Vehicle Routing Problem (VRP) is the process of selection of the most favorable roads in a road network vehicle should move during the customer service, so as such, it is a generalization of problems of a commercial traveler. Most of the algorithms for successful solution of VRP problems are consisted of several controll parameters and constants, so this paper presents the data-driven prediction model for adjustment of the parameters based on historical data, especially for practical VRP problems with realistic constraints. The approach is consisted of four prediction models and decision making systems for comparing acquired results each of the used models.

The paper explores the nature and trend of migration during 2018, on the example of Bosnia and Herzegovina. The politicization of migrants' issues as well as a number of other factors contributed to the attitude of criminalization and securitization of migrants. Most authors and researchers dealing with the issue of migrants as well as the security representatives themselves argue that migrants are not a security threat to Bosnia and Herzegovina and that the state should treat them humanely and treat them according to international standards. In this paper we have determined that it is necessary to work on building additional capacities to accommodate migrants who have not found any accommodation or are on routes of Bosnia and Herzegovina, and that is important to undertake activities on technical, material and financial support for migration management in Bosnia and Herzegovina. We have used a qualitative research approach with the use of interview techniques and desk analysis for the purpose of collecting and processing primary and secondary data.

Constant improvement and evolution is one of the basic components of human nature. It is a requirement for one’s survival and well-being of future g

This letter presents a topology inference technique for neuronal networks of the cortex of the human brain based on network tomography theory. We envision that this technique will be used for high-resolution and high-precision brain tissue tomography and imaging using principles of the Internet of Bio-Nano Things. Our network tomography solution relies on the classification of processed data of spike delay and synaptic weight functions of neuronal network activity. For a 6-layer cortical neural network, we achieved 99.27% of accuracy using the Decision Tree machine learning technique for individual neurons, 2-leaf and 4-leaf star topologies of neuronal networks.

The mosque with wooden minaret, porch and hip roof, represents the authentic building type which had been built on a large number through four centuries of the Ottoman period in Bosnia and Herzegovina (1463–1878). These structures were constructed using locally available materials and construction techniques, all done by domestic builders. Sometimes numerous, small neighbourhood (mahalle) mosques constantly decay and disappear in last hundred years, as a result of incompetent appraisal and maintenance, violent or deliberate demolition, and also unacceptable intentions to build a new, larger and more ‘modern’ mosque in place of an old one. This study aims to analyse four small neighbourhood mosques in the Tuzla region, dating back to the 16th and early 17th century, in terms of the authenticity of form, method of construction, similarity and differences with other matching examples in Bosnia, as well as problems and possibilities of their restoration, today’s use and proper maintenance. Džindijska and Mejdanska mosque in Tuzla town, Atik mosque in Cive, and Džebarska mosque, belong to a single space type with a two-story porch, both under the wooden pitched roof with integrated wooden minaret. After being worn out and with an altered look, the restoration works had given them back previous, more authentic form. As a valuable symbol of the cultural identity and continuity, this autochthonous mosque type can be preserved with sustainable methods and principles of the restoration, with due respect of the contemporary context, values and users’ needs. Key words: mosque with wooden minaret, mosque restoration, two-story wooden porch, Džindijska mosque, Mejdanska mosque, Atik mosque in Cive, Džebarska mosque, Tuzla

Postupak za priznanje i zaštitu patenta je kompliciran, dugotrajan, težak i skup. Postupak stjecanja, održavanja, sadržaj, evidencija prometa, prestanak i zaštita patenta na području Bosne i Hercegovine (BiH) propisan je Zakonom o patentu, te Pravilnikom o postupku za priznanje patenta. Postupak priznanja patenta je posebni upravni postupak koji provodi Institut za intelektualno vlasništvo Bosne i Hercegovine. Na sva procesna pitanja koja nisu uređena Zakonom o patentu Bosne i Hercegovine i Pravilnikom o postupku za priznanje patenta, kao provedbenom propisu, primjenjuje se Zakon o upravnom postupku. Iako su tri materijalnopravna uvjeta koja se moraju ispuniti kako bi se izum mogao patentirati univerzalno prihvaćena, još uvijek je pravo iskorištavanja patentiranog izuma teritorijalno ograničeno, tako da i patentna zaštita izuma u Europskoj uniji (EU) počiva na nacionalnom pravu država članica. Institut za intelektualno vlasništvo Bosne i Hercegovine vodi, pored Registra patenata, i Registar prijava patenata, stoga će se u radu analizirati značaj prijave u postupku priznanja patenta i specifičnosti samog postupka zbog čega i jest reguliran posebnim zakonom. Ključne riječi: izum, patent, upravni postupak, prijava patenta, Institut za intelektualno vlasništvo

Identifying people based on their footprint has not yet gained enough attention from the researchers. Therefore, in this paper, an investigation of human identification conducted based on the footprint. Transfer Learning used as the main concept of this investigation. The aim of using Transfer Learning is to overcome the need for a large-scale dataset and achieve high accuracy with a low-scale dataset. Five well-known models used, namely, Alexnet, Vgg16, Vgg19, Googlenet, and Inception v3. Each of these models fine-tuned to fit-in the paper’s topic. A dataset of 30 individuals constructed in order to train the models. The right and left footprint of each individual captured with iPhone camera. The models trained and evaluated based on the same settings. The evaluation shows that Inception v3 model achieved the highest accuracy compared to all other four models.

Kada nastupi socijalni rizik, odnosno smrt hranioca porodice koji je bio osiguranik ili korisnik penzije, članovi njegove porodice su, kao povjerioci socijalno-pravnog odnosa, ovlašteni da od Zavoda, odnosno Fonda za penzijsko i invalidsko osiguranje, kao dužnika, traže izvršenje socijalne prestacije. Da bi članovi porodice ostvarili pravo na porodičnu penziju nakon smrti hranioca porodice potrebno je da budu ispunjeni opći uvjeti na strani umrle osobe i posebni uslovi na strani članova njegove porodice. I jedni i drugi uvjeti podjednako su važni, jer neispunjavanje bilo kojeg od tih uvjeta čini prepreku za ostvarivanje prava na porodičnu penziju. U radu će se dati pregled svih uvjeta koji se moraju ispuniti da bi određeno lice ostvarilo pravo na porodičnu penziju. Takođe, biće ukazano na različita rješenja „starog“ i „novog“ Zakona o penzijsko-invalidskom osiguranju Federacije Bosne i Hercegovine, te će se analizirati nova rješenja u skladu s osnovnim načelima na kojima se institut porodične penzije zasniva. Ključne riječi: porodična penzija, porodica, osiguranik, udovac, udovica

We demonstrate that a single 6mm line sample of simulated near-field speckle intensity suffices for accurate estimation of the concentration of dielectric micro-particles over a range from 104 to 6⋅106 particles per ml. For this estimation, we analyze the speckle using both standard methods (linear principal component analysis, support vector machine (SVM)) and a neural network, in the form of a sparse stacked autoencoder (SSAE) with a softmax classifier or with an SVM. Using an SSAE with SVM, we classify line speckle samples according to particle concentration with an average accuracy of over 78%, with other methods close behind.