2024 - Repozytorium publikacji - Politechnika Gdańska

Pokaż publikacje z roku

Publikacje z roku 2024

Pokaż wszystkie

Przekształtnik DC-DC 24V/12kV z transformatorem macierzowym do ładowarek kondensatorów wysokonapięciowych HVCC
- Marek Adamowicz
- Jędrzej Pietryka
- Zbigniew Krzemiński
2024 Pełny tekst Przegląd Elektrotechniczny
W artykule przedstawiono projekt i wykonanie kompaktowej, przenośnej wysokonapięciowej ładowarki kondensatorów 12kV, 1kJ/s, zasilanej z baterii akumulatorów 24V. Podstawowym wyzwaniem zaprojektowania przekształtnika o tak wysokiej przekładni transformatora jest minimalizacja indukcyjności rozproszenia transformatora, która wpływa na ograniczenie mocy przenoszonej przez transformator, a tym samym uniemożliwia regulację prądu i napięcia strony wtórnej przekształtnika. Przekształtnik DC-DC ładowarki wykorzystuje transformator macierzowy wysokiej częstotliwości o wspólnym uzwojeniu pierwotnym i 16 uzwojeniach wtórnych, z których 14 jest połączonych z mostkami prostowniczymi, a dwa stanowią uzwojenia pomocnicze. Szeregowo połączone wyjścia mostków prostowniczych tworzą wysokonapięciowe wyjście ładowarki.
Psychophysiological strategies for enhancing performance through imagery – skin conductance level analysis in guided vs. self-produced imagery
- Dagmara Budnik-Przybylska
- Paweł Syty
- Maria Kaźmierczak
- Jacek Przybylski
- Łukasz Doliński
- Marta Łabuda
- Patryk Jasik
- Adrian Kastrau
- Selenia di Fronso
- Maurizio Bertollo
2024 Pełny tekst Scientific Reports
Athletes need to achieve their optimal level of arousal for peak performance. Visualization or mental rehearsal (i.e., Imagery) often helps to obtain an appropriate level of activation, which can be detected by monitoring Skin Conductance Level (SCL). However, different types of imagery could elicit different amount of physiological arousal. Therefore, this study aims: (1) to investigate differences in SCL associated with two instructional modalities of imagery (guided vs. self-produced) and six different scripts; (2) to check if SCL could differentiate respondents according to their sport expertise. Thirty participants, aged between 14 and 42 years (M = 22.93; SD = 5.24), with different sport levels took part in the study. Participants listened to each previously recorded script and then were asked to imagine the scene for a minute. During the task, SCL was monitored. We analysed the mean value, variance, slope and number of fluctuations per minute of the electrodermal signal. Unsupervised machine learning models were used for measuring the resemblance of the signal. The Wilcoxon signed-rank test was used for distinguishing guided and self-produced imagery, and The Mann–Whitney U test was used for distinguishing results of different level athletes. We discovered that among others, self-produced imagery generates lower SCL, higher variance, and a higher number of fluctuations compared to guided imagery. Moreover, we found similarities of the SCL signal among the groups of athletes (i.e. expertise level). From a practical point of view, our findings suggest that different imagery instructional modalities can be implemented for specific purposes of mental preparation.
Public space as a place of rehabilitation for the elderly – a systematic literature review
- Agnieszka Gębczyńska-Janowicz
- Rafał Janowicz
2024 Pełny tekst MEDYCYNA PRACY
The phenomenon of the population’s gradual global ageing means that an increasing proportion of research is concerned with the space in which seniors function on a daily basis. They are primarily aimed at identifying elements of the built environment that need updating in the new social context. The purpose of the analyses presented in this article is to review the current scientific literature on various aspects of physical activity of people outdoors in an urbanized environment. The scope review was based on the resources of 3 scientific databases (Web of Science, Scopus and PubMed). The analyses concerned articles published in the last decade (2013–2023). The collected material was subjected to the PRISMA procedure (Preferred Reporting Items for Systematic Reviews and Meta-Analytics), and 29 articles were extracted for analysis. The conducted research indicated thematic scopes that are undertaken in contemporary research on physical activities of a rehabilitation nature undertaken in public space by older people (>65 years of age). The research topics described in the articles analysed dealt with elements defining the characteristics of public space that mobilise older people to be active, identified barriers preventing its use and factors popularising it. The studies analysed also identified the characteristics of public spaces according to the type of activity used by seniors for rehabilitation. The result of the review is the separation of the thematic scope of research on the activation of the elderly in the open air towards rehabilitation. The information provided may be useful for architects, urban planners and people managing urban spaces to determine design solutions that meet the needs of older people.
Public valuation of social impacts. The comparison between mega and non-mega sporting events
- Krystian Zawadzki
2024 Pełny tekst Journal of Policy Research in Tourism Leisure and Events
The main aim of this study is to assign value to intangible effects,including social impacts, which appear when organising sportingevents of various scales in the city of Gdansk located in northernPoland. A survey was conducted to determine the city residents’willingness-to-pay (WTP) using the contingent valuation method(CVM). The average WTP values, which ranged between PLN 6.04and PLN 46.34, show that the scale of the sporting event may beimportant for the local community’s perception of such socialimpacts as well-being and urban regeneration. However,considering the costs of organising sporting events–includingthe preparation of sporting facilities–it turns out that it is easierto justify spending public funds for holding smaller events,among others, due to the possibility of organising such events inthe same place more frequently.
Pulse Transit Time - Fiducial Points Accuracy Determination as Examined by Means of Synthetic Signals
- Artur Poliński
- Adam Bujnowski
- Tomasz Kocejko
- Jerzy Wtorek
2024
There are many approaches to non-invasively deter-mine blood pressure. Among them there are methods based on utilizing pulse transit time measured by means of photoplethys-mography. The variability of the blood pressure drop between two measurement sensors placed along the artery and its dependence on the selected parameters describing the cardiovascular system is presented in the paper. This pressure drop modifies the pressure pulse propagation velocity, thus also value of PTT. The properties of four fiducial points on the radial and brachial arteries were analyzed. Publicly available simulation data were used for the analyses. The best results were achieved for the point defined by the maximum of the first derivative of the signal.
PVA-Based Films with Strontium Titanate Nanoparticles Dedicated to Wound Dressing Application
- Beata Kaczmarek-Szczepańska
- Lidia Zasada
- Marcin Wekwejt
- Maria Swiontek Brzezinska
- Anna Michno
- Anna Ronowska
- Magdalena Ciesielska
- Ganna Kovtun
- M. Teresa Cuberes
2024 Pełny tekst Polymers
Bioactive materials may be applied in tissue regeneration, and an example of such materials are wound dressings, which are used to accelerate skin healing, especially after trauma. Here, we proposed a novel dressing enriched by a bioactive component. The aim of our study was to prepare and characterize poly(vinyl alcohol) films modified with strontium titanate nanoparticles. The physicochemical properties of films were studied, such as surface free energy and surface roughness, as well as the mechanical properties of materials. Moreover, different biological studies were carried out, like in vitro hemo- and cyto-compatibility, biocidal activity, and anti-biofilm formation. Also, the degradation of the materials’ utilization possibilities and enzymatic activity in compost were checked. The decrease of surface free energy, increase of roughness, and improvement of mechanical strength were found after the addition of nanoparticles. All developed films were cyto-compatible, and did not induce a hemolytic effect on the human erythrocytes. The PVA films containing the highest concentration of STO (20%) reduced the proliferation of Eschericha coli, Pseudomonas aeruginosa, and Staphylococcus aureus significantly. Also, all films were characterized by surface anti-biofilm activity, as they significantly lowered the bacterial biofilm abundance and its dehydrogenase activity. The films were degraded by the compost microorganism. However, PVA with the addition of 20%STO was more difficult to degrade. Based on our results, for wound dressing application, we suggest using bioactive films based on PVA + 20%STO, as they were characterized by high antibacterial properties, favorable physicochemical characteristics, and good biocompatibility with human cells.
Quality control of cheese samples for the presence of natamycin preservative – A natural deep eutectic solvent (NADES) based extraction coupled with HPLC
- Hameed Haq
- Nail Altunay
- Mustafa Tuzen
- Grzegorz Boczkaj
2024 JOURNAL OF FOOD COMPOSITION AND ANALYSIS
A new protocol for the determination of natamycin – an antifungal agent used as a food preservative - in cheese samples – is described. This new method is based on a natural deep eutectic solvent (NADES) green extraction procedure. High-performance liquid chromatography (HPLC) was used for detection and quantification. NADESs with different molar ratios were evaluated for efficient and selective extraction. NADES made of thymol and nonanoic acid (1:1) revealed to be the best extracting solvent. All significant analytical parameters - pH, temperature, NADES volume, time for sonication were optimized using Plackett-Burman (PB) and central composite design (CCD) - response surface methodology (RSM). Optimum conditions for extraction were pH 7, temperature 25°C, NADES volume 4.5 mL for 20 mL sample, and sonication time 10 mins. The developed method has a satisfactory linearity of 2–80.4 mg/kg, limits of detections (LOD), and limit of quantification (LOQ) of 0.45 and 1.45 mg/kg respectively. Under optimized conditions, the sample preparation procedure takes 12 mins. The method was found selective due to the unique and representative features of DESs. Furthermore, the extracts are analyzed by HPLC which provides a second very effective separation step, assuring the selectivity of the method. Validation of the method confirms the robustness and reproducibility of the NADES-based extraction coupled with the HPLC method demonstrating the effectiveness of NADES. The findings of this work contribute to the field of food safety and quality control, offering a novel and efficient approach to the detection of natamycin in cheese samples.
Quantifying inconsistencies in the Hamburg Sign Language Notation System
- Maria Ferlin
- Sylwia Majchrowska
- Marta A. Plantykow
- Alicja Kwaśniewska
- Agnieszka Mikołajczyk-Bareła
- Milena Olech
- Jakub Nalepa
2024 EXPERT SYSTEMS WITH APPLICATIONS
The advent of machine learning (ML) has significantly advanced the recognition and translation of sign languages, bridging communication gaps for hearing-impaired communities. At the heart of these technologies is data labeling, crucial for training ML algorithms on a huge amount of consistently labeled data to achieve models that generalize well. The adoption of language-agnostic annotations is essential to connect different sign languages, as single-language databases often provide limited lexicon examples, insufficient for training robust ML algorithms. This study critically examines the Hamburg Sign Language Notation System (HamNoSys), which describes the signer’s initial position and body movements, in contrary to the meanings of glosses. Despite HamNoSys’s utility in standardizing transcriptions across various sign languages, our investigation uncovers inconsistencies within HamNoSys that may negatively impact the development of accurate and reliable ML models. By analyzing HamNoSys labels across five sign languages, we identified a lack of standardized annotation procedures and the complexities within HamNoSys that introduce biases and errors. Our findings underscore the urgent need for unified, standardized data annotation guidelines to enhance the accuracy and efficiency of sign language recognition technologies. This research highlights the importance of addressing annotation challenges and advocates for a comprehensive, diversified database to improve the generalization of ML models.
Quantitative loss analysis of opaque perovskite solar cells using transient and steady-state characterization
- Katarzyna Cudo
- Riccardo Ollearo
- Gerwin H. Gelinck
- Yulia Galagan
- Damian Głowienka
2024 Physical Review Applied
Perovskite solar cells have emerged as a promising technology in the field of photovoltaics, owing to their notable advancements in power conversion efficiency. Recent investigations have revealed a crucial dependency of efficiency on the source of bromide within the perovskite absorption layer. To elucidate the underlying nature of traps within these solar cells, a comprehensive series of measurements was conducted under varying light intensities. Subsequently, employing an electrodynamic theoretical model, the intrinsic processes inherent to caesium and lead-based perovskite solar cells with different bromide sources were analyzed. The study reveals significant differences in transient photocurrent measurements and photocurrent-voltage characteristics among perovskites originating from different bromide sources, measured under different light intensities. Leveraging theoretical analyses on the picosecond scale, the recombination mechanism of crystal defects was meticulously described revealing the pronounced influence of capture rates on electron-hole recombination dynamics. Furthermore, the investigation substantiated the presence of a band-bending phenomenon at the interface between the hole transport layer (HTL) and perovskite, elucidating the observed transient photocurrent phenomena. The findings significantly advance the understanding of the mechanisms underlying perovskite solar cells, offering valuable insights into their performance and paving the way for enhanced efficiency and stability in future device design and optimization.
Quantum strategies for rendezvous and domination tasks on graphs with mobile agents
- Giuseppe Viola
- Piotr Mironowicz
2024 Pełny tekst PHYSICAL REVIEW A
This paper explores the application of quantum nonlocality, a renowned and unique phenomenon acknowledged as a valuable resource. Focusing on an alternative application, we demonstrate its quantum advantage for mobile agents engaged in specific distributed tasks without communication. The research addresses the significant challenge of rendezvous on graphs and introduces a distributed task for mobile agents grounded in the graph domination problem. Through an investigation across various graph scenarios, we showcase the quantum advantage. Additionally, we scrutinize deterministic strategies, highlighting their comparatively lower efficiency compared to quantum strategies. The paper concludes with a numerical analysis, providing further insights into our findings.
Quantum-assisted rendezvous on graphs: explicit algorithms and quantum computer simulations
- Joshua Tucker
- Paul Strange
- Piotr Mironowicz
- Jorge Quintanilla
2024 NEW JOURNAL OF PHYSICS
We study quantum advantage in one-step rendezvous games on simple graphs analytically, numerically, and using noisy intermediate-scale quantum (NISQ) processors. Our protocols realise the recently discovered (Mironowicz 2023 New J. Phys. 25 013023) optimal bounds for small cycle graphs and cubic graphs. In the case of cycle graphs, we generalise the protocols to arbitrary graph size. The NISQ processor experiments realise the expected quantum advantage with high accuracy for rendezvous on the complete graph K3. In contrast, for the graph , formed by two disconnected 4-vertex complete graphs, the performance of the NISQ hardware is sub-classical, consistent with the deeper circuit and known qubit decoherence and gate error rates.
Quasilinear elliptic problem in anisotropic Orlicz–Sobolev space on unbounded domain
- Karol Wroński
2024 ANNALI DI MATEMATICA PURA ED APPLICATA
We study a quasilinear elliptic problem $-\text{div} (\nabla \Phi(\nabla u))+V(x)N'(u)=f(u)$ with anisotropic convex function $\Phi$ on the whole $\R^n$. To prove existence of a nontrivial weak solution we use the mountain pass theorem for a functional defined on anisotropic Orlicz-Sobolev space $\WLPhispace(\R^n)$. As the domain is unbounded we need to use Lions type lemma formulated for Young functions. Our assumptions broaden the class of considered functions $\Phi$ so our result generalizes earlier analogous results proved in isotropic setting.
Quasi-one-dimensional exchange interactions and short-range magnetic correlations in CuTeO4
- Zubia Hasan
- Eli Zoghlin
- Michał Winiarski
- Kathryn E. Arpino
- Thomas Halloran
- Thao Tran
- Tyrel McQueen
2024 PHYSICAL REVIEW B
CuTeO4 has been proposed as a crystallographically distinct, yet electronic structure analog, of the superconducting cuprates. Here, we present a detailed characterization of the physical properties of CuTeO4 to address this proposal. Fitting of magnetic susceptibility data indicates unexpected quasi-one-dimensional, antiferromagnetic correlations at high temperature, with a nearest-neighbor Heisenberg exchange of 1=164⁢(5) K. Low-temperature heat capacity measurements reveal a sizable -linear contribution of =9.58⁢(8) mJ mol−1K−2, qualitatively consistent with expectations for a =1/2, uniform, Heisenberg spin chain. Below ≈40 K, the susceptibility shows an upturn inconsistent with quasi-one-dimensional behavior. While heat capacity measurements show no signs of magnetic order down to low-temperature, the upturn in the magnetic susceptibility coincides with the emergence of a diffuse peak (centered at | ⃗ ⁢|≈0.7 Å) in the neutron diffraction data, indicative of persistent, short-range, antiferromagnetic order with a correlation length of =10.1⁢(9) Å at =10 K. The onset of nonlinearity and hysteresis in the isothermal magnetization curves suggests the presence of a small ferromagnetic component. This persistent, short-range order is understood in the context of structural modeling of the x-ray and neutron diffraction data that show the presence of a significant density of stacking faults. No evidence for substantive dopability is observed and CuTeO4 appears, qualitatively, to have a larger band gap than predicted by density functional theory. We ascribe this finding to the inductive withdrawal effect from high-valence Te and suggest that superconductivity in copper tellurates is more likely to be found in compounds with a decreased reductive withdrawal effect from Te.
Quinoline-based thiazolyl-hydrazones target cancer cells through autophagy inhibition
- Vladimir Ćurčić
- Mateusz Olszewski
- Natalia Maciejewska
- Aleksandar Višnjevac
- Tatjana Srdić-rajić
- Vladimir Dobričić
- Alfonso T García-sosa
- Sanja B Kokanov
- Jovana B. Araškov
- Romano Silvestri
- Roland Schüle
- Manfred Jung
- Milan Nikolić
- Nenad R. Filipovići
2024 ARCHIV DER PHARMAZIE
Heterocyclic pharmacophores such as thiazole and quinoline rings have a significant role in medicinal chemistry. They are considered privileged structures since they constitute several Food and Drug Administration (FDA)-approved drugs for cancer treatment. Herein, we report the synthesis, in silico evaluation of the ADMET profiles, and in vitro investigation of the anticancer activity of a series of novel thiazolyl-hydrazones based on the 8-quinoline (1a-c), 2-quinoline (2a-c), and 8-hydroxy-2-quinolyl moiety (3a-c). The panel of several human cancer cell lines and the nontumorigenic human embryonic kidney cell line HEK-293 were used to evaluate the compound-mediated in vitro anticancer activities, leading to [2-(2-(quinolyl-8-ol-2-ylmethylene)hydrazinyl)]-4-(4-methoxyphenyl)-1,3-thiazole (3c) as the most promising compound. The study revealed that 3c blocks the cell-cycle progression of a human colon cancer cell line (HCT-116) in the S phase and induces DNA double-strand breaks. Also, our findings demonstrate that 3c accumulates in lysosomes, ultimately leading to the cell death of the hepatocellular carcinoma cell line (Hep-G2) and HCT-116 cells, by the mechanism of autophagy inhibition.
Raman Scattering versus Strain Engineering in Phosphorene Nanostructures: An Ab Initio Studies
- Krzysztof Pyrchla
2024 Pełny tekst
The one-dimensional nanoribbons made from phosphorene are novel structures with great applicability potential in material science. The significant carrier mobility combined with intrinsic semiconductor properties makes them ideal for application in electronics, and they are excellent candidates for sensing material. The lack of a well–established multiscale modelling strategy for phosphorene nano optoelectronic devices is one of the issues slowing down research on its applications. This thesis is focused on the preparation of the hybrid workflow for complex modelling of the phosphorene nanoribbons and use it for studying the potential of applying phosphorene nanostructures as a mechanical nanooscillator. In the proposed design, the oscillating behaviour of phosphorene device can be traced by the changes in the Raman bands of this structures. To efficiently predict the magnitude of such change, the multi-stage, hybrid calculation workflow was constructed. The ab initio modelling was utilised to study the mechanical elasticity of the phosphorene nanoribbons with different widths and doping levels. The effect of surface oxidation and interaction with air humidity was also studied using ab initio molecular dynamics. The Raman bands shifts dependence on the strain, and the level of surface oxidation was also calculated using the ab initio method in frozen phonon approximation. The properties calculated for atomic models of nanoribbons were used to model the dynamical behaviour of the phosphorene nanoribbons. The phosphorene nanoribbons aspect ratios are very high, and because of that, the atomic models used in ab initio modelling were a few orders of magnitude smaller than the size of the ribbons. To extrapolate the properties of these models into microscopic structures, the finite element method (FEM) was implemented, and the atomic models of the ribbons were designed to be infinitesimal elements of the structures. Because of this synergic application of both quantum and classical modelling, this approach is called hybrid. The results achieved for the structures using the hybrid approach were compared with the force field calculations, presenting consistency between methods and significantly lower computational cost of hybrid modelling in comparison to whole structure force field modelling.
Rapid Surrogate-Aided Multi-Criterial Optimization of Compact Microwave Passives Employing Machine Learning and ANNs
- Sławomir Kozieł
- Anna Pietrenko-Dąbrowska
2024 IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES
This article introduces an innovative method for achieving low-cost and reliable multi-objective optimization (MO) of microwave passive circuits. The technique capitalizes on the attributes of surrogate models, specifically artificial neural networks (ANNs), and multi-resolution electromagnetic (EM) analysis. We integrate the search process into a machine learning (ML) framework, where each iteration produces multiple infill points selected from the present representation of the Pareto set. This collection is formed by optimizing the ANN metamodel by means of a multi-objective evolutionary algorithm. The procedure concludes upon convergence, defined as a significant similarity between the sets of non-dominated solutions acquired through consecutive iterations. Performing the majority of iterations at the low-fidelity EM simulation level enables additional computational savings. Our methodology has been showcased using two microstrip circuits. Comparative assessments against various surrogate-assisted benchmark methods demonstrate the algorithm's competitive performance in terms of computational efficiency and the quality of the Pareto set generated in the course of the optimization run.
RCS Enhancement of Millimeter Wave LTCC Van Atta Arrays With 3-D Printed Lenses for Chipless RFID Applications
- Kamil Trzebiatowski
- Weronika Kalista
- Łukasz Kulas
- Krzysztof Nyka
2024 IEEE Antennas and Wireless Propagation Letters
In this paper, we present a new method to enhance the radar- cross section (RCS) of Van Atta arrays which can be used in chipless radio-frequency identification tags operating in millimeter wave frequency bands. Small planar Low-Temperature Co-fired Ceramic (LTCC) Van Atta arrays, that are durable and can operate in harsh environments, are combined with 3-D printed lenses to increase or modify the shape of their RCS by up to 10 dB. The lenses are uniform in one direction to maintain a wide RCS angular range of the underlying Van Atta arrays. They are manufactured using affordable 3-D printing stereolithography (SLA) process using high-performance resin. The resulting manufactured and measured Van Atta retrodirective arrays integrated with lenses exhibit measured RCS levels up to -28 dBsm at 24 GHz frequency. Moreover, the proposed approach allows LTCC Van Atta tags to be easily modified and reused by exchanging their lenses to adapt them to a new application. To the best of the authors' knowledge, this is the first time an experimental evaluation of lenses combined with Van Atta arrays has been presented. This novel technique can also be integrated with other RCS enhancement methods to further increase RCS levels.
REALIZACJA PRÓBNIKA SYSTEMU REJESTROWANIA I MONITOROWANIA PARAMETRÓW JAKOŚCIOWYCH STOSUJĄCEGO STANDARD IPFIX
- Sylwester Kaczmarek
- Krzysztof Zalewski
2024 Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne
Nadzór parametrów jakościowych w sieci z protokołem IP jest jedną z ważniejszych funkcji jaką musi dysponować Operator sieci telekomunikacyjnej. W pracy przedstawiono koncepcję systemu rejestracji i monitorowania przeznaczonego do realizacji tego celu. Jest to rozwiązanie pasywne stosujące rozszerzenie standardu IPFIX, które określono mianem SIPFIX. Opisano praktyczną realizację i wyniki testów Próbnika, jednego z podstawowych elementów składowych tego systemu. Wyniki potwierdziły możliwość realizacji zaproponowanego systemu.
Real-Time Sensor-Based Human Activity Recognition for eFitness and eHealth Platforms
- Łukasz Czekaj
- Mateusz Kowalewski
- Jakub Domaszewicz
- Robert Kitłowski
- Mariusz Szwoch
- Włodzisław Duch
2024 SENSORS
Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human–computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model’s quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research.
Real-Time Skin Quality Assessment System
- Tomasz Kocejko
- Aleksandra Krajna
2024
This thesis presents a real-time skin assessment system with the main aim of detecting inflammatory acne lesions and tracking skin conditions. A facial acne lesion detection algorithm was developed, using a pre-trained YOLOv8 model for lesion detection and a Mediapipe detector for face detection. The proposed solution aims to create a system used in smart mirrors to help users self-monitor and monitor their skin condition in real time without much involvement. The work shows that it is possible to effectively detect skin changes even in a motion situation, which could be a good direction for the development of solutions based on video analytics.