List of Articles طبقه بندي

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - Determining optimal support vector machines in classification of hyperspectral images based on genetic algorithm
  farhad samadzadegan Hadis Hasani
  ۱٬۳۸۵ / ۵٬۰۰۰ Today, hyperspectral images are considered a powerful and efficient tool in remote sensing due to the wealth of spectral information and provide the possibility of distinguishing between similar complications. Considering the stability of support vector m More

  ۱٬۳۸۵ / ۵٬۰۰۰ Today, hyperspectral images are considered a powerful and efficient tool in remote sensing due to the wealth of spectral information and provide the possibility of distinguishing between similar complications. Considering the stability of support vector machines in spaces with high dimensions, they are considered a suitable option in the classification of hyperspectral images. Nevertheless, the performance of these classifiers is influenced by their input parameters and feature space. In order to use support vector machines with the highest efficiency, the optimal values ​​of the parameters and also the optimal subset of the input features should be determined. In this research, the ability of the genetic algorithm as a meta-heuristic optimization technique has been used in determining the optimal values ​​of support vector machine parameters and also selecting the subset of optimal features in the classification of hyperspectral images. The practical results of applying the above method on the hyperspectral data of AVIRIS sensor show that the input features and parameters each have a great effect on the performance of support vector machines, but the best performance of the classifier is obtained by solving them simultaneously. In the simultaneous solution of parameter determination and feature selection, for Gaussian kernel and polynomial, 5% and 15% increase in accuracy was achieved by removing more than half of the image bands. Also, the gradual cooling simulation optimization algorithm was implemented in order to compare with the genetic algorithm, and the results indicate the superiority of the genetic algorithm, especially with the large and complicated search space in the simultaneous solution approach of parameter determination and feature selection. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - Clasification of custumers of internet services, using data mining algorithms
  farid norozi hamed kazemipoor
  10.7508/jstpi.2017.01.002
  Nowadays, the role of customers has shifted from followers of the producers to guiding them.That is why the classification of customers in targeting and customizing services and prioritization of companies products on the basis of profitability makes great help. Interne More

  Nowadays, the role of customers has shifted from followers of the producers to guiding them.That is why the classification of customers in targeting and customizing services and prioritization of companies products on the basis of profitability makes great help. Internet service providers in the market, are competing with a lot of competitors because investing in on communications and internet services are profitable.In order to progress in the market, it is necessary to offer new services and innovation.To get broader share of the market, the internet providers has got to have sufficient knowledge of the market and customers, retain existing customers and attract new customers.By classifying and clustering its customers, and while identifying and supporting its active and beneficial customers, such companies can remove their offbeat customers from services providing cycle.Using data mining algorithm, this research detecting and identifying of such customers, make the internet service provider closer to their goals. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - Effect of sequential pressure on petrophysical properties of carbonate reservoir rocks
  Ali Moradzadeh yaser Salimidelshad Ezatollah Kazemzadeh abbas Majdi
  Today, oil industry significantly relies on the precise determination of rock reservoir properties, which reduces the costs and risks of production planning. The reservoir rock always is compacted by pressure drop of the reservoir, which rises effective stress, reservoi More

  Today, oil industry significantly relies on the precise determination of rock reservoir properties, which reduces the costs and risks of production planning. The reservoir rock always is compacted by pressure drop of the reservoir, which rises effective stress, reservoir compaction and alterations of reservoir properties. As these pressure variations can considerably affect petrophysical properties, in this study, several carbonate reservoir rock samples with different fabric and porosity type (according to CT scan and Archie classification analysis) subjected to cyclic and short-term loading from 600 to 6000 psi. Their petrophysical and compressive properties including pore volume, permeability and compressibility were measured using CMS-300 apparatus. Moreover, structural analysis and heterogeneity of core samples were analyzed by CT scan images. By performing this study, it will be possible to identify the value of the hysteresis effect on the reservoir rock samples as a result of increasing and decreasing of the pressure during cyclic loading. The obtained results show that, pore volume and permeability are both decreased due to loading, whereas reduction of the permeability is several times than the pore volume ones. Moreover, this reduction of pore volume is less severe in vuggy porous samples that shows the effect of heterogeneity and porosity type on hysteresis. Also, the results obtained from the behavior of the reservoir rock under various pressure conditions can provide a suitable design for gas injection studies to enhance oil recovery and also natural gas storage. Manuscript profile