Abdullah M. Dobaie

Facial expression recognition via learning deep sparse autoencoders

Abstract Facial expression recognition is an important research issue in the pattern recognition field. In this paper, we intend to present a novel framework for facial expression recognition to automatically distinguish the expressions with high accuracy. Especially, a high-dimensional feature composed by the combination of the facial geometric and appearance features is introduced to the facial expression recognition due to its containing the accurate and comprehensive information of emotions. Furthermore, the deep sparse autoencoders (DSAE) are established to recognize the facial expressions with high accuracy by learning robust and discriminative features from the data. The experiment results indicate that the presented framework can achieve a high recognition accuracy of 95.79% on the extended Cohn–Kanade (CK+) database for seven facial expressions, which outperforms the other three state-of-the-art methods by as much as 3.17%, 4.09% and 7.41%, respectively. In particular, the presented approach is also applied to recognize eight facial expressions (including the neutral) and it provides a satisfactory recognition accuracy, which successfully demonstrates the feasibility and effectiveness of the approach in this paper.

Denoising and deblurring gold immunochromatographic strip images via gradient projection algorithms

Abstract Gold immunochromatographic strip (GICS) assay provides a quick, convenient, single-copy and on-site approach to determine the presence or absence of the target analyte when applied to an extensive variety of point-of-care tests. It is always desirable to quantitatively detect the concentration of trace substance in the specimen so as to uncover more useful information compared with the traditional qualitative (or semi-quantitative) strip assay. For this purpose, this paper is concerned with the GICS image denoising and deblurring problems caused by the complicated environment of the intestine/intrinsic restrictions of the strip characteristics and the equipment in terms of image acquisition and transmission. The gradient projection approach is used, together with the total variation minimization approach, to denoise and deblur the GICS images. Experimental results and quantitative evaluation are presented, by means of the peak signal-to-noise ratio, to demonstrate the performance of the combined algorithm. The experimental results show that the gradient projection method provides robust performance for denoising and deblurring the GICS images, and therefore serves as an effective image processing methodology capable of providing more accurate information for the interpretation of the GICS images.

On Design of Robust Fault Detection Filter in Finite-Frequency Domain With Regional Pole Assignment

This brief is concerned with the fault detection (FD) filter design problem for an uncertain linear discrete-time system in the finite-frequency domain with regional pole assignment. An optimized FD filter is designed such that: 1) the FD dynamics is quadratically D-stable; 2) the effect from the exogenous disturbance on the residual is attenuated with respect to a minimized H∞-norm; and 3) the sensitivity of the residual to the fault is enhanced by means of a maximized H--norm. With the aid of the generalized Kalman-Yakubovich-Popov lemma, the mixed H-/H∞ performance and the D-stability requirement are guaranteed by solving a convex optimization problem. An iterative algorithm for designing the desired FD filter is proposed by evaluating the threshold on the generated residual function. A simulation result is exploited to illustrate the effectiveness of the proposed design technique.

Distributed Kalman Filtering With Quantized Sensing State

This paper studies a Quantized Gossip-based Interactive Kalman Filtering (QGIKF) algorithm implemented in a wireless sensor network, where the sensors exchange their quantized states with neighbors via inter-sensor communications. We show that, in the countable infinite quantization alphabet case, the network can still achieve weak consensus with the information loss due to quantization, i.e., the estimation error variance sequence at a randomly selected sensor can converge weakly (in distribution) to a unique invariant measure. To prove the weak convergence, we first interpret error variance sequences as interacting particles, then model each sequence evolution as a Random Dynamical System (RDS), and further prove its stochastically bounded nature. Moreover, based on the analysis for the countable infinite quantization alphabet case, we also prove that under certain conditions the network can also achieve weak consensus, when the quantization alphabet is finite, which is more restricted and practical.

Dynamic output-feedback control for positive Roesser system under the switched and T-S fuzzy rules

Abstract This paper is concerned with the dynamic output-feedback controller design for the positive Roesser type nonlinear system, which is intrinsically characterized by the switched mechanism and subtly decomposed into the linear form under the Takagi–Sugeno fuzzy rules. Firstly, based on the co-positive Lyapunov function and the average dwell time method, sufficient conditions are presented, under which the resulting closed-loop system is exponentially stable and has l 1 -gain bound γ . Then, explicit expressions are also given to derive the expected controller gain matrices with desired l 1 -gain bound. Finally, effectiveness of the proposed results is illustrated by two numerical examples.

Finite-time state estimation for jumping recurrent neural networks with deficient transition probabilities and linear fractional uncertainties

Abstract This paper is concerned with the finite-time stability and the finite-time boundedness issues on the estimation problem for a class of continuous-time uncertain recurrent neural networks with Markovian jumping parameters. The uncertain parameters are described by the linear fractional uncertainties and the jumping parameters obey the homogeneous Markov process with possibly deficient probability transition matrix. A full-order state estimator is constructed to estimate the neuron state, in presence of the uncertain and jumping parameters, such that the resulting error dynamics of the state estimation is (i) finite-time stable in the disturbance-free case; and (ii) finite-time bounded in case of exogenous disturbances on the measurements. By employing the Lyapunov stability theory and stochastic analysis techniques, sufficient conditions are established that ensure the existence of the desired finite-time state estimator, and then the explicit expression of such state estimators is characterized in terms of the feasibility to a convex optimization problem that can be easily solved by using the semi-definite programme method. Validity and effectiveness of the developed design method are demonstrated by a numerical example.

Robust state estimation for stochastic complex-valued neural networks with sampled-data

In this paper, the robust state estimation problem is investigated for the complex-valued neural networks involving parameter uncertainties, mixed time delays, as well as stochastic disturbances by resorting to the sampled-data information from the available output measurements. The parameter uncertainties are assumed to be norm-bounded and the stochastic disturbances are assumed to be Brownian motions, which could reflect much more realistic dynamical behaviors of the complex-valued network under a noisy environment. The purpose of the addressed problem is to design an estimator for the complex-valued network such that, for all admissible parameter uncertainties and sampled output measurements, the dynamics of the state estimation error system is assured to be globally asymptotically stable in the mean square. Matrix inequality approach, robust analysis tool, as well as stochastic analysis techniques are utilized together to derive several delay-dependent sufficient criteria guaranteeing the existence of the desired state estimator. Finally, simulation examples are illustrated to demonstrate the feasibility of the proposed estimation design schemes.

Comparison of 2D image models in segmentation performance for 3D laser point clouds

Abstract The selection of a suitable representing model for 3D laser point clouds plays a significant role in 3D outdoor scene understanding. In this paper, we compare the segmentation performance of four types of models which can transform 3D laser point clouds into 2D images. In these models, fast optimal bearing-angle (FOBA) image is a novel 2D image model, which provides a general way to project 3D laser point clouds into 2D images. A series of segmentation performance tests and data analysis for these models are conducted in four datasets, which are acquired with different laser scanning modes. According to the experimental results, we argue that 2D image models greatly reduce the time cost of scene segmentation with a little loss of accuracy. Moreover, the usage of 2D image models is not limited in scene segmentation since robust features can be extracted from 2D image models to accomplish laser point classification and scene understanding.

Autonomous road detection and modeling for UGVs using vision-laser data fusion

Abstract Autonomous road detection and modeling play a key role for UGVs navigating in complex outdoor environments. This paper investigates road detection and description for UGVs in various outdoor scenes under different weather conditions. A novel environment perception system that includes two cameras and multiple laser range finders is introduced firstly. Taking classification accuracy and time-cost into account, 8-dimensional features are selected from a 91-dimensional candidate feature set using Adaboost algorithm. To adapt to the diversity of road scenes under different weather conditions in different seasons, an online classifier based on SVM is proposed to replace the fixed one. Moreover, a road region adjusting algorithm is present to eliminate misclassified regions especially when the roads have fuzzy boundaries or obstacles. Finally, a RANSAC spline fitting algorithm is adopted to provide an accurate road border model for UGVs’ autonomous path planning and navigation. A series of experiments are conducted by using a self-built UGV platform and experimental results show the validity and practicality of the proposed approaches.

Nonlinear System Identification Using Quasi-ARX RBFN Models with a Parameter-Classified Scheme

Quasi-linear autoregressive with exogenous inputs (Quasi-ARX) models have received considerable attention for their usefulness in nonlinear system identification and control. In this paper, identification methods of quasi-ARX type models are reviewed and categorized in three main groups, and a two-step learning approach is proposed as an extension of the parameter-classified methods to identify the quasi-ARX radial basis function network (RBFN) model. Firstly, a clustering method is utilized to provide statistical properties of the dataset for determining the parameters nonlinear to the model, which are interpreted meaningfully in the sense of interpolation parameters of a local linear model. Secondly, support vector regression is used to estimate the parameters linear to the model; meanwhile, an explicit kernel mapping is given in terms of the nonlinear parameter identification procedure, in which the model is transformed from the nonlinear-in-nature to the linear-in-parameter. Numerical and real cases are carried out finally to demonstrate the effectiveness and generalization ability of the proposed method.