Search

Brownfields represent abandoned and disused sites, an exceptional strategic reserve of space and urban resource whose potentials are under-recognised in Bosnia and Herzegovina. The initial step towards urban renewal of these spaces is: their identification, evaluation, assessment of development potential and promotion. Interactive, GIS and web oriented digital database of brownfields is very useful tool for its promotion and visibility that makes process of brownfield regeneration more efficient and faster. Therefore, the paper presents the unique methodology for development of interactive brownfield databases and bundled software BrownInfo.

Urban shrinkage is an increasingly global phenomenon that equally affects large cities and small towns, as a result of complex social, economic and spatial changes, thereby causing the emergence of the so-called shrinking cities. This paper presents a model for the analysis of shrinking cities tailored to the needs of research in circumstances of insufficiently developed statistical systems for monitoring the complex structure of changes affecting cities. The model is based on an analysis of international research projects focused on this research problem, analysis of the legislative framework in Bosnia and Herzegovina (B&H) and analysis of available data. The proposed model is tested on the territory of northwest B&H (Republic of Srpska - RS) and aims at mapping, analysis and typological classification of shrinking cities. It is assumed that the process of urban shrinkage is more prevalent than that of urban growth, and that most of the cities and towns in northwest B&H (RS) are faced with this problem, which is considerably more acute when it comes to small and medium-sized towns of this region.

Predmet istraživanja ovog rada su modeli strukturne regresije, koji su dizajnirani da koriste veze između objekata prilikom predviđanja izlaznih vrijednosti. Drugim riječima, modeli strukturne regresije razmatraju atribute objekata i veze između objekata kako bi dali što tačnije predviđanje. Gaussian Conditional Random Fields (GCRF) model je jedan od najčešće korišćenih modela strukturne regresije koji integriše predikciju tradicionalnih modela nadgledanog učenja (nestrukturnih prediktora) i vezu između objekata u cilju tačnije predikcije. Glavna pretpostavka ovog modela je da su dva objekta koja su usko povezana veoma slični jedan drugom i samim tim vrijednosti njihovih izlaznih varijabli treba da budu slični. Sličnost između objekata u GCRF modelu mora da bude simetrična, ali u velikom broju realnih primjera objekti su nesimetrično povezani. U radu je predstavljeno proširenje GCRF modela koje uzima u obzir asimetričnu sličnost između objekata (nazvan usmjereni GCRF - Directed GCRF). Na sintetičkim i realnim setovima podataka pokazano je da novi model daje tačnije predviđanje od standardnog GCRF modela i tradicionalnih nestrukturnih prediktora. Rad obuhvata i razvoj softverskog alata otvorenog koda koji integriše različite vrste GCRF modela i omogućava treniranje i testiranje tih modela na različitim setovima podataka, preko grafičkog korisničkog interfejsa. Izvršena je evaluacija alata sa korisnicima različitih profila i različitog znanja iz oblasti mašinskog učenja. Rezultati su potvrdili da je alat je intuitivan i lak za korišćenje kako za eksperte, tako i za početnike i istraživače iz različitih domena kojima GCRF model može pomoći da dođu do željenih informacija., The subject of this dissertation are structured regression models that are designed to use relationships between objects for predicting output variables. In other words, structured regression models consider the attributes of objects and dependencies between objects to make predictions as accurately as possible. Gaussian Conditional Random Fields (GCRF) model is commonly used structured regression model that incorporates the outputs of traditional supervised learning models (unstructured predictors) and the correlation between output variables in order to achieve a higher prediction accuracy. A main assumption in the GCRF model is that if two objects are closely related, they should be more similar to each other and they should have similar values of the output variable. The similarity considered in GCRF is symmetric. However, in many real-world examples objects are asymmetrically linked. This dissertation presents extension of GCRF model that considers asymmetric similarities between objects (called Directed GCRF). The effectiveness of new model is characterized on synthetic datasets and real-world datasets, on which it was more accurate than the standard GCRF model and baseline unstructured predictors. This dissertation also presents development of an open-source software tool that integrates various GCRF methods and supports training and testing of those methods on different datasets using graphical user interface. The tool was evaluated with users with different level of knowledge in the machine learning field. Evaluation results confirmed that this tool is intuitive and easy to use for experts, as well as for beginners and researchers from different domains that can use GCRF for data prediction.

Узајамно деловање негативних друштвених и економских фактора на глобалном нивоу, крајем XX и почетком XXI века, резултовало је поларизацијом просторног развоја која је произвела глобалне градове који су успели да се интегришу у глобалну мрежу, али је довела и до раста неједнакости међу градовима и појаве глобалног феномена г ра д ов а у опа д ању (shrinking cities)..., The interaction of negative social and economic factors at the global level, in the late twentieth and early twenty-first century, resulted in the polarisation of spatial development that produced the global cities which managed to integrate into the global network, but also led to an increase in disparities between cities and the emergence of global phenomenon of sh r in k i ng c i t i e s . Research shows that the phenomenon of urban stagnation is increasingly widespread in Central and Eastern Europe, the United States, developed countries in Asia, North America and Australia...

The initial purpose of this research was to understand the basic patterns of urban shrinkage in Serbia. Urban shrinkage, a common phenomenon in post-socialist countries, is a novelty, albeit very present in Serbia today. Despite presenting a huge challenge for the future of the country, it has not been studied sufficiently at any level. To understand this situation, the first "task" would certainly be to identify which cities in Serbia can be considered as shrinking in a local context. The research will focus on this issue through the development of four models of shrinking cities in Serbia according to globally based factors of urban shrinkage. The aim of the paper is to clarify the potential of their use and to explore the possible locally-based factors of urban shrinkage.

Industrial heritage sites that have lost their original function represent significant and valuable cultural heritage which is a part of the urban memory and material evidence of the past, with whose decay a city is losing a part of its history. This paper deals with the problem of preserving identity of industrial heritage sites in the process of sustainable urban regeneration. More precisely, paper deals with the problem of preserving tangible as well as intangible attributes of industrial heritage identity within a context of contemporary projects of urban regeneration. The significance of this problem lies within the contradiction between the industrial heritage sites as places intended for new urban functions in accordance with strategies of contemporary urban development and the industrial heritage sites as places with the inherited spatial, functional and cultural values important to the community. Therefore, the main planning task of sustainable regeneration is finding the balance between preservation and change of industrial heritage sites. In planning practice these changes are most often driven by economic and environmental interests, while cultural values as active components of material culture and urban memory of citizens are neglected. On the other hand, this problem arises from the ambiguous notion of industrial heritage identity, as well as from the lack of appropriate planning tools for identifying and analysing identity attributes that are valuable to preserve. The aim of this paper is to draw attention to the complexity of identity of industrial heritage stemming from the various tangible as well as intangible values of cultural heritage. The paper advocates for using the concept of place as a framework for identifying and investigating identity attributes of industrial heritage sites which contribute to decision making in the initial phase of planning process. The planning treatment of industrial heritage identity in the process of riverfronts r

Priručnik za uspostavljanje informacione baze braunfild lokacija Brownlnfo nastao je kao rezultat međunarodnog naučnoistraživačkog projekta Brownlnfo - Methodological Framework for Brownfield Databases Development. Projekat je pokrenuo Arhitektonsko-građevinsko- geodetski fakultet Univerziteta u Banjoj Luci 2013. godine u saradnji sa partnerima iz zemlje, regiona i Evrope, a u njegovoj realizaciji participiralo je 160 učesnika iz 12 zemalja. Projekat su sufinansirali Ministarstvo za nauku i tehnologiju Vlade Republike Srpske i Njemačko društvo za međunarodnu saradnju - GIZ (Deutsche Gesellschaft für Internationale Zusammenarbeit), a podržan je od Ministarstva za prostorno uređenje, građevinarstvo i ekologiju Vlade Republike Srpske, Privredne komore Republike Srpske, Republičke agencija za razvoj malih i srednjih preduzeća, Fonda za zaštitu životne sredine i energetsku efikasnost Republike Srpske, Razvojne agencije CIDEA - Banja Luka, te opština Mrkonjić Grad i Teslić. Realizaciju pilot projekta značajno su pomogle: INOVA, institucija zadužena za informatički inžinjering i Poslovna zona a.d. Banja Luka, koja je obezbijedila sredstva za provođenje postupka mapiranja. Institucije učesnice projekta dolaze iz različitih domena profesionalnog djelovanja: akademskog, stručnog i upravljačkog. Riječ je fakultetima, naučnoistraživačkim institutima, stručnim institucijama, lokalnim razvojnim agencijama, odjeljenjima lokalnih samoprava, te različitim akterima iz privrednog sektora. Među institucijama učesnicama izdvajaju se: Institut za održivi urbani razvoj Češke (IURS - Institut pro udržitelny rozvoj sidel, Prag), kao institucija koja je lider u oblasti braunfild regeneracije, i Urbanistički zavod Republike Slovenije, koji su projekat podržavali tokom cijelog procesa njegove realizacije. Među akademskim institucijama istaknuto mjesto zauzima Arhitektonski fakultet Univerziteta u Beogradu, čiji je naučni kadar u velikoj mjeri doprinio realizaciji svih aktivnosti projekta. Pred