Research
Publications
729 publications
- 2025
Cyber-physical systems: Securing latvia's future(opens in a new window)
Nesenbergs Krisjanis, Blumbergs Eduards, Paikens Pēteris
Cybersecurity in Latvia: Forging Resilience amidst Emerging Threats, p. 233 - 263, Routledge
Abstract
A significant area of future threats is caused by the growing prevalence of consumer wireless devices, such as smartphones, wearables, and Internet of Things devices, that have become increasingly intertwined in our daily lives, forming a reality of cyber-physical systems, but there is a lack of security awareness and motivation of manufacturers to secure these devices. Specifically, most of these devices use wireless communication and that uses a broad range of protocols – 4G and 5G cellular data networks, WiFi, Bluetooth, and Bluetooth Low Energy, and mesh protocols such as Zigbee. As the prevalence of such devices increases and the barrier of entry for attackers decrease, for example, due to low-cost software-defined radios, these vulnerabilities and related preventive measures must be better understood. In this chapter, we analyze the current and near-future threats to cyber-physical environments and provide a review of vulnerabilities in both consumer and commercial devices in order to evaluate the risks posed by them to the general society. With this classification, we also propose potential mitigation actions that could be developed by the security community or the government to mitigate these risks and improve resilience.
Indexed in Scopus / WoS
- 2025
Ground Segmentation Method Based on Polar Grid for 3D LiDAR Point Cloud(opens in a new window)
Katrīna Tupule, Maksis Celitāns, Kaspars Ozols
2025 22nd International Conference on Networking, Sensing, and Control (ICNSC), p. 377-383, IEEE
Abstract
In autonomous driving platforms, one of the key tasks is the perception of the environment. Light Detection and Ranging (LiDAR) sensors are widely used to obtain a point cloud representation of the surrounding environment. Raw point clouds contain measurement points from different objects in the environment, and distinguishing and semantically segmenting them can be challenging, but beneficial for better understanding the environment. One of the challenges of preprocessing raw point clouds is their segmentation into groups based on the type of object they originated from. In this paper, we propose a real-time, CPU-based ground segmentation method that structures the point cloud into a polar grid and estimates the ground points based on the local features of the grid cells. Our ground segmentation method is evaluated on the SemanticKITTI dataset and achieves high accuracy with real-time performance. Index Terms—ground segmentation, autonomous driving, LiDAR, point clouds, perception, environment model.
Indexed in Scopus / WoS
- 2025
The EDI Multi-Modal Simultaneous Localization and Mapping Dataset (EDI-SLAM)(opens in a new window)
Peteris Racinskis , Gustavs Krasnikovs, Janis Arents and Modris Greitans
Data, Vol. 10 (1), p. 5, MDPI
Abstract
This paper accompanies the initial public release of the EDI multi-modal SLAM dataset, a collection of long tracks recorded with a portable sensor package. These include two global shutter RGB camera feeds, LiDAR scans, as well as inertial and GNSS data from an RTK-enabled IMU-GNSS positioning module—both as satellite fixes and internally fused interpolated pose estimates. The tracks are formatted as ROS1 and ROS2 bags, with separately available calibration and ground truth data. In addition to the filtered positioning module outputs, a second form of sparse ground truth pose annotation is provided using independently surveyed visual fiducial markers as a reference. This enables the meaningful evaluation of systems that directly utilize data from the positioning module into their localization estimates, and serves as an alternative when the GNSS reference is disrupted by intermittent signals or multipath scattering. In this paper, we describe the methods used to collect the dataset, its contents, and its intended use.
Indexed in Scopus / WoS · Scopus percentile: 69 · SNIP: 0.857
- 2025
EXPERIMENTAL SYSTEM FOR ASSESSMENT OF FREEZING AND DEFROSTING PROCESSES OF MEAT(opens in a new window)
Aleksejs Tatarinovs, Viktors Mironovs, A. Abayev and Marija Osipova
Engineering for Rural Development, Vol. 24, Latvia University of Life Sciences and Technologies
Abstract
The development of an experimental system for monitoring the freezing and defrosting processes of meat will help optimize the freezing-defrosting regimes, particularly, in shock freezing. Non-destructive assessment of dynamic changes in the volumetric properties of meat tissue during freezing and defrosting is based on ultrasonic monitoring, using the velocity and attenuation of ultrasound, as well as changes in the spectrum and shape of the ultrasonic wave. Changes in ultrasonic parameters are specific to different water and fat contents in meat and allow us to determine it using temperature dependencies. The aim of the study was to track such dependencies in the temperature range from plus 25 to minus 30 degrees Celsius. Measurements were carried out on samples of lean and fatty pork with a fat content from 4% to 55%. Ultrasound propagation parameters were measured in the frequency range of 0.8 and 2 MHz. The samples were frozen using a REMS Frigo 2F-Zero electric tube freezer with temperature control using a calibrated thermocouple. The following trends were observed during the freezing stages. The ultrasound velocity decreased in lean meat and increased in fatty meat when cooling at temperatures above zero. The rapid drop in ultrasound signals at temperatures below zero is associated with the onset of the crystallization process and the presence of both liquid and crystalline components. The study showed that the dependences of ultrasound velocity and the intensity of ultrasound signals as an indicator of sound conductivity and their dependence on temperature can serve as indicators of the degree of freezing and thawing in the volume of meat at different fat and water contents. © 2025 Elsevier B.V., All rights reserved.
- 2025
Evaluation of Factors-of-Interest in Muscle Phantoms Based on Ultrasonic Data(opens in a new window)
Vladislavs Agarkovs, Aleksandrs Sisojevs, Aleksey M. Tatarinov and Tamāra Laimina
IFMBE Proceedings, Vol. 131, p. 25 - 32, Springer Science and Business Media Deutschland GmbH
Abstract
Subcutaneous adipose tissue (SAT) and intermuscular adipose tissue (IMAT) are two forms of body fat. The differential assessment of SAT and IMAT contents in sarcopenia and obesity by ultrasonic measurements is difficult due to their complex influence. In the present study, the possibility of using pattern recognition methods applied to ultrasonic measurement data to discriminate SAT and IMAT values was investigated on muscle tissue mimicking phantoms. The muscle mimicking phantoms were made of gelatin (muscle) with oil (fat) layers (SAT) and inclusions (IMAT) with gradually varying SAT and IMAT contents from zero to 50% with a step 12.5%. The set included a net of 25 phantoms with five grades of SAT and IMAT, each varied independently. Each phantom (object under study) passed multiple repeatable ultrasound tests. For each object, a set of parameters was extracted from the set of ultrasonic signals, including speed of sound, ultrasound attenuation at two frequencies and signal amplitude integrals. Decision rules were constructed for all objects based on the set of the extracted parameters. The efficiency of the constructed rules was checked using the signals of the examination object. The results of the experiments demonstrated the potential effectiveness of the proposed approach for determining SAT and IMAT values separately. © 2025 Elsevier B.V., All rights reserved.
- 2025
Model Selection and Prompting Strategies in Resource Constrained Environments for LLM-based Robotic System(opens in a new window)
Toms Eduards Zinars, Oskars Vismanis, Peteris Racinskis, Janis Arents, Modris Greitans
Charting the Intelligence Frontiers Edge AI Systems Nexu, p. 147-165, River Publishers Series in Communications and Networking
Abstract
Large Language Models (LLMs) are increasingly becoming adopted for various applications in information processing and content generation. Coupled with the diverse availability of model weights, quantization, and fine-tuning, it is desirable to find the best-performing LLM within a certain memory budget. Prompting strategy plays a similarly major role in the quality of generation, with various methods existing that attempt to induce desired behaviour, requiring a major time investment to develop. As new models with better performance to memory ratio become available, it may be tempting to implement them into an existing system for potential performance improvements. In this work we explore the process of changing weights and note that weights from larger models or of different quantization precision are unable to replace the original model without modifications to the prompt contents, which in turn implies complications in developing modular, weight agnostic Systems.
Indexed in Scopus / WoS
- 2025
Properties Assessment of Perforated Metal Plates for Medical Use(opens in a new window)
Marija Osipova, Viktors Mironovs, Antons Pacejs, Aleksejs Tatarinovs, Janis Lungevics, Vjaceslavs Zemcenkovs
Conference Proceedings, Vol. 4, p. 265 - 269, RTU PRESS
Abstract
Thin-walled and sheet materials with regular through holes (perforation) have wide practical application in various fields, including in medicine for the manufacture of implants, trays for placing and storing cutting instruments, sterilization of consumables. Perforated metal materials (PMM), primarily made of titanium and stainless steel, are of the most attention to specialists in the field of medical engineering, since they are characterized by lower weight, high strength and biomechanical compatibility. The mechanical characteristics of PMM are determined by the initial properties of the material, the dimensions of the sheet or tape, the shape and total area of the perforation. If selected correctly, dimensions and area of the perforations can provide optimal flexibility and plasticity with a significant reduction in the weight of the implant. This paper presents properties of perforated plates made of stainless steel, obtained by non-destructive methods. In particular, the dependences of the Lamb wave velocities at different frequencies on the specific total area of the plate's perforation are shown. The data of elastic properties dependences on the perforation area. The data of microscopic studies of changes in the quality of holes obtained by laser cutting are also presented. © 2025 Elsevier B.V., All rights reserved.
- 2025
Correction to: 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, Modris Greitans
Applied Sciences (Switzerland), Vol. 15 (5), MDPI
Abstract
In the original publication [1], there was a mistake in Table 1 as published. The column data in the table are reversed. The corrected Table 1 appears below. The numbers in the Abstract referring to Table 1 were mismatched. A correction has been made to the Abstract. From “while the semantic maps exhibit maximum recall rates of 94.69% and 92.29% for the 2.5d and 3d versions, respectively.” To “while the semantic maps exhibit maximum recall rates of 92.29% and 94.69% for the 2.5d and 3d versions, respectively.” The statements in the Discussion section citing Table 1 were mismatched. A correction has been made to the Discussion Section, Paragraph 5: From “For the static depth map, using ternary embedding values appears to paradoxically result in slightly improved recall—though this peculiarity is likely to disappear with larger and more varied data sets. With the vectree map, the same output set was produced by 32-bit and 8-bit embeddings, with two otherwise recalled observations being missed (one each of “white bottle” and “energy drink bottle”) and one otherwise missed observation being recalled (“pink foam”).” To “For the vectree map, using ternary-embedding values appears to paradoxically result in slightly improved recall—though this peculiarity is likely to disappear with larger and more varied datasets. With the static depth map, the same output set was produced by 32-bit and 8-bit embeddings, with two otherwise recalled observations being missed (one each of “white bottle” and “energy drink bottle”) and one otherwise missed observation being recalled (“pink foam”) with ternary embeddings.” The authors state that the scientific conclusions are unaffected. This correction was approved by the Academic Editor. The original publication has also been updated. © 2025 Elsevier B.V., All rights reserved.
- 2025
Controlling shape of flame with differentiable physics(opens in a new window)
Laura Leja, Kārlis Freivalds
Engineering for Rural Development, Vol. 24, p. 666 - 672, Latvia University of Life Sciences and Technologies
Abstract
The study focuses on creating symbol-shaped flame designs by optimizing flame dynamics, using machine learning techniques integrated with advanced combustion modelling. This research addresses the limitations of traditional pyrotechnic systems, which lack precise control over flame shapes, by introducing a method that uses differentiable physics simulations for shaping flames. The method uses the optimization framework PhiFlow and includes radiative heat loss and chemical kinetics for improved accuracy. Machine learning is used not only to train and adapt the model but also to determine the physical parameters that correspond to the actual observed behaviour of the flames. However, it is also important to mathematically and analytically evaluate the results obtained to ensure their accuracy and relevance. Results demonstrate the successful formation of custom flame shapes in a 2D simulated environment, with promising alignment to real-world flame stage projector behaviour. This approach enables control over flame shapes and dynamics, expanding creative possibilities in stage design and interactive art while proving valuable for applications requiring detailed control of dynamic systems, such as pyrotechnics, performance art, and educational demonstrations.
Indexed in Scopus / WoS · SNIP: 0.303
- 2025
Automated Pollen Recognition in Optical and Holographic Microscopy Images(opens in a new window)
Swarn Singh Warshaneyan, Maksims Ivanovs, Blaž Cugmas, Inese Bērziņa, Laura Goldberga, Mindaugas Tamosiunas, Roberts Kadiķis
2025 3rd Cognitive Models and Artificial Intelligence Conference (AICCONF), Vol. 1 (1), IEEE
Abstract
This study explores the application of deep learning to improve and automate pollen grain detection and classification in both optical and holographic microscopy images, with a particular focus on veterinary cytology use cases. We used YOLOv8s for object detection and MobileNetV3L for the classification task, evaluating their performance across imaging modalities. The models achieved 91.3\% mAP50 for detection and 97\% overall accuracy for classification on optical images, whereas the initial performance on greyscale holographic images was substantially lower. We addressed the performance gap issue through dataset expansion using automated labeling and bounding box area enlargement. These techniques, applied to holographic images, improved detection performance from 2.49\% to 13.3\% mAP50 and classification performance from 42\% to 54\%. Our work demonstrates that, at least for image classification tasks, it is possible to pair deep learning techniques with cost-effective lensless digital holographic microscopy devices.
Indexed in Scopus / WoS
- 2025
Differentiable Physics Training Method for Robot Motion Planning(opens in a new window)
Laura Leja , Guntis Vilnis Strazds, Christos Chronis, Iraklis Varlamis, Kārlis Freivalads
1st IFAC Joint Conference on Computers, Cognition, and Communication, IFAC
Details
Indexed in Scopus / WoS
- 2025
Applied AI for Adaptive Robotic Conveyor-Feeding (I)(opens in a new window)
Guntis V. Strazds, Katrīna Viltrake, Gergely Hollosi, Laura Leja, Arnis Priedītis, Diāna Dupļevska, Makss Meiers, Christos Chronis, Iraklis Varlamis, George Dimitrakopoulos, Kārlis Freivalds
1st IFAC Joint Conference on Computers, Cognition, and Communication, IFAC
Abstract
This paper presents a modular AI-driven robotic system for dynamic production line tasks, integrating real-time vision, adaptive motion planning, and making use of LLM-based code generation to facilitate reconfiguration for new products or tasks. The architecture of the overall system is described, as are design considerations and initial evaluation results for AI-based components for bottle pose estimation, tracking of moving sockets into which bottles need to be inserted, and training of a neural network for dynamic robot-motion control.
Indexed in Scopus / WoS · Scopus percentile: 36
- 2025
Raman spectral band imaging for the diagnostics and classification of canine and feline cutaneous tumors(opens in a new window)
Tamošiūnas Mindaugas, Maciulevičius Martynas, Maļiks Romans, Dupļevska Diāna, Viškere Daira, Matīse-van Houtana Ilze, Kadiķis Roberts, Cugmas Blaž, Raišutis Renaldas
Veterinary Quarterly (Vet Q), Vol. 45 (1), p. 1–17, Taylor & Francis
Abstract
This study introduces Raman imaging technique for diagnosing skin cancer in veterinary oncology patients (dogs and cats). Initially, Raman spectral bands (with specificity to certain molecular structures and functional groups) were identified in formalin-fixed samples of mast cell tumors and soft tissue sarcomas, obtained through routine veterinary biopsy submissions. Then, a custom-built Raman macro-imaging system featuring an intensified CCD camera (iXon Ultra 888, Andor, UK), tunable narrow-band Semrock (USA) optical filter compartment was used to map the spectral features at 1437 cm−1 and 1655 cm−1 in ex vivo tissue. This approach enabled wide-field (cm2), rapid (within seconds), and safe (< 400 mW/cm2) imaging conditions, supporting accurate diagnosis of tissue state. The findings indicate that machine learning classifiers–particularly support vector machine (SVM) and decision tree (DT)–effectively distinguished between soft tissue sarcoma, mastocytoma and benign tissues using Raman spectral band imaging data. Additionally, combining Raman macro-imaging with residual near-infrared (NIR) autofluorescence as a bimodal imaging technique enhanced diagnostic performance, reaching 85–95% in accuracy, sensitivity, specificity, and precision–even with a single spectral band (1437 cm−1 or 1655 cm−1). In conclusion, the proposed bi-modal imaging is a pioneering method for veterinary oncology science, offering to improve the diagnostic accuracy of malignant tumors. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Indexed in Scopus / WoS · Scopus percentile: 98
- 2025
Virtual Staining From Optical Coherence Tomography to Hematoxylin and Eosin Stained Skin Tumor Samples in Pets
Daira Viškere, Mindaugas Tamošiūnas, Romans Maļiks, Diāna Dupļevska, Ilze Matīse-van Houtana, Roberts Kadiķis, Blaž Cugmas
31st Annual International Scientific Conference "Research for Rural Development 2025
Abstract
Histopathological biopsies with hematoxylin and eosin–stained (H&E) samples are gold standard in veterinary oncology. Since biopsy sampling is an invasive process and requires sedation of the animal, as well as sample preparation and obtaining results is time-consuming, other effective solutions are being sought. Optical coherence tomography (OCT) is known as non-invasive imaging technology that produces detail, cross-sectional images of tissues at a microscopic level and provide real-time images. In our research we trained neural network to produce virtually stained histopathological images from OCT images taken from lipomas, soft tissue sarcomas and mast cell tumors from dogs and cats. As there are no previous research done on recognizing different normal and tumor structures in veterinary skin tumor samples, we found that tumor borders, hair follicles can be recognized using noninvasive OCT. As reference for virtually stained image production H&E sections were used. Multiple 1x1 mm sections of input images were taken from different (normal and tumor tissue) regions. We trained our neural network using paired dataset and got first virtually stained H&E images. By modifying these algorithms for transfer learning we could improve future images making more important histological structures to be recognized and improving image quality allowing veterinarians make tumor diagnostics much faster.
- 2025
Deep Learning-Emerged Grid Cells-Based Bio-Inspired Navigation in Robotics(opens in a new window)
Simkuns Arturs, Saltanovs Rodions, Ivanovs Maksims, Kadiķis Roberts
Sensors, Vol. 25 (5), MDPI
Abstract
Grid cells in the brain’s entorhinal cortex are essential for spatial navigation and have inspired advancements in robotic navigation systems. This paper first provides an overview of recent research on grid cell-based navigation in robotics, focusing on deep learning models and algorithms capable of handling uncertainty and dynamic environments. We then present experimental results where a grid cell network was trained using trajectories from a mobile unmanned ground vehicle (UGV) robot. After training, the network’s units exhibited spatially periodic and hexagonal activation patterns characteristic of biological grid cells, as well as responses resembling border cells and head-direction cells. These findings demonstrate that grid cell networks can effectively learn spatial representations from robot trajectories, providing a foundation for developing advanced navigation algorithms for mobile robots. We conclude by discussing current challenges and future research directions in this field. © 2025 Elsevier B.V., All rights reserved.
Indexed in Scopus / WoS · Scopus percentile: 88
- 2025
Prioritized and Multi-Agent Reinforcement Learning-Based TSCH Schedulers(opens in a new window)
Panda Niharika, Supriya M., Elsts Atis
IEEE Open Journal of the Computer Society, Vol. 6, p. 1763 - 1774, Institute of Electrical and Electronics Engineers Inc.
Abstract
The Internet of Things (IoT) explosive growth necessitates high-performance networks that can satisfy demanding specifications, including low latency, high reliability, and energy economy. A crucial part of IEEE 802.15.4, the Time-Slotted Channel Hopping (TSCH) protocol is extensively used in IoT networks because of its ability to guarantee dependable communication and its resistance to interference. Nevertheless, traditional TSCH scheduling methods frequently find it difficult to meet the various requirements of applications in dynamic environments that are power-constrained and latency-sensitive. Prioritized Multi-Agent Reinforcement Learning (PMRL) and OPTIMA Prioritized Multi-Agent Reinforcement Learning (OPMRL) are two innovative scheduling models that we suggest as solutions to this problem. Multi-Agent Reinforcement Learning (MRL) and Double Deep Q-Networks (DDQN) are combined with traffic priority awareness in these models to allow for adaptive scheduling decisions. A smart home scenario is used to evaluate the suggested method first, laying the groundwork for later implementation in more intricate IoT environments. Comparing our models to conventional TSCH scheduling techniques, extensive simulations show that they greatly improve Packet Delivery Ratio (PDR), lower latency and power consumption, and limit collisions. The foundation is laid by this study for autonomous, scalable scheduling techniques that can be applied to industrial and smart home settings. © 2025 Elsevier B.V., All rights reserved.
- 2025
Evaluation of osteoporosis features in cortical bone models using pattern recognition methods applied to ultrasound data(opens in a new window)
Alexey Tatarinov, Aleksandrs Sisojevs
Ultrasonics, Vol. 158, Elsevier
Abstract
Cortical bone plays a crucial role in bone strength in the context of osteoporosis. Thinning of the cortex and intracortical porosity developing from the endosteum are the main independent indicators of osteoporosis-related fractures risk, which can be separately quantified by advanced imaging techniques. Numerous studies have shown the sensitivity of ultrasonic guided waves to changes in the thickness and porosity of cortical bone both in models and in human subjects. The present study demonstrates feasibility of the pattern recognition approach to separate determination of factors of diagnostic interest – cortical thickness (CTh) and intracortical porosity as the relative thickness of the porous layer (rPTh), where a set of guided waves velocities at different frequencies are used as evaluation criteria. The experiments were carried out on acrylic plastic plates as compact bone phantoms of different thicknesses with simulated pores in the form of CNC-drilled holes from below. The distance-time slopes of fast and slow wave packets at 250, 100 and 50 kHz were obtained as distance-time slopes in the corresponding spatiotemporal waveform profiles built by stepwise acquisition of ultrasonic signals. The evaluation criteria (distance-time slopes) in the training dataset formed the decision rules – 3-dimensional surfaces of the criterion distribution in the field CTh-rPTh. For the test object, the intersection of the segments of the probabilistic solution according to three decision rules gave the evaluation answer. The method allowed us to determine the values of both factors CTh and rPTh with reasonable diagnostic accuracy at different thicknesses of the covering soft tissues. The proposed approach can be adapted for the assessment of osteoporosis after obtaining an appropriate database in human studies.
Indexed in Scopus / WoS · Scopus percentile: 89
- 2025
Experimental Evaluation of NB-IoT Power Consumption and Energy Source Feasibility for Long-Term IoT Deployments
Valters Skrastiņš, Vladislavs Medvedevs, Dmitrijs Orlovs, Juris Ormanis, Janis Judvaitis
IoT (ISSN 2624-831X), MDPI
Abstract
Narrowband Internet of Things (NB-IoT) is widely used for connecting low-power devices that must operate for years without maintenance. To design reliable systems, it is essential to understand how much energy these devices consume under different conditions and which power sources can support long lifetimes. This study presents a detailed experimental evaluation of NB-IoT power consumption using a commercial System-on-Module (LMT-SoM). We measured various transmissions across different payload sizes, signal strengths, and temperatures. The results show that sending larger packets is far more efficient: a 1280-byte message requires about 7 times less energy per bit than an 80-byte message. However, standby currents varied widely between devices, from 6.7 µA to 23 µA, which has a major impact on battery life. Alongside these experiments, we compared different power sources for a 5-year deployment. Alkaline and lithium-thionyl chloride batteries were the most cost-effective solutions for indoor use, while solar panels combined with supercapacitors provided a sustainable option for outdoor applications. These findings offer practical guidance for engineers and researchers to design NB-IoT devices that balance energy efficiency, cost, and sustainability.
Indexed in Scopus / WoS
- 2025
Enhancing Hive Monitoring and Sustainability through Video Recognition and Environmental Analysis(opens in a new window)
Anatolijs Zabasta, Antons Patlins, Nadezda Kunicina, Uldis Grunde
12th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering, AIEEE 2025, Institute of Electrical and Electronics Engineers Inc.
Abstract
This paper presents a video recognition-based solution for an innovative beekeeping system, which we have developed and have evaluated in a prototype. We have designed this solution to improve the monitoring and management of beekeeping operations, a critical aspect for ensuring efficiency and sustainability in modern apiculture. The proposed system enables continuous monitoring of bee colonies, providing real-time insights into environmental changes and bee behavior. In addition, the system's analytical tools can identify and analyze correlations between following factors affecting bee productivity, such as weather conditions, geographical location of the apiary, and other environmental influences.The introduction of this stand-alone beekeeping solution offers beekeepers the ability to remotely track key hive conditions. For instance, it can detect whether the temperature inside the hive is nearing critical levels, or whether the bees are facing food shortages. This timely information allows beekeepers to take swift action to prevent potential harm to the colonies, thereby improving overall colony health and productivity. Such a system must be particularly beneficial during winter, helping to preserve hibernating bee colonies, while also saving valuable time and resources typically spent on manual hive inspections.The autonomous beekeeping system aligns with the broader goals of promoting economically sustainable agriculture, supporting the conservation of agricultural and forestry resources. The introduction of advanced monitoring and control features ensures that beekeepers can maintain optimal hive conditions with minimal manual intervention. Moreover, as the project progresses, we are planning further enhancements, such as incorporating artificial intelligence (AI) techniques, including neural networks, to enhance image processing capabilities. This would significantly expand the system's functionality, providing even more comprehensive data analysis and decision-making tools for beekeepers. © 2025 Elsevier B.V., All rights reserved.
- 2025
Development of Autonomous Wireless Beehive Monitoring System Solution(opens in a new window)
Anatolijs Zabasta, Antons Patlins, Nadezda Kunicina, Uldis Grunde
12th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering, AIEEE 2025, Institute of Electrical and Electronics Engineers Inc.
Abstract
The autonomous beekeeping solution provides the possibility to monitor the bee hives from a distance. The distance monitoring opens a floor for new business opportunities, like production of mono-floral honey, as well as more intensive manufacture of honey products. The solution is based on new generation of IoT resources, and deployment of IoT concept in agricultural sector [3; 23; 24; 25]. It is worth noting that physical survey disturbs the bees and causes them stress, which can negatively affect the productivity of the bee colony, as well as taking beekeeper time. In addition, distance does not always allow the beekeeper to react quickly to crisis situations in the apiary. The technology developed in the project allows to use distance monitoring of the beehive, which significantly facilitates the daily life of the beekeeper, allows quick decision-making in critical situations and does not reduce bee productivity, as it does not affect the daily life of the beehive.The beekeeper can observe the apiary remotely and will be able to decide to visit the apiary only if necessary. A great helper is the hive video surveillance system, which will help to monitor the flight activity of bee colonies during the day, as well as to visually assess the condition of the apiary. The new system uses alternative energy sources (solar, wind energy) for the power supply of the system, which increases the possibilities of using the system in distance monitoring on fields. © 2025 Elsevier B.V., All rights reserved.