In this paper, we develop a multi-step prediction algorithm that is guaranteed to converge when using general function approximation. Besides, the new algorithm should satisfy the following requirements: first, it doe...
详细信息
In this paper, we develop a multi-step prediction algorithm that is guaranteed to converge when using general function approximation. Besides, the new algorithm should satisfy the following requirements: first, it does not have to be faster than TD(0) in the look-up table representation; however, the new algorithm should be faster than residual gradient method. Second, the new algorithm should learn optimally
In this paper, we discuss the minimal positive realizations for nth-order rational transfer function of a discrete time-invariant linear single-input-single-output (SISO) system with negative poles. By the constructiv...
详细信息
In this paper, we discuss the minimal positive realizations for nth-order rational transfer function of a discrete time-invariant linear single-input-single-output (SISO) system with negative poles. By the constructive method, the necessary and sufficient conditions are provided for these transfer functions to have a positive realization of dimension n. With the benefit of these results, an improvement is made on the existing results about the positive decomposition problem in positive system theory. Numerical examples are employed to validate the results.
A novel fuzzy global sliding mode control (FGSMC) scheme is proposed for position tracking of a class of second-order nonlinear uncertain system. In the proposed scheme, we integrate input-output linearization techniq...
详细信息
A novel fuzzy global sliding mode control (FGSMC) scheme is proposed for position tracking of a class of second-order nonlinear uncertain system. In the proposed scheme, we integrate input-output linearization technique to cancel the nonlinearities. By designing global sliding mode surface, the proposed scheme eliminates reaching phase problem so that the closed-loop system always shows invariance property to parameter uncertainties. Fuzzy logic systems are used to approximate the unknown system functions and switch item. Robust adaptive law is proposed to reduce approximation errors between true nonlinear functions and fuzzy systems, thus chattering phenomenon can be eliminated. Stability of the proposed control scheme is proved and the scheme is applied to an inverted pendulum system. Simulation studies are provided to confirm performance and effectiveness of the proposed control approach
Language model is widely used in OCR *** this paper,based on language model,we propose a two-step method for post-processing of off-line handwritten Chinese address *** to the characteristics of high level and low lev...
详细信息
Language model is widely used in OCR *** this paper,based on language model,we propose a two-step method for post-processing of off-line handwritten Chinese address *** to the characteristics of high level and low level addresses,two different strategies are used:for high level addresses, word-based language model is used with weighed matching search algorithm proposed;for low level addresses,ME model is implemented with similar character *** post-processing,recognition accuracy rises from 41.60%to 78.19%,which means 62.65%errors reduction.
To alleviate the chattering problem, a new type of fuzzy global sliding mode controller (FGSMC) is presented. In this controller, the switching gain is estimated by fuzzy logic system based on the reachable conditions...
详细信息
To alleviate the chattering problem, a new type of fuzzy global sliding mode controller (FGSMC) is presented. In this controller, the switching gain is estimated by fuzzy logic system based on the reachable conditions of SMC, thus the effect of Lugre friction on switch chattering can be alleviated. Moreover, global sliding mode is realized by designing an exponential dynamic sliding surface. Simulation example for flight simulator servo system with Lugre friction model is given to indicate that the proposed controller can guarantee high robust performance all the time and can alleviate chattering phenomenon effectively
This paper deals with the class of Markovian singularly perturbed linear continuous-time systems with time varying and mode-dependent time-delay. The stochastic stability and H infin performance and the H infin stat...
详细信息
This paper deals with the class of Markovian singularly perturbed linear continuous-time systems with time varying and mode-dependent time-delay. The stochastic stability and H infin performance and the H infin state feedback stabilization are tackled. Sufficient conditions in the LMI setting are established for both the problems. A numerical example is provided to show the effectiveness of the developed results
In this paper, we address the general problem of learning from both labeled and unlabeled data. Based on the reasonable assumption that the label of each data can be linearly reconstructed from its neighbors’ labels,...
详细信息
In this paper, we address the general problem of learning from both labeled and unlabeled data. Based on the reasonable assumption that the label of each data can be linearly reconstructed from its neighbors’ labels, we develop a novel approach, called Linear Neighborhood Propagation (LNP), to learn the linear construction weights and predict the labels of the unlabeled data from the labeled data. The main procedure is composed of two steps: (1) it computes the local neighborhood geometry according to the image information by solving a constrained least squares problem, (2) the obtained geometry will be used to predict the labels of unlabeled data by solving a linearly constrained quadratic optimization problem. LNP has at least three characteristics. Firstly, it is much practical in that only one free parameter, the size of neighborhood, requires user-tuning. Secondly it can be easily extended to out-of-sample examples. Finally the labels achieved from LNP can be sufficiently smooth with respect to the intrinsic structure collectively revealed by the labeled and unlabeled points. Many promising experimental results, such as object recognition, data ranking and interactive image segmentation, demonstrate the effectiveness and efficiency of the proposed approach.
Language model is widely used in OCR post-processing. In this paper, based on language model, we propose a two-step method for post-processing of off-line handwritten Chinese address recognition. According to the char...
详细信息
Language model is widely used in OCR post-processing. In this paper, based on language model, we propose a two-step method for post-processing of off-line handwritten Chinese address recognition. According to the characteristics of high level and low level addresses, two different strategies are used: for high level addresses, word-based language model is used with weighed matching search algorithm proposed; for low level addresses, ME model is implemented with similar character method. After post-processing, recognition accuracy rises from 41.60% to 78.19%, which means 62.65% errors reduction
A new type of PID controller is introduced and some properties are given. The novelty of the proposed controller consists in the extension of derivation and integration order from integer to non-integer order. The PI...
详细信息
A new type of PID controller is introduced and some properties are given. The novelty of the proposed controller consists in the extension of derivation and integration order from integer to non-integer order. The PIλDμ controller generally has three advantages when compared to the integerl-order controller: the first is that it has more degrees of freedom in the model; the second is that it has a memory in model,the memory insure the history and its impact to present and future,the third is it ensures the stability of missile. This approach provides a more flexible tuning strategy and therefore an easier achieving of control requirements. Flight dynamic model of an aerodynamic missile is taken into account in implementing the PIλDμ controller. Simulation results show that the PIλDμ controller is not sensitive to the changes of control parameters and the system parameters. Also,the controller has more flexible structure and stronger robustness.
Correlation algorithms based on pixel gray value are very popular and widely used in image template matching. However, these algorithms have high time complexity and are sensitive to the variation of image luminance a...
详细信息
Correlation algorithms based on pixel gray value are very popular and widely used in image template matching. However, these algorithms have high time complexity and are sensitive to the variation of image luminance and scale. To avoid that, a new algorithm based on coding image grey value is proposed. This algorithm divides the image into certain size blocks called R-block, sums the gray value of each R-block pixel, and codes the R-block according to the sorting result among the neighborhood of R-blocks. Image and template are matched by comparing their R-block coding. The R-block is very rapidly and easily coded and only equality comparison is needed. The new algorithm is robust to the linear transformation of pixel grey value and image noise. Its time complexity is reduced to O(M2log(N)), or namely is improved two order of magnitude in contrast to the current correlation algorithms'.
暂无评论