The Knowledge Grid is an intelligent and sustainable Internet application environment that enables people and roles to effectively capture, publish, share and manage explicit knowledge resources. As an important funct...
详细信息
The Semantic Link Network model SLN and Resource Space Model RSM are semantic models proposed separately for effectively specifying and managing versatile resources across the Internet. Collab.rating the relational se...
详细信息
This paper describes a preprocessing mask technique based statistical mixture components segmentation method for extracting blood vessels from brain magnetic resonance angiography (MRA) dataset. The voxels whose inten...
详细信息
ISBN:
(纸本)1581138849
This paper describes a preprocessing mask technique based statistical mixture components segmentation method for extracting blood vessels from brain magnetic resonance angiography (MRA) dataset. The voxels whose intensity is high in the dataset belong to blood vessels or brain skulls, which may bias the adjustment of the blood vessels. Maximum intensity projection (MIP) of the dataset in the Z axis direction was computed and segmented as a mask. The masked MRA dataset was segmented by a low threshold and the remanent voxels were modeled by one normal distribution and one uniform distribution. The parameters were estimated by Expectation-Maximization (EM) algorithm. The results show that this method is feasible for vessel extraction from MRA dataset.
It is a vital and challenging issue in AI community to get the "Right info.mation" to the "Right People" in the "Right Language" in the "Right Timeframe" in the "Right Leve...
详细信息
ISBN:
(纸本)1577352017
It is a vital and challenging issue in AI community to get the "Right info.mation" to the "Right People" in the "Right Language" in the "Right Timeframe" in the "Right Level of Granularity". More and more researchers recognized that a well-designed instructional plan in intelligent tutoring systems will open up new possibilities of genuinely intelligent knowledge delivery for future education society. This paper proposes a novel three-layer student-state model and discusses the core elements in the architecture of a practical ITS model based on the theory of instructional automata The main advantages of instruction automata theory lie in that it can not only generate, regulate, update and implement instructional plans for individualized learner in the efficient and effective way, but also provide a uniform and extensible domain-independent environment for ITS designers and engineers.
In order to deal with some vague assertions more efficiently, fuzzy modal logics have been discussed by many researchers. This paper introduces the notation of fuzzy assertion based on propositional modal logic. As an...
详细信息
In order to deal with some vague assertions more efficiently, fuzzy modal logics have been discussed by many researchers. This paper introduces the notation of fuzzy assertion based on propositional modal logic. As an extension of the traditional semantics about the modal logics, the fuzzy Kripke semantics are considered and the formal system of the fuzzy reasoning based on propositional modal logic is established and the properties about the satisfiability of the reasoning system are discussed.
An algebraic multi-class classification method AHSC, i.e. Algebraic Hyper Surface Classification, is proposed. The separating algebraic hyper surface of two-class data may be directly constructed by a single polynomia...
详细信息
ISBN:
(纸本)0780384032
An algebraic multi-class classification method AHSC, i.e. Algebraic Hyper Surface Classification, is proposed. The separating algebraic hyper surface of two-class data may be directly constructed by a single polynomial in theory, but it is too difficult to separate multi-class data by a single polynomial even though the polynomial is multivalued. AHSC can be used for classifying multi-class data by integrating a series of polynomial networks based on binary numbers which are used for lab.ling the classes of samples. The problem that multi-class data can not always be separated by a single polynomial is solved by AHSC. Moreover, the order of polynomial can be chosen by using an adaptive method. The experiment results show that the new method can efficiently and accurately classify multi-class and high dimension data.
Extracting and using goal orderings is a way to improve efficiencies of planning algorithms. During extracting goal orderings, some of existing methods can only deal with atomic goals of a specific problem that will i...
详细信息
ISBN:
(纸本)0780382730
Extracting and using goal orderings is a way to improve efficiencies of planning algorithms. During extracting goal orderings, some of existing methods can only deal with atomic goals of a specific problem that will introduce too much redundant work, and the others deal with predicates of a planning domain that can not extract enough goal orderings. The paper addressed an abstract method to extract goal orderings. The method used unification to identify different instantiations of a predicate when dealing with predicates. It can not only reduce redundant work during extracting, but also get enough goal orderings.
It has been several years since the research of vectoring topographical map, and there are quite a few progresses in it. But, most of the researches focus on the identification of contour lines;ignoring another import...
详细信息
ISBN:
(纸本)0780375084
It has been several years since the research of vectoring topographical map, and there are quite a few progresses in it. But, most of the researches focus on the identification of contour lines;ignoring another important element of map, spot elevation. As a kind of element of map, spot elevation is rather than a single point. It should be of significance to the comprehension of map, combining with the contour lines. According to analyzing the features of annotation of contour and of elevation point, the paper gives a method of identifying elevation annotation of a scanned topographical map and discusses the principle of the method, including separating character series on the basis of morphological translating and splitting individual character on the basis of vertical projection. At the end of the paper, there is a performance evaluation.
The main idea of SVM, i.e. Support Vector Machine, is mapping nonlinear separable data into higher dimension linear space where the data can be separated by hyper plane. Based on Jordan Curve Theorem, a general classi...
详细信息
The main idea of SVM, i.e. Support Vector Machine, is mapping nonlinear separable data into higher dimension linear space where the data can be separated by hyper plane. Based on Jordan Curve Theorem, a general classification method HSC, Classification based on Hyper Surface, is put forward in this paper. The separating hyper surface is directly made to classify large database. The data are classified according to whether the intersecting number is odd or even. It is a novel approach which has no need of either mapping from lower dimension space to higher dimension space or considering kernel function. It can directly solve the nonlinear classify problem. The experiments show that the new method can efficiently and accurately classify large data.
A Clothoid spline is a planar G2 curve with piecewise linear curvature. Its discrete analogon, planar discrete clothoid spline (PDCS for short) generated by non-linear subdivision, is also of high quality owing to pie...
详细信息
A Clothoid spline is a planar G2 curve with piecewise linear curvature. Its discrete analogon, planar discrete clothoid spline (PDCS for short) generated by non-linear subdivision, is also of high quality owing to piecewise linear curvature distribution. We extend the PDCS to 3D by introducing discrete curvature binormal vectors and discrete Frenet frame. An algorithm similar to the planar case is developed for creation of 3D discrete clothoid splines. Experiments show that 3D discrete clothoid spline still retains high quality. This result makes it possible to construct discrete clothoid spline surfaces on open triangle meshes or curve nets of arbitrary topology.
暂无评论