فهرست مطالب h. ashoori

Texture quantization is a useful method for extracting spatial relevance between pixels, which is used in the human brain for image interpretation. Aside from spectral bands, textural features of high spatial resolution image can be used to improve classification accuracy. Finding proper textural features among available features is important for special case studies.

In this paper, two methods based on genetic algorithm (GA) are introduced to choose efficient features. The first is binary GA, which improves classification accuracies through selecting the best textural features. The second one is GA with a variable number of selected features in a refined and full feature space. Results show that the best combination does not necessarily consist of features with improved individual accuracy.

The proposed methods have better accuracy, less number of features, and less computational time when comparing with the simple GA. They could be used based on the number of spectral bands, number of generated features, and train and check pixel number. Second method needs more prerequisite time and could be used for images with fewer bands, train and check pixels, and generated features, because increasing these items increase computational time very much. Second method could be used in large images with more train and check pixels but led to more selected features.

Results obtained on three datasets indicate 7.7 to 50.48 percent improvement in mean accuracy.

The alteration in the landform pattern leads to changes in other landscape parameters such as soil, geology, and vegetation. Hence, the study of landforms and the investigation of factors that influence their formation and evolution are significant scientific disciplines in the fields of geomorphology and pedology. Climatic conditions with influencing on the geological processes, in conjunction with topographic features and the characteristics of parent materials, play an important role in forming and transformation of landforms.

In this research, the landforms of the study area were delineated using a digital elevation model with a resolution of 10 meters and the SAGA software based on the topographic position index. Subsequently, in two landforms, namely the plain and the open slope, which exhibited the highest degree of repeatability in the region, excavation and sampling were conducted, and the physicochemical properties and parameters such as parent material, elevation, and slope percentage were examined for each profile.

The studies indicated that in the plain landform the variation of slope is low and its maximum is three percent. This subject proves the transportation of parent materials from higher geomorphic surfaces accumulated in lower areas, resulting in the formation of this specific type of landform which is suitable for agriculture. Moreover, in the open slope landform with relatively high slope variations, erodible marl parent materials underwent alterations and transformations over time, leading to the development of distinct geomorphic surfaces. In this landform, the percentage of clay is reduced with depth, except for the profiles that have irregular patterns. Because of almost high slope, the soil depth of this landform is low. The reason for this low depth of soil is that the position of slope has the most important effect on the soil depth. Therefore, the positions on the top of the slope have low depth soils than the position on the bottom of the slope.

Topography has been known as a major factor in evolution and development of soils. The studied landform of this research showed that not only topography has a direct role in pedogenic processes but also parent materials are very importance in change of the processes and in landform construction. In this research, the landforms of the study area were separated based on topographic position index. In topographic position index, height and slope are used as the basic parameters for analyzing and classification of the landforms. Surveying the physical and chemical characteristics as well as assessing the parent material, height and slope percentage of the dug-up profiles in the more consequential landforms of the study area revealed that parent materials and slope have effective roles in creation of the landform. However, in the study area because of the arid and semi-arid conditions of the region and reduction of aeration and washing, the role of slope in creation of landforms was stronger than the role of parent materials. Thus, simultaneous study of the role of slope and parent materials in the regions with high aeration and active processes in geomorphic surface changes may create a broad context of research on creation of landforms.

In this paper, a neural network backstepping controller is designed for the control of a  reentry vehicle. The backstepping control system is applied to the nonlinear six degree of freedom dynamics of the reentry vehicle for tracking the desired input. The neural network is used for estimation of nonlinear parts of backstepping controller during entry to atmosphere and to estimate the nonlinear terms as well as the external disturbances. Numerical simulations have been performed to verify the performance of the proposed control  method.