Search

The article presents research on the application of image processing techniques and convolutional neural networks (CNN) for the detection and measurement of seed sizes, specifically focusing on coffee and white bean seeds. The primary objective of the study is to evaluate the potential of using CNNs to develop tools that automate seed recognition and measurement in images. A database was created, containing photographs of coffee and white bean seeds with precise annotations of their location and type. Image processing techniques and You Only Look Once v8 (YOLO) models were employed to analyze the seeds’ position, size, and type. A detailed comparison of the effectiveness and performance of the applied methods was conducted. The experiments demonstrated that the best-trained CNN model achieved a segmentation accuracy of 90.1% IoU, with an average seed size error of 0.58 mm. The conclusions indicate a significant potential for using image processing techniques and CNN models in automating seed analysis processes, which could lead to increased efficiency and accuracy in these processes.

The objective of the article is to recognize users’ emotions by classifying facial electromyographic (EMG) signals. A biomedical signal amplifier, equipped with eight active electrodes positioned in accordance with the Facial Action Coding System, was used to record the EMG signals. These signals were registered during a procedure where users acted out various emotions: joy, sadness, surprise, disgust, anger, fear, and neutral. Recordings were made for 16 users. The mean power of the EMG signals formed the feature set. We utilized these features to train and evaluate various classifiers. In the subject-dependent model, the average classification accuracies were 96.3% for KNN, 94.9% for SVM with a linear kernel, 94.6% for SVM with a cubic kernel, and 93.8% for LDA. In the subject-independent model, the classification results varied depending on the tested user, ranging from 91.4% to 48.6% for the KNN classifier, with an average accuracy of 67.5%. The SVM with a cubic kernel performed slightly worse, achieving an average accuracy of 59.1%, followed by the SVM with a linear kernel at 53.9%, and the LDA classifier at 41.2%. Additionally, the study identified the most effective electrodes for distinguishing between pairs of emotions.

Liturgia stanowi przestrzeń szczególnego spotkania teologii i prawa. Nawet, jeśli niektórym wydaje się, że powinna być ona ograniczona tylko do wymiaru czysto mistycznego, bo widzi się w niej specjalny rodzaj modlitwy, to w rzeczywistości jej kształt jest dokładnie określony przez normy prawa kościelnego. Krytyczna ocena Kodeksu Prawa Kanonicznego z 1983 r. musiała uwzględnić obiektywne stwierdzenie, że nie każdy przepis w nim określony i zawarty oddał w sposób precyzyjny sensus Ecclesiae twórców i uczestników Soboru Watykańskiego II. Tak było chociażby w przypadku kan. 838 KPK/83. Zawarte w nim normy odnoszące się do adaptacji i akomodacji oraz określające zasady współpracy pomiędzy Stolicą Apostolską a lokalnymi konferencjami biskupów wymagały uzgodnienia z przepisami przyjętymi już w ramach obrad Soboru Watykańskiego II. Dlatego na mocy listu apostolskiego motu proprio Magnum principium papież dokonał stosownych zmian, które uczyniły współpracę Stolicy Apostolskiej i konferencji biskupów jeszcze sprawniejszą i bardziej owocną w służbie wiernym. Ponadto dzięki tej nowelizacji modlitwa liturgiczna ma być bardziej przystosowana do zrozumienia ludzi.

Instytucja ubezwłasnowolnienia, posiadająca ogromne znaczenie z punktu widzenia prawnego, społecznego i rodzinnego, wzbudza liczne kontrowersje. Niektórzy autorzy zastanawiają się, czy powinna mieć obecnie rację bytu, z racji ograniczenia zdolności do czynności prawnych osoby, której dotyczy. Z drugiej zaś strony – z perspektywy osób podejmujących się opieki nad seniorami – wydaje się być niezwykle pomocna. Chociaż pojawiają się nowe propozycje, które mogły zastąpić ubezwłasnowolnienie, pozostają one póki co na poziomie postulatów. Dlatego niniejsze opracowanie stanowi po pierwsze prezentację, a obok tego ocenę instytucji ubezwłasnowolnienia w polskim systemie prawnym. Aby mogła ona spełnić swoje przedmiotowe zadanie, a jednocześnie wykluczyć wszelkie nadużycia w jej stosowaniu, konieczne jest zachowanie stosownych przepisów prawa, które zapewnią podmiotowe traktowanie osoby i ochronę jej interesów.

One approach employed in brain–computer interfaces (BCIs) involves the use of steady-state visual evoked potentials (SSVEPs). This article examines the capability of artificial intelligence, specifically convolutional neural networks (CNNs), to improve SSVEP detection in BCIs. Implementing CNNs for this task does not require specialized knowledge. The subsequent layers of the CNN extract valuable features and perform classification. Nevertheless, a significant number of training examples are typically required, which can pose challenges in the practical application of BCI. This article examines the possibility of using a CNN in combination with data augmentation to address the issue of a limited training dataset. The data augmentation method that we applied is based on the spectral analysis of the electroencephalographic signals (EEG). Initially, we constructed the spectral representation of the EEG signals. Subsequently, we generated new signals by applying random amplitude and phase variations, along with the addition of noise characterized by specific parameters. The method was tested on a set of real EEG signals containing SSVEPs, which were recorded during stimulation by light-emitting diodes (LEDs) at frequencies of 5, 6, 7, and 8 Hz. We compared the classification accuracy and information transfer rate (ITR) across various machine learning approaches using both real training data and data generated with our augmentation method. Our proposed augmentation method combined with a convolutional neural network achieved a high classification accuracy of 0.72. In contrast, the linear discriminant analysis (LDA) method resulted in an accuracy of 0.59, while the canonical correlation analysis (CCA) method yielded 0.57. Additionally, the proposed approach facilitates the training of CNNs to perform more effectively in the presence of various EEG artifacts.

The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection.

Electroencephalography (EEG) signals are disrupted by technical and physiological artifacts. One of the most common artifacts is the natural activity that results from the movement of the eyes and the blinking of the subject. Eye blink artifacts (EB) spread across the entire head surface and make EEG signal analysis difficult. Methods for the elimination of electrooculography (EOG) artifacts, such as independent component analysis (ICA) and regression, are known. The aim of this article was to implement the convolutional neural network (CNN) to eliminate eye blink artifacts. To train the CNN, a method for augmenting EEG signals was proposed. The results obtained from the CNN were compared with the results of the ICA and regression methods for the generated and real EEG signals. The results obtained indicate a much better performance of the CNN in the task of removing eye-blink artifacts, in particular for the electrodes located in the central part of the head.

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

Urząd wikariusza parafialnego, który przeszedł długą ewolucję w Kościele, nie mo­że być postrzegany jako wykonywanie doraźnych zadań zleconych przez proboszcza. Posługa wikariusza parafialnego nie jest też określana, jak w Kodeksie z 1917 roku, za pomocą pięciu różnych kategorii: wikariusz aktualny, zarządca, zastępca, pomocnik, współpracownik. Obecne prawo – inspirowane Soborem Watykańskim II – uznaje nato­miast wikariusza za autentycznego współpracownika proboszcza i uczestnika jego tro­ski, który jest ustanowiony do tej posługi przez biskupa diecezjalnego, aby – na zasa­dzie braterskiego współdziałania – sprawował pod władzą proboszcza dzieło nie tylko o charakterze duszpasterskim, ale i pasterskim (por. kan. 545 § 1 KPK/83). Obowiązki i uprawnienia wikariusza parafialnego, oprócz tych kodeksowych przyznających mu w określonych sytuacjach nawet uprawnienia do zastępowania proboszcza, zostały bar­dziej szczegółowo określone przez prawo partykularne. Dla lepszego zrozumienia za­leżności pomiędzy współpracą i autonomią wikariusza parafialnego w posługiwaniu duszpasterskim należy posłużyć się postanowieniami synodów diecezjalnych, które uwzględniając specyfikę konkretnych parafii i diecezji, określiły właściwe miejsce wi­ka­riusza parafialnego. Sprawuje on swoje posługiwanie z mandatu biskupa diecezjal­nego, ale pod władzą proboszcza, z którym winien uzgadniać wszystkie plany i zamie­rzenia. Jako współbrat proboszcza w trosce o parafię, otrzymał on stosowną autonomię, która nie tylko pozwoli uczynić jego posługę bardziej owocną, ale i przygotowuje go do podjęcia w przyszłości samodzielnych zadań pasterskich.

Background & objectives: Many etiological agents of zoonoses are considered as significant biological hazard to people visiting forested areas frequently, for instance, hunters. They may be exposed to ticks, rodents, and birds as well as excreta/secretions of wild animals or contaminated water and soil. Hence, this population is at risk of contracting infection with pathogens such as Borrelia burgdorferi sensu lato (s.l.), Anaplasma phagocytophilum, Babesia spp., tick-borne encephalitis virus, Bartonella spp., Francisella tularensis, Echinococcus spp., or hantaviruses. The aim of the study was to assess the seroprevalence of zoonotic agents, viz. A. phagocytophilum, hantaviruses, and Echinococcus spp., with special regard to B. burgdorferi s.l., among hunters in Lubelskie Voivodeship (eastern Poland). Methods: Serum samples collected from 134 hunters from Lubelskie Voivodeship were analyzed with the use of immunological techniques (enzyme-linked immunosorbent assay, line immunoblot test, and indirect fluorescence assay) for the presence of antibodies against the agents. Results: Specific antibodies were detected in 66% of the tested individuals. Antibodies against B. burgdorferi s.l. (39%), A. phagocytophilum (30%), hantaviruses (9%), and Echinococcus spp. (8%) were detected individually or as mixed results. Interpretation & conclusion: The results confirm that there is a risk of exposure to different pathogens in the forested areas in eastern Poland and that hunters are highly vulnerable to infection with the examined zoonotic agents. A significant proportion of co-occurring antibodies against different pathogens was noticed. Thus, hunters have to take special care of their health status evaluation and mitigate the exposure risk by using adequate prophylaxis measures.

Scientists employing methods of genetic engineering have developed a new group of living organisms, termed ‘modified organisms’, which found application in, among others, medicine, the pharmaceutical industry and food distribution. The introduction of transgenic products to the food market resulted in them becoming a controversial topic, with their proponents and contestants. The presented study aims to systematize objective data on the potential benefits and risks resulting from the consumption of transgenic food. Genetic modifications of plants and animals are justified by the potential for improvement of the food situation worldwide, an increase in yield crops, an increase in the nutritional value of food, and the development of pharmaceutical preparations of proven clinical significance. In the opinions of critics, however, transgenic food may unfavourably affect the health of consumers. Therefore, particular attention was devoted to the short- and long-lasting undesirable effects, such as alimentary allergies, synthesis of toxic agents or resistance to antibiotics. Examples arguing for the justified character of genetic modifications and cases proving that their use can be dangerous are innumerable. In view of the presented facts, however, complex studies are indispensable which, in a reliable way, evaluate effects linked to the consumption of food produced with the application of genetic engineering techniques. Whether one backs up or negates transgenic products, the choice between traditional and non-conventional food remains to be decided exclusively by the consumers.

Although smallpox was eradicated over 30 years ago, the disease remains a major threat. High mortality, high infectivity and low resistance of the contemporary population make the smallpox virus very attractive to terrorists. The possible presence of illegal stocks of the virus or risk of deliberate genetic modifications cause serious concerns among experts. Hence, it is reasonable to seek effective drugs that could be used in case of smallpox outbreak. This paper reviews studies on compounds with proven in vitro or in vivo antipoxviruses potential, which show various mechanisms of action. Nucleoside analogues, such as cidofovir, can inhibit virus replication. Cidofovir derivatives are developed to improve the bioavailability of the drug. Among the nucleoside analogues under current investigation are: ANO (adenozine N[sub]1[/sub]-oxide) and its derivatives, N-methanocarbothymidine [(N)-MCT], or derivatitives of aciklovir, peninclovir and brivudin. Recently, ST-246 – which effectively inhibits infection by limiting release of progeny virions – has become an object of attention. It has been also been demonstrated that compounds such as: nigericin, aptamers and peptides may have antiviral potential. An interesting strategy to fight infections was presented in experiments aimed at defining the role of individual genes (E3L, K3L or C6L) in the pathogenesis, and looking for their potential blockers. Additionally, among substances considered to be effective in the treatment of smallpox cases, there are factors that can block viral inhibitors of the human complement system, epidermal growth factor inhibitors or immunomodulators. Further studies on compounds with activity against poxviruses are necessary in order to broaden the pool of available means that could be used in the case of a new outbreak of smallpox.

The search for the answer of the following question is still actual: How to teach pupils religion in order to bring them to the proper participation in liturgy? To fulfil this assignment means to feed the catechised with the word and grace of God. Both the liturgy and catechesis are in their own ways a space for preaching the word of God and experiencing the grace of God. There are close correlations between liturgy and catechesis. Liturgy needs catechesis and catechesis needs liturgy. The Eucharist should be presented in catechesis in an encouraging way to bring the young people to the Holy Mass. Carrying out this assignment should be based on the wisdom of the Church: “Regulation of the sacred liturgy depends solely on the authority of the Church […] Therefore no other person, even if he be a priest, may add, remove, or change anything in the liturgy on his own authority” (Sacrosanctum Concilium, 22, 1–3). Those recommendations are also applicable in preparing the catechised to the sacraments in particular: First Communion, confirmation and confession. However, if the assignment of bringing the catechised to a mature participation in the liturgy is to be fully achieved the catechists should be taken in care as well. They transfer the teaching of Christ and should have proper traits. “For the noblest human and Christian attributes guarantee more fruitful catechesis than any elaborated methods” (Dyrektorium ogólne o katechizacji, 71).

The shipping industry is going through a period of technology transition that aims to increase the use of carbon-neutral fuels. There is a significant trend of vessels being ordered with alternative fuel propulsion. Shipping’s future fuel market will be more diverse, reliant on multiple energy sources. One of very promising means to meet the decarbonisation requirements is to operate ships with sustainable electrical energy by integrating local renewables, shore connection systems and battery energy storage systems (BESS). With the increasing number of battery/hybrid propulsion vessels in operation and on order, this kind of vessel propulsion is becoming more common, especially in the segment of short range vessels. This paper presents review of recent studies of electrification or hybridisation, different aspects of using the marine BESS and classes of hybrid propulsion vessels. It also reviews several types of energy storage and battery management systems used for ships’ hybrid propulsion. The article describes different marine applications of BESS systems in relation to peak shaving, load levelling, spinning reserve and load response. The study also presents the very latest developments of hybrid/electric propulsion systems offered by leading maritime market manufacturers.

In this article, we aimed to present a system that enables identifying experts in the field of visual art based on oculographic data. The difference between the two classified groups of tested people concerns formal education. At first, regions of interest (ROI) were determined based on position of fixations on the viewed picture. For each ROI, a set of features (the number of fixations and their durations) was calculated that enabled distinguishing professionals from laymen. The developed system was tested for several dozen of users. We used k-nearest neighbors (k-NN) and support vector machine (SVM) classifiers for classification process. Classification results proved that it is possible to distinguish experts from non-experts.