In any measuring system the categorization of the error generation factors leads to simplification of complex error problems and to higher suppression of the error. In this paper we categorize, quantify and analyze th...
详细信息
Modern spacecraft demand an attitude control system with very high performance and accuracy, and many new features, such as self-modification, adaptability, more autonomy and fault tolerance. NN adaptive control can b...
详细信息
Modern spacecraft demand an attitude control system with very high performance and accuracy, and many new features, such as self-modification, adaptability, more autonomy and fault tolerance. NN adaptive control can be applied to spacecraft attitude control to meet the demanding requirements and to provide many new features. To control spacecraft attitude motion, a recurrent NN is used to train as an identification model and an adaptive controller. The quaternion method can overcome the singularity problem in a traditional Euler differential equation. To accelerate the convergence speed of the NN training course, an extended Kalman filter method is used to train NN weights.
In this paper, a novel learning method for special Bayesian networks which consist of noisy-OR and noisy-AND nodes is introduced. This method can learn networks with hidden variables and discover hidden variables when...
详细信息
In this paper, a novel learning method for special Bayesian networks which consist of noisy-OR and noisy-AND nodes is introduced. This method can learn networks with hidden variables and discover hidden variables when necessary. Compared with previous techniques for learning Bayesian networks, it uses the information in the data to guide the search for useful revisions, and can greatly improve the efficiency of the algorithm. Furthermore, this method can also be used for theory refinement. The experiments demonstrate that its performance is comparable to that of other existing hybrid theory refinement systems, while the networks produced by this method have more precise semantics and are more easily understood. In addition, this method also provides a direct mechanism for incorporating knowledge expressed as propositional Horn-clause rules into a Bayesian network. This mechanism could potentially ease the process of building Bayesian networks.
Path-constrained robot trajectory planning in the vicinity of ordinary singularities is studied in this paper. First, the desired end-effector path is parameterized with an untimed variable q/sub 0/, by which the robo...
详细信息
ISBN:
(纸本)0780374908
Path-constrained robot trajectory planning in the vicinity of ordinary singularities is studied in this paper. First, the desired end-effector path is parameterized with an untimed variable q/sub 0/, by which the robot kinematics can be formulated as a nonlinear equation. The solution to this equation forms a spatial curve in the augmented joint space. Then the path-tracking problem can be fulfilled by computing the curve solution numerically. This produces a pseudo trajectory with respect to an artificial independent parameter s, which represents the arc-length of the solution curve. The trajectory with respect to time can be obtained naturally by arbitrarily assigning s(t). Numerical simulations are carried out to verify the algorithm.
*** is a boosting method specifically designed for solving multi-class, multi-label text categorization problems. Fabrizio Sebastiani et al. (2000) provided another idea to improve these base classifiers: combining tw...
详细信息
*** is a boosting method specifically designed for solving multi-class, multi-label text categorization problems. Fabrizio Sebastiani et al. (2000) provided another idea to improve these base classifiers: combining two or more weak hypotheses as a single base classifier. Its main problem is that the amount of hypotheses selected to combine is determined not by their importance, but by the boosting iteration times already performed. This paper proposes two dynamical ways for combining any number of hypotheses according to their importance. Experimental results show that the new ideas do improve the performance of boosting.
The time that system takes to find out exceptions cannot be too long in a real-time system. In this paper, we first construct a stochastic Petri net to analyze the relationship between the time the system takes to dia...
详细信息
The time that system takes to find out exceptions cannot be too long in a real-time system. In this paper, we first construct a stochastic Petri net to analyze the relationship between the time the system takes to diagnose faults and the system's availability. We conclude that the shorter the time it takes the higher the availability it can achieve. Next, we explain how the self-detecting fault can be realized. Finally, several experiments have been designed to prove its effectiveness.
How to provide high-quality service of hot data has become more and more important in all network solutions. In this paper, basing on RAID connected directly in the network, we put forward a strategy of migrating data...
详细信息
How to provide high-quality service of hot data has become more and more important in all network solutions. In this paper, basing on RAID connected directly in the network, we put forward a strategy of migrating data automatically, which can enlarge the I/O ability of the single server several times. In the following text, we will explain in detail the principle, process, and layer in which the strategy is turned into reality. At last, we make analysis of the serving efficiency in this case.
Multimedia data, typically image data, is increasing rapidly across the Internet and elsewhere. To keep pace with the increasing volumes of image information, new techniques need to be investigated to retrieve images ...
详细信息
In this paper, we present a real-time method for mining the facial patterns and tracking the facial emotion. We first recognize the facial patterns based on a nonsupervised idea of pattern mining from video. To raise ...
详细信息
暂无评论