Essentially all data mining algorithms assume that the datagenerating process is independent of the data miner's activities. However, in many domains, including spam detection, intrusion detection, fraud detection, surveillance and counter-terrorism, this is far from the case: the data is actively manipulated by an adversary seeking to make the classifier produce false negatives. In these domains, the performance of a classifier can degrade rapidly after it is deployed, as the adversary learns to defeat it. Currently the only solution to this is repeated, manual, ad hoc reconstruction of the classifier. In this paper we develop a formal framework and algorithms for this problem. We view classification as a game between the classifier and the adversary, and produce a classifier that is optimal given the adversary's optimal strategy. Experiments in a spam detection domain show that this approach can greatly outperform a classifier learned in the standard way, and (within the parameters of the problem) automatically adapt the classifier to the adversary's evolving manipulations.

Model-based diagnosis has largely operated on hardware systems. However, in most complex systems today, hardware is augmented with software functions that influence the system’s behavior. In this paper, hardware models are extended to include the behavior of associated embedded software, resulting in more comprehensive diagnoses. Prior work introduced probabilistic, hierarchical, constraint-based automata (PHCA) to allow the uniform and compact encoding of both hardware and software behavior. This paper focuses on PHCA-based monitoring and diagnosis to ensure the robustness of complex systems. We introduce a novel approach that frames diagnosis over a finite time horizon as a soft constraint optimization problem (COP), allowing us to leverage an extensive body of efficient solution methods for COPs. The solutions to the COP correspond to the most likely evolutions of the complex system. We demonstrate our approach on a vision-based rover navigation system, and models of the SPHERES and Earth Observing One spacecraft.

Abstract. This paper deals with self-adapting software that is structured according to a control theory architecture. Such software contains, in addition to its main function, two components- a Controller and a Quality-of-Service module. We show an example of an application and analyze the mapping of this application onto various control theory-based architectures. The application is a radar-based target tracking system. We show how architectural constraints are propagated through the mapping. We also analyze various architectural solutions with respect to stability and time complexity. 1

Abstract. For most real applications of computer vision, variations in operating conditions result in poor reliability. As a result, real world applications tend to require lengthy set-up and frequent intervention by qualified specialists. In this paper we describe how autonomic computing can be used to reduce the cost of installation and enhance reliability for practical computer vision systems. We begin by reviewing the origins of autonomic computing. We then describe the design of a tracking-based software component for computer vision. We use a software component model to describe techniques for regulation of internal parameters, error detection and recovery, self-configuration and self-repair for vision systems.

Abstract. In mission critical applications of distributed information systems, autonomous information resources are coordinated to meet the information demands of client specific decision-support views. A major challenge is handling dynamic changes in QoS constraints of the clients and/or changes in QoS properties of the resources. This paper presents a negotiation-based adaptive view coordination approach to address such run-time changes. The three key ideas are as follows. a) A negotiation-based reasoning model for adapting view maintenance policies to meet changes in QoS needs and context constraints. b) A dynamic software architecture of the collaborating information resources supporting the client task of maintaining a specific view. c) Coordination mechanisms in the architecture that realize negotiated changes in the policies for view maintenance. The paper describes an initial prototype of the support system for the supply-chain task domain. 1

To perform as desired in a dynamic environment a vision system must adapt to a variety of operating conditions by selecting vision modules, tuning their parameters, and controlling image acquisition. Knowledge-based (KB) controller-agents that reason over explicitly represented knowledge and interact with their environment can be used for this task; however, the lack of a unifying methodology and development tools makes KB controllers difficult to create, maintain, and reuse. This paper presents the IN-VICON toolkit, based on the IndiGolog agent programming language with elements from control theory. It provides a basic methodology, a vision module declaration template, a suite of control components, and support tools for KB controller development. We have evaluated INVICON in two case studies that involved controlling vision-based pose estimation systems. The case studies show that INVICON reduces the effort needed to build KB controllers for challenging domains and improves their flexibility and robustness. 1.

In this paper, we define Self Adaptive Software (SAS), discuss paradigms for implementing SAS, the core problem of self evaluation, discuss some applications, and indicate some area of future work.

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 What We Have Achieved . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2 Abstract Representations: Qualitative Reasoning and Qualitative Physics 8 2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 Qualitative Reasoning and Self-Adaptive Software . . . . . . . . . . . . . . . . . . . 8 2.3 Qualitative Reasoning: State of the Art . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.4 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3 Interval Arithmetic Kalman Filtering 13 3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2 The Biscay Distribution Filter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.3...

Distributed Data Mining(DDM) has evolved into an important and active area of research because of theoretical challenges and practical applications associated with the problem of extracting, interesting and previously unknown knowledge from very large real-world databases. Extension Set Theory is a mathematical formalism for representing uncertainty that can be considered an extension of the classical set theory. It has been used in many different research areas, including those related to inductive machine learning and reduction of knowledge in Distributed data-based systems. Extenics is a theory to solve the contradiction problem, it will be a new way to look for and find knowledge through analysis the contradiction and transformation the result of the data mining using the extension methods. In this paper, introduced the matter-element and extension set that is the base of the extenics, researched the way to find out and generate the new knowledge that help by the divergence, change and transformation based on the extension The main aim is to show how Extension sets can be effectively used to extract knowledge from large databases.