Computing and Information Systems - Theses
Permanent URI for this collection
Search Results
1 - 2 of 2
-
ItemHierarchical clustering and summarization of network traffic data( 2008)An important task in managing IP networks is understanding the different types of traffic that are utilizing a network, based on a given trace of the packets or flows in the network. One of the key challenges in this task is the volume and complexity of the data that is available in traffic traces. What is needed by network managers in this context is a concise report of the significant traffic patterns that are present in the network. In this thesis, we address the problem of how to generate a succinct traffic report that contains a set of aggregated traffic flows, such that each aggregate flow corresponds to a significant traffic pattern in the network. We view the problem of generating a report of the significant traffic patterns in a network as a form of clustering problem. In particular, some distance-based hierarchical clustering techniques have advantages in terms of scalability when analyzing the types of large traffic traces that arise in this context. However, there are several important problems that need to be addressed before we can effectively use these types of clustering techniques on network traffic traces. The first research problem we address is how to handle non-numeric attributes that appear in network traffic data, such as attributes with a categorical or hierarchical structure. We have proposed a hierarchical similarity measure that is suitable for comparing hierarchical attributes in network traffic data. We have then developed a one-pass, hierarchical clustering scheme that can exploit the structure of hierarchical attributes in combination with categorical and numerical attributes. We demonstrate that our clustering scheme achieves significant improvements in both accuracy and execution time on a standard benchmark dataset, compared to an existing approach based on frequent itemset clustering. The second research problem we address is how to improve the scalability of our hierarchical clustering scheme when computing resources are limited. We propose an adaptive, two-stage sampling technique, which controls the rate at which records from frequently seen patterns are received by our clustering scheme. This enables more computational resources to be allocated to clustering new or unusual traffic patterns. We demonstrate that our two-stage sampling technique can identify less frequent traffic patterns with greater accuracy than when traditional systematic sampling is used. The third research problem we address is how to generate a concise yet accurate summary report from the results of our hierarchical clustering. We present two approaches to summarization, based on the size and the homogeneity of the clusters in the hierarchical cluster tree. We demonstrate that these approaches to summarization can substantially reduce the final report size with little impact on the accuracy of the report.
-
ItemArguments and actions: decoupling preference and planning through argumentation( 2011)Automated decision-making and planning is a capability that lays the foundation for the development of intelligent decision-support. These systems range from sophisticated multi-agent solutions for corporate decision-support, to decision recommendation for the general consumer. The ideas, algorithms, and tools developed within this thesis cater for this latter category - a class of approaches that includes online travel planners, smart environments, context-aware navigational aides, and personal shopping assistants. Operating on behalf of a human user, these tools are charged with the recommendation of a decision that best serves their interests - characterised by their preference over available choices. The mission of an automated decision-maker is to extract and use this knowledge in the selection of a decision. Across the range of problem-domain scenarios faced by a human decision-maker, the appropriate means by which their preference is communicated varies - from the quantitative to qualitative, logical to heuristic, and simple to complex. The capacity of these tools to select choices on the basis of such wide ranging classes of preference increases their utility as human decision aides. This thesis considers the decoupling of preference from the decision-making and planning algorithms that underly such systems. These algorithms operate on this preference as if it were an instance of an abstract type - supporting the use of general expressions of preference while abstracting away from its representational detail. Such algorithms can not only be reused across a range of decision-making problems faced by an agent or user, but cater for the diversity of human users on whose behalf decision-making is taking place. This thesis presents three key contributions within this domain. The existing body of work within the field of automated decision-making and planning with preference is critiqued, identifying the field of computational argumentation as a promising vehicle for the discovery of decoupled decision-making. The argumentation-based approach to decision-making allows preference to be captured by structures - structures that are manipulated by the decision-making process as abstract entities. This thesis develops a decoupled algorithm for the selection of choices on the basis of general mechanisms of choice comparison - a feat not achieved within existing work. Attention is then shifted from decision-making over single choices or actions to the problem of planning with preference. Algorithms are developed that chart a course of action for an agent or human user to follow in pursuit of their goals. This thesis focuses on a specific planning formalism - the GOLOG family of agent programming languages. High level instructions in the form of programs are interpreted to discover a sequence of actions for an agent or human user to perform. Two interpreters are devised for the discovery of preferred program executions - the first providing support for only one form of preference expression; the second presenting a decoupled approach to program interpretation with general preference. These interpreters go beyond the capabilities of existing works, with improved heuristic guidance in the form of a relaxed lookahead and support for decoupling through argumentation-based program interpretation.