摘要
（3852）
PDF（pc）
（1824KB）（1868）
收藏With massive amounts of data stored in databases, mining information and knowledge in databases has become an important issue in recent research. Researchers in many different fields have shown great interest in data mining and knowledge discovery in databases. Several emerging applications in information providing services, such as data warehousing and on-line services over the Internet, also call for various data mining and knowledge discovery techniques to understand user behavior better, to improve the …

摘要
（3257）
PDF（pc）
（254KB）（1526）
收藏In this paper, rough set theory is used to extract roughly-correct inference rules from information systems. Based on this idea, the learning algorithm ERCR is presented. In order to refine the learned roughly-correct inference rules, the knowledge-based neural network is used. The method presented here sufficiently combines the advanages of rough set theory and neural network.

摘要
（3143）
PDF（pc）
（708KB）（1324）
收藏This paper proposes a novel elastic model and presents a deformable registration method based on the model. The method registers images without the need to extract features from the images, and therefore works directly on grey-level images. A new similarity metric is given on which the formation of external forces is based. The registration method, taking the coarse-to-fine strategy constructs external forces in larger scales for the first few iterations to rely more on global evidence, and then in smaller …

摘要
（3074）
PDF（pc）
（446KB）（1368）
收藏In this papert a brief survey on knowledge-based animation techniques is given.Then a VideoStream-based Knowledge Representation Model (VSKRM) for Joint Objects is presented which includes the knowledge representation of: Graphic Object,Action and VideoStream. Next a general description of the UI framework of a system is given based on the VSKRM model. Finally a conclusion is reached.

摘要
（2859）
PDF（pc）
（325KB）（1148）
收藏In this paper, an interactive learning algorithm of context-free language is presented. This algorithm is designed especially for system SAQ, which is a system for formal specification acquisition and verification. As the kernel of concept acquisition subsystem (SAQ/CL) of SAQ, the algorithm has been implemented on SUN SPARC workstation. The grammar to be obtained can represent sentence structure naturally.

摘要
（3567）
PDF（pc）
（606KB）（1222）
收藏Motion perception is one of the most important aspects of the biological visual system, from which people get a lot of information of the natural world. In this paper, trying to simulate the neurons in MT (motion area in visual cortex) which respond selectively both in direction and speed, the authors propose a novel multiplicative inhibitory velocity detector (MIVD) model, whose spatiotemporal joint parameter K determines its optimal velocity. Based on the Response Amplitude Disparity (RAD) property of MIV…

摘要
（3131）
PDF（pc）
（668KB）（1198）
收藏An important issue in Knowledge Discovery in Databases is to allow the discovered knowledge to be as close as possible to natural languages to satisfy user needs with tractability on one hand, and to offer KDD systems robustness on the other hand. At this junction, this paper describes a new concept of linguistic atoms with three digital characteristics: expected value Ex, entropy En, and deviation D. The mathematical description has effectively illtegrated the fuzziness and randomness of linguistic terms i…

摘要
（5753）
PDF（pc）
（893KB）（1870）
收藏The blur in target images caused by camera vibration due to robot motion or hand shaking and by object(s) moving in the background scene is different to deal with in the computer vision system. In this paper, the authors study the relation model between motion and blur in the case of object motion existing in video image sequence, and work on a practical computation algorithm for both motion analysis and blur image restoration. Combining the general optical flow and stochastic process, the paper presents an approach by which the motion velocity can be calculated from blurred images. On the other hand, the blurred image can also be restored using the obtained motion information. For solving a problem with small motion limitation on the general optical flow computation, a multiresolution optical flow algorithm based on MAP estimation is proposed. For restoring the blurred image, an iteration algorithm and the obtained motion velocity are used. The experiment shows that the proposed appro…

摘要
（3005）
PDF（pc）
（404KB）（1240）
收藏A recent trend in computer graphics and image processing is to use Iterated Function System (IFS) to generate and describe both man-made graphics and natural images. Jacquin was the first to propose a fully automatic gray scale image compression algorithm which is referred to as a typical static fractal transform based algorithm in this paper. By using this algorithm, an image can be condensely described as a fractal transform operator which is the combination of a set of fractal mappings. When the fractal transform operator is iteratedly applied to any initial image, a unique attractor (reconstructed image) can be achieved. In this paper) a dynamic fractal transform is presented which is a modification of the static transform. Instead of being fixed, the dynamic transform operator varies in each decoder iteration, thus differs from static transform operators. The new transform has advantages in improving coding efficiency and shows better convergence for the decoder.

摘要
（3310）
PDF（pc）
（257KB）（1172）
收藏This paper gives an outline of knowledge base revision and some recently presented complexity results about propositional knowledge base revision. Different methods for revising propositional knowledge baize have been proposed recently by several researchers, but all methods are intractable in the general case. For practical application, this paper presents a revision method for special case, and gives its corresponding polynomial algorithm.

摘要
（3045）
PDF（pc）
（478KB）（1171）
收藏Some concepts used in knowledge base maintenance, such as sequence, new law, user's rejection and reconstructions of a knowledge base, are first introduced, and then a framework for extended logic programming (ELP) is given,where an extended logic program is equivalent to a knowledge base. A transition system called R-calculus for ELP is provided. For a given knowledge base and a user's rejection, the Rcalculus for ELP will deduce best revisions of the base. The soundness and the completeness of the Rcalcul…

摘要
（3449）
PDF（pc）
（574KB）（1414）
收藏New algorithms based on artificial neural network models are presented for cubic NURBS cuxve and surface interpolation. When all the knot spans are identical, the NURBS curve interpolation procedtire degenerates into that of uniform rational B-spline curves. If all the weights of data points are identical,then the NURBS curve interpolation procedure degenerates into the integral B-spline curve interpolation.

摘要
（2989）
PDF（pc）
（166KB）（1217）
收藏In this paper, the constrained optimization technique for a substantial prob-lem is explored, that is accelerating training the globally recurrent neural net-work. Unlike most of the previous methods in feedforward neuxal networks, the authors adopt the constrained optimization technique to improve the gradiellt-based algorithm of the globally recuxrent neural network for the adaptive learn-ing rate during training. Using the recurrent network with the improved algo-rithm, some experiments in two real-world…

摘要
（3018）
PDF（pc）
（432KB）（1475）
收藏This paper presents a new approach to the outdoor road scene understand-ing by using omni-view images and backpropagation networks. Both the road directions used for vehicle heading and the road categories used for velilcle local-ization are determined by the integrated system. There are three main features about the work. First, an omni-view image sensor is used to extract image samples, and the original image is preprocessed so that the inputs of the net-work is rotation-invariant and simple. Second, the …

摘要
（3367）
PDF（pc）
（209KB）（1368）
收藏This paper presents a neural network based fault diagnosis approach for analog circuits, taking the tolerances of circuit elements into account. Specifi-cally, a normalization rule of input information, a pseudo-fault domain border (PFDB) pattern selection method and a new output error function are proposed for training the backpropagation (BP) network to be a fault diagnoser. Experi-mental results demonstrate that the diagnoser performs as well as or better than any classical approaches in terms of accurac…

摘要
（3811）
PDF（pc）
（735KB）（1347）
收藏This paper proposes NNF - a fuzzy Petri Net system based on neural network for proposition logic representation, and gives the formal definition of NNF. For the NNF model, forward reasoning algorithm, backward reason-ing algorithm and knowledge learning algorithm are discussed based on weight training algorithm of neural network - Back Propagation algorithm. Thus NNF is endowed with the ability of learning a rule. The paper concludes with a discussion on extending NNF to predicate logic, forming NNPrF, and …

摘要
（3355）
PDF（pc）
（594KB）（1416）
收藏This paper presents a framework called logical knowledge object (LKO),which is taken as a basis of the dependable development of knowledge based systems(KBSs). LKO combines logic programming and object-oriented programming paradigms, where objects are viewed as abstractions with states,constraints, behaviors and inheritance. The operational semantics defined in the style of natural semantics is simple and clear. A hybrid knowledge represen-tation amalgamating rule, frame, semantic network and blackboard is …

摘要
（2813）
PDF（pc）
（113KB）（1339）
收藏In this paper, we propose a behaviorbased path planner that can self learn in anunknown environment. A situated learning algorithm is designed which allows therobot to learn to coordinate several concurrent behaviors and improve its performanceby interacting with the environmellt. Behaviors are implemented using CMAC neuralnetworks. A simulation environment is set up and some simulation experiments arecarried out to rest our learning algorithm.

摘要
（2751）
PDF（pc）
（607KB）（1188）
收藏This paper first establishes a neural network model for logic circuits fromthe truth table by using linear equations theory, presents a kind of ATPG neuralnetwork model, and investigates energy local minima for the network- And then,it proposes the corresponding techniques to reduce the number of energy localminima as well as some approaches to escaping from local minimum of eliergyFinally, two simulation systems, the binary ATPG neural network and thecontinuous ATPG neural network, are implemented oli SUN …

摘要
（2945）
PDF（pc）
（280KB）（1333）
收藏This paper presents and analyzes three fundamental problems in knowledgeacquisition, and proposes a general method for tackling them. The methoddivides the whole process of knowledge acquisition into a set of almost indepen-dent pieces, each of which can be finished by knowledge engineers, experts andassistants, respectively.

摘要
（2732）
PDF（pc）
（264KB）（1235）
收藏The maintenance sequences of a knowledge base and their limits are intro-duced. Some concepts used in knowledge base maintenance, such as new laws,user's rejections, and reconstructions of a knowledge base are defined; the re-lated theorems are proved. A procedure is defined using transition systems; itgenerates maintenance sequences for a given user's model and a knowledge base.It is proved that all sequences produced by the procedure are convergent, andtheir limit is the set of true sentences of the model…

摘要
（2755）
PDF（pc）
（239KB）（1314）
收藏We have developed a fuzzy neural expert system that has the precisionand learning ability of a neural network. Knowledge is acquired from domainexperts as fuzzy rules and membership functions. Then, they are convertedinto a neural network which implements fuzzy inference without rule matching.The neural network is applied to problem-solving and learns from the dataobtained during operation to enhance the accuracy The learning ability of theneural network makes it easy to modify the membership functions defi…

摘要
（2897）
PDF（pc）
（383KB）（1287）
收藏In this paper we discuss the learning convergence of the cerebellar model articulation controller (CMAC) in cyclic learning. We prove the following results. First, if the training samples are noiseless, the training algorithm converges if and only if the learning rate is chosen from (0, 2). Second, when the training samples have noises, the learning algorithm will converge with a probability of one if the learning rate is dynandcally decreased. Third, in the case with noises, with a small but fixed learnin…

摘要
（2761）
PDF（pc）
（338KB）（1149）
收藏To solve the Imperfect Theory Problem(ITP)faced by Explanation Based Generalization(EBG), this paper proposes a methodology,Deep Knowledge Based Learning Methodology(DKBLM)by name, and gives an implementstion of DKBLM,called Hierarchically Distributed Learning System(HDLS).As an example of HDLS's application,this paper shows a learning system(MLS)in meteorology domain and its running with a simplified example. DKBLM can acquire experiential knowledge with causality in it.it is applicable to those kinds of d…

摘要
（2928）
PDF（pc）
（266KB）（1246）
收藏In this paper,the memory capacity of Probabilistic Logic Neuron(PLN)network is discussed. We obtain two main results:(1)the method for constructing a PLN network with a given memory capacity;(2)the relationship between the memory capacity and the size of a PLN network.We show that the memory capacity of a PLN network depends on not only the number of input ports of its element but also the number of elements themselves.The results provide a new method for designing a PLN network.

摘要
（2856）
PDF（pc）
（164KB）（1309）
收藏This paper proposes a knowledge-based specification technique(KST)for protocol development. This technique semi-automatically translates a protocol described in an informal description(natural languages or graphs)into one described in formal specifications(Estelle and SDL).The translation processes are supported by knowledge stored in the knowledge base.This paper discusses the concept, the specification control mechanism of KST and the rules and algorithms for production of FSM's which is the basis of Este…

摘要
（3728）
PDF（pc）
（571KB）（1171）
收藏Machine learning(ML)is a major subfield of artificial intelligence(AI).It has been seen as a feasi- ble way of avoiding the knowledge bottleneck problem in knowledge-based systems development.Re- search on ML has concentrated in the main on inductive learning,a paradigm for inducing rules from unordered sets of exmaples.AQ11 and ID3,the two most widespread algorithms in ML,are both induc- tive.This paper first summarizes AQ11,ID3 and the newly-developed extension matrix approach based HCV algorithm;and then…

摘要
（2364）
PDF（pc）
（279KB）（1076）
收藏Up to now, no satisfactory theory has been established for formalizing incomplete knowledge in incomplete databases. In this paper, we clarify why existing closed world approaches, such as the CWA, the GCWA, the ECWA, circumscription, predicate completion and the PWA, fail to do so, and propose a new method. The method is an augmentation of both the ECWA and circumscrip- tion with the mechanism to discriminate implicitly expressed positive knowledge, negative knowledge and truly unknown knowledge.

摘要
（2516）
PDF（pc）
（645KB）（1034）
收藏Automatic medical image analysis shows that image segmentation is a crucial task for any practical AI system in this field. On the basis of evaluation of the existing segmentation methods, a new image segmentation method is presented. To seek the perfect solution to knowledge representation in low level machine vision, a new knowledge representation approach—— "Notebook" approach is proposed and the processing of visual knowledge is discussed at all levels. To integrate the computer vision theory with Gesta…

摘要
（2689）
PDF（pc）
（290KB）（1141）
收藏New users of an application system, especially computer novices, can become confused and frus- trated after experiencing the first, perhaps not recoverable error situations during the early stages of explora- tion and learning. System facilities, which let users UNDO and REDO executed commands, are suggested to be an aid for active learning and can be used as a method for systematic exploration through recovering from unknown and newly explored (perhaps wrong) system states by cancelling executed commands w…

摘要
（2308）
PDF（pc）
（295KB）（1247）
收藏The traditional reasoning system based on first order predicate logic can t represent and handle de- fault knowledge.This paper presents a logical framework representation approach for default reasoning. Based on Mixed SLDNF-resolution,a nonmonotonic reasoning system has been constructed.

摘要
（2244）
PDF（pc）
（424KB）（1133）
收藏This paper proposes an approach for functional knowledge representation based on problem reduction,which represents the organization of problem-solving activities in two levels:reduction and reasoning.The former makes the functional plans for problem-solving while the latter constructs functional units, called handlers,for executing subproblems designated by these plans.This approach emphasizes that the representation of domain knowledge should be closely combined with(rather than separated from)its use the…

摘要
（2631）
PDF（pc）
（691KB）（1193）
收藏This paper describes some experiments of analogical learning and automated rule construction.The present investigation focuses on knowledge acquisition,learning by analogy,and knowledge retention. The developed system initially learns from scratch,gradually acquires knowledge from,its environment through trial-and-error interaction,incrementally augments its knowledge base,and analogically solves new tasks in a more efficient and direct manner.

摘要
（2391）
PDF（pc）
（584KB）（1022）
收藏Competition based neural networks have been used to solve the generalized assignment problem and the quadratic assignment problem.Both problems are very difficult and are ε approximation complete.The neural network approach has yielded highly competitive performance and good performance for the quadratic assignment problem.These neural networks are guaranteed to produce feasible solutions.

摘要
（2385）
PDF（pc）
（327KB）（1140）
收藏A prototype expert system for generating image processing programs using the subroutine pack- age SPIDER is described in this paper.Based on an interactive dialog,the system can generate a complete application program using SPIDER routines.

摘要
（2250）
PDF（pc）
（450KB）（1233）
收藏A domain knowledge driven user interface development approach is described.As a conceptual de- sign of the user interface,the domain knowledge defines the user interface in terms of objects,actions and their relationships that the user would use to interact with the application system.It also serves as input to a user interface management system(UIMS)and is the kernel of the target user interface. The principal ideas and the implementation techniques of the approach is discussed.The user interface model,use…

摘要
（2134）
PDF（pc）
（313KB）（1007）
收藏This paper presents a new algorithm for generating 3D images of B-reps objects with trimmed surface boundaries.The 3D image is a discrete voxel-map representation within a Cubic Frame Buffer(CFB). The definition of 3D images for curve,surface and solid object are introduced which imply the connectivity and fidelity requirements.Adaptive Forward Differencing matrix(AFD-matrix)for 1D-3D manifolds in 3D space is developed.By setting rules to update the AFD-matrix,the forward difference direction and stepwise c…

摘要
（2280）
PDF（pc）
（334KB）（1084）
收藏To use reasoning knowledge accurately and efficiently,many reasoning methods have been proposed. However,the differences in form among the methods may obstruct the systematical analysis and harmonious integration of them.In this paper,a common reasoning model JUM(Judgement Model)is introduced. According to JUM,a common knowledge representation form is abstracted from different reasoning methods and its limitation is reduced.We also propose an algorithm for transforming one type of JUMs into another.In some ...

摘要
（2455）
PDF（pc）
（498KB）（1095）
收藏This paper proposes an approach to synthesize functional programs of Backus FP system from input/output instances.Based on a theory of orthogonal expansion of programs,the task of program synthesis is expressed in program equations,and fulfilled by solving them according to the knowledge about the equivalence between programs.Some general knowledge of solving program equations with a number of examples are given in the paper.

摘要
（2266）
PDF（pc）
（582KB）（1070）
收藏The attributed grammar is expanded by emphasizing semantic information.Various relations between variables of a production,and control strategies are introduced.As a result, two kinds of generalized attributed grammars are obtained.On the basis of such attributed grammars,a syntactic-semantic approach is suggested for one dimensional wave description, pictorial pattern recognition,hierarchical image processing and knowledge representation in some specific domains.