Identification of piecewise affine systems based on statistical clustering technique

This paper is concerned with the identification of a class of piecewise affine systems called a piecewise affine autoregressive exogenous (PWARX) model. The PWARX model is composed of ARX sub-models each of which corresponds to a polyhedral region of the regression space. Under the temporary assumption that the number of sub-models is known a priori, the input-output data are collected into several clusters by using a statistical clustering algorithm. We utilize support vector classifiers to estimate the boundary hyperplane between two adjacent regions in the regression space. In each cluster, the parameter vector of the sub-model is obtained by the least squares method. It turns out that the present statistical clustering approach enables us to estimate the number of sub-models based on the information criteria such as CAIC and MDL. The estimate of the number of sub-models is performed by applying the identification procedure several times to the same data set, after having fixed the number of sub-models to different values. Finally, we verify the applicability of the present identification method through a numerical example of a Hammerstein model.     

Safe diagnosability for fault-tolerant supervision of discrete-event systems

The problem of achieving fault-tolerant supervision of discrete-event systems is considered from the viewpoint of safe and timely diagnosis of unobservable faults. To this end, the new property of safe diagnosability is introduced and studied. Standard definitions of diagnosability of discrete-event systems deal with the problem of detecting the occurrence of unobservable fault events using model-based inferencing from observed sequences of events. In safe diagnosability, it is required in addition that fault detection occur prior to the execution of a given set of forbidden strings in the failed mode of operation of the system. For instance, this constraint could be required to prevent local faults from developing into failures that could cause safety hazards. If the system is safe diagnosable, reconfiguration actions could be forced upon the detection of faults prior to the execution of unsafe behaviour, thus achieving the objective of fault-tolerant supervision. Necessary and sufficient conditions for safe diagnosability are derived. In addition, the problem of explicitly considering safe diagnosability in controller design, termed “active safe diagnosis problem”, is formulated and solved. A brief discussion of safe diagnosability for timed models of discrete-event systems is also provided.     

Kalman filtering for multiple time-delay systems

This paper is to study the linear minimum variance estimation for discrete-time systems with instantaneous and l-time delayed measurements by using re-organized innovation analysis. A simple approach to the problem is presented in this paper. It is shown that the derived estimator involves solving l+1 different standard Kalman filtering with the same dimension as the original system.     

Clean system inversion learning control law

In this paper, an iterative learning control approach, clean system inversion, is proposed for multi-input multi-output (MIMO) time-invariant systems, as a remedy to the system inversion law. The analysis and design are carried out in the frequency domain. This model based scheme relies on non-causal filtering and need no high order derivatives of error signals and no numerical differentiation. Experimental results on an industrial robot system show that the scheme is effective.     

On discrete dynamic output feedback min-max controllers

The paper considers output feedback min-max controllers for non-square discrete time uncertain linear systems. Based on previous work, it is demonstrated that static output feedback min-max controllers are only realizable for a specific class of systems. To broaden this class, a compensator based framework is proposed to introduce additional degrees of freedom. The conditions for the existence of such dynamic output feedback min-max controllers are given and are shown to be relatively mild. Furthermore, a simple parameterization of the available design freedom is proposed. An explicit procedure is described which shows how a Lyapunov matrix, which satisfies both a discrete Riccati inequality and a structural constraint, can be obtained using Linear matrix inequality optimization. This Lyapunov matrix is used to calculate the robustness bounds associated with the closed-loop system. A simple aircraft example is provided to demonstrate the efficacy of the design approach.     

Extraction of reference lines and items from form document images with complicated background

The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images. This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support. We also present a method of extracting items using the extracted reference lines and multiresolution wavelet sub-images, which is independent of the intensity of the strokes and backgrounds. The experimental results demonstrate the effectiveness of our proposed methods.     

Classifier combination based on confidence transformation

This paper investigates the effects of confidence transformation in combining multiple classifiers using various combination rules. The combination methods were tested in handwritten digit recognition by combining varying classifier sets. The classifier outputs are transformed to confidence measures by combining three scaling functions (global normalization, Gaussian density modeling, and logistic regression) and three confidence types (linear, sigmoid, and evidence). The combination rules include fixed rules (sum-rule, product-rule, median-rule, etc.) and trained rules (linear discriminants and weighted combination with various parameter estimation techniques). The experimental results justify that confidence transformation benefits the combination performance of either fixed rules or trained rules. Trained rules mostly outperform fixed rules, especially when the classifier set contains weak classifiers. Among the trained rules, the support vector machine with linear kernel (linear SVM) performs best while the weighted combination with optimized weights performs comparably well. I have also attempted the joint optimization of confidence parameters and combination weights but its performance was inferior to that of cascaded confidence transformation-combination. This justifies that the cascaded strategy is a right way of multiple classifier combination.     

Fingerprint classification using fast Fourier transform and nonlinear discriminant analysis

In this paper, we present a new approach for fingerprint classification based on discrete Fourier transform (DFT) and nonlinear discriminant analysis. Utilizing the DFT and directional filters, a reliable and efficient directional image is constructed from each fingerprint image, and then nonlinear discriminant analysis is applied to the constructed directional images, reducing the dimension dramatically and extracting the discriminant features. The proposed method explores the capability of DFT and directional filtering in dealing with low-quality images and the effectiveness of nonlinear feature extraction method in fingerprint classification. Experimental results demonstrates competitive performance compared with other published results.     

Steerable pyramid-based face hallucination

In this paper we propose a robust learning-based face hallucination algorithm, which predicts a high-resolution face image from an input low-resolution image. It can be utilized for many computer vision tasks, such as face recognition and face tracking. With the help of a database of other high-resolution face images, we use a steerable pyramid to extract multi-orientation and multi-scale information of local low-level facial features both from the input low-resolution face image and other high-resolution ones, and use a pyramid-like parent structure and local best match approach to estimate the best prior; then, this prior is incorporated into a Bayesian maximum a posterior (MAP) framework, and finally the high-resolution version is optimized by a steepest decent algorithm. The experimental results show that we can enhance a 24×32 face image into a 96×128 one while the visual effect is relatively good.