Showing 1 to 27 of 27 matching Articles
Results per page:
Export (CSV)
By
Sandoval, Alejandro Cruz; Yu, Wen
Post to Citeulike
Dynamic neural networks with different timescales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of the designed network be stable. In this paper, the passivitybased approach is used to derive stability conditions for dynamic neural networks with different timescales. Several stability properties, such as passivity, asymptotic stability, inputtostate stability and bounded input bounded output stability, are guaranteed in certain senses. Numerical examples are also given to demonstrate the effectiveness of the theoretical results.
more …
By
Li, Kang; Peng, JianXun; Fei, Minrui; Li, Xiaoou; Yu, Wen
Show all (5)
Post to Citeulike
This paper investigates the construction of a wide class of singlehidden layer neural networks (SLNNs) with or without tunable parameters in the hidden nodes. It is a challenging problem if both the parameter training and determination of network size are considered simultaneously. Two alternative network construction methods are considered in this paper. Firstly, the discrete construction of SLNNs is introduced. The main objective is to select a subset of hidden nodes from a pool of candidates with parameters fixed ‘a priori’. This is called discrete construction since there are no parameters in the hidden nodes that need to be trained. The second approach is called continuous construction as all the adjustable network parameters are trained on the whole parameter space along the network construction process. In the second approach, there is no need to generate a pool of candidates, and the network grows one by one with the adjustable parameters optimized. The main contribution of this paper is to show that the network construction can be done using the above two alternative approaches, and these two approaches can be integrated within a unified analytic framework, leading to potentially significantly improved model performance and/or computational efficiency.
more …
By
Toxqui, Rigoberto Toxqui; Yu, Wen; Li, Xiaoou
Post to Citeulike
2 Citations
This paper considers the problem of PD control of overhead crane in the presence of uncertainty associated with crane dynamics. By using radial basis function neural networks, these uncertainties can be compensated effectively. This new neural control can resolve the two problems for overhead crane control: 1) decrease steadystate error of normal PD control. 2) guarantee stability via neural compensation. By Lyapunov method and inputtostate stability technique, we prove that these robust controllers with neural compensators are stable. Realtime experiments are presented to show the applicability of the approach presented in this paper.
more …
By
Jesús Rubio, José; Yu, Wen
Post to Citeulike
In this paper, we present a new sliding mode controller for a class of unknown nonlinear discretetime systems. We make the following two modifications: 1) The neural identifier which is used to estimate the unknown nonlinear system, applies new learning algorithms. The stability and nonzero properties are proved by deadzone and projection technique. 2) We propose a new sliding surface and give a necessary condition to assure exponential decrease of the sliding surface. The timevarying gain in the sliding mode produces a lowchattering control signal. The closedloop system with sliding mode controller and neural identifier is proved to be stable by Lyapunov method.
more …
By
Jesus Rubio, Jose; Yu, Wen
Post to Citeulike
5 Citations
Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence, since it has a similar structure as Kalman filter. OBE has some advantages over Kalman filter training, the noise is not required to be Guassian. In this paper OBE algorithm is applied traing the weights of recurrent neural networks for nonlinear system identification. Both hidden layers and output layers can be updated. From a dynamic systems point of view, such training can be useful for all neural network applications requiring realtime updating of the weights. A simple simulation gives the effectiveness of the suggested algorithm.
more …
By
Li, Xiaoou; Yu, Wen
Post to Citeulike
By using differential neural networks, we present a novel robust adaptive controller for a class of unknown nonlinear systems. First, deadzone and projection techniques are applied to neural model, such that the identification error is bounded and the weights are different from zero. Then, a linearization controller is designed based on the neuro identifier. Since the approximation capability of the neural networks is limited, four kinds of compensators are addressed.
more …
By
Yu, Wen; Li, Xiaoou
Post to Citeulike
1 Citations
In general, RBF neural network cannot match nonlinear systems exactly. Unmodeled dynamic leads parameters drift and even instability problem. According to system identification theory, robust modification terms must be included in order to guarantee Lyapunov stability. This paper suggests new learning laws for normal and adjustable RBF neural networks based on InputtoState Stability (ISS) approach. The new learning schemes employ a timevarying learning rate that is determined from inputoutput data and model structure. The calculation of the learning rate does not need any prior information such as estimation of the modeling error bounds.
more …
By
Sandoval, Alejandro Cruz; Yu, Wen; Li, Xiaoou
Post to Citeulike
Many physical systems contains fast and slow phenomenons. In this paper we propose a dynamic neural networks with different timescales to model the nonlinear system. Passivitybased approach is used to derive stability conditions for neural identifer. Several stability properties, such as passivity, asymptotic stability, inputtostate stability and bounded input bounded output stability, are guaranteed in certain senses. Numerical examples are also given to demonstrate the effectiveness of the theoretical results.
more …
By
Ortiz, Floriberto; Yu, Wen; MorenoArmendariz, Marco; Li, Xiaoou
Show all (4)
Post to Citeulike
Normal fuzzy CMAC neural network performs well because of its fast learning speed and local generalization capability for approximating nonlinear functions. However, it requires huge memory and the dimension increases exponentially with the number of inputs. In this paper, we use recurrent technique to overcome these problems and propose a new CMAC neural network, named recurrent fuzzy CMAC (RFCMAC). Since the structure of RFCMAC is more complex, normal training methods are difficult to be applied. A new simple algorithm with a timevarying learning rate is proposed to assure the learning algorithm is stable.
more …
By
López Chau, Asdrúbal; Li, Xiaoou; Yu, Wen; Cervantes, Jair; MejíaÁlvarez, Pedro
Show all (5)
Post to Citeulike
1 Citations
Border points are those instances located at the outer margin of dense clusters of samples. The detection is important in many areas such as data mining, image processing, robotics, geographic information systems and pattern recognition. In this paper we propose a novel method to detect border samples. The proposed method makes use of a discretization and works on partitions of the set of points. Then the border samples are detected by applying an algorithm similar to the presented in reference [8] on the sides of convex hulls. We apply the novel algorithm on classification task of data mining; experimental results show the effectiveness of our method.
more …
By
Rosa, Erick; Yu, Wen; Sossa, Humberto
Post to Citeulike
Deep learning techniques have been successfully used for pattern classification. These advantage methods are still not applied in fuzzy modeling. In this paper, a novel datadriven fuzzy modeling approach is proposed. The deep learning methods is applied to learn the probability properties of input and output pairs. We propose special unsupervised learning methods for these two deep learning models with input data. The fuzzy rules are extracted from these properties. These deep learning based fuzzy modeling algorithms are validated with three benchmark examples.
more …
By
Yu, Wen; Li, Xiaoou; Irwin, George W.
Post to Citeulike
This chapter proposes a novel antiswing control strategy for an overhead crane. The controller includes both position regulation and antiswing control. Since the crane model is not exactly known, fuzzy rules are used to compensate friction, gravity as well as the coupling between position and antiswing control. A highgain observer is introduced to estimate the joint velocities to realize PD control. Using a Lyapunov method and an inputtostate stability technique, the controller is proven to be robustly stable with bounded uncertainties, if the membership functions are changed by certain learning rules and the observer is fast enough. Realtime experiments are presented comparing this new stable antiswing PD control strategy with regular crane controllers.
more …
By
Tang, Jian; Zhao, LiJie; Long, Jia; Chai, Tianyou; Yu, Wen
Show all (5)
Post to Citeulike
1 Citations
Load parameters inside the ball mill have direct relationships with the optimal operation of grinding process. This paper aims to develop a selective ensemble modeling approach to estimate these parameters. At first, the original vibration signal is decomposed into a number of intrinsic mode functions (IMFs) using empirical mode decomposition (EMD) adaptively. Then, frequency spectra of these IMFs are obtained via fast Fourier transform (FFT), and a serial of kernel partial least squares (KPLS) submodels are constructed based on these frequency spectra. At last, the ensemble models are obtained by integrating the branch and band (BB) algorithm and the information entropybased weighting algorithm. Experimental results based on a laboratory scale ball mill indicate that the propose approach not only has better prediction accuracy, but also can interpret the vibration signal more deeply.
more …
By
Cervantes, Jair; Li, Xiaoou; Yu, Wen
Post to Citeulike
9 Citations
Support vector machine (SVM) has been successfully applied to solve a large number of classification problems. Despite its good theoretic foundations and good capability of generalization, it is a big challenging task for the large data sets due to the training complexity, high memory requirements and slow convergence. In this paper, we present a new method, SVM classification based on fuzzy clustering. Before applying SVM we use fuzzy clustering, in this stage the optimal number of clusters are not needed in order to have less computational cost. We only need to partition the training data set briefly. The SVM classification is realized with the center of the groups. Then the declustering and SVM classification via reduced data are used. The proposed approach is scalable to large data sets with high classification accuracy and fast convergence speed. Empirical studies show that the proposed approach achieves good performance for large data sets.
more …
By
Rodriguez, Floriberto Ortiz; Yu, Wen; MorenoArmendariz, Marco A.
Post to Citeulike
The conventional fuzzy CMAC can be viewed as a basis function network with supervised learning, and performs well in terms of its fast learning speed and local generalization capability for approximating nonlinear functions. However,it requires an enormous memory and the dimension increase exponentially with the input number. Hierarchical fuzzy CMAC (HFCMAC) can use less memory to model nonlinear system with high accuracy. But the structure is very complex, the normal training for hierarchical fuzzy CMAC is difficult to realize. In this paper a new learning scheme is employed to HFCMAC. A timevarying learning rate assures the learning algorithm is stable. The calculation of the learning rate does not need any prior information such as estimation of the modeling error bounds. The new algorithms are very simple, we can even train each subblock of the hierarchical fuzzy neural networks independently.
more …
By
Cervantes, Jair; Huang, DeShuang; Li, Xiaoou; Yu, Wen
Show all (4)
Post to Citeulike
This paper presents a method for classification of imbalanced splicesite classification problems, the proposed method consists of the generation of artificial instances that are incorporated to the dataset. Additionally, the method uses a genetic algorithm to introduce just instances that improve the performance. Experimental results show that the proposed algorithm obtains a better accuracy to detect splicesites than other implementations on skewed datasets.
more …
By
Tovar, Julio César; Yu, Wen
Post to Citeulike
This paper describes a novel nonlinear modeling approach by online clustering, fuzzy rules and support vector machine. Structure identification is realized by an online clustering method and fuzzy support vector machines, the fuzzy rules are generated automatically. Timevarying learning rates are applied for updating the membership functions of the fuzzy rules. Finally, the upper bounds of the modeling errors are proven.
more …
By
Tovar, Julio César; Yu, Wen; Li, Xiaoou
Post to Citeulike
This paper describes a novel fuzzy rulebased modeling approach for some slow industrial processses. Structure identification is realized by clustering and support vector machines. When the process is slow, fuzzy rules can be obtained automatically. Parameters identification uses the techniques of fuzzy neural networks. A timevarying learning rate assures stability of the modeling error.
more …
By
Cong, Qiumei; Yu, Wen; Chai, Tianyou
Post to Citeulike
Water quality measurement is important for wastewater treatment plants. Up to the present moment, there are not economic online sensors for it. In this paper a new soft measurement method is proposed, which uses mechanism model and hierarchical neural networks to resolve a modeling accuracy problem. Since wastewater treatment plants are cascaded processes, hierarchical neural networks can match these structures and predict water quality in inner reactors. By comparing our method with the other soft measurement approaches, we find that based on mechanism model and hierarchical neural networks, the hierarchical model is effective for wastewater treatment plants.
more …
By
Cordova, Juan; Yu, Wen
Post to Citeulike
10 Citations
Since wavelet transform uses the multiscale (or multiresolution) techniques for time series, wavelet transform is suitable for modeling complex signals. Haar wavelet transform is the most commonly used and the simplest one. The Haar wavelet neural network (HWNN) applies the Harr wavelet transform as active functions. It is easy for HWNN to model a nonlinear system at multiple time scales and sudden transitions. In this paper, two types of HWNN, feedforward and recurrent wavelet neural networks, are used to model discretetime nonlinear systems, which are in the forms of the NARMAX model and statespace model. We first propose an optimal method to determine the structure of HWNN. Then two stable learning algorithms are given for the shifting and broadening coefficients of the wavelet functions. The stability of the identification procedures is proven.
more …
By
Yu, Wen
Post to Citeulike
14 Citations
In this paper, we propose a new recurrent fuzzy neural network, which has the standard state space form, we call it statespace recurrent neural networks. Inputtostate stability is applied to access robust training algorithms for system identification. Stable learning algorithms for the premise part and the consequence part of fuzzy rules are proved.
more …
By
Yu, Wen; Li, Xiaoou
Post to Citeulike
38 Citations
Dynamic neural networks with different timescales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of the designed networks are stable. In this paper, the passivitybased approach is used to derive stability conditions for dynamic neural networks with different timescales. Several stability properties, such as passivity, asymptotic stability, inputtostate stability and bounded input bounded output stability, are guaranteed in certain senses. A numerical example is also given to demonstrate the effectiveness of the theoretical results.
more …
By
Rodriguez, Floriberto Ortiz; Yu, Wen; MorenoArmendariz, Marco A.
Post to Citeulike
2 Citations
Normal fuzzy CMAC neural network performs well for nonlinear systems identification because of its fast learning speed and local generalization capability for approximating nonlinear functions. However, it requires huge memory and the dimension increases exponentially with the number of inputs. It is difficult to model dynamic systems with static fuzzy CMACs. In this paper, we use two types of recurrent techniques for fuzzy CMAC to overcome the above problems. The new CMAC neural networks are named recurrent fuzzy CMAC (RFCMAC) which add feedback connections in the inner layers (local feedback) or the output layer (global feedback). The corresponding learning algorithms have timevarying learning rates, the stabilities of the neural identifications are proven.
more …
By
Jesús Rubio, José; Yu, Wen; Ferreyra, Andrés
Post to Citeulike
4 Citations
Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence, since it has a similar structure as Kalman filter. OBE has some advantages over Kalman filter training, the noise is not required to be Guassian. In this paper OBE algorithm is applied in training the weights of the feedforward neural network for nonlinear system identification. Both hidden layers and output layers can be updated. From a dynamic system point of view, such training can be useful for all neural network applications requiring realtime updating of the weights. Two simulations give the effectiveness of the suggested algorithm.
more …
By
Yu, Wen; Francisco, Panuncio Cruz; Li, Xiaoou
Post to Citeulike
11 Citations
A levitation platform can be inserted into a patient’s abdominal cavity to perform diagnosis or a surgery procedure with a significantly reduced level of incision and an enhanced field of vision and operation. This paper proposes a new controller for the magnetic levitation, which connects the neural control (NC) and the slidingmode control (SMC) serially, while the other neural slidingmode controllers (NSMC) combine NC and SMC parallel. We call the new NSMC as twostage neural sliding control. It has less chattering during its discrete realization and ensures finitetime convergence. Realtime experiments for a prototype of magnetic levitation in minimal invasion surgery are presented. The comparisons with other regular controllers, such as PID, NC, SMC, and normal NSMC, are made by experiment.
more …
