Introduction Deep learning techniques are gaining momentum in medical research. Evidence shows that deep learning has advantages over humans in image identification and classification, such as facial image analysis in detecting people’s medical conditions. While positive findings are available, little is known about the state-of-the-art of deep learning-based facial image analysis in the medical context. For the consideration of patients’ welfare and the development of the practice, a timely understanding of the challenges and opportunities faced by research on deep-learning-based facial image analysis is needed. To address this gap, we aim to conduct a systematic review to identify the characteristics and effects of deep learning-based facial image analysis in medical research. Insights gained from this systematic review will provide a much-needed understanding of the characteristics, challenges, as well as opportunities in deep learning-based facial image analysis applied in the contexts of disease detection, diagnosis and prognosis. Methods Databases including PubMed, PsycINFO, CINAHL, IEEEXplore and Scopus will be searched for relevant studies published in English in September, 2021. Titles, abstracts and full-text articles will be screened to identify eligible articles. A manual search of the reference lists of the included articles will also be conducted. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was adopted to guide the systematic review process. Two reviewers will independently examine the citations and select studies for inclusion. Discrepancies will be resolved by group discussions till a consensus is reached. Data will be extracted based on the research objective and selection criteria adopted in this study. Ethics and dissemination As the study is a protocol for a systematic review, ethical approval is not required. The study findings will be disseminated via peer-reviewed publications and conference presentations. PROSPERO registration number CRD42020196473.

Društveni značaj i kvalitet naučnog istraživanja u velikoj mjeri ovise o korisnosti rezultata istraživanja za društvenu i naučnu zajednicu. Nedostatak sredstava i želja da se sredstva dodijele visokokvalitetnim istraživanjima čine sve značajnijim procjenu kvaliteta istraživanja i valorizaciju znanja. Međutim, vrlo je teško primijeniti kriterije koji mogu objektivno procijeniti naučna istraživanja, pružajući precizne kvalitativne i kvantitativne podatke na kojima bi agencije za finansiranje mogle temeljiti svoje odluke. Proizvod naučnog istraživanja uglavnom su informacije objavljene u naučnim časopisima. One su temelj širenja znanja i osnovni kriterij za akademsku i naučnu evaluaciju, regrutovanje sredstava za naučna istraživanja i napredovanje u karijeri. Pored evaluacije naučnih publikacija, postoji širok spektar drugih aktivnosti koji odražavaju naučni kredibilitet znanstvenika, kao što su: broj i kvalitet grantova za naučnoistraživačke projekte, liderstvo u nacionalnim ili međunarodnim akademskim društvima, članstvo u redakcijama uglednih časopisa, mentorstva u doktorskim disertacijama i slično. Mada su te aktivnosti važne i daju kredibilitet znanstveniku, relevantni scientimetrijski sistemi pokrivaju samo publikacije, izostavljajući druge kriterije od naučne važnosti, u ocjenjivanju prilikom akademskog napredovanja znanstvenika, kao i konkursima za dobijanje grantova za finansijsku potporu naučnim istraživanjima. Razlog tome je činjenica da su ove aktivnosti, bez obzira na važnost, vrlo heterogene, sa specifičnim karakteristikama i zahtijevaju veoma raznolike parametre za ocjenu. Stoga, za ove aktivnosti ne postoje univerzalni kriterijumi vrednovanja i njihov se kvalitet, uglavnom, procjenjuje individualno, ovisno o namjeni procjene. Bez obzira na manjkavosti, sistemi rangiranja univerziteta su važni komparativni parametri za procjenu kvaliteta naučne i edukativne vrijednosti univerziteta.

The social significance and quality of scientific research largely depend on the usefulness of research results for the social and scientific community. The lack of funds and the desire to allocate funding to high-quality research projects make the assessment of the quality of research and the valorization of knowledge increasingly important. However, it is very difficult to apply criteria that can objectively assess scientific research, providing precise qualitative and quantitative data on which funding agencies could base their decisions. The product of scientific research is mainly information published in scientific journals. They are the basis for the dissemination of knowledge and the basic criteria for academic and scientific evaluation, fundraising for scientific research and career advancement. In addition to the evaluation of scientific publications, there is a wide range of other activities that reflect the scientific credibility of scientists, such as: number and quality of grants for scientific research projects, leadership in national or international academic societies, membership in editorial boards of reputable journals, doctoral dissertation mentorships and the like. Although these activities are important and give credibility to the scientist, the relevant scientometric systems cover only publications, neglecting other criteria of scientific importance in evaluation for purpose of academic advancement of a scientist, as well as competitions for grants for financial support of scientific research. The reason for this is the fact that these activities, regardless of their importance, are very heterogeneous, with specific characteristics, and require very diverse parameters for evaluation. Therefore, there are no universal evaluation criteria for these activities and their quality is generally assessed individually, depending on the purpose of the assessment. Regardless of the shortcomings, university ranking systems are important comparative parameters for assessing the quality of scientific and educational value of universities.

Iterative methods are widely used for solving sparse linear systems of equations and eigenvalue problems. Their performances are relevant to the conditioning of the linear systems. This work explores factors which affects the conditioning of the discretized system, including material heterogeneity, different constitutive characteristics and element sizes, and reveals the dependencies among solvers performance and the conditioning of linear systems. Results show that multiple materials can alter the eigenvalue distributions significantly, while lowering Young’s modulus results in higher condition numbers but has less effects on the spectral scope, additionally, there is a approximately reciprocal square linear relation between element size and condition numbers. These entangled effects along with the chosen pre-conditioners render that there is no simple monotonic increasing dependency among condition numbers and solving time, except with specific conditions. It is hoped that this work will provide more understanding of the iterative sparse linear solver behavior used in similar structural problems.

Osnovna funkcija univerziteta, pored obrazovanja, je naučnoistraživački rad. Na bosanskohercegovačkim univerzitetima je naučnoistraživački rad zapostavljen. Dva su osnovna razloga za to. Prvi je nedovoljno finansijsko ulaganje u nauku i istraživanja, a drugi je nedovoljno razvijena svijest o značaju naučnoistraživačkog rada, kako u bosanskohercegovačkom društvu, tako i na samim univerzitetima. U ovom radu je ukazano na to šta je potrebno uraditi da se ova druga teškoća prevaziđe. Pored toga, analizirane su mogućnosti unapređenja nauke i oblikovanja sistema nauke na bosanskohercegovačkim univerzitetima, kako bi oni postali i istraživački univerziteti. Na naučnoistraživački rad se nadovezuju istraživačko-razvojni rad, tehnološki razvoj, saradnja s privredom i razvoj naučno-tehnoloških parkova. Ove djelatnosti su još manje zastupljene na bosanskohercegovačkim univerzitetima nego naučnoistraživački rad. U ovom radu je ukazano na načine kako prevazići te teškoće, kako bi istraživački univerziteti postali nosioci tehnološkog razvoja Bosne i Hercegovine.

This paper presents a generic method to enhance performance and incorporate temporal information for cardiorespiratory-based sleep stage classification with a limited feature set and limited data. The classification algorithm relies on random forests and a feature set extracted from long-time home monitoring for sleep analysis. Employing temporal feature stacking, the system could be significantly improved in terms of Cohen’s κ and accuracy. The detection performance could be improved for three classes of sleep stages (Wake, REM, Non-REM sleep), four classes (Wake, Non-REM-Light sleep, Non-REM Deep sleep, REM sleep), and five classes (Wake, N1, N2, N3/4, REM sleep) from a κ of 0.44 to 0.58, 0.33 to 0.51, and 0.28 to 0.44 respectively by stacking features before and after the epoch to be classified. Further analysis was done for the optimal length and combination method for this stacking approach. Overall, three methods and a variable duration between 30 s and 30 min have been analyzed. Overnight recordings of 36 healthy subjects from the Interdisciplinary Center for Sleep Medicine at Charité-Universitätsmedizin Berlin and Leave-One-Out-Cross-Validation on a patient-level have been used to validate the method.Clinical relevance— The method can be employed generically to feature sets for (small scale) datasets to improve classification performance for classification problems with temporal relations with random forest classifiers.

Introduction. Despite its high accuracy, polysomnography (PSG) has several drawbacks for diagnosing obstructive sleep apnea (OSA). Consequently, multiple portable monitors (PMs) have been proposed. Objective. This systematic review aims to investigate the current literature to analyze the sets of physiological parameters captured by a PM to select the minimum number of such physiological signals while maintaining accurate results in OSA detection. Methods. Inclusion and exclusion criteria for the selection of publications were established prior to the search. The evaluation of the publications was made based on one central question and several specific questions. Results. The abilities to detect hypopneas, sleep time, or awakenings were some of the features studied to investigate the full functionality of the PMs to select the most relevant set of physiological signals. Based on the physiological parameters collected (one to six), the PMs were classified into sets according to the level of evidence. The advantages and the disadvantages of each possible set of signals were explained by answering the research questions proposed in the methods. Conclusions. The minimum number of physiological signals detected by PMs for the detection of OSA depends mainly on the purpose and context of the sleep study. The set of three physiological signals showed the best results in the detection of OSA.

The paper presents the assessment of the building “Radnički dom” (Workers’ Home) in Mostar, which was built in the Austro-Hungarian period, and represents one of the buildings of cultural and historical significance, located in the area of the historic urban core of the city. The paper explains the steps in assessing the condition of the existing structure, which include the collection of existing documentation, structural inspections, tests and calculations, and the assessment and decision on further action. The paper presents the drafts and gives descriptions of the performed visual inspection and the performed static calculation of the existing structure. At the end of the paper, recommendations are given for the rehabilitation and consolidation of the walls of the building: classical methods (injection and grouting) as well as modern methods (carbon strips). The paper points out the complexity of the procedure for the restoration of cultural and historical heritage buildings, the need for valid expertise of the condition and causes of building degradation, the importance of designing details of new structural elements and their corresponding and adequate connections with the original structure of the object.

Additional strengthening of superalloy N07080 described in this work was achieved by warm rolling. Control of the ratio of strength and ductile properties of the superalloy is possible by appropriate selection of the amount of warm deformation and the appropriate selection of the partial recrystallization temperature. In addition, recrystallization annealing makes it possible to equalize the grain size across the cross section of the warm rolled bars, which before recrystallization differ significantly in size in the central and peripheral parts of the bars.

Pear as a fruit species has a special place because of its quality characteristic. The fact that about 20,000 pear seedlings are considered to be sold annually in Bosnia and Herzegovina, which are autochthonous or spontaneously expanded varieties, also speaks in favor. The main goal of this research is to analyze the genetic variability of nine autochthonous pear varieties in Tuzla Canton, Bosnia and Herzegovina to enable the conservation and expansion of existing genetic resources. The study included nine autochthonous pear varieties. Samples of young leaves were collected on the following localities: the town of Srebrenik, the town of Gradačac, the municipality of Čelić-Tuzla Canton, Bosnia and Herzegovina, in the spring 2019. To determine genetic diversity, 12 SSR (Simple Sequence Repeats) markers were genotyped. There were no cases of synonyms or homonyms in the analyzed set. Each of the nine tested varieties represents a unique genotype. Autochthonous pear cultivars analyzed in this paper represent an interesting genetic resource, with useful agronomic traits that can be used in future cultivation.