Tahsin Yomralioglu

Object-based classification with rotation forest ensemble learning algorithm using very-high-resolution WorldView-2 image

Machine learning algorithms reported to be robust and superior to the conventional parametric classifiers have been recently employed in object-based classification. Within these algorithms, ensemble learning methods that construct set of individual classifiers and combining their predictions to make final decision about unlabelled data have been successfully applied. In this study, performance and effectiveness of a novel ensemble learning algorithm, rotation forest (RotFor) aiming to build diverse and accurate classifiers, was investigated for the first time in object-based classification using a WorldView-2 (WV-2) satellite image. Also, the combination of satellite imagery and ancillary data (i.e. normalized difference vegetation index and principal components) were assessed. Random forest (RF), support vector machine (SVM) and nearest neighbour (NN) algorithms were also used as benchmark classifiers to evaluate the power of RotFor. The classification results confirmed that integration of ancillary data increased the classification accuracy in comparison to using solely spectral bands of WV-2. While RotFor and SVM generally produced similar results, they outperformed the RF and NN based on McNemar’s and Wilcoxon’s signed-rank test of statistical significance results.

Geo-Relationship between Cancer Cases and the Environment by GIS: A Case Study of Trabzon in Turkey

Cancer is an important health issue in Turkey because it ranks as the second cause of death in the country. Examination of the relationships between the distribution of cancer cases and geo-environmental factors is significant in determining the causes of cancer. In this study, GIS were used to provide data about the distribution of cancer types in Trabzon province, Turkey. To determine the cancer occurrence density, the cancer incidence rates were calculated according to local census data, then a cancer density map was produced, and correlations between cancer types and geographical factors were examined.

Re-engineering of Turkish land administration

Abstract The role assigned to cadastral systems has evolved over time from supporting taxation to assisting the land market, land management and sustainable development. This change has forced countries to re-engineer their traditional cadastral systems into land administration systems. Governments need to develop their own solutions in the re-engineering process for their own circumstances. In this context, this paper examines the findings of academic research carried out to analyse the efficiency of the current Land Administration System (LAS) in Turkey and then to develop a new vision for the future of the Turkish LAS. The analysis shows that there is a need for re-engineering the Turkish LAS. The main characteristics of the vision, inspired by the case study research carried out in some European countries and the statements of some well known international reports, are a land law, a leading institution and a land information system.

A spatial multicriteria decision-making method for natural gas transmission pipeline routing

Abstract In accordance with current demands, the natural gas transmission pipeline (NGTP) is one of the most appropriate methods used in the distribution of existing reserves. Construction of long-distance pipelines requires large expenditures. Decreasing the time and cost of such construction and minimising environmental damage depend upon identifying the optimum routes from the onset of the project. Route determination is one of the most important steps in NGTP projects. The route determination process requires obtaining the existing graphic and non-graphic data from different institutions and organisations, as well as gathering, storing, querying and analysing non-existing data in an appropriate and efficient manner. Accessing the correct results rapidly by analysing such large data-sets can be achieved with spatial multicriteria decision-making technologies based on the geographic information system as an effective decision support tool. In this study, three methods were implemented for two NGTP projects of 103.60 and 60.89 km in length. At the end of this study, it was concluded that Spatial technique for order preference by similarity to ideal solution was the most effective of the three pipeline routing methods and that it could reduce project costs by approximately 21%.

Cadastre or Land Administration: A Case Study of Turkey

Cadastral systems have evolved over time primarily based on the changes in humankind to land relationship and technology. Land was regarded as a main symbol of wealth during the agricultural revolution and feudal system, and the cadastre recorded land ownership in this period. Cadastre became a tool to support land transfer and land markets during the Industrial Revolution when a process of strong physical ties to the land began. The post-World War II period with population boom generated awareness that land was a scarce resource. Countries preferred to address the scarcity with better planning in this period, and cadastre supported the planning process. Finally, in the 1980s, the focus was on wider issues of environmental degradation, sustainable development and social equity, and thus, land became a ‘scarce community resource’. This forced the extension of cadastres into land administration systems (Ting and Williamson 1999; Williamson 2001a; Bogaerts et al. 2002; Steudler et al. 2004; Bennett et al. 2013; Cete and Yomralioglu 2013).

Alternative suitable landfill site selection using analytic hierarchy process and geographic information systems: a case study in Istanbul

Solid waste management is an important environmental event for developed and developing countries. One of the most sensitive issues in waste management is the selection of a suitable location for the landfill site. This paper presents geographic information systems and analytic hierarchy process approach for selecting the alternative for landfill site selection in Istanbul, Turkey. Totally, eleven factors were used, and two main classification groups were set up in the study which is environmental and economic. Environmental factors are land use, geology, settlement areas, surface waters, population density, airports, and protected areas. Economic factors are slope, solid waste transfer stations, land values, and highways. The identified factors are separated by sub-criteria according to the appropriateness of solid waste landfill. One of the studies that has been made is the discussion of the creation of a dynamic model for the location selection of the solid waste dumping site. In light of legal restrictions, 80% of the study area is classified as unauthorized area. As a result of the study, 1% of the region is unsuitable, 4% is less suitable, 13% is suitable and 2% is very suitable and the digital map bases leading the decision makers were created.

A Crime Prevention System in Spatiotemporal Principles With Repeat, Near-Repeat Analysis and Crime Density Mapping: Case Study Turkey, Trabzon

In this study, we investigated crime events with repeat and near-repeat analysis for Turkey’s Trabzon city’s crime data after standardization process on raw crime data. First, a new crime geodatabase model was created. All types of recorded crime data for events between the years 2010 and 2014 were standardized, generalized, and Geo-referenced. We gave certain locations to crime events with geocoding techniques. Then, we created density maps of crime events with Kernel method in Geographic Information Systems (GIS). Repeat and near-repeat methods were tested on Burglary crime type in this geodatabase. Studies focused to applying prediction analysis besides showing current situation. These predictive analyses may be applied for all the security, intelligence, or defense departments at local, national, or international levels.

Geospatial Analysis of Cancer Cases in the Eastern Black Sea Region of Turkey

Cancer has remained an important health issue in recent years. Examining variations of cancer cases temporally and spatially is necessary to develop strategies to combat its occurrence and to put cancer control programmes into practice. Creating cancer maps is necessary for obtaining information such as the location and frequency of cancer cases, the geographic distribution of cancer types and the location of the highest densities of cases. Consequently, creating more reliable and precise data infrastructures will increase the number of accurate decision making options available and aid in determining how and where to implement control strategies.