Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Andres Vejar has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deep Reinforcement Learning for Energy-Efficient 6G V2X Networks

    by Faysal Marzuk, Andres Vejar, Piotr Chołda

    The deployment of 6G vehicle-to-everything (V2X) networks is a challenging task given the 6G requirements of ultra-high data rates along with ultra-low latency levels. For intelligent transportation systems (ITSs), V2X communications involve a high density of user equipment (UE), vehicles, and next-generation Node-B (gNB). Therefore, optimal management of the current network infrastructure plays a key role in minimizing energy and latency. Optimal resource allocation using linear programming methods cannot be scaled to the required scenarios of 6G V2X communications and is not suitable for online allocation. To overcome these limitations, deep reinforcement learning (DRL) is a promising approach given its properties of direct integration with online allocation models. In this work, we investigate the problem of optimal resource allocation in 6G V2X networks, where ITSs are deployed to execute tasks offloaded by vehicles subject to data rate and latency requirements. We apply a policy optimization-based DRL to jointly reduce the number of active gNBs and the latency concerning the offloaded tasks going on in the vehicle. The model is analyzed for several ITS scenarios to investigate the performance observed and the advantages of the proposed policy optimization allocation for 6G V2X networks. Our evaluation results illustrate that the proposed DRL-based algorithm produces dynamic solutions that approximate the optimal ones at reasonable rates of energy consumption. Our numerical results indicate that DRL-based solutions are distinguished by equivalently balanced energy consumption under different scenarios.


  • Open Access

    Privacy-preserving Framework for Automated Detection of Arrhythmia in ECG Data

    by Kacper Gil, Andres Vejar

    The integration of machine learning in biomedical engineering applications is crucial to ensure user data security and privacy. This work explores anonymization and differential privacy (DP) frameworks to reduce the risk of biometric identification. The DP method is used to train models in biosignal data without compromising the diagnostic results. The proposed approach for privacy-preserving arrhythmia detection uses a machine learning diagnostic system that reduces discrepancies between prepossessed and raw data, maintaining a correct level of diagnostic precision while improving privacy. The application is evaluated using a control model to analyze the accuracy difference when using privacy-preserving input data.


  • Open Access

    k-anonymity in Resource Allocation for Vehicle-to-Everything (V2X) Systems

    by Andres Vejar, Faysal Marzuk, Piotr Chołda

    Sixth generation (6G) vehicle-to-everything (V2X) systems face numerous security threats, including Sybil and denial-of-service (DoS) cyber-attacks. To provide a secure exchange of data and protect users' identities in 6G V2X communication systems, anonymization techniques - such as k-anonymity - can be used. In this work, we study centralized vs. k-anonymity based resource allocation methods in a vehicular edge computing (VEC) network. Allocation decisions for vehicular networks are classically posed as a centralized optimization task. Therefore, an information flow is transmitted from the vehicles to the communication premises. In addition to a resource allocation decision, vehicle information is not required. We analyze the centralized allocation versus k-anonymous allocation models. To show a potential deterioration introduced by anonymity, we quantify the gap in the optimal goal in two cases: based on resource allocation and with aim at energy reduction. Our numerical results indicate that energy consumption rises by 1% in smaller scenarios and 23% in medium scenarios, whereas it decreases by 14% in larger scenarios.


  • Exploratory Study on Remote Photoplethysmography using Visible Light Cameras

    by Tomasz Szabała, Andres Vejar

    With visible light video cameras, it is possible to estimate the cardiac pulse, tracking the intensity changes in the image produced by the blood volume variations in the microvascular tissue. This estimation is provided by a measuring technique called remote photoplethysmography (RPPG). In this study we explore the data acquisition of the RPPG using standard video cameras used in personal computers

  • Analysis of 3D head rotations for eye tracking calibration in large computer monitors

    by Oleksii Hyka, Andres Vejar

    In order to operate in the center of the vision field, the computer user maintains a frontal pose with respect to the screen. In this ideal situation, the computer user can visually explore the screen, moving only the eyes. The user activity changes when the computer screen is large, and it is necessary to change the pose and gaze orientation in order to explore the entire screen. The availability of high-end and high-size computer monitors (621mm width, 341mm height, or bigger), improves the possibilities of computer visualization but requires constant head pose changes to be performed by the computer user. In this study, we evaluate the 3D head rotation activity for the process of calibration on eye tracking. We compare the activity data for a fixed zigzag calibration pattern with respect to a random calibration pattern. The results show that the rotation data provide important information about the user screen exploration, and the incorporation of head rotations can contribute to reducing the quantity of information required to estimate the parameters of calibration models.

  • Concurrent data acquisition of electrocardiogram and respiration rate using predictive filtering

    by Tomasz Rymarczyk, Andres Vejar, Timur Kassymov

    For e-health monitoring, concurrent data acquisition and processing of electrocardiogram and respiratory rate biosignals is needed to provide clean input signals for the detection algorithms. Given that cardiac and respiration rhythms are correlated, but they have different characteristic rates, we explored a sensor fusion approach to model the filtered future state of both signals. Therefore, a time-delayed structure with raw and filtered data fusion was used to improve the quality of the model. We apply Lasso and Ridge regression to the time-delayed data structure and study the approach using low and high sample rates for the data processing. At low sample rates, the validation for respiratory rate is high, while for electrocardiogram is comparatively low. With higher sample rates, the results are improved for both cases.

  • Open Access

    Electrical Tomography Reconstruction Using Reconfigurable Waveforms in a FPGA

    by Andres Vejar, Tomasz Rymarczyk

    The principal objective of this research is to conceive a mobile system based on electrical tomography for subsurface imaging and monitoring in order to enable simultaneous recording of electrical potentials of cardiac and pulmonary activity. For an exploration of excitation waveforms in electrical tomography, specialized hardware is required. As the main principle of tomography is the measurement of electrical perturbations on an unknown object, it is crucial to synchronize excitation and sensing processes in a very precise way for the purpose of acquiring meaningful data. To cope with this problem, an FPGA device is used, with an architecture that allows us to trigger excitation signals and to read sensed data simultaneously via independent processes that share the same clock. In this way, waveform reconfiguration on frequency and shape can be provided and studied. The system is connected to a standard microcontroller SoC with a simple API that allows for IoT capabilities for on-line operation and tracking, given that the design is targeted for in vivo medical monitoring. As a result of the research work, a measuring device was developed, the surface data analyzed and the image was reconstructed using the selected configuration.


  • Electrical activity with ECG analysis for Body Surface Potential Mapping

    by Tomasz Rymarczyk, Michał WOŚ, Michał BARTOSIK, Andres Vejar, Edward Kozłowski, Michał MAJ

    Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.


  • Waveform-Reconfigurable Emitter Design for Multi Frequency Electrical Tomography

    by Tomasz Rymarczyk, Andres Vejar

    Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.