فصلنامه سنجش از دور و GIS ایران
سال پنجم شماره 3 (پیاپی 19، پاییز 1392)

The first as well as the foremost phase in water quality management is zonation the quality, because it provides researchers with proper understanding of the processes and the changes of pollution, regarding the specific temporal and particular conditions. The present research has been designed to study the zonation of pollution quality of water in Simineh Rood River using Artificial Neural Networks (ANN) and Geography Information System (GIS). Qualitative data used in this study were collected by sampling in three seasons: spring and autumn of 1387 and spring of 1388. The data were then simulated by using QUAL2K model. The output was then compared with actual data and parameters Nitrate, Dissolved Oxygen, and electrical conductivity related to fall 1387 were utilized target data in neural network models. Data related to land users, geology, erosion capability, and population centers related to Simineh Rood basin were introduced to neural network models as input data. In the present study, five structures of FFBP neural networks model have been used. Results of the best structure have been compared with the output resulted from multivariable regression model, which resulted in proving superiority of the cited neural network model. The result of this research indicated that FEBP network with 4-40-40-3 structure have the best ability. This structure network considers to correlation coefficient in test data, validated data and education data and RMS error in compare to other stricter is preferred. Then used neural network model can be useful in finding the mentioned relation. Generally speaking, the result of this research shows portional ability of neural network in order to river water pollution.

Matching is one of the challenging problems in remote sensing and photogrammetry. This process is widely used for many purposes in remote sensing such as multispectral classification, environment monitoring, change detection, image mosaicing, etc. Many methods have been presented for matching; one of these methods is global matching by Hopfield neural network. Most researches carried out include object recognition and close range images and up to now it was not implemented on aerial and satellite images. The main goal of this paper has been implementing the matching method using Hopfield neural network on various aerial and satellite images. In order to perform the affine invariant matching. The fourth-order Hopfield neural network has been applied and the experimental results achieved on two pairs of satellite images showed the high efficiency of the mentioned method.

Sand dunes of Gavkhouni (Varzaneh Erg) are active and semi-active ones in the southeast of Isfahan province and west of Gavkhouni international wetland. They play key role in increasing dust storms and causing damages to roads in the region. In this study, sand dunes changes have been detected using satellite MSS, TM, ETM and LISS III images during a 32 year period. In pre-processing stage, all images were geometrically registered with RMS error of less than one pixel. Land use/cover maps of the region were produced using image processing techniques including principle component analysis, false color composite, NDVI vegetation index and supervised classification applying maximum likelihood classifier. The accuracy assessment of the classified maps indicated that there were more than 89% agreements between the satellite and field data. Comparison of spatial distribution of sand dunes in different times using post classification method, revealed that the area of sand dunes has been increased to nearly 5086 ha (from 14475 to 19561ha) in past three decades. This increasing has been observed in the inter-dune areas, mostly in central and southern sections of the Erg.

The main step in tourism planning is selecting the attractions and determining the best ways to reach over (visit) them. In this research, a recommender system for personalized tourism web browser has been designed and implemented. The system makes tourism planning in accordance with the interests and preferences for each individual in specified time frame. The main advantage of the mentioned system is simultaneously paying attention to the user's interests, route planning and time management in tourism planning. In developing this system the authors have used the integration of methods based on spatial decision support systems and spatial analysis functions and as well as various technologies for the Web Embed this system. In order to evaluate, the authors have implemented the system for tourist places in region one, Tehran. Results of system performance showed that the system helps to the tourists by selecting attractive places accordance with user's interests and available time zones determine the best way to visit these places and also to provide various information on the mentioned sites.

Human has always inspired by his environment to challenge complex issues. This is exposed in many approximation algorithms; from Darvin theory to numerous swarm intelligence procedures. Due to the importance of Traveling Salesman Problem (TSP) in combinatorial optimization, numerous methods are proposed to solve the problem. This paper firstly extends Ant Colony Optimization (ACO) by identifying and optimizing its efficient parameters. Then, a novel method is presented to solve TSP in large scales, based on the improved ACO and Genetic Algorithm (GA) operators. To assess the algorithm, its results are compared with two other procedures, namely ACO and GA in routings between centers of various provinces. It is demonstrated that by using the proposed algorithm, the results have been improved; the running times as well as the necessary storage for saving acquired data in different conditions are reduced. Due to paying attention to the optimum and constant results of the proposed algorithm as well as the importance of improving the services in GIS, the usage of the algorithm in tourism industry is presented.

Optimal natural resources management depends on reliable as well as up-to-date data. For this objective, land use map is among the important sources of information on the natural resources management. The aim of present study is to compare two methods of pixel-Base and object-oriented classification in land use mapping with using ETM image in Malekshahi town, Ilam province. After supplying related image and geometric and radiometric corrections implement on image, the authors used tow method classification to land use mapping. To assess the accuracy of classification method they used index of overall accuracy, kappa coefficient, producer accuracy and user accuracy. The results showed that the object-oriented classification method has more resolution in comparison to the pixel-based classification method. The results of determine accuracy showed that method of object-oriented in tow index of overall accuracy and kappa coefficient with (respectively) 96 percent and 93 percent was more accuracy related to pixel-based classification method. Based on the results the forest and grassland covers about 98 percent of this town. The result of this study suggested that used from object-oriented classification method to production of land use map.