the linear algebraic invariant calculus is a powerful technique for the verification of Petri nets. Traditionally it is used for structural verification, i.e. for avoiding the explicit construction of a state space. I...
详细信息
In this paper, a hybrid decision tree learning approach is presented that combines fuzzy C-means method and the ID3 algorithm in decision tree construction from continuous-valued features. the fuzzy C-means method is ...
详细信息
In this paper, a hybrid decision tree learning approach is presented that combines fuzzy C-means method and the ID3 algorithm in decision tree construction from continuous-valued features. the fuzzy C-means method is applied to find a number of central means for each continuous-valued feature and thus discretize such features. the ID3 algorithm is subsequently used to build a decision tree from the discretized data. Preliminary experiments using a real-world time-series data set from the Louisiana coast are reported that compare our method withthe OC1 system for oblique decision tree learning. the experiment results seem to suggest that the proposed hybrid method achieves better or comparable classification accuracy.
Many safety-critical systemsthat have been considered by the verification community are parameterized by the number of concurrent components in the system, and hence describe an infinite family of systems. Traditiona...
详细信息
A method is developed to combine multiresolution analysis with fuzzy system to build dynamic system model. the proposed method consists of two parts, the construction and application of model. To construct the model, ...
详细信息
ISBN:
(纸本)0780378105
A method is developed to combine multiresolution analysis with fuzzy system to build dynamic system model. the proposed method consists of two parts, the construction and application of model. To construct the model, the signals are decomposed respectively to form data pairs on different scale and, the data pairs are used to construct the model on different scale whose output will be reconstructed to approximate the original signal. When this method is put into use, a certain length of past signal and current signal are used to predict the model output and, at next time instance, the past signal is push forward. this is a repeated procedure. the simulation shows the method is effective.
Hybrid dynamic systems include both continuous and discrete state variables. Properties of hybrid systems, which have an infinite state space, can often be verified using ordinary model checking together with a finite...
详细信息
the construction of fuzzy measures in the fuzzy integral, which is considered to be the crucial point for the extended utilization of this fusion methodology, is attained in the here presented paper through a Self-Org...
详细信息
the construction of fuzzy measures in the fuzzy integral, which is considered to be the crucial point for the extended utilization of this fusion methodology, is attained in the here presented paper through a Self-Organizing Map (SOM). this fact can improve the performance in the fuzzy measure assessment specially in high-dimensional feature spaces. Different methodologies for knowledge discovery related to the SOM paradigm are taken into consideration in order to achieve the assessment of the fuzzy measure coefficients. Furthermore an overview of the utilization of the fuzzy integral in classification problems is given. Finally two hybrid frameworks considering the SOM and the fuzzy integral are presented and used for fuzzy classification.
By definitionTimedAutomata have an infinite state-space, thus for verification purposes, an exact finite abstraction is required. We propose a locationbased finite zone abstraction, which computes an abstraction based...
详细信息
Traditional classification rules are in the form of production rules. Recent works in hybrid classification algorithms have proposed the generation of contextual rules, whereby the right-hand side of the production ru...
详细信息
ISBN:
(纸本)0769520383
Traditional classification rules are in the form of production rules. Recent works in hybrid classification algorithms have proposed the generation of contextual rules, whereby the right-hand side of the production rule is replaced by a classifier, to achieve higher accuracy. In this work, we present a framework to further generalize classification rules such that the left-hand side of a production rule is expressed as a conjunction of classifiers, called space splitters. An intelligent divide-and-conquer approach is designed to construct such generalized classification rules. the construction algorithm, GCTree, is elegant, efficient and scalable. the resulting classifier is able to achieve high predictive accuracy that outperforms naive Bayes and C4.5. Experiments demonstrate that GCTree is compact and stable.
the paper deals withthe problem of error estimation in 3D reconstruction. It shows how interval analysis can be used in this way for 3D vision applications. the description of an image point by an interval assumes an...
详细信息
the paper deals withthe problem of error estimation in 3D reconstruction. It shows how interval analysis can be used in this way for 3D vision applications. the description of an image point by an interval assumes an unknown but bounded localization. We present a new method based on interval analysistools to propagate this bounded uncertainty. this way of computation can produce guaranteed results since a datum is not the most probabilistic value but an interval which contains the true value. We validate our method by computing a guaranteed model for a projective camera, and we achieve a guaranteed 3D reconstruction.
the paper proposes a machine learning method for self-localising a mobile agent, using the images supplied by a single omni-directional camera. the images acquired by the camera may be viewed as an implicit topologica...
详细信息
ISBN:
(纸本)0769519482
the paper proposes a machine learning method for self-localising a mobile agent, using the images supplied by a single omni-directional camera. the images acquired by the camera may be viewed as an implicit topological representation of the environment. the environment is a priori unknown and the topological representation is derived by unsupervised neural network architecture. the architecture includes a self-organising neural network, and is constituted by a growing neural gas, which is well known for its topology preserving quality. the growth depends on the topology that is not a priori defined, and on the need of discovering it, by the neural network, during the learning. the implemented system is able to recognise correctly the input frames and to reconstruct a topological map of the environment. Each node of the neural network identifies a single zone of the environment and the connections between the nodes correspond to the real space connections in the environment.
暂无评论