Lublin University of Technology Journals
Not a member yet
4285 research outputs found
Sort by
Classification Performance Comparison of BERT and IndoBERT on SelfReport of COVID-19 Status on Social Media
Get PDFMessages shared on social media platforms like X are automatically categorized into two groups: those who self-report COVID-19 status and those who do not. However, it is essential to note that these messages cannot be a reliable monitoring tool for tracking the spread of the COVID-19 pandemic. The classification of social media messages can be achieved through the application of classification algorithms. Many deep learning-based algorithms, such as Convolutional Neural Networks (CNN) or Long Short-Term Memory (LSTM), have been used for text classification. However, CNN has limitations in understanding global context, while LSTM focuses more on understanding word-by-word sequences. Apart from that, both require a lot of data to learn. Currently, an algorithm is being developed for text classification that can cover the shortcomings of the previous algorithm, namely Bidirectional Encoder Representations from Transformers (BERT). Currently, there are many variants of BERT development. The primary objective of this study was to compare the effectiveness of two classification models, namely BERT and IndoBERT, in identifying self-report messages of COVID-19 status. Both BERT and IndoBERT models were evaluated using raw and preprocessed text data from X. The study's findings revealed that the IndoBERT model exhibited superior performance, achieving an accuracy rate of 94%, whereas the BERT model achieved a performance rate of 82%
Efficiency comparison of message brokers
Get PDFThe aim of the article is to compare three main brokers used in the development of web applications: RabbitMQ, Apache Kafka and Apache Pulsar. To conduct the research, a custom application was created to compare two key metrics in the context of message queue performance. These metrics are: latency and number of processed messages per second. The conducted experiments showed that in scenarios requiring processing of backlogged messages by the broker and in cases of minimizing the impact of the SSL protocol on broker performance, Apache Pulsar proved to be the best solution. In the scenario examining message delivery delays, RabbitMQ turned out to be the best tool, while in the case of examining the stability of message processing in real-time, the best results were achieved with Apache Kafka
FILTERING STRATEGIES FOR SMARTPHONE EMITTED DIGITAL SIGNALS
Get PDFIn today's digitalized and technology-driven society, where the number of IoT devices and the volume of collected data is exponentially increasing, the use of sensor data has become a necessity in certain fields of activity. This paper presents a concise history of sensor evolution and specialization, with a focus on the sensors used for localization, particularly those present in microelectromechanical systems (MEMS) that make up inertial measurement units. The study starts with a general overview and progresses towards a more specific analysis of data sets collected from an accelerometer. In the materials and methods section, it emphasizes the imperfect nature of sensor measurements and the need to filter digital signals. Three different digital signal filtering techniques belonging to distinct filter categories are comparatively analyzed, with each technique having its own particularities, advantages and disadvantages. The analysis considers the effectiveness in reducing measurement errors, the impact of the filtering process on the original signal, the ability to highlight the underlying phenomenon, as well as the performance of the analyzed algorithms. The ultimate purpose of this article is to determine which filtration method is best suited for the signal at hand in the context of an indoor localization application
THE IMPACT OF APPLYING UNIVERSAL DESIGN PRINCIPLES ON THE USABILITY OF ONLINE ACCOMMODATION BOOKING WEBSITES
Get PDFOne of the concepts of human-computer interaction is the usability of websites, consisting of features such as efficiency, satisfaction, memorability, and learnability. Usability is particularly important in the case of websites that the user is expected to learn on their own. The main aim of this study is to evaluate the usability of user interfaces of websites and, based on this, to find how this evaluation is affected by the application of universal design principles. The objects of the study are two websites, one complying with the principles of universal design - created for the purpose of the study, and the other – an existing commercial website operating in the market, which does not follow these principles. Three hypotheses are defined: 1) effectiveness and efficiency of analyzed websites are higher for a service that followed the principles of universal design than a website that did not comply with these rules; 2) the quality of the user interface is greater for the service fulfilling the principles of universal design; 3) the satisfaction with the interaction with the interface is greater in case of websites conformed to the principles of universal design. The study uses two methods: eye tracking and questionnaires. The experiment involves 10 participants who had to perform a scenario consisting of 10 instructions that involved locating various elements in each of the tested GUI interfaces. The eye activity is recorded using a Gazepoint GP3 HD desktop eye tracker, which makes it possible to determine the effectiveness and efficiency values of using the analyzed interfaces. Each participant was also asked to fill out two questionnaires: the Lublin University of Technology one and the Questionnaire for User Interaction Satisfaction. The study proves the truth of the hypotheses, that is, the positive impact of universal design on the usability evaluation of user interfaces
EMOTION RECOGNITION FROM HEART RATE VARIABILITY WITH A HYBRID SYSTEM COMBINED HIDDEN MARKOV MODEL AND POINCARE PLOT
No full textThe best emotion recognition system based on physiological signals with a simple operatory should have higher accuracy and fast response speed. This paper aims to develop an emotion recognition system using a novel hybrid system based on Hidden Markov Model and Poincare plot. For this purpose, an electrocardiogram from the MAHNOB-HCI database was used. A novel feature extraction from a hybrid system combining Hidden Markov Model and Poincare plot was presented. The authors extracted time and frequency domain features from heart rate variability, and used two central hybrid systems, the Support Vector Machine/ Hidden Markov Model and the Hidden Markov Model/ Poincare Plot. Finally, the support vector machine was used as a classifier to classify emotions into positive and negative. The proposed method showed a classification accuracy of 95.02 ± 1.97 % overall. Also, the computing time of the method is around 163 milliseconds. The key of this paper is in the use of hybrid machines to improve accuracy without high computation time. This method can be used as a real-time system due to the low computation time and can be developed in many fields, such as medical examination and security systems
Kontrola bezpieczeństwa obiektu budowlanego przez monitorowanie obciążenia śniegiem
No full textClimatic loading in the form of snow load is a significant factor for building structures. This is relevant during the design stage, the execution stage, and especially throughout the operational period. Building owners are legally required to ensure that their roofs are cleared of snow, often raising the question of whether such action is necessary in a particular situation. To address this, various devices have been developed to facilitate the systematic monitoring and measurement of snow load on roofs. These devices measure snow weight either indirectly or directly. The methods for monitoring snow weight and evaluating the effect of snow load on structural safety have been extensively discussed in the literature, considering aspects of structural integrity, operation under harsh conditions, and the economic implications of building management. In this paper, the authors propose an innovative approach to monitoring snow load using snow scales, supplemented by roof deflection measurements with tilt sensors (inclinometers). Such systems not only ensure the safety of the building and its occupants by providing reliable and verified results but also achieve this in a cost-effective manner.Obciążenie klimatyczne w postaci obciążenia śniegiem jest bardzo ważną kwestią, szczególnie w przypadku połaci dachowych lekkich hal. Wynika to z faktu, że w przypadku tych dachów jest to obciążenie o największej objętości. Elementem wspomagającym kontrolę obciążenia dachu śniegiem jest systematyczny pomiar wartości tego obciążenia. Pomiar ten może być wykonywany na wiele sposobów. Większość metod pomiarowych ma swoje ograniczenia i wady. Jednym z najlepiej sprawdzonych systemów jest monitoring online zbudowany z wag śniegowych i czujników nachylenia (inklinometrów), które kontrolują zachowanie konstrukcji. Takie systemy nie tylko zapewniają bezpieczeństwo budynku i jego mieszkańców przez dostarczanie wiarygodnych, weryfikowalnych wyników, ale także nie są bardzo kosztowne
OPTYMALIZACJA PROGNOZOWANIA SZEREGÓW CZASOWYCH: WYKORZYSTANIE MODELI UCZENIA MASZYNOWEGO W CELU ZWIĘKSZENIA DOKŁADNOŚCI PREDYKCYJNEJ
Get PDFEngaging in investment activities plays a crucial and strategic role in fostering the growth of businesses and ensuring their resilience in the market. This involvement entails expenditures on acquiring assets, embracing technological advancements, expanding production capacities, conducting research and development, among various other domains. Collectively, these aspects form the foundation for the sustained success of an organization over the long term. This thesis will delve into an exploration of leveraging machine learning techniques to forecast key parameters in business, including investments and their impact on the financial health of the company. In this research, explored a variety of time series models and identified that both the Random Forest Regressor and Decision Tree Regressor models deliver superior accuracy, showcasing identical RMSE values of 88.36 on the validation dataset. Furthermore, the Cat Boost and Light GBM models exhibited praiseworthy performance, registering RMSE values of 92.47 and 104.69, respectively. These findings highlight the robust performance of Random Forest Regressor and Decision Tree Regressor, emphasizing their capability to provide accurate predictions. It is noted that Random Forest Regressor and Decision Tree Regressor are distinguished by high accuracy in time series forecasting, and the choice between them should take into account the trade-offs between computational efficiency and interpretability of the model. These results allow us to propose practical strategies for managing investment resources to ensure the sustainable development and prosperity of the enterprise in the long term.Zaangażowanie w działalność inwestycyjną odgrywa kluczową i strategiczną rolę we wspieraniu rozwoju przedsiębiorstw i zapewnianiu ich stabilności na rynku. Zaangażowanie to pociąga za sobą wydatki na nabycie aktywów, wdrażanie postępu technologicznego, zwiększanie zdolności produkcyjnych, prowadzenie badań i rozwoju oraz wiele innych obszarów. Łącznie aspekty te stanowią podstawę trwałego sukcesu organizacji w perspektywie długoterminowej. Niniejsza rozprawa dotyczy wykorzystania technik uczenia maszynowego do prognozowania kluczowych parametrów w biznesie, w tym inwestycji i ich wpływu na kondycję finansową firmy. W tym artykule zbadano różne modele szeregów czasowych i stwierdzono, że zarówno modele Random Forest Regressor, jak i Decision Tree Regressor zapewniają najwyższą dokładność, wykazując identyczne wartości RMSE wynoszące 88,36 w zbiorze danych walidacyjnych. Co więcej, modele Cat Boost i Light GBM wykazały się godną pochwały wydajnością, rejestrując wartości RMSE odpowiednio 92,47 i 104,69. Wyniki te podkreślają solidną wydajność regresorów Random Forest Regressor i Decision Tree Regressor, podkreślając ich zdolność do dostarczania dokładnych prognoz. Należy zauważyć, że Random Forest Regressor i Decision Tree Regressor wyróżniają się wysoką dokładnością w prognozowaniu szeregów czasowych, a wybór między nimi powinien uwzględniać kompromisy między wydajnością obliczeniową a interpretowalnością modelu. Wyniki te pozwalają nam zaproponować praktyczne strategie zarządzania zasobami inwestycyjnymi w celu zapewnienia zrównoważonego rozwoju i dobrobytu przedsiębiorstwa w perspektywie długoterminowej
Analysis of the usability of graphical interfaces of car rental websites with consideration of universal design principles
Get PDFThe study presents an analysis of two versions of a car rental website’s graphical interface in terms of usability and accessibility. a literature review was conducted to clarify concepts such as universal design, usability, and user experience. Two types of the car rental website were developed: one adhering to universal design principles and the other not considering these principles. The research employed tools such as WAVE, surveys, the LUT checklist, and an eye tracker. Metrics like time to first fixation and user ratings were analyzed. The experiments demonstrated that the website following universal design principles is more intuitive and user-friendly. Heatmaps and gaze paths illustrate that the version developed according to universal design principles significantly facilitates users in finding the information they need. Survey results proved that users rate websites developed according to universal design principles significantl
Dzisiejsze znaczenie Karty Weneckiej
No full textThe purpose of the research is to verify how current the Venice Charter is and how valid it still is today. The main field of criticism was that the Charter was an expression of a Eurocentric mentality or a Western-only vision. But bearing in mind all the signatories of that document, we instead see how it was the fruit of varied experiences and expressions from various parts of the world.Celem badania jest sprawdzenie, na ile aktualna i ważna dziś jest Karta Wenecka. Głównym obszarem krytyki było to, że Karta była wyrazem eurocentrycznej mentalności lub wizji wyłącznie zachodniej. Mając jednak na uwadze wszystkich sygnatariuszy tego dokumentu, widzimy, że był on owocem różnorodnych doświadczeń i wypowiedzi z różnych części świata
Kopiowanie reliktów geologicznych w procesie ochrony i restauracji zabytków architektury
No full textLviv is a historic city known for its architectural landmarks. The historic part of Lviv, which is included in the UNESCO World Heritage List, has the majority of its buildings constructed from stone. This architecture – walls, towers, townhouses on Rynok Square, sacred structures, and so on – requires preservation, constant care, and often restoration. For professional and thorough restoration of stone objects, it is essential to understand the nature of the material from which the monument was built. Here, collaboration with the Faculty of Geology at Lviv University provides invaluable support. Professors and geology students study the geological material from which Lviv was built, including its precise dating and origin. Such information is particularly valuable when it is necessary to supplement damaged details or replicate lost ones.
At the same time, during such detailed study of geological materials on Lviv’s streets, geology students discover fossils or remnants of ancient organisms, which are valuable scientific objects. Most often, these are various shells, and sometimes plant leaves. A true gem discovered on a stone in a street curb at 6 Akademika Hnatyuka Street in Lviv is a fossil of a starfish. This unique and extraordinary geological relic undoubtedly deserves preservation. Simultaneously, this geological relic is part of the city’s street, meaning it is part of its architecture, and currently cannot be removed.
As part of the collaboration between Lviv University and Polytechnic University, involving the Department of Geology and the Department of Architecture and Restoration, a mold was taken from the relic, and subsequently, a replica of the starfish fossil was created. Today, the object is housed in the university’s geological museum and is one of its valuable exhibits. This article analyzes the methodology for copying geological relics and presents the step-by-step process of creating a copy of such a relic, using the example of the starfish from Lviv.Lwów jest historycznym miastem znanym ze swoich zabytków architektury. Historyczna część Lwowa, wpisana na listę światowego dziedzictwa UNESCO, składa się głównie z budynków wykonanych z kamienia. Ta architektura – mury, wieże, kamienice na Rynku, budowle sakralne itp. – wymaga zachowania, stałej troski, a często także restauracji. Aby profesjonalnie i dokładnie restaurować kamienne obiekty, istotne jest zrozumienie natury materiału, z którego wykonano dany zabytek. W tym aspekcie nieocenioną okazuje się współpraca z Wydziałem Geologii Uniwersytetu Lwowskiego. Wykładowcy i studenci geologii badają materiał geologiczny, z którego zbudowano Lwów, wyjaśniają jego dokładne datowanie oraz pochodzenie. Takie informacje są szczególnie cenne w przypadku konieczności uzupełnienia uszkodzonych detali lub wykonania replik elementów utraconych.
Równocześnie, podczas szczegółowego badania materiałów geologicznych na ulicach Lwowa, studenci geologii odkrywają skamieniałości, które są cennymi obiektami naukowymi. Najczęściej są to różnorodne muszle, czasami liście roślin. Prawdziwą perełką odkrytą na kamieniu w krawężniku ulicznym pod adresem ul. Akademika Hnatiuka 6 we Lwowie jest skamieniałość rozgwiazdy. Jest to unikatowy i wyjątkowy zabytek geologiczny, który bez wątpienia zasługuje na zachowanie. Jednocześnie ten zabytek geologiczny jest częścią ulicy miasta, a więc także częścią jego architektury, i obecnie nie można go usunąć.
W ramach współpracy pomiędzy Uniwersytetem Lwowskim a Politechniką, Katedrą Geologii i Katedrą Architektury i Restauracji, wykonano formę od reliktu, a następnie kopię skamieniałości rozgwiazdy. Obecnie obiekt znajduje się w muzeum geologicznym uniwersytetu i jest jego cennym eksponatem. W artykule przeanalizowano metodykę kopiowania zabytków geologicznych oraz przedstawiono kolejne etapy wykonania kopii na przykładzie rozgwiazdy z miasta Lwowa