Mohamed N. Nounou

Texas A&M University at Qatar, Ad Dawḩah, Ad Dawḩah, Qatar

Are you Mohamed N. Nounou?

Claim your profile

Publications (87)38.18 Total impact

  • Majdi Mansouri, hazem Nounou, Mohamed Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: Induction machine is highly nonlinear model with states that change with operating point and temperature. In these cases, estimating these variables from other easily obtained measurements can be extremely useful. This paper deals with the problem of state estimation of induction machine on the basis of a third-order electrical model using Bayesian methods. The performances of Bayesian estimation techniques are compared when they are utilized to achieve this objective. These techniques include the extended Kalman filter (EKF), the unscented Kalman filter (UKF), the particle filter (PF), and the developed improved particle filter (IPF). The estimation results, which are validated using simulations, show that IPF provides improved estimation performance over PF, even with abrupt changes in estimated states, and both of them can provide improved accuracy over UKF and EKF. These advantages of the IPF are due to the fact that it uses a better proposal distribution that takes the latest observation into account.
    IEEE Multi-Conference on Systems, Signals & Devices (SSD), 2014 11th International, Castelldefels-Barcelona, Spain; 02/2014
  • Majdi Mansouri, Hazem Nounou, Mohamed Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we address the problem of genetic algorithm optimization for jointly selecting the best group of candidate sensors and optimizing the quantization for target tracking in wireless sensor networks. We focus on a more challenging problem of how to effectively utilize quantized sensor measurement for target tracking in sensor networks by considering best group of candidate sensors selection problem. The main objective of this paper is twofold. Firstly, the quantization level and the group of candidate sensors selection are to be optimized in order to provide the required data of the target and to balance the energy dissipation in the wireless sensor network. Secondly, the target position is to be estimated using quantized variational filtering (QVF) algorithm. The optimization of quantization and sensor selection are based on the Fast and Elitist Multi-objective Genetic Algorithm (NSGA-II). The proposed multi-objective (MO) function defines the main parameters that may influence the relevance of the participation in cooperation for target tracking and the transmitting power between one sensor and the cluster head (CH). The proposed algorithm is designed to: i) avoid the problem lot of computing times and operation counts, and ii) reduce the communication cost and the estimation error, which leads to a significant reduction of energy consumption and an accurate target tracking. The computation of these criteria is based on the predictive information provided by the QVF algorithm. The simulation results show that the NSGA-II -based QVF algorithm outperforms the standard quantized variational filtering algorithm and the centralized quantized particle filter.
    Journal of Signal Processing Systems 02/2014; · 0.55 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Biological pathways can be modeled as a nonlinear system described by a set of nonlinear ordinary differential equations (ODEs). A central challenge in computational modeling of biological systems is the determination of the model parameters. In such cases, estimating these variables or parameters from other easily obtained measurements can be extremely useful. For example, time-series dynamic genomic data can be used to develop models representing dynamic genetic regulatory networks, which can be used to design intervention strategies to cure major diseases and to better understand the behavior of biological systems. Unfortunately, biological measurements are usually highly affected by errors that hide the important characteristics in the data. Therefore, these noisy measurements need to be filtered to enhance their usefulness in practice. This paper addresses the problem of state and parameter estimation of biological phenomena modeled by S-systems using Bayesian approaches, where the nonlinear observed system is assumed to progress according to a probabilistic state space model. The performances of various conventional and state-of-the-art state estimation techniques are compared. These techniques include the extended Kalman filter (EKF), unscented Kalman filter (UKF), particle filter (PF), and the developed improved particle filter (IPF). Specifically, two comparative studies are performed. In the first comparative study, the state variables (the enzyme CadA, the transport protein CadB, the regulatory protein CadC and lysine Lys for a model of the Cad System in E. coli (CSEC)) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error (RMSE) with respect to the noise-free data. In the second comparative study, the state variables as well as the model parameters are simultaneously estimated. In this case, in addition to comparing the performances of the various state estimation techniques, the effect of the number of estimated model parameters on the accuracy and convergence of these techniques is also assessed. The results of both comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the IPF provides a significant improvement over PF because, unlike the PF which depends on the choice of sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of the sampling distribution, which also accounts for the observed data. The results of the second comparative study show that, for all techniques, estimating more model parameters affects the estimation accuracy as well as the convergence of the estimated states and parameters. However, the IPF can still provide both convergence as well as accuracy related advantages over other estimation methods.
    Digital Signal Processing 01/2014; · 1.92 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new model-free technique to design fixed-structure controllers for linear unknown systems. In the current control design approaches, measured data are used to first identify a model of the plant, then a controller is designed based on the identified model. Due to errors associated with the identification process, degradation in the controller performance is expected. Hence, we use the measured data to directly design the controller without the need for model identification. Our objective here is to design measurement-based controllers for stable and unstable systems, even when the closed-loop architecture is unknown. This proposed method can be very useful for many industrial applications. The proposed control methodology is a reference model design approach which aims at finding suitable parameter values of a fixed-order controller so that the closed-loop frequency response matches a desired frequency response. This reference model design problem is formulated as a nonlinear programming problem using the concept of bounded error, which can then be solved to find suitable values of the controller parameters. In addition to the well-known advantages of data-based control methods, the main features of our proposed approach are: (1) the error is guaranteed to be bounded, (2) it enables us to avoid issues related to the use of minimization methods, (3) it can be applied to stable and unstable plants and does not require any knowledge about the closed-loop architecture, and (4) the controller structure can be selected a priori, which means that low-order controllers can be designed. The proposed technique is experimentally validated through a real position control problem of a DC servomotor, where the results demonstrate the efficacy of the proposed method.
    Automatica. 01/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: A central challenge in computational modeling of biological systems is the determination of the model parameters. In such cases, estimating these variables or parameters from other easily obtained measurements can be extremely useful. For example, time-series dynamic genomic data can be used to develop models representing dynamic genetic regulatory networks, which can be used to design intervention strategies to cure major diseases and to better understand the behavior of biological systems. Unfortunately, biological measurements are usually highly infected by errors that hide the important characteristics in the data. Therefore, these noisy measurements need to be filtered to enhance their usefulness in practice. This paper addresses the problem of state and parameter estimation of biological phenomena modeled by S-systems using Bayesian approaches, where the nonlinear observed system is assumed to progress according to a probabilistic state space model. The performances of various conventional and state-of-the-art state estimation techniques are compared. These techniques include the extended Kalman filter (EKF), unscented Kalman filter (UKF), particle filter (PF), and the developed variational Bayesian filter (VBF). Specifically, two comparative studies are performed. In the first comparative study, the state variables (the enzyme CadA, the model cadBA, the cadaverine Cadav and the lysine Lys for a model of the Cad System in E. coli (CSEC)) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error (RMSE) with respect to the noise-free data. In the second comparative study, the state variables as well as the model parameters are simultaneously estimated. In this case, in addition to comparing the performances of the various state estimation techniques, the effect of the number of estimated model parameters on the accuracy and convergence of these techniques is also assessed. The results of both comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the VBF provides a relative improvement over PF because, unlike the PF which depends on the choice of sampling distribution used to estimate the posterior distribution, the VBF yields an optimum choice of the sampling distribution, which also accounts for the observed data. The results of the second comparative study show that, for all techniques, estimating more model parameters affects the estimation accuracy as well as the convergence of the estimated states and parameters. However, the VBF can still provide both convergence as well as accuracy related advantages over other estimation methods.
    Mathematical biosciences 01/2014; · 1.30 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an approach to design a measurement-based controller for induction machines. The proposed control approach is motivated by the fact that developing an appropriate mechanical model of such induction machines is a challenging task. Since our proposed control methodology is only on the basis of measured data, the controller design does not require any information about the model of the mechanical part. The control of motor drive is often based on sensorless field-oriented control techniques because of their advantages such as noise and cost reductions and high reliability. Hence, we assume here that measurements used for the controller design are collected using an estimator based on the electrical equations of the induction machine. A practical application to control the speed of an induction machine is presented to validate and demonstrate the efficiency of the proposed method.
    Emerging and Selected Topics in Power Electronics, IEEE Journal of. 01/2014; 2(2):308-318.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Network component analysis (NCA) is an efficient method of reconstructing the transcription factor activity (TFA), which makes use of the gene expression data and prior information available about transcription factor (TF) - gene regulations. Most of the contemporary algorithms either exhibit the drawback of inconsistency and poor reliability, or suffer from prohibitive computational complexity. In addition, the existing algorithms do not possess the ability to counteract the presence of outliers in the microarray data. Hence, robust and computationally efficient algorithms are needed to enable practical applications. We propose ROBust Network Component Analysis (ROBNCA), a novel iterative algorithm that explicitly models the possible outliers in the microarray data. An attractive feature of the ROBNCA algorithm is the derivation of a closed form solution for estimating the connectivity matrix, which was not available in prior contributions. The ROBNCA algorithm is compared to FastNCA and the Non-iterative NCA (NI-NCA). ROBNCA estimates the TF activity profiles as well as the TF-gene control strength matrix with a much higher degree of accuracy than FastNCA and NI-NCA, irrespective of varying noise, correlation and/or amount of outliers in case of synthetic data. The ROBNCA algorithm is also tested on Saccharomyces Cerevisiae data and Eschericia coli data and it is observed to outperform the existing algorithms. The run time of the ROBNCA algorithm is comparable to that of FastNCA, and is hundreds of times faster than NI-NCA. The ROBNCA software is available at http://people.tamu.edu/∼amina/ROBNCA. serpedin@ece.tamu.edu.
    Bioinformatics 08/2013; · 5.47 Impact Factor
  • Muddu Madakyaru, Mohamed N. Nounou, Hazem N. Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: Proper control of distillation columns requires estimating some key variables that are challenging to measure online (such as compositions), which are usually estimated using inferential models. Commonly used inferential models include latent variable regression (LVR) techniques, such as principal component regression (PCR), partial least squares (PLS), and regularized canonical correlation analysis (RCCA). Unfortunately, measured practical data are usually contaminated with errors, which degrade the prediction abilities of inferential models. Therefore, noisy measurements need to be filtered to enhance the prediction accuracy of these models. Multiscale filtering has been shown to be a powerful feature extraction tool. In this work, the advantages of multiscale filtering are utilized to enhance the prediction accuracy of LVR models by developing an integrated multiscale LVR (IMSLVR) modeling algorithm that integrates modeling and feature extraction. The idea behind the IMSLVR modeling algorithm is to filter the process data at different decomposition levels, model the filtered data from each level, and then select the LVR model that optimizes a model selection criterion. The performance of the developed IMSLVR algorithm is illustrated using three examples, one using synthetic data, one using simulated distillation column data, and one using experimental packed bed distillation column data. All examples clearly demonstrate the effectiveness of the IMSLVR algorithm over the conventional methods.
    Modelling and Simulation in Engineering 04/2013; 2013.
  • Source
    N Meskin, H Nounou, M Nounou, A Datta
    [Show abstract] [Hide abstract]
    ABSTRACT: Recent advances in high-throughput technologies for biological data acquisition have spurred a broad interest in the construction of mathematical models for biological phenomena. The development of such mathematical models relies on the estimation of unknown parameters of the system using the time-course profiles of different metabolites in the system. One of the main challenges in the parameter estimation of biological phenomena is the fact that the number of unknown parameters is much more than the number of metabolites in the system. Moreover, the available metabolite measurements are corrupted by noise. In this paper, a new parameter estimation algorithm is developed based on the stochastic estimation framework for nonlinear systems, namely the unscented Kalman filter (UKF). A new iterative UKF algorithm with covariance resetting is developed in which the UKF algorithm is applied iteratively to the available noisy time profiles of the metabolites. The proposed estimation algorithm is applied to noisy time-course data synthetically produced from a generic branched pathway as well as real time-course profile for the Cad system of E. coli. The simulation results demonstrate the effectiveness of the proposed scheme.
    IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM 03/2013; 10(2):537-43. · 2.25 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The utilization of mathematical tools in the analysis and synthesis of models representing biological phenomena is rapidly growing. Adding to these efforts, in this paper, a mathematical method based on the sliding mode control approach will be used for the purpose of developing a therapeutic intervention strategy for a class of biological phenomena. Such an intervention scheme aims at moving an undesirable state of a diseased network towards a more desirable state using drugs to act on some genes/metabolites that characterize the undesirable behavior. S-systems, which offer a good compromise between accuracy and mathematical flexibility, are a promising framework for modeling the dynamical behavior of biological phenomena as well as genetic regulatory networks. Since biological phenomena modeled by S-systems are complex nonlinear processes, the need for robust nonlinear intervention strategies that are capable of guiding the target variables to their desired values often arises. The main objective of this paper is to develop an intervention scheme based on sliding mode control theory, sometimes referred to as variable structure control theory, and evaluate the robustness of the sliding mode intervention scheme in the presence of model parameter uncertainties. The proposed intervention strategy is applied to a glycolytic-glycogenolytic pathway model and the simulation results demonstrate the effectiveness of the proposed scheme.
    Journal of Biological Systems 02/2013; 20(04). · 0.73 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The large influx of data from high-throughput genomic and proteomic technologies has encouraged the researchers to seek approaches for understanding the structure of gene regulatory networks and proteomic networks. This work reviews some of the most important statistical methods used for modeling of gene regulatory networks (GRNs) and protein-protein interaction (PPI) networks. The paper focuses on the recent advances in the statistical graphical modeling techniques, state-space representation models, and information theoretic methods that were proposed for inferring the topology of GRNs. It appears that the problem of inferring the structure of PPI networks is quite different from that of GRNs. Clustering and probabilistic graphical modeling techniques are of prime importance in the statistical inference of PPI networks, and some of the recent approaches using these techniques are also reviewed in this paper. Performance evaluation criteria for the approaches used for modeling GRNs and PPI networks are also discussed.
    Advances in Bioinformatics 01/2013; 2013:953814.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Safe process operation requires effective fault detection (FD) methods that can identify faults in various process parameters. In the absence of a process model, principal component analysis (PCA) has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T2 or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abilities. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. The performance of the PCA-based GLR fault detection algorithm is illustrated and compared to conventional fault detection methods through two simulated examples, one using synthetic data and the other using simulated continuously stirred tank reactor (CSTR) data. The results of these examples clearly show the effectiveness of the developed algorithm over conventional methods.
    Journal of Loss Prevention in the Process Industries 01/2013; 26(1):129–139. · 1.15 Impact Factor
  • H.N. Nounou, M.N. Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: The main contribution of this work is the application of delay-dependent adaptive control techniques to control nonlinear continuous stirred tank reactor (CSTR) model with state delay. The delay-dependent adaptive control problem is first formulated and stabilizing adaptive control algorithms are developed and then applied to the CSTR process model. The CSTR model includes a nonlinear perturbation which is assumed to have a norm that is bounded by a scaled norm of the state vector. Here, we consider two cases where the weight of the state norm is assumed to be known and unknown. Simulation results show the efficacy of the delay-dependent adaptive control schemes in controlling the CSTR nonlinear process model.
    Computational Intelligence in Control and Automation (CICA), 2013 IEEE Symposium on; 01/2013
  • F. Harrou, M.N. Nounou, H.N. Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: Ozone is one of the lost serious air pollution problems. Monitoring abnormal changes in the concentration of ozone in the troposphere is of great interest because of its negative influence on human health, vegetation, and materials. Modeling ozone is very challenging because of the complexity of the ozone formation mechanisms in the troposphere and the uncertainty about the meteorological conditions in urban areas. In the absence of a process model, principal component analysis (PCA), which is a multivariate statistical technique, has been successfully used as a data-based fault detection (FD) method for highly correlated process variables. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abilities. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The developed PCA-based GLR FD algorithm is utilized to enhance monitoring the ozone concentrations in Upper Normandy, France. The performances of PCA and PCA-based GLR test are compared through two practical case studies, one involving a sensor fault and the other involving tropospheric ozone pollution in multiple measuring stations. The results show that the PCA-based GLR test can detect abnormal ozone levels with a smaller number of false alarms than the conventional PCA method.
    Computational Intelligence and Data Mining (CIDM), 2013 IEEE Symposium on; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper addresses the problem of rotor speed, flux and parameters estimation of induction motor on the basis of a three-order electrical model. Thus, we propose to use a particle filtering (PF) to estimate states and parameters for an induction motor. It is assumed that only the voltages stator currents are measurable. In addition, the rotor resistance and magnetizing inductance, which vary with the motor temperature and magnetization level, can also be estimated within the same framework. Hence, the objective of this work is to estimate three states (the rotor speed, the rotor flux, and the stator flux) and two parameters (the rotor resistance and the magnetizing inductance). Simulation analysis demonstrates that the Bayesian algorithm can well estimate the states/parameters under disturbs of the noise, and it provides efficient accuracies for the states estimation. In addition, detailed case studies show that Bayesian algorithm has advantages over Unscented Kalman filter (UKF) for highly nonlinear estimation problems. Evaluation of the methods was performed by using Root Mean Square Error.
    Systems, Signals & Devices (SSD), 2013 10th International Multi-Conference on; 01/2013
  • M. Mansouri, H. Nounou, M. Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: Due to the challenges associated with measuring some of the key variables of chemical processes, state estimators are often used to overcome this problem. This paper deals with the problem of state estimation of a chemical process model representing a continuously stirred tank reactor (CSTR) using the Extended Kalman Filter (EKF), Particle Filter (PF), and recently developed Variational Bayesian Filter (VBF). The VBF has been recently proposed to solve the nonlinear estimation problem because it can be applied to large parameter spaces, has better convergence properties and relatively easy to implement. Here, a comparative study is conducted to compare the estimation performances of these three estimation techniques in estimating the two states (the concentration and temperature) of the CSTR process model. Simulation results show that the VBF has improved state estimation performance over both EKF and PF, and the PF shows improved state estimation performance over EKF.
    Systems, Signals & Devices (SSD), 2013 10th International Multi-Conference on; 01/2013
  • M. Madakyaru, M.N. Nounou, H.N. Nounou
    [Show abstract] [Hide abstract]
    ABSTRACT: Many operations, such as monitoring and control, require the availability of some key process variables. When these variables are difficult to measure, it is usually relied on inferential models that can be used to estimate these variables from other easier-to-measure variables. Latent variable regression (LVR) techniques, such as principal component regression (PCR), partial least square (PLS), and regularized canonical correlation analysis (RCCA), are commonly used as inferential models. In this paper, these linear LVR modeling techniques are first reviewed, and then a new algorithm that extends these LVR modeling techniques to nonlinear processes is presented. The developed nonlinear LVR (NLLVR) modeling algorithm utilizes nonlinear functions in the form of polynomials to capture the nonlinear relationships between the latent variables are the model output. The structures of these polynomials as well as the number of latent variables used are optimized using cross validation. The performances of the developed NLLVR modeling techniques are illustrated and compared with those the conventional linear LVR techniques (PCR, PLS, and RCCA). This comparison is performed using two examples, one using synthetic data and the other using simulated distillation column data. The results of both examples show that a significant improvement in model predictions can be achieved using the NLLVR modeling methods.
    Computational Intelligence in Control and Automation (CICA), 2013 IEEE Symposium on; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new measurement based approach to solve synthesis problems in linear systems with applications to mechanical systems, hydraulic networks, civil engineering structures, etc. We show that few strategic measurements reveal the functional dependency of a desired system variable on the set of the design elements. Once the functional dependency is found, one can apply the design constraints to obtain the feasible set of values for the design elements.
    Control Conference (ASCC), 2013 9th Asian; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper deals with fixed-structure controller design for stable linear systems by using measurements. Most control design approaches developed in the literature are generally based on a mathematical model which can be obtained via identification system by using a set of measured data. However, an identified model, which is often built on the basis of some assumptions, cannot perfectly describe complex behaviors characterizing physical systems. Thus, the performance expected for the closed-loop system will be limited by the quality of such models used in the control design process. Hence, data-based controller design methods can be viewed as a possible alternative to model-based methods. In this paper, we propose to directly utilize frequency response data in the controller design. The principle is to design fixed-structure controllers for which the closed-loop frequency response fits a desired frequency response. This problem is formulated as an error minimization problem. The main feature of our proposed approach is that controller can be designed free of any mathematical model, which allows to avoid errors associated with identification process. Moreover, it enables to select low-order controllers, which are suitable for embedded systems. A simulation example is given to illustrate and validate the efficacy the proposed approach.
    Control Conference (ASCC), 2013 9th Asian; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, particle filtering (PF) is addressed for both estimation and control to be integrated into a unified closed-loop or feedback control system that is applicable for a general family of nonlinear control structures. In the current work, the state variables (the rotor speed, the rotor flux, and the stator flux) as well as the model parameters are simultaneously estimated from noisy measurements of these variables, and the estimation technique is evaluated by computing the estimation root mean square error (RMSE) with respect to the noise-free data. In this case, in addition to comparing the performances of the estimation, the effect of the number of estimated model parameters on the accuracy and convergence of this technique is also assessed. Simulation analysis demonstrates that the particle filter can well estimate the states/parameters under disturbs of the noise, and it provides efficient accuracies for the states estimation.
    Systems, Signals & Devices (SSD), 2013 10th International Multi-Conference on; 01/2013

Publication Stats

175 Citations
38.18 Total Impact Points

Institutions

  • 2007–2014
    • Texas A&M University at Qatar
      Ad Dawḩah, Ad Dawḩah, Qatar
  • 2007–2012
    • Texas A&M University
      • • Department of Electrical and Computer Engineering
      • • Department of Chemical Engineering
      College Station, TX, United States
  • 2011
    • Qatar University
      • Department of Electrical Engineering
      Doha, Baladiyat ad Dawhah, Qatar
  • 2004–2006
    • United Arab Emirates University
      • Department of Chemical and Petroleum Engineering
      Al ‘Ayn, Abu Zaby, United Arab Emirates
  • 1999–2002
    • The Ohio State University
      • Department of Statistics
      Columbus, OH, United States