فا   |   En
Login
73 74 75 76 77 78 79 80 81 82 83 84 85
Paper Title Authors Conference Abstract
Improving the Noise Reduction Performance Using AEC-GSC for Reverberant Environments Pejman Mowlaee Begzade Mahale
Mohammad Hossein Kahaei
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
In this paper, noise reduction performance of the Generalized Side-lobe Canceller (GSC) algorithm and its performance degradation under reverberant environments are briefly reviewed. An acoustic echo canceller (AEC) is employed as a ... more
In this paper, noise reduction performance of the Generalized Side-lobe Canceller (GSC) algorithm and its performance degradation under reverberant environments are briefly reviewed. An acoustic echo canceller (AEC) is employed as a pre-processor for GSC noise reduction algorithm in order to improve the noise reduction performance of the GSC especially in highly reverberant environments where GSC alone fails to work properly. The proposed AEC-GSC algorithm consists of an AEC pre-processor, which includes Segment Variable Stepsize Proportionate Normalized Least Mean Square (SVS-PNLMS) algorithm recently proposed, and the GSC noise reduction algorithm. The performance of both AEC-GSC and GSC alone is evaluated through computer simulations, using real speech recordings in reverberant room environment. Through different computer simulations it is demonstrated that the proposed AEC-GSC structure performs better than GSC alone in terms of speech distortion parameters and ERLE. It also presents a better tracking behavior between the pause intervals during a speech signal due to using the SVS-PNLMS algorithm in its AEC section. less
In this paper, noise reduction performance of the Generalized Side-lobe Canceller (GSC) algorithm and its performance degradation under reverberant environments are briefly reviewed. An acoustic echo canceller (AEC) is employed as a ... more
خرید مقاله
Scheduling for Input-Queued Switches based on High Throughput and QoS Changiz Roidel
Morteza Analoui
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
Input-Queued switch architecture has become attractive for implementing high performance routers because the switching fabric and the buffer need not run at a multiple of input link's rate. It is challenging to ... more
Input-Queued switch architecture has become attractive for implementing high performance routers because the switching fabric and the buffer need not run at a multiple of input link's rate. It is challenging to provide a scheduling technique that is both highly efficient and fair in resource allocation. We propose an iterative Cell- based Fair scheduling (iCFS) scheme, based on SLIP that support fair bandwidth distribution among flows and achieves asymptotically 100 percent throughput. less
Input-Queued switch architecture has become attractive for implementing high performance routers because the switching fabric and the buffer need not run at a multiple of input link's rate. It is challenging to ... more
خرید مقاله
A Parallel Genetic Approach to Construct Near Optimal Binary Search Tree A. Fatemi
K. zamanifar
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
Many definitive and approximate methods have been so far proposed for the construction of an optimal binary search tree. One such method is the use of evolutionary algorithms with satisfactorily improved ... more
Many definitive and approximate methods have been so far proposed for the construction of an optimal binary search tree. One such method is the use of evolutionary algorithms with satisfactorily improved cost efficiencies. This paper will propose a new genetic algorithm for constructing a near optimal binary search tree. In this algorithm, a new greedy method is used for the crossover of chromosomes while a new way is also developed for inducing mutation in them. Practical results show a rapid and desirable convergence towards the near optimal solution. The use of a heuristic to create not so costly chromosomes as the first offspring, the greediness of the crossover, and the application of elitism in the selection of future generation chromosomes are the most important factors leading to near optimal solutions by the algorithm at desirably high speeds. Due to the practical results, increasing problem size does not cause any considerable difference between the solution obtained from the algorithm and exact solution. Task parallelism causes an improving effect on proposed algorithm. less
Many definitive and approximate methods have been so far proposed for the construction of an optimal binary search tree. One such method is the use of evolutionary algorithms with satisfactorily improved ... more
خرید مقاله
Multi-Agent Computer Network Routing System Based on Recursive Modeling Method and Bayesian Belief Update Kambiz Rahbar
Mohammad-R Akbarzadeh-T
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
This research addresses computer network routing based on recursive modeling method (RMM). In our proposed method, each router as an intelligent agent uses RMM tree-like structure to make a rational and intelligent ... more
This research addresses computer network routing based on recursive modeling method (RMM). In our proposed method, each router as an intelligent agent uses RMM tree-like structure to make a rational and intelligent decision on transmitting packages. This decision is made based on the models of other routers in the network and its belief about them. However, as the network conditions vary with time, the needs of updating each routers belief about others can not be neglected. To achieve this goal, Bayesian law is used to update routers belief about others. To validate the proposed method, we test it as a computer simulation. The results show that this method increases the network performance by decreasing the network overhead arising from routers packages. Additionally, as the network dynamics increases, employing Bayesian law helps the routers to quickly adapt to the new conditions. less
This research addresses computer network routing based on recursive modeling method (RMM). In our proposed method, each router as an intelligent agent uses RMM tree-like structure to make a rational and intelligent ... more
خرید مقاله
An Iterative Geometrical Noise Cancellation Approach to Closed-form Camera Pose Estimation Kambiz Rahbar
Hamid Reza Pourreza
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
This research addresses a new iterative geometrical noise cancellation method for closed-form camera pose estimation based on collinearity theory. We first explain how to estimate camera position and it’s orientation by employing ... more
This research addresses a new iterative geometrical noise cancellation method for closed-form camera pose estimation based on collinearity theory. We first explain how to estimate camera position and it’s orientation by employing extra nonsingular point of the edge line of the landmark’s corner through a closed-form geometrical pose estimation algorithm. Then, we propose a new iterative noise cancellation algorithm to reduce the estimation error of camera transaction matrix, which has the most portion in camera pose estimation errors. To validate our proposed method, we test it as a computer simulation. The results show that this method is efficient, accurate and robustness. But the drawback is that the camera rotation matrix, which used in noise cancellation algorithm, may not always be inverseable. less
This research addresses a new iterative geometrical noise cancellation method for closed-form camera pose estimation based on collinearity theory. We first explain how to estimate camera position and it’s orientation by employing ... more
خرید مقاله
Process Agent: A Solution for Workflow Automation Hesam Chiniforooshan Esfahani
Seyed Hassan Mirian Hosseinabadi
Amirreza Abdolrashidi
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
Considerable speed of process engineering improvement and the consequent impact on workflow management systems has brought up a new wave of researches in reconsidering current solutions for workflow systems and proposing more ... more
Considerable speed of process engineering improvement and the consequent impact on workflow management systems has brought up a new wave of researches in reconsidering current solutions for workflow systems and proposing more brilliant ideas for such type of software systems. Agent technology as a semi-matured methodology of software design, has introduced itself as a promising approach in building complex software systems. In this paper we presented a simple ready for use agent architecture which can be deployed in many types of workflow automations. less
Considerable speed of process engineering improvement and the consequent impact on workflow management systems has brought up a new wave of researches in reconsidering current solutions for workflow systems and proposing more ... more
خرید مقاله
An Automated Negotiation Technique for Self-interest Agents Hassan Kkosravi
Mohammad E. Shiri
Hamid Khosravi
Ehsan Iranmanesh
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
Due to the rapid growth of electronic environments (such as internet) much research is currently being performed on autonomous trading mechanisms. Also in the last few years there has been an increasing ... more
Due to the rapid growth of electronic environments (such as internet) much research is currently being performed on autonomous trading mechanisms. Also in the last few years there has been an increasing interest from the agent community in the use of techniques from decision theory and game theory. Our paper connects theses two fields. In real world, when two agents negotiate, it seems rational that they emphasize on their highest priorities first. We give a strategy based on the 7 types presented by Raymund J. Lin and Seng-cho T. Chou [7] in which an agent can gain more profit by sacrificing or delaying some high priority tasks. The focus of this paper is on negotiation of self interest agents. less
Due to the rapid growth of electronic environments (such as internet) much research is currently being performed on autonomous trading mechanisms. Also in the last few years there has been an increasing ... more
خرید مقاله
A New Approach to Early Software Reliability Prediction Based on a Formal Specification of System Hooshmand Alipour
Ayaz Isazadeh
Eslam Nazemi
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
Prediction of reliability in early phases of software development is one of the discussions which has been attracting more and more attentions during the recent three decades. Techniques and models are ... more
Prediction of reliability in early phases of software development is one of the discussions which has been attracting more and more attentions during the recent three decades. Techniques and models are mostly used at the test phase; there are only a few models that are employed at early phase of software development. Early prediction, however, is very important for better prognosis and management of risks. In this paper we propose an approach for software reliability early prediction based on software behavior. The major difference between our approach and those of others is the fact that we use a formal method, called Viewcharts [1], to specify the behavior of software systems. less
Prediction of reliability in early phases of software development is one of the discussions which has been attracting more and more attentions during the recent three decades. Techniques and models are ... more
خرید مقاله
Improvement on Concentrator Location Problem in Access Network Design using Growing Neural Network Sajjad Moradi
Bahador Bakhshi
Siavash Khorsandi
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
The goal of network topological design is to find a minimum cost configuration of network components. Design of access network is discussed here. The objective is minimizing the access network cost ... more
The goal of network topological design is to find a minimum cost configuration of network components. Design of access network is discussed here. The objective is minimizing the access network cost by means of finding optimal number and location of concentrators. The network cost consists of the concentrators cost and cost of access links, that connecting terminals to the concentrators. Here, contrary to most of other methods, which use candidate locations for concentrators, the search space is continuous. Solution to the problem is improved in this article. The problem is solved using a type of self organizing neural network called Growing Neural Network. In this method, terminal locations are used as input of neural network and self organizing feature leads to optimal solution. Furthermore, an improved version of the COM algorithm is proposed. Improvement is achieved by means of applying cost constraint in cluster merging phase. The simulation results for different networks with various cost parameters show the new methods achieve the better performance than that of previous methods. less
The goal of network topological design is to find a minimum cost configuration of network components. Design of access network is discussed here. The objective is minimizing the access network cost ... more
خرید مقاله
The Anticipatory Classifier System for Function Approximation Amin Nikanjam
Adel Rahmani
دوازدهمین کنفرانس بین‌المللی سالانه انجمن کامپیوتر ایران
The Anticipatory Classifier System (ACS) employs the learning classifier system framework and the learning theory of anticipation behavioral control. The resulting evolutionary system can build an internal environmental model and then applies ... more
The Anticipatory Classifier System (ACS) employs the learning classifier system framework and the learning theory of anticipation behavioral control. The resulting evolutionary system can build an internal environmental model and then applies reinforcement learning techniques to develop an optimal set of classifiers. XCSF is another novel version of learning classifier systems (LCS) which introduced the concept of computable classifier prediction and successfully applied to function-approximation problems. In this paper, we apply ACS to function approximation. ACSF is a new version of ACS introduced to develop more accurate approximations. less
The Anticipatory Classifier System (ACS) employs the learning classifier system framework and the learning theory of anticipation behavioral control. The resulting evolutionary system can build an internal environmental model and then applies ... more
خرید مقاله
73 74 75 76 77 78 79 80 81 82 83 84 85
Conferences and Events





Registration in Computer Society of Iran
Search Papers