Sharif Digital Repository

Segmentation of the human airway tree from volumetric computed tomography images is an important stage for many clinical applications such as virtual bronchoscopy. The main challenges of previously developed methods are to deal with two problems namely, leaking into the surrounding lung parenchyma during segmentation and the need to manually adjust the parameters. To overcome these problems, a multi-seeded fuzzy based region growing approach in conjuction with the spatial information of voxels is proposed. Comparison with a commonly used region growing segmentation algorithm shows that the proposed method retrieves more accurate results by achieving the specificity and sensitivity of 98.81%... 

Automatic translation of a high-level specification language to an executable implementation would be highly useful in maximizing the benefits of formal methods. We will introduce a set of translation functions to fill the specification-implementation gap in the domain of database applications. Because the mathematical foundation of Z has many properties in common with SQL, a direct mapping from Z to SQL structures can be found. We derive a set of translation functions from Z to SQL for the generation of a database. The proposed methodology results in reducing the expenses and duration of the software development, and also, prevents the errors originated from the manual translation of... 

Inserting redundancy to arithmetic codes is a common strategy to add error detection capability to this well-known family of source codes. By using this strategy error correction is possible through some decoding algorithms such as Viterbi decoder. In this paper a system has proposed that uses finite state integer arithmetic codes (FSAC) as a joint source-channel code in combination with a cyclic redundancy check (CRC) and a List Viterbi decoder. The proposed scheme has shown better performance than previous ones. © 2009 IEEE  

The Block method approach to solve EIT problem leads to an exact solution if the measurements are done without error. Non-iterative method is a feasible approach on solving 3D EIT forward problem. However, the effect of the measurement error has not been considered in this method yet. In this article, the 3D model of EIT with block method has been considered. The required equations to solve the forward problem are then generated. To solve the forward problem, non-iterative method has been employed. Effect of the measurement error on forward problem for a 3D model of EIT are generated. It has been shown that for a sample 3D model, measurement error can propagate exponentially. ©2007 IEEE  

The key element of a spoken dialogue system is Spoken Language Understanding (SLU) part. HVS and EHVS are two most popular statistical methods employed to implement the SLU part which need lightly annotated data. Since annotation is a time consuming, we present a novel semi-supervised learning for EHVS to reduce the human labeling effort using two different statistical classifiers, SVM and KNN. Experiments are done on a Persian corpus, the University Information Kiosk corpus. The experimental results show improvements in performance of semi-supervised EHVS, trained by both labeled and unlabeled data, compared to EHVS trained by just initially labeled data. The performance of EHVS improves... 

Data mining is a very popular technique which is successfully used in many areas. The aim of this paper is to present a data mining system for extracting knowledge from input datasets. We use the hybrid ant colony and simulated annealing algorithms to optimize extracted fuzzy rule set. The proposed method has the main feature of data mining techniques which is high accuracy. The proposed method is then implemented on UCI datasets. The results are compared with those of well-known methods, and show the competitive systems efficiency  

This paper presents a new model of call admission control which consists of a few key elements for protecting the network in different conditions of workload in a manner that, calls blocking /dropping are kept under desired level. This model consists of two traffic classes of voice and data. In order to give a priority to handoff call over new call, some parameters in this model are adjusted in a manner that handoff dropping is reduced to the least probability in the target cell and the adjacent cells. Some channels are reserved for voice and data calls in each cell to guarantee the quality of service requirements in the network. Limited fractional guard channel is used to have an optimized... 

This paper presents a technique for estimation of amplitude information from an interferometric time-domain optical coherence tomography (OCT) signal. The conventional estimation scheme is based on the in-phase and quadrate (IQ) demodulation concept. A disadvantage of this method is that the IQ components include a ripple whose frequency is the double of the interferometric signal frequency. The improved method of demodulation, presented in this paper, yields a more precise estimation of the amplitude information by fundamentally removing the ripple. Theoretical and experimental OCT signals are applied to both demodulation systems and the amplitude is computed. The detected signals from both... 

Electrical Impedance Tomography (EIT) is a visualization of the internal electric conductivity of an object using measurements performed on its surfaces. As an Inverse problem, the solution can be approximated by means of Artificial Neural Networks. In this paper, an Artificial Neural Network solution to this Inverse Problem is presented. Based on the electrical voltage and current measurements on the boundary of the object, the conductivity distribution has been found and the resulting error is calculated. The error is compared for different Neural Network architectures to detect and minimize the errors caused by the solution method. Also, different Neural Networks were tested in the noisy... 

Electrical impedance tomography (EIT) is a simple, economic and healthy technique to capture images from the internal area of the body. Although EIT is cheaper and smaller than other imaging systems and requires no ionizing radiation, the resolution associated with this technique is intrinsically limited and the image reconstruction algorithms proposed up to now are not efficient enough. In addition to low resolution EIT is an ill-posed inverse problem. Block method in EIT is based on electrical properties of materials and used to enhance image resolution and also to improve the reconstruction algorithm. Recently an inverse solution for EIT based on block method has been developed, however,...