- Full text PDF available (5)
An intelligent problem solver must be able to decompose a complex problem into simplex parts. A decomposition algorithm would not only be beneficial for traditional subgoal-oriented planning systems but also support distributed, multi-agent planners. In this paper , we present an algorithm for automatic problem decomposition. Given a domain description with… (More)
In this paper, we present a new image indexing and retrieval method for image database applications. We introduce a novel image content description feature termed Scene Structural Matrix (SSM). The SSM captures the overall structural information of the scene by indexing the geometric features of the image. In this work, we also introduce a constraint… (More)
In this paper, we provide a nonmonotonic logic for analogical reasoning and a graphical representation method to facilitate the calculation of analogies .
We introduce a simple image coding method, the block truncation coding (BTC) technique, as a novel approach to the construction of colour image databases. It is shown that BTC can not only be used to compress the images thus achieving storage eflciency. the BTC codes can also be used directly to construct image features for effective image retrieval. From… (More)
In this paper, we develop a decision-theoretic planning approach to synthesizing high-quality contract anytime algorithms. Anytime algorithms are considered as time-parameterized probabilistic actions. Given a set of primitive anytime algorithms and their performance prooles, the problem of synthesizing high-quality anytime algorithms is translated to a… (More)