Number 6 Volume 2

Open Access Article

1 - Improving the accuracy of the GMM model in the form of the GMM-VSM system in the application of speech language recognition
Fahimeh GHasemian Mohamad mahdi Homaion por

The GMM model is one of the most widely used and successful models in the field of automatic language recognition. In this article, a new model called Adapted Weight-GMM (AW-GMM) is presented. This model is similar to GMM, with the difference that the weight of its comp More

The GMM model is one of the most widely used and successful models in the field of automatic language recognition. In this article, a new model called Adapted Weight-GMM (AW-GMM) is presented. This model is similar to GMM, with the difference that the weight of its components in the form of GMM-VSM system is determined based on the strength of the components in differentiating one language from other languages. Also, due to the computational complexity in the GMM-VSM system in the case where a 2-component sequence is considered, a technique for constructing a 2-component sequence has been presented, which can be used to construct higher-order sequences as well. used The evaluations carried out on 4 languages English, Persian, French and German from OGI data show the effectiveness of the presented techniques. Manuscript profile

Open Access Article

2 - Designing a fuzzy expert system for choosing the right contractor in information technology outsourcing
nadia kalantari nadia kalantari alireza Hasanzadeh shaban elahi

The increase in the complexity and cost of information technology systems has created many problems for companies in the field of infrastructure and manpower, which have been reduced by using outsourcing. All organizations try to increase the probability of success of t More

The increase in the complexity and cost of information technology systems has created many problems for companies in the field of infrastructure and manpower, which have been reduced by using outsourcing. All organizations try to increase the probability of success of their outsourcing projects in different ways. One of the reasons for the failure of these projects, especially in the field of information technology, due to its important role in gaining a competitive advantage, is the selection of an inappropriate contractor, which is complicated due to the existence of multiple and contradictory criteria. The purpose of this research is to find the important criteria for selecting the contractor and provide its framework and specify the importance of the criteria and finally to design a fuzzy expert system for choosing the right contractor in intra-border outsourcing of information technology. The method of obtaining knowledge from experts, which includes information technology specialists and managers, is a questionnaire, and it has been used in an information technology company to validate the system, and the results indicate the optimal performance of the system. Manuscript profile

Open Access Article

3 - A matching probability-based flood algorithm for mobile ad hoc networks
fateme nourazar sabaei sabaei

The flood algorithm is one of the most important primary operations and infrastructure for routing protocols in mobile ad hoc networks. However, since this algorithm generates many additional messages, it is very costly, it has caused a waste of network bandwidth, consu More

The flood algorithm is one of the most important primary operations and infrastructure for routing protocols in mobile ad hoc networks. However, since this algorithm generates many additional messages, it is very costly, it has caused a waste of network bandwidth, consuming more energy than the nodes need, which may eventually cause an all-broadcast storm. Many methods have been proposed to improve the flood algorithm, which are mainly divided into two categories of deterministic and probabilistic methods, and the second category has received more attention. But these methods mainly cause delay and lack of complete coverage. In this paper, we have proposed a new method to improve the performance of SIL-ASA algorithm. The basis of this probabilistic replay method is based on local observations. In this new method, the probability of message replay by each node is a function of local observations. The results of the simulation have shown that the proposed method provides complete network coverage in comparison with similar methods while significantly reducing the packet delivery delay with an acceptable message overhead. Manuscript profile

Open Access Article

4 - Correcting camera lens misalignment using Zernik moments
kambiz rahbar karim faez

۷۲۹ / ۵٬۰۰۰ The reduction of image quality in an optical system depends on different parameters such as lens aberration, digitization error and system assembly error. Among these, the present article aims to study the astigmatism of the lens and correct and compensate More

۷۲۹ / ۵٬۰۰۰ The reduction of image quality in an optical system depends on different parameters such as lens aberration, digitization error and system assembly error. Among these, the present article aims to study the astigmatism of the lens and correct and compensate its astigmatism defect. For this purpose, Zernike moments are introduced for the modeling of Abirai and its coefficients are classified into two classes, symmetric and asymmetric. Then these coefficients are estimated using multispectral analysis. For this purpose, tri-coherence analysis has been used to estimate the coefficients of symmetrical sentences, and bi-coherence analysis has been used for the coefficients of asymmetric sentences. Considering the accuracy of the obtained results in comparison with the results of Abirai estimation using multi-spectral analysis, it shows that the proposed method can achieve an accuracy of 0.1 pixel. ارسال بازخورد Manuscript profile

Open Access Article

5 - Training of MLP neural network in image compression using GSA method
maryam dehbashian hamid zahiri

One of the important research areas in image processing is image compression. Until now, various methods for image compression have been presented, among which neural networks have attracted many audiences. The most common training method of neural networks is the error More

One of the important research areas in image processing is image compression. Until now, various methods for image compression have been presented, among which neural networks have attracted many audiences. The most common training method of neural networks is the error backpropagation method, which converges and stops at local optima are considered one of its most important weaknesses. The researchers' new approach is to use innovative algorithms in the process of training neural networks. In this article, a new educational method based on gravity search method (GSA) is introduced. The gravity search method is the latest and newest version of all types of collective intelligence search and optimization methods. In this method, the candidate answers in the search space are objects that are affected by the force of gravity and their positions change. Gradually, objects with better fit have more mass and have a greater effect on other objects. In this research, an MLP neural network is trained for image compression using the GSA algorithm. Manuscript profile

Open Access Article

6 - Semi-blind labeling of images using SVD in the field of discrete wavelet transform
morteza makhlooghi danyali danyali fardin akhlaghi

With the rapid development of communication technology and the expansion of the Internet and the significant increase in forgery and unauthorized copying of data, the value of marking is increasing day by day. In this paper, a new semi-blind marking method using singula More

With the rapid development of communication technology and the expansion of the Internet and the significant increase in forgery and unauthorized copying of data, the value of marking is increasing day by day. In this paper, a new semi-blind marking method using singular value decomposition (Singular Value Decomposition) in the domain of discrete wavelet transform is presented to protect property rights. In the proposed method, first the discrete wavelet transform step is applied to the original image K and its lowest frequency subband is selected as the reference image. Then, by applying a discrete wavelet transformation step to the reference image and the reference image, the unique values of the frequency sub-bands of the converted signal image are embedded in the unique values of the corresponding sub-bands of the reference transformed image. Since in this method, a reference image is needed to recover the sign, and the original image is not needed, therefore it is called a Semi-Blind method. The resistance of the proposed method against different attacks was investigated. The results show that the proposed method is much more resistant to various attacks than similar works, and at the same time, the marked image is more transparent. Manuscript profile

Open Access Article

7 - Sliding mode control for congestion in TCP/IP networks
roohollah barzamini masoud shafiee

Congestion phenomenon is one of the important problems faced by computer network designers and in recent years it has reduced the efficiency of networks. So far, various methods have been proposed to prevent and control this phenomenon, which are based on control theory More

Congestion phenomenon is one of the important problems faced by computer network designers and in recent years it has reduced the efficiency of networks. So far, various methods have been proposed to prevent and control this phenomenon, which are based on control theory. For this purpose, the closed loop structure of the data transfer process in computer networks can be considered in such a way that the controllers from the Dynamic Queue Management (AQM) family are designed to be implemented in the pathfinders of the network and the rest of the network from the point of view of the pathfinder. It is defined as the control target system or plant. In the field of AQM controller design, many researches have been done and many controllers have been designed. In this article, sliding mode control is introduced as AQM controller. Sliding mode control is resistant to modeling uncertainties and disturbances. In sliding mode control, mode paths must reach a predefined level (sliding level) in a limited period of time and remain at the same level over time. Movement on the sliding surface is independent of uncertainties; Therefore, this technique is one of the resistant control methods. After implementing the sliding mode control on the network model, with the help of Matlab software, how the network behaves in the presence of this The controller was examined and the results obtained were compared with the results of several other controllers. Manuscript profile

XML

List of Articles