Nesenbergs, Armands Ancans, Modris Greitans

  MeMeA 2024, The 19th edition of the IEEE International Symposium on Medical Measurements and Applications, IEEE

  Abstract

  In the pursuit of enhancing healthcare through biomedical engineering and wearable technology, this research conducts a thorough investigation into the efficacy of different electrodes for BioZ and BCC applications. We meticulously analyze Ag/AgCl, EMS, and gold-plated electrodes across a variety of metrics such as SNR, Settling Time, and CER. Through a series of experiments tailored to assess their performance in monitoring heart rate, breathing, and facilitating data transmission through the human body, we uncover the specific contexts in which each electrode type excels. This study highlights the critical role of electrode choice in advancing non-invasive diagnostic methods through wearable technology. It provides a comprehensive comparison of various electrode types, highlighting their respective benefits for specific health monitoring applications. This research aims to guide the future development of wearable devices, aiming for an optimal balance between sustainability, accuracy, and user convenience in electrode selection for BioZ measurement and BCC applications. This study highlights the critical role of electrode choice in advancing non-invasive diagnostic methods through wearable technology. It provides a comprehensive comparison of various electrode types, highlighting their respective benefits for specific health monitoring applications. This research aims to guide the future development of wearable devices, aiming for an optimal balance between sustainability, accuracy, and user convenience in electrode selection for \gls{BioZ} measurement and \gls{BCC} applications.

  Indexed in Scopus / WoS
• 2024

  Spatio-temporal Object Detection with Deep Spiking CNNs Using Time-of-Flight Data

  Edgars Lielāmurs, Kaspars Ozols

  2024 19th Biennial Baltic Electronics Conference (BEC), IEEE

  Abstract

  Perceiving the surrounding environment with vision sensors, including LiDAR and direct time-of-flight (dToF), is a common task across several domains, such as autonomous vehicles, industrial automation and robotics. As sensors and perception algorithms continue to evolve, their applications are likely to expand further and put more strain on computing resources, necessitating more efficient processing. Neuromorphic computing is a promising solution for efficiently handling sparse event streams, aligning well with the characteristics of sparse LiDAR sensory data. Moreover, the advent of dedicated neuro- morphic vision processors and efficient spike backpropagation training through surrogate gradient (SG) is further inspiring the development of Spiking Neural Networks (SNNs). Thus, in this work, we take advantage of sparse LiDAR sensor point cloud data by formalizing a temporal spike encoding method and implement a 3D object detection convolutional SNN. We conducted comprehensive experiments on the KITTI automotive dataset, showing that the proposed model outperforms closely related spiking neural network solutions and approaches conven- tional state-of-the-art solution performance. More importantly, achieving a mean sparsity of 55.73% underlines the potential of using SNNs for a more efficient way of processing time-of-flight Data.

  Indexed in Scopus / WoS · Scopus percentile: 100 · SNIP: 4.73
• 2024

  Signal Acquisition and Algorithm Design for Bioimpedance-Based Heart Rate Estimation from the Wrist(opens in a new window)

  Didzis Lapsa, Margus Metshein, Andrei Krivošei, Rims Janeliukstis, Olev Märtens, Atis Elsts

  Applied Sciences, Vol. 14 (21), p. 9632, MDPI

  Abstract

  Background: Heart rate (HR) is a critical biomarker that provides insights into overall health, stress levels, and the autonomic nervous system. Pulse wave signals contain valuable information about the cardiovascular system and heart status. However, signal acquisition in wearables poses challenges, particularly when using electrical sensors, due to factors like the distance from the heart, body movement, and suboptimal electrode placement. Methods: Electrical bioimpedance (EBI) measurements using bipolar and tetrapolar electrode systems were employed for pulse wave signal acquisition from the wrist in both perpendicular and distal configurations. Signal preprocessing techniques, including baseline removal via Hankel matrix methods, normalization, cross-correlation, and peak detection, were applied to improve signal quality. This study describes the combination of sensor-level signal acquisition and processing for accurate wearable HR estimation. Results: The bipolar system was shown to produce larger Δ𝑍(𝑡)ΔZ(t), while the tetrapolar system demonstrated higher sensitivity. Distal placement of the electrodes yielded greater Δ𝑍(𝑡)ΔZ(t) (up to 0.231 ΩΩ) when targeting both wrist arteries. Bandpass filtering resulted in a better signal-to-noise ratio (SNR), achieving 3.6 dB for the best bipolar setup and 4.8 dB for the tetrapolar setup, compared to 2.6 and 3.3 dB SNR, respectively, with the Savitzky–Golay filter. The custom HR estimation algorithm presented in this paper demonstrated improved accuracy over a reference method, achieving an average error of 1.8 beats per minute for the best bipolar setup, with a mean absolute percentage error (MAPE) of 8%. Conclusions: The analysis supports the feasibility of using bipolar electrode setups on the wrist and highlights the importance of electrode positioning relative to the arteries. The proposed signal processing method, featuring a preprocessing pipeline and HR estimation algorithm, provides a proof-of-concept demonstration for HR estimation from EBI signals acquired at the wrist.

  Indexed in Scopus / WoS · Scopus percentile: 75
• 2024

  Determination of Factors of Interest in Bone Models Based on Ultrasonic Data(opens in a new window)

  Chuchalina, M.; Sisojevs, A. and Tatarinov, A.

  Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods – ICPRAM, Vol. 1, p. 281-287, SciTePress

  Abstract

  Osteoporosis is characterized by increased bone fragility due to a decrease in thickness of the cortical layer CTh and the development of internal porosity in it. The assessment of bone models that simulate the state of osteoporosis causes difficulties due to their complex and multi-layered structure. In the present work, the possibility of using machine learning approaches to determine internal porosity using the ultrasonic data obtained by scanning bone models was researched. The bone models were represented as sets of PMMA plates with gradually varying CTh from 2 to 6 mm. A stepwise progression of porosity from 0 to 100% of CTh was set by increasing the thickness of the porous layer PTh in steps of 1 mm. The evaluation method was based on the results of the supervised multi-class classification of the raw ultrasonic signals and their magnitude of the DFT spectrum with PTh used for labeling. Ultrasonic data was split into training and testing datasets while preserving the percentag e of samples for each class. The results of the experiments demonstrated the potential effectiveness of the PTh classification, while optimization of the datasets and additional signal processing may contribute to the improvement of the results.

  Indexed in Scopus / WoS
• 2024

  Learning to Move Objects with Fluid Streams in a Differentiable Simulation(opens in a new window)

  Kārlis Freivalds, Laura Leja, Oskars Teikmanis

  ROBOT 2024 7th Iberian Robotics Conference, IEEE,

  Abstract

  We introduce a method for contactless manipulation of objects in three-dimensional space using controlled fluid streams. To achieve this, we train a neural network controller in a differentiable simulation and evaluate it in a simulated environment consisting of an $8\times8$ grid of vertical emitters. By carrying out various horizontal displacement tasks such as moving objects to specific positions while reacting to external perturbations, we demonstrate that a controller, trained with a limited number of iterations, can generalise to longer episodes and learn the complex dynamics of fluid-solid interactions. Importantly, our approach requires only the observation of the manipulated object's state, paving the way for the development of physical systems that enable contactless manipulation of objects using air streams.

  Indexed in Scopus / WoS
• 2024

  Shaping Flames with Differentiable Physics Simulations(opens in a new window)

  Laura Leja, Oskars Teikmanis, Kārlis Freivalds

  "Machine Learning and the Physical Sciences" at NeurIPS 202, NeurIPS

  Abstract

  We introduce a method for shaping simulated flames into customisable forms, with the goal of overcoming the limitations of current pyrotechnic systems, which are typically restricted to producing basic fire columns with minimal control over the resulting shape. Our approach leverages differentiable physics and combustion simulations. We demonstrate the use of differentiable physics-based training to produce simulated letter-shaped flames, and take initial steps towards implementing this method on real flame projectors by aligning the simulation with a physical device. The ability to control flame shape would significantly expand the possibilities for stage pyrotechnics and creative applications in performance art.
• 2024

  Learning Fluid-Directed Rigid Body Control(opens in a new window)

  Kārlis Freivalds, Oskars Teikmanis, Laura Leja, Rodions Saltanovs, Ralfs Āboliņš

  Machine Learning and the Physical Sciences, NeurIPS

  Abstract

  We introduce a method for contactless manipulation of objects in three-dimensional space using controlled fluid streams. To achieve this, we train a neural network controller in a differentiable simulation and evaluate it in a simulated environment consisting of a grid of vertical emitters. By carrying out various horizontal displacement tasks such as moving objects to specific positions while reacting to external perturbations, we demonstrate that a controller, trained with a limited number of iterations, can generalise to longer episodes and learn the complex dynamics of fluid-solid interactions. We are in the process of building a floor-standing device that embodies the proposed method, and we describe its key components and design decisions towards displacing and manipulating delicate objects on the device's surface.
• 2024

  Deviations Detection in Registered 3D Point Clouds

  Ibrahim Sayed, Andrejs Cvetkovs, Kaspars Ozols and Rihards Novickis

  2024 19th Biennial Baltic Electronics Conference (BEC, p. 1-4, IEEE

  Abstract

  This paper explores the validity of three distance metrics: a Point-to-Point distance, a Point-to-Plane distance and a Modified Hausdorff Distance, in detecting the misplacement of a Time-of-Flight camera in a registered 360-degree surround view perception system installed on a vehicle. The vehicle's undamped mechanical vibrations can unexpectedly pivot one of the cameras to an unforeseen orientation, leading to inaccurate processes that rely on correct registered point clouds. Parameterizing the camera exterior 3D orientation and synthesizing point clouds of a city model inside Blender shows that a pair of registered point clouds has a unique distance value in the camera configuration space for each metric method. This allows continuous monitoring over time and notifies the user of any sudden changes in the camera configuration.

  Indexed in Scopus / WoS
• 2024

  Study of a Radar Sensor Transmitter to Optimize a Bipolar Ultrawideband Pulse Used to Excite the Antenna

  V. Aristov, M.Greitans

  Automatic Control and Computer Sciences, Vol. 58 (6), © Allerton Press

  Abstract

  The desire to increase the energy of the pulses by which the impact excitation of ultra-wideband antennas is carried out prompts some authors of equipment (radars) to change the shape of these pulses. In particular, pulses are made bipolar. This article explores the issue of optimizing the shift of the second component of the excitation pulse. Such a shift allows obtaining the maximum level of the spectrum at the frequency of interest, determined by the transmitter-receiver path.

  Indexed in Scopus / WoS
• 2024

  Transmission sensing of dielectric objects to determine the geometric shape of the slice and to detect internal inhomogeneities

  V. Aristov

  utomatic Control and Computer Sciences, Vol. 58 (1), © Allerton Press

  Abstract

  This paper investigates the possibility of determining the geometric slice shape of dielectric objects with a priori information of their internal heterogeneity or detecting the integral internal heterogeneity with a priori information of the geometric slice shape during transmission sensing of these objects by ultra-wideband pulse radar of one gigahertz range.

  Indexed in Scopus / WoS
• 2024

  Interpreting microscopic structures in virtually stained histological sections for veterinary oncology applications

  Diāna Dupļevska, Romans Maļiks, Mindaugas Tamošiūnas, Mikus Melderis, Daira Viškere, Blaž Cugmas, Roberts Kadiķis, Ilze Matīse-van

  SPIE BiOS 2024, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXII, Vol. 128310, SPIE

  Abstract

  We employed a Pix2Pix generative adversarial network to translate the multispectral fluorescence images into colored brightfield representations resembling H&E staining. The model underwent training using 512x512 pixel paired image patches, with a manually stained image serving as the reference and the fluorescence images serving as the processing input. The baseline model, without any modifications, did not achieve high microscopic accuracy, manifesting incorrect color attribution to various biological structures and the addition or removal of image features. However, through the substitution of simple convolutions with Dense convolution units in the U-Net Generator, we observed an increase in the similarity of microscopic structures and the color balance between the paired images. The resulting improvements underscore the potential utility of virtual staining in histopathological analysis for veterinary oncology applications.

  Indexed in Scopus / WoS · Scopus percentile: 23 · SNIP: 0.22
• 2024

  Organ-On-A-Chip (OOC) Image Dataset for Machine Learning and Tissue Model Evaluation(opens in a new window)

  Valērija Movčana, Arnis Strods, Karīna Narbute, Fēlikss Rūmnieks, Roberts Rimša, Gatis Mozoļevskis, Maksims Ivanovs, Roberts Kadiķis, Kārlis Gustavs Zviedris, Laura Leja, Anastasija Zujeva, Tamāra Laimiņa, Arturs Abols

  Data, Vol. 9 (2), p. 28, MDPI

  Abstract

  Organ-on-a-chip (OOC) technology has emerged as a groundbreaking approach for emulating the physiological environment, revolutionizing biomedical research, drug development, and personalized medicine. OOC platforms offer more physiologically relevant microenvironments, enabling real-time monitoring of tissue, to develop functional tissue models. Imaging methods are the most common approach for daily monitoring of tissue development. Image-based machine learning serves as a valuable tool for enhancing and monitoring OOC models in real-time. This involves the classification of images generated through microscopy contributing to the refinement of model performance. This paper presents an image dataset, containing cell images generated from OOC setup with different cell types. There are 3072 images generated by an automated brightfield microscopy setup. For some images, parameters such as cell type, seeding density, time after seeding and flow rate are provided. These parameters along with predefined criteria can contribute to the evaluation of image quality and identification of potential artifacts. This dataset can be used as a basis for training machine learning classifiers for automated data analysis generated from an OOC setup providing more reliable tissue models, automated decision-making processes within the OOC framework and efficient research in the future.

  Indexed in Scopus / WoS · Scopus percentile: 75

  DOI(opens in a new window)
• 2024

  Annotating SLAM data sets with Apriltag markers(opens in a new window)

  Peteris Racinskis, Janis Arents, Modris Greitans

  2024 10th International Conference on Automation, Robotics and Applications (ICARA), p. 438-442, IEEE Xplore

  Abstract

  This paper motivates and describes a methodology for annotating SLAM benchmark data sets where GPS or motion capture equipment is not viable. Ground truth camera pose measurements are obtained at the camera frame rate using surveyed Apriltag2 visual markers. The design of the marker plates, procedures for placing and positioning them, as well as the procedures for sensor track collection, are described. An estimate of the measurement accuracy is obtained by comparison with the Optitrack motion capture system, and the advantage over RTK-corrected GPS as a ground truth pose measurement source in certain environmental conditions is demonstrated experimentally.

  Indexed in Scopus / WoS

  DOI(opens in a new window)
• 2024

  Multi-Objective Optimization of Orchestra Scheduler for Traffic-Aware Networks(opens in a new window)

  Niharika Panda, S. Muthuraman, Atis Elsts

  Smart Cities, Vol. 2024 (7), p. 2542-2571, MDPI

  Abstract

  The Internet of Things (IoT) presents immense opportunities for driving Industry 4.0 forward. However, in scenarios involving networked control automation, ensuring high reliability and predictable latency is vital for timely responses. To meet these demands, the contemporary wireless protocol time-slotted channel hopping (TSCH), also referred to as IEEE 802.15.4-2015, relies on precise transmission schedules to prevent collisions and achieve consistent end-to-end traffic flow. In the realm of diverse IoT applications, this study introduces a new traffic-aware autonomous multi-objective scheduling function called OPTIMAOrchestra. This function integrates slotframe and channel management, adapts to varying network sizes, supports mobility, and reduces collision risks. The effectiveness of two versions of OPTIMAOrchestra is extensively evaluated through multi-run experiments, each spanning up to 3600 s. It involves networks ranging from small-scale setups to large-scale deployments with 111 nodes. Homogeneous and heterogeneous network topologies are considered in static and mobile environments, where the nodes within a network send packets to the server with the same and different application packet intervals. The results demonstrate that OPTIMAOrchestra_ch4 achieves a current consumption of 0.72 mA while maintaining 100% reliability and 0.86 mA with a 100% packet delivery ratio in static networks. Both proposed Orchestra variants in mobile networks achieve 100% reliability, with current consumption recorded at 6.36 mA. Minimum latencies of 0.073 and 0.02 s are observed in static and mobile environments, respectively. On average, a collision rate of 5% is recorded for TSCH and RPL communication, with a minimum of 0% collision rate observed in the TSCH broadcast in mobile networks. Overall, the proposed OPTIMAOrchestra scheduler outperforms existing schedulers regarding network efficiency, time, and usability, significantly improving reliability while maintaining a balanced latency–energy trade-off.

  Indexed in Scopus / WoS · Scopus percentile: 98 · SNIP: 2.24

  DOI(opens in a new window)
• 2024

  Towards Open-Set NLP-Based Multi-Level Planning for Robotic Tasks(opens in a new window)

  Peteris Racinskis , Oskars Vismanis , Toms Eduards Zinars , Janis Arents and Modris Greitans

  Applied Sciences, Vol. 14 (22), p. 10717, MDPI

  Abstract

  This paper outlines a conceptual design for a multi-level natural language-based planning system and describes a demonstrator. The main goal of the demonstrator is to serve as a proof-of-concept by accomplishing end-to-end execution in a real-world environment, and showing a novel way of interfacing an LLM-based planner with open-set semantic maps. The target use-case is executing sequences of tabletop pick-and-place operations using an industrial robot arm and RGB-D camera. The demonstrator processes unstructured user prompts, produces high-level action plans, queries a map for object positions and grasp poses using open-set semantics, then uses the resulting outputs to parametrize and execute a sequence of action primitives. In this paper, the overall system structure, high-level planning using language models, low-level planning through action and motion primitives, as well as the implementation of two different environment modeling schemes—2.5 or fully 3-dimensional—are described in detail. The impacts of quantizing image embeddings on object recall are assessed and high-level planner performance is evaluated using a small reference scene data set. We observe that, for the simple constrained test command data set, the high-level planner is able to achieve a total success rate of 96.40%, while the semantic maps exhibit maximum recall rates of 94.69% and 92.29% for the 2.5d and 3d versions, respectively.

  Indexed in Scopus / WoS · Scopus percentile: 79 · SNIP: 0.924

  DOI(opens in a new window)
• 2024

  Experimental system for investigating processes of shock freezing of meat(opens in a new window)

  Mironovs, V., Tatarinov, A., Abayev, A. and Zemchenkovs, V.

  Journal Agronomy Research, Vol. 22 (1), p. 495-502

  Abstract

  Shock freezing affords reduction of freezing time, production of much smaller ice crystals that preserves the tissue structure and nutritional value of the product. The advantage of using ultrasonic bulk waves for monitoring the freezing process is the ability to trace the dynamics of changes in the properties of the meat tissue directly using ultrasound velocity, attenuation and the waveform shape. The purpose of the study was to create an experimental freezing system with follow up ultrasound propagation parameters in meat specimens during shock freezing. The samples were frozen by the electric pipe-freezing unit Frigo 2F-Zero of REMS with the temperature control by a calibrated thermocouple. Ultrasonic signals were recorded continuously by a custom-made ultrasonic setup in the through transmission mode using a pair of 2.5 MHz transducers mounted on a calliper-based probe. The following trends were observed during the freezing stages. Ultrasound velocity decreased in lean meat and increased in fatty meat with cooling at temperatures above zero. Rapid drop of ultrasonic signals at temperatures below zero associated with the beginning of the crystallization process and the presence of both liquid and crystal components. Ultrasonic signals increased as the samples were completely frozen and ultrasound velocity increased to values close to those in icy bodies. Differences in ultrasonic parameters on a time scale during freezing were revealed for lean and fatty meat samples demonstrating a possibility to investigate specific freezing regimes for different types of meat.

  Indexed in Scopus / WoS · SNIP: 0.485
• 2024

  Bone porosity and thickness evaluation by ultrasonic signals using pattern recognition.

  Mamontovs M., Sisojevs A. and Tatarinov A.

  n Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2024, Game and Entertainment Technologies 2024 and Computer Graphics, Visualization, Computer Vision and Image Processing 2024 – Part of the 18th Multi Conference , p. 200-204, IADIS Press

  Abstract

  The fragility of long bones in osteoporosis is linked to a decrease in cortical layer thickness (CTh) and the development of internal porosity (P) within the cortex. This study is dedicated to investigate whether it is possible and how accurately P and CTh can be determined using a pattern recognition methods, utilizing discrete Fourier transform (DFT) analysis of ultrasonic signals transmitted through a soft tissue layer. As input data, ultrasound scans of phantom of cortical bone with different grades of CTh and P were used. Each of the phantom scans was chosen in turn as a test object, while other specimens composed the training set. For analysis, three different existing approaches were applied firstly and the later one was developed by improving the existing ones. The analysis was carried out in three categories: P and CTh ratio, P only and CTh only. Based on the results of each analysis, a method was obtained that predicts P and CTh better than other applied ones. A comparison of the methods for P and CTh determining and choosing the most effective ones are shown.

  Indexed in Scopus / WoS
• 2024

  Wavelet transform based decomposition of ultrasound signals for cortical bone model evaluation

  Laksis Dans, Tatarinovs Aleksejs, Freivalds Kārlis

  EUSIPCO 2024 32nd EUROPEAN SIGNAL PROCESSING CONFERENCE, p. 1496-1500

  Abstract

  With the global population aging, there is a growing demand for precise, cost-effective, and accessible methods to assess cortical bones for diagnosing degenerative bone conditions like osteoporosis. This article delves into innovative techniques for decomposing ultrasound signals to enhance current state-ofthe-art methodologies. Our approach focuses on deriving quantitative parameters for evaluating bone model characteristics. Utilizing ultrasound scans of bone model surfaces, acquired signals undergo continuous wavelet transform. Subsequently, we extract two key parameters pertinent to bone models: cortical speed of sound and cumulative magnitude sum. Through this methodology, we aim to contribute to advancements in the assessment of cortical bone health.

  Indexed in Scopus / WoS
• 2024

  Cell Manipulation with Piezoelectric Micro Pumps and Control Valves

  Addisu Kidanemariam, Brijesh Patel, Peter Lai, Yun-Ju Lai, Vytautas Bučinskas, Modris Greitans, Po Ting Lin*

  2024 International Automatic Control Conference (CACS 2024)

  Abstract

  This study explores the use of piezoelectric micro pumps combined with control valves for microbial cell manipulation. By integrating the micropump with two three-port valves, a reversible and controlled flow was achieved through the timely actuation of relay switches. Experimental results demonstrated that at the pump's lowest setting (50 mW, 2.5 mbar), a volume of 0.029 ml was accurately aspirated and dispensed. This method effectively handles delicate biological samples, showcasing its potential for precise aspiration and dispensing in biomedical applications.
• 2024

  A Comprehensive Review of Sensor-Based Smart Building Monitoring and Data Gathering Techniques(opens in a new window)

  Ingrida Lavrinovica, Janis Judvaitis, Dans Laksis, Marija Skromule, Kaspars Ozols

  Applied Sciences, Vol. 12 (21), MDPI

  Abstract

  In an era where buildings are increasingly becoming multifaceted entities, the paradigm of smart buildings has witnessed significant evolution. This advancement integrates sophisticated communication technologies, the Internet of Things (IoT), artificial intelligence (AI), and data analytics. Intending to design an effective smart building monitoring system, this research paper explores and compares various solutions for measuring building parameters by identifying a broad spectrum of review articles considering building occupant behavior, sensor deployment, and implementation complexity. The objective of our paper is to compile diverse information on various sensors used for monitoring building conditions and provide a comprehensive overview of data structuring and processing, all within a single article. Additionally, this paper addresses the challenges of combining data from decentralized systems and the need for managerial tools to optimize user experiences. The findings contribute to the advancement of smart building management, offering valuable insights for improving building performance and user experience as well as evaluating future research directions in this field. This review is designed to serve as an introduction for anyone venturing into the field of building monitoring.

  Indexed in Scopus / WoS · Scopus percentile: 79