Providing cognitive assistance in smart homes is a field of research that receives a lot of attention lately. In order to give adequate assistance at the opportune moment, we need to recognize the observed behavior when the patient carries out some activities in a smart home. To address this challenging issue, we present a formal activity recognition framework based on possibility theory. We present initial results from an implementation of this possibilistic recognition approach in a smart home laboratory.

Visual information can be communicated using informal sketches of the sort used by people in design conversations. These sketches can be captured using TabletPCs, however, they can be hard or impossible to understand without additional context, domain knowledge, and interaction with the user. We illustrate the utility of these components with examples and then describe a system, midos, that uses these components to reason about a simple mechanical design.

Reinforcement learning algorithms are often tasked with learning an optimal control policy in a continuous state space. Since it is infeasible to learn the optimal action to take for every possible observation in a continuous state space, use- ful abstractions of the space must be constructed and subse- quently learned on. Abstraction techniques that generalize the space into very few abstract states must take care to avoid creating an abstraction that prevents learning the optimal policy. Many commonly used abstractions, such as CMAC can take considerable effort to tune to ensure a learnable abstraction is created. In this work we propose three methods that derive state abstractions automatically, in part by making use of the dimensionality reduction capability of the RL-SANE algorithm. We show that abstractions derived from these automatic methods can allow a learning algorithm to converge to the optimal policy faster than with a fixed abstraction. Ad- ditionally, these techniques are able to break the space into very few abstract states, further facilitating rapid learning.

Visual feedback is an important approach in persuasive technology. We present four significant design dimensions of persuasive feedback systems. We investigate several previous notable projects and find out the underlying metaphorical structures within them. We analyze the meaning of metaphor in the persuasive feedback design, and examine how metaphor is being used. The results tell us that metaphor analysis plays a useful role in interpreting the creativity of visual design in the persuasive feedback system.

The quality and nature of knowledge that can be found by an automated knowledge-extraction system depends on its inputs. For systems that learn by reading text, the Web offers a breadth of topics and currency, but it also presents the problems of dealing with casual, unedited writing, non-textual inputs, and the mingling of languages. The results of extraction using the KNEXT system on two Web corpora — Wikipedia and a collection of weblog entries — indicate that, with automatic filtering of the output, even ungrammatical writing on arbitrary topics can yield an extensive knowledge base, which human judges find to be of good quality, with propositions receiving an average score across both corpora of 2.34 (where the range is 1 to 5 and lower is better) versus 3.00 for unfiltered output from the same sources.

Learning, which aims at combining probabilistic graphical Markov networks have proved to be a very useful tool to models with first order logics representations. The represent probability distributions over large domains (see work that we present in this paper has been motivated by for instance, Chapter 8 in (Bishop 2006)). A Markov Network Markov Logic Networks (MLN), introduced in (Richardson is an undirected graphical model, where variables are and Domingos 2006). A Markov Logic Network is defined represented by nodes and features on subsets of variables by a set of weighted first-order formulas.

Reinforcement learning (RL) algorithms have the ability to learn optimal policies for control problems by exploring a domain's state space. Unfortunately, for most problems the size of the state space is too great for RL technologies to fully explore in order to find good policies. State abstraction is one way of reducing the size and complexity of a domain's state space in order to enable RL. In this paper we introduce a new approach for automatically deriving state abstractions called Evolutionary Tile Coding that uses a genetic algorithm for deriving effective tile codings. We provide an empirical analysis of the new algorithm comparing it to another adaptive tile coding method as well as fixed tile coding. Our results show that our approach is able to automatically derive effective state abstractions for two RL benchmark problems. Additionally, we present an intriguing result that shows the classical mountain car problem's state space can be reduced to just two states and still preserve the discovery of an optimal policy.

Past research has shown that when tree-structured background knowledge is available, it can be exploited to increase the efficiency of classification learning. When this kind of background knowledge is available, the problem becomes one of compositional classification. Of course, if the background knowledge contains errors, the quality of the learned hypothesis will suffer. In this paper we study the effect of faulty knowledge engineering on compositional classification learning. We present and analyze empirical results that show the impact on the quality of compositional classification learning as the quality of knowledge engineering is degraded.

This paper investigates how readily an unsolvable constraint satisfaction problem can be reformulated so that it becomes solvable. We investigate small changes in the definitions of the problemís constraints, changes that alter neither the structure of its constraint graph nor the tightness of its constraints. Our results show that structured and unstructured problems respond differently to such changes, as do easy and difficult problems taken from the same problem class. Several plausible explanations for this behavior are discussed.

One approach to combining ASP and CP is to integrate There are several approaches to representing and solving theory-specific predicates into propositional formulas (motivated constraint satisfaction problems: constraint programming by SMT), and to extend the ASP solver's decision (CP; Dechter 2003, Rossi, van Beek, and Walsh 2006), answer engine with a higher level proof procedure (Baselice, set programming (ASP; Baral 2003), propositional satisfiability Bonatti, and Gelfond 2005; Mellarkod and Gelfond 2008; checking (SAT; Biere et al. 2009), its extension Gebser, Ostrowski, and Schaub 2009). However, the resulting to satisfiability modulo theories (SMT; Nieuwenhuis, Oliveras, systems have a number of limitations. First, they are and Tinelli 2006), and many more. Each has its particular tied to particular ASP and CP solvers. Second, the support strengths: for example, CP systems support global constraints, for global constraints is limited. Third, communication between ASP systems permit recursive definitions and offer the ASP and CP solver is restricted. Alternative techniques, default negation, whilst SAT solvers often exploit very such as reformulating constraints into ASP have received efficient implementations.