فهرست مطالب محمدرضا مومن زاده

Cervical cancer begins in superficial cells and over time can invade deeper tissues and surrounding tissues. This paper presents a creative idea of using an ensemble classification algorithm that improves the predictive performance of an artificial intelligence system based on cervical cancer screening. This study aimed to classify Pap-smear images by different machine learning methods to achieve high accuracy detection.

This study was performed on 917 Pap-smear images from the Herlev public database. In the feature extraction stage, 20 geometric features and 76 texture features were extracted. After that, using ensemble classification method, the images were classified into two categories (i.e., normal and abnormal) and then into seven categories (i.e., superficial epithelial, intermediate epithelial, columnar epithelial, mild dysplasia, moderate dysplasia, severe dysplasia and carcinoma) and the accuracy of the proposed method was evaluated.

The algorithm in the ensemble classification was able to achieve accuracy of 99.9% with a processing time of 0.028 second in the two-class classification and accuracy of 76.5% with a processing time of 0.033 second in the seven-class classification.

Based on the results, the designed algorithm can be used as a computer aided diagnostic tool to increase the accuracy and speed of predicting the risk of cervical cancer.

Practical Implications: 

 Cervical cancer is one of the most common cancers among women. Early diagnosis of the disease can save various costs and prevent the patients’ frequent visits to medical centers. This research proposed an artificial intelligence method for automatic classification of cervical cells and improving the accuracy of diagnosis.

Cervical cancer is one of the most common cancers among women worldwide, which can be diagnosed more quickly via using digital systems. The purpose of this study was to classify the cells in Pap smear test images into two types of normal and abnormal by using image processing to diagnose cervical cancers.

We used Herlev public database, which contained 917 cells. 35 geometric and 263 histologic features such as Gray Level Co-Occurrence Matrix (GLCM), Local Binary Pattern (LBP), and rotational gradient histogram were extracted from cell images. T test filter method was applied on the data set after extraction of geometrical and textural features. We used different classification methods such as support vector machine (SVM), decision tree (DT), k nearest neighbor (KNN) and ensemble classifiers.

The best results were for SVM classifier as 97.5% accuracy in two-class classification with 20 features.

Feature selection and feature extraction methods are very important for classify normal and abnormal cervical cell images. By optimizing and choosing the right methods, we can optimizing accuracy, and speed and error (2-3 percent).

Summary Metropolitan underground tunnels is increasingly used these days. Besides, Iran has strategic importance in the Middle East meanwhile risking always military attacks of hegemonic countries and local terroristic activities. Concerning the mentioned points, it is crucial to investigate and analyze such structures under explosive loadings. This research focuses on the most critical scenario of damage distribution in the tunnel covering cause by TNT explosion. Moreover, the effects of soil overburden height as well as the amount of explosive material is studied on the maximum stresses and deformations created in the covering of twin tunnels under 4 explosive loadings of 15, 30, 45 and 60 Kg TNT. At the end, the effect of soft soil rehabilitation is assessed on the improvement of tunnels covering response under explosive loading. Introduction Chio et.al (2006) studied the response of underground structures subjected to the explosion through nonlinear analysis [5]. In 2006, Gui et. al investigated the effects of ground surface explosion on the tunnel of Taipei Shongsan airport. Two dimensional solution of the problem by Gui et. al has been in the line of its simplification [6]. Lui has focused on the effects of explosion in New York subway. The conducted numerical investigations have been mainly two dimensional. The researchers mostly believe that plane strain assumption in the modeling is dramatically conservative in the explosion issue. Methodology and Approaches In this research, soil and tunnel have been subjected to the inside ground explosive loading in tri- dimensional form using ABAQUS6-11-1 finite element software. The explosive loading has been estimated through empirical relations of compression applied to the underground structure due to the explosion. Besides, the soil has been simulated by Druker Prager and the tunnel covering by Concrete Damage plasticity behavior models. Here, the effects of different parameters are investigated on the responses of twin tunnels under explosive loadings. Results and Conclusions The brief results of this investigation are as follows: 1- Increasing in the overburden height will cause the reduction of stresses and deformations in the covering of tunnels; 2- The most critical scenario of damage distribution in the tunnel section is in the overburden height of 10m under 60Kg TNT of explosive loading; the highest width of created crack is 91mm. the highest the height of soil overburden is, the more the created damage is in the tunnels covering under internal explosion; 3- The strength and stiffness of the ground should be rehabilitated in the soft soil surrounding the tunnel. The maximum stress is reduced for 44% with increasing the thickness of tunnel surrounding soil for 1m; 4- The maximum stress created in the tunnels covering is reduced by increasing the stiffness of soil. This reduction in the stress response is stopped in the status of increasing the thickness from 3m to 4m. 5- The stresses created in the tunnels covering are reduced with increasing the soil stiffness. The maximum stress remains approximately in a constant range in different values of soil strength.

Underground tunnels, particularly, have distinct seismic behaviour due to their complete enclosure in soil or rock and their significant length. Therefore, seismic response of tunnel support systems warrant closer attention. The geological settings in which they are placed are often difficult to describe due to limited site investigation data and vast spatial variability. Therefore, the parameters which govern the design are many and their variabilities cannot be ignored. A solution to this issue is reliability based analysis and design. These real conditions of variability can only be addressed through a reliability based design.
The concepts of reliability has been less considered by the researchers in the engineering analysis and design of tunnels and underground spaces. Laso et. al (1995) studied the reliability in the designing of tunnel lining. Quing Lu et. al (2013) evaluated the reliability of the rock tunnels with respecting to several statuses of rupture mode. The studies conducted on the reliability of tunnels, mostly ignored the seismic design parameters as well as the consideration of reliability in the parameters of the surrounding tunnel soil.
Methodology and Approaches :In this research, response surface method (RSM), the reliability concept of Hasofer-Lind and finite element method (FEM) are composed in order to investigate the reliability of the lining of shallow underground tunnels. For this purpose, an underground tunnel with the height of 5m has been subjected to 7 earthquake records using finite element software ABAQUS. The random variables considered for surface response method are soil dynamic elasticity module, cohesion and internal friction angle of the soil. The reliability index has been approximated for axial force, flexural moment, shear force and displacement of tunnel by conducting trial and error tests on the three mentioned parameters.
Results and The results obtained in this research are briefly summarized as follows:The reliability index value is lower in the tunnel lining under seismic loads for all obtained responses, comparing to those under static loading. In the other words, the reliability of soil and tunnel systems are reduced concerning the random nature and criticality of loading as well as randomness of soil parameters .
The reliability index values are lower for the shear force response of the tunnel lining under Earthquake records, comparing to those of axial force and flexural moment. Consequently, it is recommended to retrofit the whole soil under earthquake loading against shear cracking.

In this paper، a new method is presented to find tunnel target racking displacement in the earthquake considering nonlinear behavior of lining and soil and also soil- structure interaction. In the next step tunnel racking reduction factor has been evaluated for an incomplete ellipse tunnel located in two soil types، A and B، with overburden depth of 5 and 20 m by performing nonlinear static analysis. Finally، to verify the values of racking reduction factors، tunnel responses obtained by linear static analyses reduced by the calculated values of racking reduction factor are compared with responses obtained by nonlinear dynamic analyses. Design and analysis of the underground structures such as tunnels are performed on the basis of structure and ground deformations because the seismic response of such structures is very sensitive to the imposed ground deformations. In recent years، Several researches have indicated the importance of the harmful effects of earthquakes on tunnels and underground structures. Methodology and Approaches: In this paper، by combining Wang (1993) and Hashash (2000) methods in determination of tunnel target racking displacement and using the trial and error method to correct tunnel structure stiffness، possibility of redistribution of the forces and deformations became possible and it was tried to present a comprehensive method to determine the tunnel target racking displacement. In the next step، by using the force-racking displacement curve and applying the existing equations of reduction factors of the structures and their generalization for tunnels and underground structures and considering the soil-structure interaction، tunnel racking reduction factor is estimated. Then، using ABAQUS software، a comparison has been performed between dynamic and static forces in the tunnel lining. Results and Comparison of lining force (bending moment and axial force) between linear static analyses modified by tunnel racking reduction factors and nonlinear time history analyses shows that the accuracy of achieved tunnel racking reduction factors is acceptable. The studies also show that implementing linear static analyses without tunnel racking reduction factor leads to very conservative results of lining force in tunnel. Nonlinear time history dynamic analyses are time consuming and complicated in modeling procedure and analysis duration. Thus، By using the proposed racking reduction factors، Linear static analyses could be an alternative for nonlinear dynamic analyses with a suitable accuracy.