Artificial intelligence and machine learning techniques have progressed dramatically and become powerful tools required to solve complicated tasks, such as computer vision, speech recognition, and natural language processing. Since these techniques have provided promising and evident results in these fields, they emerged as valuable methods for applications in human physiology and healthcare. General physiological recordings are time-related expressions of bodily processes associated with health or morbidity. Sequence classification, anomaly detection, decision making, and future status prediction drive the learning algorithms to focus on the temporal pattern and model the nonstationary dynamics of the human body. These practical requirements give birth to the use of recurrent neural networks (RNNs), which offer a tractable solution in dealing with physiological time series and provide a way to understand complex time variations and dependencies. The primary objective of this article is to provide an overview of current applications of RNNs in the area of human physiology for automated prediction and diagnosis within different fields. Finally, we highlight some pathways of future RNN developments for human physiology.

Here, from macrophylogeographic mtDNA empirical data, we proposed a scenario of the evolution and speciation of two important forest trees, European Black Pine and Scotch Pine, and their multiple subspecies and varieties. Molecular clock simulations revealed that INDELs variability in the Pinus mitochondrial genome is relatively old, i.e., from the Pliocene-Miocene epoch, and related to historical tectonic continental fluctuations rather than climate change on a large geographic scale. Special attention is paid to the relationships between different speciation models and historical migration patterns and between peripheral and central populations. Species evolution involves the mixing of different speciation modes rather than only one of them, and one speciation mode has different results/effects on different DNA types (e.g., mitochondrial vs. chloroplast vs. nuclear DNA). The misbalance between different meta-population census size vs. effective population size contributions for asymmetric migration pattern is a result of different genotypes (and sub-phylogenetic lines) responding to selection pressing and adaptive evolution.

OBJECTIVE Patients with cutaneous melanoma and a positive sentinel node (SN) are currently eligible for adjuvant treatment with targeted therapy and immune checkpoint inhibitors. Near-infrared (NIR) fluorescence imaging could be an alternative and less invasive tool for SN biopsy to select patients for adjuvant treatment. One potential target for NIR is the mesenchymal-epithelial transition factor (MET). This study aimed to assess MET immunoreactivity in positive SNs and to evaluate its potential diagnostic, prognostic and therapeutic value. METHODS In this retrospective study, positive SN samples from patients with primary cutaneous melanoma were collected to assess MET immunoreactivity. To this end, paraffin-embedded SNs were stained for MET (monoclonal antibody D1C2). A 4-point Histoscore was used to determine cytoplasmic and membranous immunoreactivity (0 negative/1 weak/2 moderate/3 strong). Samples were considered positive when ≥10% of the cancer cells showed MET expression (staining intensity ≥1). Patient and clinicopathological characteristics were used for descriptive statistics, binary logistic regression, and survival analyses. RESULTS Positive MET immunohistochemistry was observed in 24 out of 37 samples (65%). No statistically significant associations were found between MET positivity and the following prognostic factors: Breslow thickness (P = 0.961), ulceration (P = 1.000), and SN tumor burden (P = 0.792). According to MET positivity, Kaplan-Meier curves showed no significant differences in survival. CONCLUSION This exploratory study found no evidence to support MET immunoreactivity in positive SNs as a possible diagnostic or prognostic indicator in patients with melanoma.

Time series prediction is a widespread and well studied problem with applications in many domains (medical, geoscience, network analysis, finance, econometry etc.). In the case of multivariate time series, the key to good performances is to properly capture the dependencies between the variates. Often, these variates are structured, i.e. they are localised in an abstract space, usually representing an aspect of the physical world, and prediction amounts to a form of diffusion of the information across that space over time. Several neural network models of diffusion have been proposed in the literature. However, most of the existing proposals rely on some a priori knowledge on the structure of the space, usually in the form of a graph weighing the pairwise diffusion capacity of its points. We argue that this piece of information can often be dispensed with, since data already contains the diffusion capacity information, and in a more reliable form than that obtained from the usually largely hand-crafted graphs. We propose instead a fully data-driven model which does not rely on such a graph, nor any other prior structural information. We conduct a first set of experiments to measure the impact on performance of a structural prior, as used in baseline models, and show that, except at very low data levels, it remains negligible, and beyond a threshold, it may even become detrimental. We then investigate, through a second set of experiments, the capacity of our model in two respects: treatment of missing data and domain adaptation.

ABSTRACT In ethnically divided consociational societies small minorities opt for different channels of political participation. They may do so to increase the importance of their group or challenge the consequences of limited participation channels, thus navigating the exclusion-amid-inclusion dilemma. However, it remains unclear how and why individuals belonging to small ethnic minorities with limited political opportunities, engage in politics. This article aims to explore and explain the levels of political participation of Jews and Poles in Bosnia and Herzegovina. It seeks to understand why some members of these communities choose to participate actively while others engage only in voting practices or refrain from getting involved. This is outlined using four different criteria: whether the act communicates a message about an individual's political preference, the potential degree of conflict, the effort put into the activity and the degree of cooperation with other people involved in the action. The qualitative analysis of this study relies on a series of semi-structured interviews and focus-groups conducted among the two ethnic communities.

: Several methodologies based on the international standard ISO/IEC 27001 have been developed for modelling information security management systems within higher education. This paper transformed the ISO/IEC 27001 standard into a questionnaire, which was sent digitally to about 100 universities in Bosnia and Herzegovina, and to the EU, Norway and the USA. The questions are arranged by levels, and the levels have their numerical weights, derived from individual questions in the levels themselves. Otherwise, the questions are asked with Yes or No and thus are reduced to binary variables. The rules necessary for the functioning of the system have been calculated. The fuzzy logic method represents a new approach to the problems of managing complex systems, which is very difficult to describe with a certain mathematical model, as well as in systems with a large number of inputs and outputs where there are unclear interactions. Risk assessment is a major part of the ISMS process. Traditional risk calculation models are based on the application of probability and classical set theory. Here, we have converted the risk assessment into a system rating of 5 to 10 numerically or from five to ten descriptively. We perform fuzzy optimization by finding the values of the input parameters of a complex simulated system, which results in the desired output. We use the fuzzy logic controller to execute fuzzy inference rules from the fuzzy rule database in determining congestion parameters, obtaining warning information and appropriate action. Simulating the situation of an advanced system that evaluates the protection quality of such a system with fuzzy logic, we use MATLAB. The paper combines the original Visual Basic programming language and MATLAB's Fuzzy Toolbox, to solve the complex problem of assessing compliance with the ISO/IEC 27001 standard, as one of the main standards for information systems security modelling. University information systems were used, but it is also applicable to all other information systems. The evaluation has been done for several universities and it has been proven that the system evaluates correctly, but these universities must not be publicly named. There was no such approach in the use of fuzzy logic and on such systems, and that is the originality of this work.

U nekim fazama svog razvoja, kod kompanija se vrlo èesto pojavljuje potreba da se privuku spoljni izvori finansiranja. Jedan od naèina za privlaèenje novca za finansiranje neke kompanije ili investicionog projekta su pozajmice. Te pozajmice mogu biti u obliku vlastitih izvora finansiranja, u vidu emisije akcija i u obliku pozajmljenih izvora finansiranja u vidu emisije obveznica ili kredita od banaka. Meðutim, jedno od osnovnih pitanja koje se postavlja jeste: koji je optimalan odnos duga i akcijskog kapitala u finansiranju kompanije, odnosno kako se odreðuje optimalna struktura kapitala neke kompanije? Dakle, ovdje je rijeè o strukturiranju pasive bilansa stanja preduzeæa, odnosno o uspostavljanju optimalnog odnosa sopstvenog kapitala i dugova (obaveza). Istraživanje je obuhvatilo analizu godišnjih finansijskih izvještaja 612 nefinansijskih akcionarskih društava koja jesu ili su bila listirana na Banjaluèkoj berzi hartija od vrijednosti u periodu od 2011. do 2020. godine. Istraživaèko pitanje glasi: "Kako menadžeri listiranih akcionarskih društava u Republici Srpskoj komponuju strukturu kapitala?" Kao zavisna varijabla u modelu posmatran je odnos kratkoroènog duga prema ukupnom zaduženju. Kao nezavisne varijable korišteni su sljedeæi fundamentalni pokazatelji poslovanja: povrat na akcijski kapital, povrat na aktivu, fiksna imovina, tekuæi racio, tekuæa aktiva prema ukupnoj aktivi, ukupan dug prema ukupnom kapitalu i velièina firme. Ukupan broj opservacija iznosio je 2.905. Svrha rada je identifikovati faktore specifične za privredna društva koja posluju u zemljama u razvoju, a koji značajno utiču na odluke o zaduživanju, odnosno finansiranju, te uzimajući u obzir te faktore konstruisati odgovarajući ekonometrijski model. Rezultati istraživanja pokazali su da su najjači uticaj na zavisnu varijablu, tj. kratkoročni dug prema ukupnim obavezama, zabilježile sljedeće nezavisne varijable: fiksna aktiva/ukupna aktiva i neto dobit/prosječan kapital (ROE). Sa druge strane, negativan uticaj na zavisnu varijablu imale su ostale varijable. Kada se uzorak podijeli na društva u većinskom javnom i u većinskom privatnom vlasništvu, zaključak je da kod obje vrste društava najveći uticaj ima odnos fiksna aktiva/ukupna aktiva ali da su ostali pokazatelji različitog uticaja.

Cilj istraživanja je da se utvrdi jačina veze između dostignutog nivoa tehnološkog razvoja i inovacija sa jedne strane, te bruto domaćeg proizvoda per capita, razvoja finansijskog tržišta, indeksa ljudskog razvoja i indeksa pranja novca sa druge strane. Korišteni su relevantni podaci za period od 2012. do 2021. godine za sve zemlje za koje su navedeni pokazatelji dostupni. Korištene metode za ovaj proces su komparativna metoda, analiza i regresiona analiza te analiza varijanse, odnosno prosta linearna regresija, te sinteza prethodnih istraživanja i teoretskih nalaza da bi zaključci bili izvučeni metodom indukcije - od pojedinačnog ka opštem. Dobijeni rezultati podvrguti su suštinskoj i statističkoj analizi. Rad pokazuje da postoji značajna veza između posmatranih varijabli, tj. da postoji direktan uticaj nivoa inovacija u zemlji na BDP, razvoj finansijskog tržišta, indeksa ljudskog razvoja te indeks pranja novca. Ograničenja u istraživanju uslovljena su definisanim problemom i metodama koje su primijenjene u radu, uzimajući u obzir standardne probleme kod istraživanja korelacija. Dalja istraživanja treba usmjeriti u pravcu u kojem je potrebno istražiti da li finansijsko ulaganje u inovacije ima efekta na rezultate posmatranih varijabli.

Agricultural waste has always been a global problem that causes environmental pollution, and thanks to the efforts of scientists, this agricultural waste has become not a neglected product, but rather a source of many effective chemical compounds that have industrial, pharmaceutical and food applications. Viral disease therapy has attracted a great deal of scientific interest worldwide. Therefore, the pace of research is increasing for effective and safe treatment. The potential inhibitory activity of pomegranate peel extract polyphenols against virus for effective viral disease therapy has attracted a great deal of scientific interest. The aim of this review was to present an overview of the pomegranate peel effects on viruses such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), Influenza virus, Norovirus, Adenovirus, Herpes simplex virus, Coronavirus disease (COVID-19). Pomegranate is consumed as fresh fruit and juice for its reported health benefits as antioxidant, antidiabetic, hypolipidemic, antibacterial, anti-inflammatory, antiviral, anticarcinogenic activities, and improves cardiovascular as well as oral health. The health benefits of pomegranate have been attributed to its wide range of phytochemicals, which are predominantly polyphenols, ellagitannins, anthocyanins, and other polyphenols. Instead of the pomegranate peel being a neglected product, it is considered as a promising antiviral agent which also offers other health benefits without side effects.

Salt stress results from excessive salt accumulation in the soil can lead to a reduction in plant growth and yield. Due to climate change, in the future climatic pressures, changed precipitation cycles and increased temperature will increase the pressures on agriculture, including increasing severity of salt stress. Brassica species contains oilseed and vegetable crops with great economic importance. Advances in understanding the mechanisms of salt stress in Brassica plants have enabled the development of approaches to better induce plant defense mechanisms at the time of their occurrence through the use of beneficial microorganisms or molecules. Both endophytic and rhizospheric microbes contribute to the mitigation of abiotic stresses in Brassica plants by promoting the growth of their host under stress conditions. In this review we summarized so far reported microorganisms with beneficial effects on Brassica plants and their mode of action. Another approach in mitigating the harmful effect of soil salinity may involve the application of different molecules that are involved in the stress response of Brassica plants. We reviewed and summarized their potential mode of action, methods of application and pointed out further research directions.

Many drugs with different mechanisms of action and indications available on the market today are capable of inducing hepatotoxicity. Drug-induced liver injury (DILI) has been a treatment challenge nowadays as it was in the past. We searched Medline (via PubMed), CENTRAL, Science Citation Index Expanded, clinical trials registries and databases of DILI and hepatotoxicity up to 2021 for novel therapies for the management of adult patients with DILI based on the combination of three main search terms: 1) treatment, 2) novel, and 3) drug-induced liver injury. The mechanism of action of novel therapies, the potential of their benefit in clinical settings, and adverse drug reactions related to novel therapies were extracted. Cochrane Risk of bias tool and Grading of Recommendations Assessment, Development and Evaluation (GRADE) assessment approach was involved in the assessment of the certainty of the evidence for primary outcomes of included studies. One thousand three hundred seventy-two articles were identified. Twenty-eight articles were included in the final analysis. Eight randomized controlled trials (RCTs) were detected and for six the available data were sufficient for analysis. In abstract form only we found six studies which were also anaylzed. Investigated agents included: bicyclol, calmangafodipir, cytisin amidophospate, fomepizole, livina-polyherbal preparation, magnesium isoglycyrrhizinate (MgIG), picroliv, plasma exchange, radix Paeoniae Rubra, and S-adenosylmethionine. The primary outcomes of included trials mainly included laboratory markers improvement. Based on the moderate-certainty evidence, more patients treated with MgIG experienced alanine aminotransferase (ALT) normalization compared to placebo. Low-certainty evidence suggests that bicyclol treatment leads to a reduction of ALT levels compared to phosphatidylcholine. For the remaining eight interventions, the certainty of the evidence for primary outcomes was assessed as very low and we are very uncertain in any estimate of effect. More effort should be involved to investigate the novel treatment of DILI. Well-designed RCTs with appropriate sample sizes, comparable groups and precise, not only surrogate outcomes are urgently welcome.

The micro-roughness represents the basic structure of the roughness of the treated surfaces and they are mainly a consequence of the machining during the production. The microgeometry of treated surfaces has a significant impact on the contact conditions of surfaces, which is reflected in the quality of gluing, pressing, and surface treatment and assembly, ie the interchangeability of structural details of the product, and thus the product quality. The roughness of treated wood surfaces is almost impossible to reliably determine theoretically using analytical models, and the application of experimental analysis of the investigated influential parameters is essential to improve the treatment regime, while maintaining the cost and quality of treatment at a satisfactory level. The aim of this paper is to examine the significance of the influential parameters of roughness of the treated surface, ie wood density, feed rate and cutting depth when turning solid wood elements, and analysis of experimental data for achieving lower roughness of the treated surface, without compromising the quality and total production costs. The purpose of the experimental plan is to generate a mathematical model that describes the process.