Browsing by Author "Ghorbani, Ali, A."

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    A Language for High-Level Description of Adaptive Web Systems
    (2006) Hossein Sadat, S.; Mohtasham, K.; Ghorbani, Ali, A.
    This paper focuses on the proposal, design, and implementation of AWL, the Adaptive Web Language. Also, an example application named PENS is explained and implemented in AWL. AWL development was inspired by several issues and shortcomings in the development of adaptive Web systems using the framework for adaptive Web systems, developed in the Intelligent and Adaptive Systems Research Group, at the University of New Brunswick, Fredericton, Canada. Lack of verification mechanisms and difficulty in development are two of the existing issues in the framework. Not only does AWL address those issues in the framework, but it also offers mechanisms to increase software quality attributes, especially, reusability. AWL has been designed based on the analysis of adaptive Web systems, having taken into account the principles of reuse-based software engineering (product-lines), domain-specific languages, and aspect-oriented programming, all of which are ongoing research fields in software engineering research. A compiler, named AWL Compiler has been developed, as the implementation of AWL for our adaptive Web framework. AWL Compiler automates the development process through hiding the framework internals from the application designer, and provides verification services so that applications can be verified to be consistent and meaningful. PENS, a personalized e-News system, is explained and its various aspects are developed using AWL. Key words: Adaptive Web Systems, Domain-Specific Languages, Reuse-based Design
  • Thumbnail Image
    Item
    Adaptive resonance theory networks using incremental communication
    Chen, Ming; Ghorbani, Ali, A.; Bhavsar, Virendra, C.
    The incremental inter-node communication method is applied to the adaptive resonance theory 2 (ART2) networks. The incremental communication is aimed at reducing the communication costs of parallel and VLSI implementations of artificial neural networks. A node architecture incorporating the incremental communication is presented. A simulator is developed to stndy the behavior of ART2 networks with varying precisions of incremental data communication. Experiments are carried out to study the effects of the incremental communication on the convergence and savings in communication costs. We have found that even 7-bit precision in fixed-point and 13-bit (including 8-bit exponent) floating-point representations may be sufficient for the network to give the same results as those with conventional communication using 32-bit precision. The simulation results show that the limited precision errors are bounded and do not seriously affect the convergence of ART2 networks.
  • Thumbnail Image
    Item
    Architectural components of information sharing societies
    Carter, Jonathan; Ghorbani, Ali, A.; Marsh, Stephen
    Two similar multiagent systems have been designed to address the issue of information sharing within a multiagent system. This paper examines architectural components that have been added to our information sharing societies, ACORN and MP3. Through this exploration, we conclude that these components and their underlying concepts can be added to other information retrieval societies. ACORN consists of a set of information sharing locations referred to as Cafes. Cafes are defined as meeting locations for like-minded agents. Like-minded agents are defined as agents that share a common set of interests. As an example, a cafe may contain agents that are interested in information relating to cars. A dynamic cafe clustering method is developed. The performance evaluation of the proposed structure for the cafe is presented. The concept of a fat/thin agent architecture is introduced. This agent architecture allows for minimizing network traffic as agents traverse the network in search of or distribution of knowledge. The directory server component is presented along with its relation to the fat/thin agent architecture. Lastly, anonymity service provider which allows anonymity for users is introduced. The MP3 society exists with the sole purpose of finding MP3's throughout a given network. Through this society, the core design issues of agent verification, and agent validation are addressed and solutions are presented through respective interface components. Key words: Agent, fat/thin agents, multiagent systems, clustering, MP3, information sharing
  • Thumbnail Image
    Item
    Astrolabe: A Collaborative Multi-Perspective Goal-Oriented Risk Analysis Methodology
    Bagheri, Ebrahim; Ghorbani, Ali, A.
    The intention of this paper is to introduce a risk analysis methodology, called Astrolabe. Astrolabe is based on the key idea of mining system risks from their origins and sources in order to both align the current standpoint of the system with its intentions and identify any vulnerabilities or hazards threatening its being. Astrolabe adopts concepts from organizational theory and software requirement analysis. The aim of Astrolabe is to guide risk analysis through its phases so that a near complete investigation of system risks is performed. The concepts driving the Astrolabe methodology have been defined in a metamodel that has been introduced in this paper. Keywords: Risk Analysis, Goal-Oriented Modeling, Risk Lifecycle
  • Thumbnail Image
    Item
    Incremental communication for artificial neural networks
    (1993) Ghorbani, Ali, A.; Bhavsar, Virendra, C.
    A learning procedure based on the backpropagation algorithm using the incremental communication is presented. In the incremental communication method instead of communicating the whole value of a variable, the increment or decrement to its previous value is only sent on a communication link. The incremental value may be either a fixed-point or a floating-point value. The method is applied to four different error backpropagation networks and the effect of the precision of the incremental values of activation, weights and error signals on the convergence behavior is examined. It is shown through simulation that at least 7-bit precision in fixed-point and 2-digit precision in floating-point representations are required for the network to generalize. With 12-bit fixed-point or 4-digit floating-point precision almost the same results are obtained as that with the conventional communication using 32-bit precision. The proposed method of communication can lead to enormous savings in the communication cost for implementations of artificial neural networks on parallel computers as well as direct hardware realizations. This method is applicable to many other types of artificial neural systems and can be incorporated along with the other limited precision strategies for representation of variables suggested in literature.
  • Thumbnail Image
    Item
    Incremental communication for multilayer neural networks: error analysis
    (1996) Ghorbani, Ali, A.; Bhavsar, Virendrakumar, C.
    Artificial neural networks (ANNs) involve large amount of inter-node communications. To reduce the communication cost as well as time of learning process in ANNs, we have earlier proposed incremental inter-node communication method. In the incremental communication method, instead of communicating the full magnitude of the output value of a node, only the increment or decrement to its previous value is sent on a communication link. In this paper, the effects of limited precision incremental communication method on the convergence behavior and performance of multilayer neural networks are investigated. The nonlinear aspects of representing the incremental values with reduced (limited) precision on the commonly used error backpropagation training algorithm are analyzed. It is shown that the nonlinear effect of small perturbation in the input(s)/output of a node does not enforce instability. The analysis is supported by simulation studies of two problems.
  • Thumbnail Image
    Item
    Parallel tangent learning algorithm for training artificial neural networks
    (1993) Ghorbani, Ali, A.; Bhavsar, Virendra, C.
    A modified backpropagation training algorithm using deflecting gradient technique is proposed. Parallel tangent (Partan) gradient is used as a deflecting method to accelerate the convergence. This method can also be thought as a particular implementation of the method of conjugate gradient. Partan gradient consists of two phases namely, climbing through gradient and accelerating through parallel tangent. Partan overcomes the inefficiency of zigzagging in the conventional backpropagation learning algorithm by deflecting the gradient through acceleration phase. The effectiveness of the proposed method in decreasing the rate of convergence is investigated by applying it to four learning problems with different error surfaces. It is found through simulation that regardless of the degree of the complexity of the problems used, the Partan backpropagation algorithm shows faster rate of convergence to the solution. In particular, for the exclusive-or problem its convergence time is approximately five times faster than that of standard backpropagation, whereas about two times faster rate of convergence is obtained for Encoder/Decoder, Binary-to-local, and Sonar problems.
  • Thumbnail Image
    Item
    Reputation formalization for an information sharing multiagent system
    Carter, Jonathan; Bitting, Elijah; Ghorbani, Ali, A.
    We propose that through the formalization of concepts related to trust, a more accurate model of trust can be implemented. This paper presents a new model of trust that is based on the formalization of reputation. A multidisciplinary approach is taken to understanding the nature of trust and its relation to reputation. Through this approach, a practical definition of reputation is adopted from sociological contexts and a model of reputation is designed and presented. Reputation is defined as role fulfillment. In order to formalize reputation, it is necessary to formalize the expectations placed upon an agent within a particular Multiagent System (MAS). In this case, the agents are part of an information sharing society. Five roles are defined along with the ways in which these roles are objectively fulfilled. Through the measurement of role fulfillment, a vector representing reputation can be developed. This vector embodies the magnitude of the reputation and describes the patterns of behavior associated with the direction of the vector. Experiments are conducted to verify the sensibility of the proposed models for role fulfillment and overall reputation. The simulation results shows that the roles, defined for building reputation in an information-sharing MAS environment, react to different agent and user actions in a consistent with the formal definitions. Keywords: Agent, Information Sharing, Multiagent Systems, Reputation, Trust.