انجمن کامپیوتر ایران

The power of grid technology in aggregating autonomous resources owned by several organizations into a single virtual system has made it popular in compute-intensive and data-intensive applications. Complex and dynamic nature of grid makes failure of users’ jobs fairly probable. Furthermore, traditional methods for job failure recovery have proven costly and thus a need to shift toward proactive and predictive management strategies is necessary in such systems. In this paper, an innovative effort is made to predict the futurity of jobs submitted to a production grid environment (AuverGrid). By analyzing grid workload traces and extracting patterns describing common failure characteristics, the success or failure status of jobs during 6 months of AuverGrid activity was predicted with around 96% accuracy. The quality of services on grid can be improved by integrating the result of this work into management services like scheduling and monitoring.

The discovery of suitable web services for a given task is one of the major operations in SOA architecture, and researches are being done to automate this step. For the large amount of available Web services that can be expected in real-world settings, the computational costs of automated discovery based on semantic matchmaking become important. To make a discovery engine a reliable software component, we must aim at minimizing both the mean and the variance of the duration of the discovery task. For this, we present an extension for discovery engines in SWS environments that exploit structural knowledge and previous discovery results for reducing the search space of consequent discovery operations. Our prototype implementation shows significant improvements when applied to the Stanford SWS Challenge scenario and dataset.

A hybrid feature and decision level information fusion architecture is proposed for human emotion recognition from facial expression and speech prosody. An active buffer stores the most recent information extracted from face and speech. This buffer allows fusion of asynchronous information through keeping track of individual modality updates. The contents of the buffer will be fused at feature level; if their respective update times are close to each other. Based on the classifiers’ reliability, a decision level fusion block combines results of the unimodal speech and face based systems and the feature level fusion based classifier. Experimental results on a database of 12 people show that the proposed fusion architecture performs better than unimodal classification, pure feature level fusion and decision level fusion.

In this paper we propose a new integration method for multi-feature object tracking in a particle filter framework. We divide particles into separate clusters. All particles within a cluster measure a specific feature. The number of particles within a cluster is in proportion to the reliability of associated feature. We do a compensation stage which neutralizes the effect of particles weights mean within a cluster. Compensation stage balances the concentration of particles around local maximal. So, particles are distributed more effectively in the scene. Proposed method provides both effective hypothesis generation and effective evaluation of hypothesis. Experimental results over a set of real-world sequences demonstrate better performance of our method compared to the common methods of feature integration.

This paper introduces a revisited hybrid algorithm for function approximation. In this paper, a simple and fast learning algorithm is proposed, which automates structure and parameter identification simultaneously based on input-target samples. First, without need of clustering, the initial structure of the network with the specified number of rules is established, and then a training process based on the error of other training samples is applied to obtain a more precision model. After the network structure is identified, an optimization learning, based on the criteria error, is performed to optimize the obtained parameter set of the premise parts and the consequent parts. At the end, comprehensive comparisons are made with other approaches to demonstrate that the proposed algorithm is superior in term of compact structure, convergence speed, memory usage and learning efficiency.

This paper estimates and segments the moving objects based on center of mass model to decrease the search window and to provide a new algorithm, which achieves an accurate and rapid tracking. Furthermore, a novel method is proposed to update the template size adaptively by using estimation and segmentation of moving objects. The estimated results of moving target is transformed to wavelet domain and target tracking is performed in that domain. To improve the algorithm center of mass model is performed in wavelet domain. By using kalman predictor and thresholding method, a new approach is presented for object tracking failure and recovery.

In this paper, we introduce a refinement approach to develop probabilistic programs formally. To achieve this goal, we first present a way to specify probabilistic programs in a Z-based notation. We then use an existing method of translating Z into a refinement calculus to transform our Z-style specifications of probabilistic programs into specification statements of the refinement calculus. We finally add new laws to the refinement calculus helping us to refine the resulting specification statements into probabilistic choice constructs of a probabilistic imperative language. In this way, we will provide a completely formal way for developing probabilistic programs.