kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
Classification of Polarimetric SAR Images Based on Combining Support Vector Machine Classifier and Markov Random Fields
1
18
FA
Ali
Masjedi
K.N.Toosi University of Technology
amasjedi@mail.kntu.ac.ir
Y
Yasser
Maghsoudi
K.N.Toosi University of Technology
N
Mohamad Javad
Valadan Zoej
K.N.Toosi University of Technology
N
10.29252/jgit.3.4.1
Recent studies show that image classification techniques which use both spectral and spatial information are more suitable, effective, and robust than those that use only spectral information. Although late model support vector machines (SVMs) have been providing accurate results in the studies, this method is intrinsically non-contextual, which represents significant limitation in image classification. In this paper, we propose a rigorous framework which integrates SVMs and Markov random field models in a unique formulation for spatial contextual classification of various species of forest trees, ground vegetation, and water using polar metric synthetic aperture radar data. Genetic algorithm is employed for selecting appropriate features and automatic estimation of optimal parameters. Comparison of the accuracy of the proposed method with baseline methods was performed. Comparison of the accuracy of the proposed method with some other methods was carried out. The results show that this algorithm allowed approximately 19%, 14%, 11%, 5% and 3% increase in overall accuracy with respect to the Wishart, WMRF, SVM, aMRF and MSVC methods, respectively.
Markov Random Fields, Support Vector Machine, Contextual Image Classification, Spatial Information.
http://jgit.kntu.ac.ir/article-1-303-en.html
http://jgit.kntu.ac.ir/article-1-303-en.pdf
kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
Comparing the efficiency of GA and PSO metaheuristic algorithms in optimal allocation of water to agricultural farms in water scarcity condition
19
42
FA
Bahram
Saeidian
K.N.Toosi University of Technology
Bahram_saeidian@yahoo.com
Y
Mohamad Saadi
Mesgari
K.N.Toosi University of Technology
N
Mostafa
Ghodousi
K.N.Toosi University of Technology
N
10.29252/jgit.3.4.19
Water requirements in agricultural production sector have increased in recent years. This necessitates the adequate management of limited water resources. Since agriculture is the main water consumer, finding proper methods and models for the allocation of water to farm lands is vital to the management of available water. The goal of this study is to find ways to optimize the allocation of water to the farms in water scarcity condition, using Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), and to compare their capabilities. First, the needed data was generated and prepared using analysis functions of GIS. Then, the water attainable from several resources and water required by different farms were computed. Afterwards, objective function was calculated using the land area, the crop price and yield response factor. The allocation of water to lands was optimized such that the total economic profits of all farms were maximized. The profits resulted from PSO were slightly about 106938976 Rial higher than GA. In addition, the convergence of PSO was much faster than GA. The repeatability test showed higher stability of PSO (The variance of the normalized values for GA and PSO are 0.151 and 0.104 respectively. In two different scenarios, termination conditions are considered as to reach a specified run number and to reach a defined accuracy of answers. For both scenarios, the execution times of PSO were less than GA (320 and 272 seconds correspondingly). In general, PSO performance is better than GA regarding all evaluation criteria. The only drawback of PSO is that it allocates no water to some of the farms. In other words, the algorithm suggests that for maximizing the economic revenue, some of the crops and farms should be left without irrigation.
Agricultural Water Allocation, Water Scarcity, GIS, GA, PSO.
http://jgit.kntu.ac.ir/article-1-304-en.html
http://jgit.kntu.ac.ir/article-1-304-en.pdf
kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
An Online Approach for Spatio-Temporal Prediction of Air Pollution in Tehran using Support Vector Machine
43
63
FA
Zeinab
Ghaemi
K.N.Toosi University of Technology
zghaemi@mail.kntu.ac.ir
Y
Mahdi
Farnaghi
K.N.Toosi University of Technology
N
Abbas
Alimohammadi
K.N.Toosi University of Technology
N
10.29252/jgit.3.4.43
Due to its critical impact on human health and the environment, monitoring and prediction of air pollution have become an important issue during the past decades. Non-linear behavior of air pollution in one hand and high volume of required data on the other hand, intensifies the complexity of air pollution prediction especially in online applications. In order to overcome the deficiencies of traditional methods, this study proposes an online algorithm based on Support Vector Machine (SVM) to predict the time series of air pollution in the city of Tehran, Iran. Prediction is performed on the basis of time series data of pollutant concentrations, weather condition, and geographical parameters such as traffic, surface curvature and local altitude. Evaluation of the outputs shows that prediction errors are within an acceptable range and the online algorithm has an outstanding speed in comparison with the conventional SVM. The overall accuracy of 0.71, RMSE of 0.54 and R2 of 0.81 prove the efficiency of the proposed algorithm to develop a system to dynamically predict Tehran’s air pollution in advance.
Online air pollution prediction, Support Vector Machine, Time series, Geographic Information System, Big data.
http://jgit.kntu.ac.ir/article-1-305-en.html
http://jgit.kntu.ac.ir/article-1-305-en.pdf
kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
Spatial Demographic Distribution Zoning of a City with Area Interpolation Method using Image-based Geo-spatial Information System-Case Study: Tehran City
65
82
FA
Reza
Aghataher
Azad University
Reza_Aghataher@yahoo.com
Y
Najmeh
Neysani Samany
University of Tehran
N
10.29252/jgit.3.4.65
Demographic characteristics of a city are of a primary needs for urban decision makers. These demographic data, however are prepared or revised over long periods of e.g. about five to ten years. During these periods, the population is estimated based on subjective and approximate data like migration, along with more precise and objective data like birth and death. The result, which is subjective and imprecise data, cannot be used for deriving population distribution. Considering the need for more objective and precise estimation of population and population distribution of cities, this paper provides a spatial methodology. The premise is that the spatial characteristics of land uses and population density and population have specific relations. By defining these relations and using a precise and objective estimation of the land uses, we can project the population density and population. This methodology improves the population estimation by providing higher level of precision and objectiveness. In this paper, we introduceour findings of specific relations between land uses, e.g. settlement pattern and the human attitude to live near other human settlements and spatial continuous distribution of population. These relations are implemented in a geographical information system (GIS) using estimation-maximization (EM) approach and population density and distribution of the city Tehran, Iran is derived. The EM is used here as an area interpolation approach. The land use data are extracted from IRS-D satellite images. Besides, strategies are described in this paper dealing with the problem of lacking the spatial data.
Topology, Demographic data, Satellites Image, Area Interpolation
http://jgit.kntu.ac.ir/article-1-306-en.html
http://jgit.kntu.ac.ir/article-1-306-en.pdf
kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
An algorithm for compression of a spatio-temporal trajectory preserving its semantic nature
83
95
FA
Somaie
Aghel Shahneshin
University of Tehran
N
Simin Sadat
Mirvahabi
University of Tehran
N
Rahim Ali
Abbaspor
University of Tehran
abaspour@ut.ac.ir
Y
10.29252/jgit.3.4.83
A common way to store information of spatio-temporal moving objects is to display the path of the objects as the form of a three-dimensional trajectory using the geographic location and time. In recent years, extensive research has been done on the trajectories. These studies have focused mainly on geometric aspects of trajectories. However, semantic trajectory is a relatively new concept that has been developed with the purpose of effective semantic analysis on captured data. In semantic trajectory, which is a secondary display of geometric trajectory, the movement of object is described as series of stop-and-move. Production of semantic trajectory from the collected raw data is a process with several steps. Due to the huge amount of data, one of the important processes is reducing the number of points of trajectory with maintaining the required accuracy by using compression techniques. However, data reduction techniques commonly are based on linear simplification and are not able to protect stop and move of trajectories. In this paper, a data reduction technique is presented which is based on combination of two distance functions for approximation of semantic trajectory. The first distance function has used speed of points to calculate the approximation error of trajectories. The second function is based on the development of well-known Douglas-Peuker algorithm, which assumes constant acceleration to calculate the approximation error. The proposed algorithm is implemented on real trajectory data and the results show improved performance compared with other algorithms in preservation of the stop and move of trajectories.
Semantic Trajectory, compression, Stop-Move Model, Ev-E2
http://jgit.kntu.ac.ir/article-1-307-en.html
http://jgit.kntu.ac.ir/article-1-307-en.pdf
kntu
Engineering Journal of Geospatial Information Technology
2008-9635
3
4
2016
3
1
Determining Effective Factors on Forest Fire Using the Compound of Geographically Weighted Regression and Genetic Algorithm, a Case Study: Golestan, Iran
97
120
FA
Amin
Raei
University of Tehran
N
Parham
Pahlavani
University of Tehran
pahlavani@ut.ac.ir
Y
Mahdi
Hasanlou
University of Tehran
N
10.29252/jgit.3.4.97
Determining the effective factors on fire is so important, because the plenty areas of forests around the world are destroyed every year by fire. It helps us to identify most dangerous locations and times in forest fire. Hence, we can prevent many of driving factors of forest fire by law enforcement, efficient forest management policies and more supervision. In the current study, we identified the impressive factors on the fire in Golestan forest using the compound of Geographically Weighted Regression (GWR) method and Genetic Algorithm that is suitable for the spatial regression problem, because it obtains the effective factors considering the autocorrelation and non-stationarity properties of spatial data. In this study, three different fire areas as well as two kernels of Gaussian and Tricube for weighting of GWR were used that for these three fire areas resulted to R2=0.9538, R2=0.9990, and R2=0.9903 for Gaussian kernel and R2=0.9931, R2=0.9999, and R2=0.9980 for Tricube kernel, respectively. This research shows that both of the biophysical and anthropogenic factors have significant effects on forest fire in our study areas. In biophysical factors, the elevation, the aspect, the minimum and mean tempreture and in anthropogenic factors, the landuse and the distance from the residential areas were identified as the most impressive factors. Weighting by Tricube kernel concluded to more precise results.
Forest Fire, Geographically Weighted Regression, Genetic Algorithm, Golestan Forest
http://jgit.kntu.ac.ir/article-1-308-en.html
http://jgit.kntu.ac.ir/article-1-308-en.pdf