Kaspars Ozols
Dr. sc. ing.
Deputy director of development, Senior Researcher
Dr. Kaspars Ozols is a deputy director of development, a Member of the scientific council as well as a senior researcher at the Institute of Electronics and Computer Science (EDI) where he leads teams of engineers and researchers. Dr. Ozols is also a member of the Scientific Council of the INSIDE Industry Association. Dr. Ozols also leads several committees within the EDI, including those focused on intellectual property valuation, auctions, ethics, and gender equality, among others. He holds a Ph.D. in Electronics from Riga Technical University.
He has been involved in various international projects dedicated to pioneering innovative data acquisition, transmission, and signal processing methods and devices across a diverse spectrum of applications, encompassing fields such as transport, health, and manufacturing. Notably, he has actively contributed to over 15 European joint research projects (in Horizon Europe, Horizon 2020, KDT-JU, ECSEL-JU, ARTEMIS-JU, ERA-NET, EIT programs). Latvian representative for the COST CA16222 "Wider Impacts and Scenario Evaluation of Autonomous and Connected Transport" (WISE-ACT) initiative. For over seven years, he has also served as an expert in evaluating project proposals and as a vice-chair overseeing the work of experts for the European Commission and scientific councils across different countries.
Dr. Ozols possesses a wealth of expertise in ICT system simulation, modeling, design, development, implementation, testing, validation and commercialization. He is the author of 50+ peer-reviewed scientific articles and 1 patent. His research interests are extensive and encompass a broad array of cutting-edge topics, including Self-Driving/Autonomous cars, Cyber-Physical Systems, Signal Processing, Wireless Communications, Wireless Sensor Networks, the Internet of Things, Embedded and Low Power solutions, Artificial Intelligence, Robotics, and the digitization of industries. Beyond his research endeavors, Dr. Ozols is actively involved in the preparation of international project proposals, where he skillfully fulfills roles as both a partner and coordinator.
His impressive track record boasts the successful acquisition of funding for more than 25 diverse international projects, primarily from the aforementioned programs. Moreover, Dr. Ozols possesses extensive experience in direct contract research with industry, further solidifying his expertise and contributions to the field. He further demonstrates exceptional institutional management skills, showcasing expertise in various crucial areas, including strategic planning, financial and resource management, change management, risk management, legal and regulatory compliance, innovation and intellectual property management, legal affairs, stakeholder engagement, communication proficiency, and policy and regulation knowledge. Moreover, his significant contributions extend to the development of strategic and political documents, with a clear aim of advancing both EDI and the entire nation's progress. He has also assumed the role of Chair for the Organizing Committee of the "International Workshop on Embedded Digital Intelligence" (IWoEDI), further underscoring his dedication to advancing research and collaboration. His passion for nurturing innovation and entrepreneurship is evident through his active mentorship and consultation of numerous start-ups, having mentored more than 10 of them. Dr. Ozols is also an expert in technology transfer and has strongly supported the commercialization of 5+ science-based technologies. His impact extends to the realm of education, where he has supervised more than 10 engineering, bachelor's, and master's theses, as well as 3 Ph.D. theses. Dr. Ozols has received 1st place in the ResearchSlam competition. He was also awarded the Latvian Academy of Sciences (LAS) Prize for one of the most significant achievements in Latvian science in 2018, as well as a Letter of Appreciation from the President of the Latvian Academy of Sciences for one of the most significant achievements in Latvian science in 2025.
Projects
3 results
- More than Moore for Disruptive Innovations in Power Electronics (Moore4Power) 01.05.2026 – 30.04.2029
- A mosaic of essential electronic components and systems (ECS) for our automated digital future in industry and mobility (MOSAIC) 01.07.2025 – 30.06.2028
- Ensuring European ECS Value Chain Sovereignty through Shaping the Future of ECS for Automotive Applications (ShapeFuture) 01.05.2024 – 30.04.2027
Publications
- 2026
Differentially Private Federated Learning for Remaining Useful Life Prediction(opens in a new window)
Arturs Nikulins, Kārlis Freivalds, Ivars Namatēvs, Kaspars Sudars, Audris Arzovs, Wilhelm Söderkvist Vermelin, Madhav Mishra, Kaspars Ozols.
Applied Sciences, Vol. 16 (6), p. 2784 (raksta numurs), MDPI
Abstract
Accurate remaining useful life (RUL) prediction is essential for the safe and cost-effective operation of safety-critical systems such as electronic components and engines. While data-driven machine learning approaches have demonstrated strong performance for RUL estimation, their effectiveness is limited by the lack of full run-to-failure data and by strict privacy and intellectual property constraints in industrial settings. Federated learning (FL) enables collaborative model training across multiple data owners without direct data sharing, but it does not, by itself, provide formal privacy guarantees and remains vulnerable to information leakage. This paper presents a privacy-preserving DP-enhanced FL setup for RUL prediction that combines federated learning with differential privacy (DP). We describe an end-to-end implementation based on the Opacus DP library, highlight practical challenges arising from the integration of DP into recurrent neural network architectures, and propose solutions to address them. Using two representative RUL datasets (CMAPSS and SiC MOSFET), we analyze the effect of DP noise on prediction performance and on the functional dependence between the predicted RUL and the already lived life feature. The results demonstrate that differential privacy can be integrated into federated RUL prediction with limited degradation in predictive performance, providing practical insights for deploying privacy-aware collaborative models in industrial environments.
Indexed in Scopus / WoS · Scopus percentile: 79 · SNIP: 0.956
- 2026
ConMonity: An IoT-Enabled LoRa/LTE-M Platform for Multimodal, Real-Time Monitoring of Concrete Curing in Construction Environments(opens in a new window)
Namatēvs, I., Gaigals, G., & Ozols, K.
Sensors, Vol. 26 (1), p. 14, MDPI
Abstract
Monitoring the curing process of concrete remains a challenging and critical aspect of modern construction, often hindered by labour-intensive, invasive, and inflexible methods. The primary aim of this study is to develop an integrated IoT-enabled platform for automated, real-time monitoring of concrete curing, using a combination of LoRa-based sensor networks and an LTE-M backhaul. The resulting ConMonity system employs embedded multi-sensor nodes—capable of measuring strain, temperature, and humidity‒connected via an energy-efficient, TDMA-based LoRa wireless protocol to an LTE-M gateway with cloud-based management and analytics. By employing a robust architecture with battery-powered embedded nodes and adaptive firmware, ConMonity enables multi-modal, multi-site assessments and demonstrates stable, autonomous operation over multi-modal, multi-site assessment and demonstrates stable, autonomous operation over multi-month field deployments. Measured data are transmitted in a compact binary MQTT format, optimising cellular bandwidth and allowing secure, remote access via a dedicated mobile application. Operation in laboratory construction environments indicates that ConMonity outperforms conventional and earlier wireless monitoring systems in scalability and automation, delivering actionable real-time data and proactive alerts. The platform establishes a foundation for intelligent, scalable, and cost-effective monitoring of concrete curing, with future work focused on extending sensor modalities and enhancing resilience under diverse site conditions.
Indexed in Scopus / WoS · Scopus percentile: 88
- 2025
Privacy Auditing of Lithium-Ion Battery Ageing Model by Recovering Time-Series Data Using Gradient Inversion Attack in Federated Learning(opens in a new window)
Kaspars Sudars, Ivars Namatēvs, Arturs Nikulins, Kaspars Ozols
Applied Sciences (Switzerland), Vol. 15 (10), MDPI
Abstract
The exchange of gradients is a widely used method in modelling systems for machine learning (e.g., distributed training, federated learning) in privacy-sensitive domains. Unfortunately, there are still privacy risks in federated learning, as servers can reconstruct clients‘ training data through gradient inversion attacks. To protect against such attacks, we need to know when and how privacy is being undermined, largely due to the black box nature of deep neural networks. Although gradient inversion has been used to classify images and text data, its use in time-series is still largely unexplored. In this paper, we empirically evaluate the practicality of recovering lithium-ion battery time-series data from the gradients of a transformer-based model, both without and with differential privacy, in a time-series federated learning framework. It is especially significant in the case of electric vehicles (EVs). As shown in this paper, additional protection by differential privacy leads to the saturation of gradient inversion attacks, i.e., the reconstructed signal maintains a certain error level, depending on the applied privacy budget level. With this empirical evaluation, we provide insights into effective gradient perturbation directions, unfairness with respect to privacy, and privacy-preferred model initialisation. © 2025 Elsevier B.V., All rights reserved.
- 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
Privacy Auditing of Lithium-Ion Battery Ageing Model by Recovering Time-Series Data Using Gradient Inversion Attack in Federated Learning(opens in a new window)
Sudars, K., Namatevs, I., Nikulins, A., & Ozols, K.
Applied Sciences, Vol. 15 (10), p. 5704, MDPI
Abstract
The exchange of gradients is a widely used method in modelling systems for machine learning (e.g., distributed training, federated learning) in privacy-sensitive domains. Unfortunately, there are still privacy risks in federated learning, as servers can reconstruct clients‘ training data through gradient inversion attacks. To protect against such attacks, we need to know when and how privacy is being undermined, largely due to the black box nature of deep neural networks. Although gradient inversion has been used to classify images and text data, its use in time-series is still largely unexplored. In this paper, we empirically evaluate the practicality of recovering lithium-ion battery time-series data from the gradients of a transformer-based model, both without and with differential privacy, in a time-series federated learning framework. It is especially significant in the case of electric vehicles (EVs). As shown in this paper, additional protection by differential privacy leads to the saturation of gradient inversion attacks, i.e., the reconstructed signal maintains a certain error level, depending on the applied privacy budget level. With this empirical evaluation, we provide insights into effective gradient perturbation directions, unfairness with respect to privacy, and privacy-preferred model initialisation.
Indexed in Scopus / WoS · Scopus percentile: 79
Patents
LR patents Nr. 15877
Gatis GAIGALS, Kaspars OZOLS METODE SAKARU IEKĀRTU SAVIENOJUMA UZLABOŠANAI UN PATĒRĒTĀS ENERĢIJAS SAMAZINĀŠANAI VIDĒS AR MAINĪGIEM FIZIKĀLIEM PARAMETRIEM
Description and link
View the patent on Espacenet(opens in a new window)LR patents Nr. 15877, Gatis GAIGALS, Kaspars OZOLS METODE SAKARU IEKĀRTU SAVIENOJUMA UZLABOŠANAI UN PATĒRĒTĀS ENERĢIJAS SAMAZINĀŠANAI VIDĒS AR MAINĪGIEM FIZIKĀLIEM PARAMETRIEM
