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.

Comprehension of speech in noise is a challenge for hearing-impaired (HI) individuals. Electroencephalography (EEG) provides a tool to investigate the effect of different levels of signal-to-noise ratio (SNR) of the speech. Most studies with EEG have focused on spectral power in well-defined frequency bands such as alpha band. In this study, we investigate how local functional connectivity, i.e. functional connectivity within a localized region of the brain, is affected by two levels of SNR. Twenty-two HI participants performed a continuous speech in noise task at two different SNRs (+3 dB and +8 dB). The local connectivity within eight regions of interest was computed by using a multivariate phase synchrony measure on EEG data. The results showed that phase synchrony increased in the parietal and frontal area as a response to increasing SNR. We contend that local connectivity measures can be used to discriminate between speech-evoked EEG responses at different SNRs.

Background DIALOG+ is a patient-centred, solution-focused intervention, which aims to make routine patient-clinician meetings therapeutically effective. Existing evidence suggests that it is effective for patients with psychotic disorders in high-income countries. We tested the effectiveness of DIALOG + for patients with depressive and anxiety disorders in Bosnia and Herzegovina, a middle-income country. Methods We conducted a parallel-group, cluster randomised controlled trial of DIALOG+ in an outpatient clinic in Sarajevo. Patients inclusion criteria were: 18 years and older, a diagnosis of depressive or anxiety disorders, and low quality of life. Clinicians and their patients were randomly allocated to either the DIALOG + intervention or routine care in a 1:1 ratio. The primary outcome, quality of life, and secondary outcomes, psychiatric symptoms and objective social outcomes, were measured at 6- and 12-months by blinded assessors. Results Fifteen clinicians and 72 patients were randomised. Loss to follow-up was 12% at 6-months and 19% at 12-months. Quality of life did not significantly differ between intervention and control group after six months, but patients receiving DIALOG + had significantly better quality of life after 12 months, with a medium effect size (Cohen's d = 0.632, p = 0.007). General symptoms as well as specifically anxiety and depression symptoms were significantly lower after six and 12 months, and the objective social situation showed a statistical trend after 12 months, all in favour of the intervention group. No adverse events were reported. Limitations Delivery of the intervention was variable and COVID-19 affected 12-month follow-up assessments in both groups. Conclusion The findings suggest DIALOG + could be an effective treatment option for improving quality of life and reducing psychiatric symptoms in patients with depressive and anxiety disorders in a low-resource setting.

The creep of the pre-strained superalloy N07080 is described in this work. The pre-strain was achieved by warm rolling at 1050 oC.-The warm rolling was performed due to additional strengthening, i.e increasing of the superalloy hardness.-The pre-strain drastically reduces the creep rupture life of the superalloy compared to the creep rupture life of the standard heat treated superalloy.-The drastic reductionof the creep rupture life is result of rapid creep cavity nucleation on stress concentration sites along primary grain boundaries of the pre-strained superalloy.-Recrystallization eliminates potential sites for rapid cavity nucleation and prolongates the creep rupture life.

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.

More recently a modified stainless steels have been used to produce various structural elements that work in complex operating conditions. Stainless steel X8CrNiS18-9 (standard EN 10088-3: 2005) is the most commonly used austenitic stainless steel due to its good machinability. This steel has high mechanical and working properties thanks to a complex alloying, primarily with the elements such as chromium and nickel. The content of sulphur present in the steel from 0.15 to 0.35% improves machinability. However, while sulphur improves machinability at the same time decreases the mechanical properties particularly toughness. The addition of sulphur, which is the cheapest available additive for free machining, will impair not only the transverse strength and toughness, but also the corrosion resistance.The aim of this work is to determine the influence of microalloying with boron on the machinability, corrosion resistance and mechanical properties the mentioned steel, but alsoto determine the effect of microalloying with boron on above steel, which is already microalloyed with zirconium, tellurium, or both elements (zirconium and tellurium) due to modification of non-metallic inclusions and improvement of properties.

Dynamical systems models for controlling multi-agent swarms have demonstrated advances toward resilient, decentralized navigation algorithms. We previously introduced the NeuroSwarms controller, in which agent-based interactions were modeled by analogy to neuronal network interactions, including attractor dynamics and phase synchrony, that have been theorized to operate within hippocampal place-cell circuits in navigating rodents. This complexity precludes linear analyses of stability, controllability, and performance typically used to study conventional swarm models. Further, tuning dynamical controllers by manual or grid-based search is often inadequate due to the complexity of objectives, dimensionality of model parameters, and computational costs of simulation-based sampling. Here, we present a framework for tuning dynamical controller models of autonomous multi-agent systems with Bayesian optimization. Our approach utilizes a task-dependent objective function to train Gaussian process surrogate models to achieve adaptive and efficient exploration of a dynamical controller model’s parameter space. We demonstrate this approach by studying an objective function selecting for NeuroSwarms behaviors that cooperatively localize and capture spatially distributed rewards under time pressure. We generalized task performance across environments by combining scores for simulations in multiple mazes with distinct geometries. To validate search performance, we compared high-dimensional clustering for high- vs. low-likelihood parameter points by visualizing sample trajectories in 2-dimensional embeddings. Our findings show that adaptive, sample-efficient evaluation of the self-organizing behavioral capacities of complex systems, including dynamical swarm controllers, can accelerate the translation of neuroscientific theory to applied domains.

Com a ascensão do comércio eletrônico em todo o mercado mundial, empresas e lojas físicas desenvolveram plataformas de vendas online para acompanhar a evolução digital e adentrar nesse novo âmbito concorrencial. Baseado nisso, o presente estudo implementou o programa 5S em operações de uma empresa de e-commerce com o objetivo de verificar a possibilidade de eliminação de desperdícios, redução de custos e otimização de seu desempenho operacional, visando garantir vantagem competitiva nesse meio. Para aplicação prática do programa, primeiramente foi feita uma visita especulativa sem aviso prévio à empresa, a fim de analisar a situação inicial do ambiente de trabalho e registrá-la por meio de fotografias e da classificação de um primeiro checklist por dois avaliadores. Além disso, foi medido o tempo de ciclo (separação no estoque, faturamento, embalagem e expedição) de um pedido para três funcionários, previamente à implementação do 5S. Posteriormente, foi então feita a aplicação da ferramenta no setor estudado através de técnicas requeridas para este fim, descritas na literatura e agrupadas em cinco sensos. De modo a garantir a constância destes sensos, o ciclo PDCA também foi utilizado. Para análise dos resultados, foi aplicado um segundo checklist pelos mesmos avaliadores e o tempo de ciclo pós modificações foi cronometrado para os mesmos funcionários e pedido. Houve um aumento de 38,4% na média de pontos dada pelos avaliadores no segundo checklist, com a categorização do ambiente de trabalho passando de “substancial” (préimplementação) para “ótima” (pós-implementação). O tempo de ciclo foi otimizado em 74,1% (pós-implementação). Portanto, a aplicação da ferramenta 5S nos processos de operação logística da empresa de ecommerce estudada, supervisionada pelo ciclo PDCA, otimizou a condição e o desempenho operacional do seu ambiente de trabalho.

New technologies primarily affect the lives of all people, their habits, needs, desires, but also significantly affect the demands placed on various business sectors. Discussions on the increasingly rapid development of technical-technological solutions that can be applied in the postal sector and logistics have a long history. New technologies in all areas bring a constant change in the relationship between companies and their customers, which significantly affect the quality of work and activities. In the years to come, it will be an increasing challenge for postal operators around the world, as well as for other companies, to achieve substantive communication and understanding of their customers through the application of innovative technologies. Understanding and learning about customer issues is key to offering them services that, with their precise targeting of stakeholders, quality, visibility, efficiency, and, perhaps most importantly, flexibility, will be able to meet needs that change so quickly over time. This will be possible with new technologies and innovative solutions. The paper presents a market research on the potential use of autonomous vehicles and drones in the postal sector in Bosnia and Herzegovina. The research is based on a survey questionnaire on the use of drones and autonomous vehicles in the postal sector in the segment of shipment delivery.

Information-Communication Technologies (ICTs) are currently used in various fields and there are many amazing inventions that are already present and make communication and life easier for us on a daily basis. The use of ICTs is less represented in the social work institutions. Therefore, this paper presents the implementation of ICTs through the chatbot application for the needs of social work created on the Tidio platform and within the webpage of the Public Institution “Center for Social Work Tešanj”. The application facilitates the work of social workers in collecting information from the users and eases the aid received by the users of social care in terms of faster responses to inquiries during emergencies, such as the COVID-19 pandemic, but also after. For the purpose of this research, an end-user survey was created and conducted with the aim of collecting user opinions on the acceptance and motivation for the use of chatbots in social work institutions. The results showed good acceptance and usage motivation of social work chatbot.

Limited knowledge exists about the effects of commonly used diuretic medications on the human normal flora. Thus, we investigated potential stimulatory effects of diuretic drug furosemide on urogenital tract microbiota in women. Three strains of E. coli and C. albicans with different biofilm forming capacities were obtained from female patients diagnosed with urinary tract infections. All tested strains were treated with two different concentrations of furosemide drug, in comparison to non-treated strains as the negative control. At specific time intervals, samples were obtained from growing culture and analyzed for their proliferation rate, aspartyl proteinase excretion and biofilm formation ability. E. coli and C. albicans strains significantly increased their aspartyl proteinase excretion under furosemide treatment. This effect was frequently observed after 16 hours of incubation at 37oC. This drug has also increased the biofilm forming capacities of E. coli and C. albicans strains. Interestingly, both E. coli and C. albicans non-biofilm former strains, gained the capacity of biofilm formation when treated with furosemide at certain concentrations. E. coli control became a weak biofilm former after 48 hours of incubation, while non-biofilm former C. albicans strain became a weak biofilm former in dose-dependent fashion, after 48 hours incubation with furosemide in concentration of 0.1 mg/mL, and after 16 hours of incubation with furosemide in concentration of 0.5 mg/mL. Loop diuretic drug furosemide is able to increase the microbial virulence and turn commensal microbes into opportunistic pathogens. Additionally, the results suggest that enzyme aspartyl proteinase might act as a signal molecule for the biofilm formation, leading to the increased microbial pathogenicity.