Search

Transport management is one of the most important logistical tasks, and the designing the optimal transport routes plays a major role in that process. Vehicle routing is primarily of interest to companies that organize the transportation of goods to end users, with the aim of minimizing the total cost of the routes. Being a well-known NP-hard problem, the theoretical background of the vehicle routing problem has been researched for many years and it has been the basis for the development of a large number of commercial software. However, affordable software solutions are lacking. Difficult access to high quality and reliable spatial data related to the road network is also a limitation. This paper discusses the possibilities of applying open-source software for solving the VRP. Open spatial data from a collaborative project of the virtual community was used as the basis for modeling the road network graph. The experiment was carried out on data on vehicles and customers of a certain retail chain and refers to the territory of Serbia.

Airborne Laser Scanning (ALS) is one of the most popular and cost-effective approaches for collecting Digital Elevation Model (DEM) data. This especially applies to large areas, forested areas, areas with dense vegetation and urban environments. The ALS results in a vast amount of data in the form of point clouds. Successful use of such data requires applying semi-automatic and automatic approaches to classify points according to which objects or phenomena it represents. LAStools software package represents a set of highly efficient tools for processing ALS data. Through this study, the functionality of the LAStools software package for DEM generation has been analyzed. The proposed procedure for generating DEM products from ALS point cloud with LAStools has been determined and presented. The study also focuses on the important parameters of each tool in the proposed DEM procedure, with a special focus on advantages and disadvantages, possibilities and limitations.

The inventory of woody vegetation is of great importance for good forest management. Advancements of remote sensing techniques have provided excellent tools for such purposes, reducing the required amount of time and labor, yet with high accuracy and the information richness. Sentinel-2 is one of the relatively new satellite missions, whose 13 spectral bands and short revisit time proved to be very useful when it comes to forest monitoring. In this study, the novel spatio-temporal classification framework for mapping woody vegetation from Sentinel-2 multitemporal data has been proposed. The used framework is based on the probability random forest classification, where temporal information is explicitly defined in the model. Because of this, several predictions are made for each pixel of the study area, which allow for specific spatio-temporal aggregation to be performed. The proposed methodology has been successfully applied for mapping eight potential forest and shrubby vegetation types over the study area of Serbia. Several spatio-temporal aggregation approaches have been tested, divided into two main groups: pixel-based and neighborhood-based. The validation metrics show that determining the most common vegetation type classes in the neighborhood of 5 × 5 pixels provides the best results. The overall accuracy and kappa coefficient obtained from five-fold cross validation of the results are 82.97% and 0.75, respectively. The corresponding producer’s accuracies range from 36.74% to 97.99% and user’s accuracies range from 46.31% to 98.43%. The proposed methodology proved to be applicable for mapping woody vegetation in Serbia and shows a potential to be implemented in other areas as well. Further testing is necessary to confirm such assumptions.

ESA CCI SM products have provided remotely-sensed surface soil moisture (SSM) content with the best spatial and temporal coverage thus far, although its output spatial resolution of 25 km is too coarse for many regional and local applications. The downscaling methodology presented in this paper improves ESA CCI SM spatial resolution to 1 km using two-step approach. The first step is used as a data engineering tool and its output is used as an input for the Random forest model in the second step. In addition to improvements in terms of spatial resolution, the approach also considers the problem of data gaps. The filling of these gaps is the initial step of the procedure, which in the end produces a continuous product in both temporal and spatial domains. The methodology uses combined active and passive ESA CCI SM products in addition to in situ soil moisture observations and the set of auxiliary downscaling predictors. The research tested several variants of Random forest models to determine the best combination of ESA CCI SM products. The conclusion is that synergic use of all ESA CCI SM products together with the auxiliary datasets in the downscaling procedure provides better results than using just one type of ESA CCI SM product alone. The methodology was applied for obtaining SSM maps for the area of California, USA during 2016. The accuracy of tested models was validated using five-fold cross-validation against in situ data and the best variation of model achieved RMSE, R2 and MAE of 0.0518 m3/m3, 0.7312 and 0.0374 m3/m3, respectively. The methodology proved to be useful for generating high-resolution SSM products, although additional improvements are necessary.

Breast cancer screening involves recognizing so far unrecognized disease using a screening test, in particular case using the mammographic examination method. The high price of a single mammogram and the relatively large population of the women who need to be examined make screening challenging, especially for less developed countries such as the Republic of Serbia. Within this paper an analysis of available equipment for breast cancer screening – mammography in the Republic of Serbia was performed. As a result, series of choropleth maps were made, from which potentially problematic areas in the Republic of Serbia can be determined. All processing is done using the "R" programming language, and all used data are available for free download and use., Скрининг рака дојке подразумева препознавање до тог тренутка непрепознате болести коришћењем скрининг теста, методом мaмогрaфског прегледа. Висока цена појединачног мамографа, а релативно велика популација жена коју треба прегледати, чине организовани скрининг изазовом, посебно за слабије развијене државе попут Републике Србије. У оквиру овог рада извршена је анализа расположиве опреме за скрининг рака дојке – мамографа у Републици Србији. Као резултат, направљена је серија хороплет карата на којима се одговарајућом скалом боја могу уочити потенцијално проблематичне области у Републици Србији. Сва обрада је извршена коришћењем „R“ програмског језика, а сви искоришћени подаци су доступни за слободно преузимање и коришћење.

The market value of apartments is, as the name itself suggests, defined by the sellers and the buyers through supply and demand – elements that collectively make up the market. Observing a large number of factors affecting the price of real estate is not an easy job. Price formation depends on both the characteristics of the apartment and the buyer’s value-system. The basic question that a rational customer asks himself is "why would I pay a larger sum of money for the same or practically same thing than what someone else paid for it just recently?". This fact leads to the conclusion that it is necessary to know the characteristics and prices of the real estates traded in the near past and in the close surrounding. A comparative way of customer’s thinking is the basic principle for defining one such model. This is a necessary but not sufficient condition. Models based on the machine learning algorithms (among them k-Nearest Neighbors algorithm) require having a larger amount of data, so that the made conclusions can be reliable, accurate, and precise., Tržišnu vrednost stanova, kao što sama reč govori, definišu prodavci i kupci kroz ponudu i tražnju, koje u osnovi i čine samo tržište. Sagledavanje velikog broja faktora uticaja na cenu nepokretnosti nije nimalo lak posao. Formiranje cena zavisi kako od karakteristika stana, tako i od sistema vrednosti kupaca. „Zašto bih ja za istu ili sličnu stvar platio veći iznos nego što je neko drugi platio u neposrednoj prošlosti“ jeste osnovno pitanje koje racionalan kupac postavlja sebi. Ova činjenica dovodi do zaključka da je potrebno znati karakteristike i cene nepokretnosti koje su oglašene ili prometovane u neposrednoj prošlosti u bliskom okruženju. Komparativni način razmišljanja kupca je osnovni uslov i princip za definisanje jednog ovakvog modela. Ovo je neophodan, ali ne i dovoljan uslov. Modeli bazirani na algoritmima mašinskog učenja, kao što je i k-najbližih suseda, podrazumevaju poznavanje nešto veće količine kvalitetnih podataka, kako bi doneti zaključci bili pouzdani, tačni i precizni.

One of the dimensions describing accessibility to health services is its spatial component. This paper presents the methodology of using GIS technologies for the analysis of existing locations of health institutions in Serbia. The methodology includes determining the coordinates of hospitals using the geotagging, on the basis of which isochrons are created with 10 minutes time interval. For that purpose, the road network and functionalities provided by HERE Maps and its APIs are used. This service is selected since it offers high quality and complete data related to the network of roads in the territory of interest. Taking demographic data into account, the goal is to examine the impact that the distribution of institutions has on the population, first of all as the percentage of the population living at a certain distance from the nearest institution. The obtained results can be significant for future development, as critical spots with poor accessibility can be identified. These locations are suitable for the construction of new health care facilities., Jedna od dimenzija koje opisuju pristupačnost zdravstvenim uslugama jeste prostorna komponenta. U ovom radu je predstavljena metodologija korišćenja GIS tehnologija za potrebe analize postojećih lokacija zdravstvenih ustanova u Srbiji. Metodologija obuhvata određivanje koordinata bolnica u postupku geotagovanja, na osnovu kojih se kreiraju izohrone s vremenskim intervalom od 10 minuta. Tom prilikom se koriste putna mreža i funkcionalnosti koje pruža HERE Maps u okviru svojih API-ja. Ovaj servis je odabran zato što nudi kvalitetne i kompletne podatke koji se odnose na mrežu saobraćajnica teritorije od interesa. Uzimajući u obzir demografske podatke, cilj je sagledavanje uticaja rasporeda ovih ustanova na stanovništvo, najpre u pogledu procenta stanovništva koji živi na određenoj udaljenosti od najbliže ustanove. Dobijeni rezultati mogu biti značajni za budući razvoj, s obzirom na to da se mogu utvrditi kritična mesta na kojima je pristupačnost loša. Upravo te lokacije jesu pogodne za izgradnju novih zdravstvenih ustanova.

This paper presents the possibility of applications of GIS technologies on remote sensing data in order to understand the trends of the mine expansion and thereby enable putting these processes under control. The proposed solution includes creating a web mapping service that provides the opportunity for an interested user to gain insight into the status of the mine excavation in different epochs, as well as an overview of the changes that occurred during the period between certain two epochs. The final web service is in the form of a geoportal and has a set of functionalities that meet the needs of the different profiles of users. The example shows оpen-pit copper mines of copper mining and smelting complex located in Bor, Serbia., У раду је предочена могућност примене ГИС технологија над подацима даљинске детекције, са циљем да се сагледају трендови ширења копова и омогућило увођење ових процеса под контролу. Предлог решења јесте креирање веб-картографског сервиса који заинтересованом кориснику омогућује да добије увид у стање површинских копова у различитим епохама, као и преглед промена које су настале у периоду између одређених двеју епоха. Коначни веб-сервис има форму геопортала и поседује сет функционалности које задовољавају потребе корисника различитих профила. За пример су узети површински копови рудника бакра Рударско-топионичарског басена Бор.

Air temperature is one of the most often measured meteorological parameters. Precise air temperature measurements are done in meteorological stations, whose spatial distribution may be uneven and for some applications unsuitable. Therefore, in order to provide the necessary temperature model for the appropriate applications, prediction of air temperature is performed. This paper presents a methodology of stochastic prediction of air temperature using the programming language "R". An example of the analysis and selection of the optimal set of predictors necessary for the prediction of temperature is provided. As "R" is basically statistical package, at the same time its possibilities as a GIS tool are shown., Температура ваздуха представља један од метеоролошких параметара који се најчешће мере. Прецизна мерења температуре ваздуха врше се у метеоролошким станицама, чији просторни размештај може бити неравномеран и за поједине примене неодговарајући. Због тога се прибегава предикцији температуре ваздуха, како би се обезбедио неопходни температурни модел за одговарајуће примене. У оквиру овог рада приказана је техника стохастичке предикције температуре ваздуха користећи се програмским језиком „R“. Приказан је и пример анализе и одабира оптималног сета предиктора неопходних за предикцију температуре. Како „R“ у основи представља статистички пакет, истовремено су приказане и његове могућности коришћења као ГИС алата.

The airborne laser scanning has been proven as very efficient method for collecting the surface data. As ALS collects extremely large amount of data, efficient use of this data involves the use of some semi-automatic or automatic methods. For this purpose, large number of solutions, different in scope, cost and efficiency are available on the market. One of the available solutions is LAStools software package. Focus of this paper is on the functionalities of the LAStools software package, which are tested and assessed through the experiment. The experiment covered creation of standard topographic products from ALS point cloud using LAStools. At the end of this paper, conclusions about the possibilities of the LAStools software package are made, with a special overview of the advantages and disadvantages, the possibilities and shortcomings., Laserska metoda snimanja iz vazduha se pokazala kao veoma efikasna za prikupljanje podataka o površi terena. Zbog izuzetno velike količine podataka koja je nastaje avio-laserskim skeniranjem, efikasno korišćenje ovih podataka podrazumeva korišćenje nekih poluautomatskih ili automatskih metoda. Za potrebe obrade podataka laserskog skeniranja na tržištu je na raspolaganju veliki broj rešenja, različitih po mogućnostima, ceni i efikasnosti. Jedno od takvih rešenja predstavlja LAStools softverski paket. Tema ovog rada su funkcionalnosti LAStools softverskog paketa, koje su eksperimentalno ispitane i ocenjene. Eksperiment je podrazumevao kreiranje standardnih topografskih produkata iz avio-oblaka tačaka primenom LAStools-a. Na kraju rada su doneti zaključci o mogućnostima LAStools softverskog paketa, uz poseban osvrt na prednosti i mane, mogućnosti i nedostatke.

Vehicle routing plays a major role in the industry, primarily in companies that organize the transport of goods to end-users. The theoretical background of the vehicle routing problem has been known for many years and it has been the basis for developing a lot of commercial software solutions. However, in practice, there is a barrier in the form of the lack of affordable software solutions. The difficult access to quality and reliable spatial data relating to the road network is also a limitation. This paper looks into the possibilities of applying open source software to solve this NP-difficult problem. The free spatial data from OpenStreetMap, a joint project of the virtual community, was used as a basis for modeling the graph of the road network. The experiment was carried out over the data on vehicles and users of the specific retail chain and relates to the territory of Serbia., Rutiranje vozila ima veliku ulogu u industriji, prvenstveno u kompanijama koje se bave organizovanjem transporta dobara do krajnjih korisnika. Teorijska pozadina problema rutiranja vozila je već dugi niz godina poznata i na osnovu nje je razvijeno mnoštvo komercijalnih softverskih rešenja. Međutim, u praksi se javlja prepreka u vidu nedostatka pristupačnih softverskih rešenja. Ograničenje predstavlja i otežan pristup kvalitetnim i pouzdanim prostornim podacima koji se odnose na putnu mrežu. U radu su ispitane mogućnosti primene softvera otvorenog koda za rešavanje ovog NP-teškog problema. Kao osnova za modelovanje grafa mreže saobraćajnica, uzeti su slobodni prostorni podaci OpenStreetMapa, udruženog projekta virtualne zajednice. Eksperiment je izvršen nad podacima o vozilima i korisnicima jednog trgovinskog lanca i odnosi se na područje Srbije.