Admir Mulahusic

Prof. Dr. Admir Mulahusic

University of Sarajevo, Sarajevo, Bosnia and Herzegovina, Federation of, Bosnia and Herzegovina
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2018 in Survey Review
Verified
Journal Article
Closed access
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
NTNedim Tuno
Nedim Tuno
DGDubravko Gajski
Dubravko Gajski
JTJusuf Topoljak
Jusuf Topoljak
Laser scanning does not provide unlimited geometrical accuracy and integrity when scanning complex objects. Scanning systems have a minimum and maximum range in which they operate, depending on the technical characteristics. Scanning below or above these limits results in gross errors and registering of incorrect data. Laser scanners can have difficulties with certain materials such as marble and reflective surfaces. This paper presents the results of laser scanning of a complex monument of cultural and historical heritage using two different types of terrestrial laser scanners. Afterwards, the comparison and analysis of the results are shown. The scanners used were terrestrial laser scanners Faro Focus 3D (phase mode distance measurements) and STONEX X300 (pulse mode distance measurements).

1 August 2017 in Journal of Surveying Engineering
Verified
Journal Article
Closed access
NTNedim Tuno
Nedim Tuno
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
DKDušan Kogoj
Dušan Kogoj
This paper presents an attempt to reduce positional errors in digital cadastral maps produced by digitization (scanning, georeferencing, and vectorization) of existing Bosnian-Herzegovinian analog (paper-based) maps. The geometric content of the digital cadastral maps generated by the aforementioned procedure is encumbered by nonuniform and irregularly distributed positional distortions. Errors created during the original elaboration of the analog maps (based on hand drawings using the drafting instruments) cannot be corrected through the geometric transformation of the cadastral map with the use of common (tie) points on the map coordinate grid. This study focused on the elimination of errors in the original map drafts through better selection of common points, with the aim of obtaining a homogeneous spatial accuracy of cadastral maps. With the use of the flexible thin plate spline (TPS) transformation model, which includes information on systematic distortions caused by errors of the original mapping process, the authors made a significant step toward the enhancement of the positional accuracy of boundary points in the digital cadastral maps. The use of TPS transformation reduces heterogeneity of each cadastral map, and maps are efficiently georeferenced to the state plane coordinate grid. Digital cadastral maps generated by reconstruction of original state survey measurements are typically more accurate than those obtained by digitizing scanned maps, and these types of maps were not considered in this study.

22 July 2022 in Ecological Informatics
Verified
Journal Article
Closed access
MĐMuamer Đidelija
Muamer Đidelija
NKNedim Kulo
Nedim Kulo
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
NTNedim Tuno
Nedim Tuno
JTJusuf Topoljak
Jusuf Topoljak

22 January 2022 in Journal of Cultural Heritage
Verified
Journal Article
Closed access
NTNedim Tuno
Nedim Tuno
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
JTJusuf Topoljak
Jusuf Topoljak
MĐMuamer Đidelija
Muamer Đidelija

19 October 2023 in Environmental Monitoring and Assessment
Verified
Journal Article
Closed access
PDF file
MĐMuamer Đidelija
Muamer Đidelija
NKNedim Kulo
Nedim Kulo
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
NTNedim Tuno
Nedim Tuno
JTJusuf Topoljak
Jusuf Topoljak

18 December 2023 in Poljoprivreda
Verified
Journal Article
Open access
PDF file
Dorijan RadočajDorijan Radočaj
Dorijan Radočaj
NTNedim Tuno
Nedim Tuno
Admir MulahusicAdmir Mulahusic
Admir Mulahusic
MJMladen Jurišić
Mladen Jurišić
Soil fertility is pivotal for agricultural productivity, and iron (Fe) is a critical micro- nutrient essential for a successful crop development. This study investigates a potential of ensemble machine-learning methods in geospatial prediction of soil Fe in Croatia. Using a dataset of 686 soil samples, three individual machine-learning methods, including the extreme gradient boosting (XGB), support vector machine (SVM), and Cubist, as well as their ensemble, were evaluated for the soil Fe predi- ction. The ensemble method outperformed the individual models, exhibiting a higher prediction accuracy expressed by the coefficient of determination (R2 = 0.578), with a lower root-mean-square error (RMSE = 0.837) and the mean absolute error (MAE = 0.550). The soil clay content emerged as the most influential predictor, followed by the sand content, pH values, and select bioclimatic variables. This study’s results demonstrate the effectiveness of ensemble machine learning in an accurate predicti- on of soil Fe content and contribute to an informed decision-making in sustainable agricultural land-use planning and management. By including the complementary machine-learning methods into an ensemble with the representative environmental covariates, a geospatial prediction aids to a reliable comprehension of soil proper- ties and their spatial variability.