The Unscented Kalman Filter estimates the plasma insulin from glucose measurement

Understanding the simultaneous interaction within the glucose and insulin homeostasis in real-time is very important for clinical treatment as well as for research issues. Until now only plasma glucose concentrations can be measured in real-time. To support a secure, effective and rapid treatment e.g. of diabetes a real-time estimation of plasma insulin would be of great value. A novel approach using an Unscented Kalman Filter that provides an estimate of the current plasma insulin concentration is presented, which operates on the measurement of the plasma glucose and Bergman's Minimal Model of the glucose insulin homeostasis. We can prove that process observability is obtained in this case. Hence, a successful estimator design is possible. Since the process is nonlinear we have to consider estimates that are not normally distributed. The symmetric Unscented Kalman Filter (UKF) will perform best compared to other estimator approaches as the Extended Kalman Filter (EKF), the simplex Unscented Kalman Filter (UKF), and the Particle Filter (PF). The symmetric UKF algorithm is applied to the plasma insulin estimation. It shows better results compared to the direct (open loop) estimation that uses a model of the insulin subsystem.     

An algorithmic approach to constructing the on-line estimation system for the specific growth rate

The objective of this article is to propose an algorithm for the on-line estimation of the specific growth rate in a batch or a fed-batch fermentation process. The algorithm shows the practical procedure for the estimation method utilizing the macroscopic balance and the extended Kalman filter. A number of studies of the on line estimation have been presented. However, there are few studies discussing about the selection of the observed variables and for the tuning of some parameters of the extended Kalman filter, such as covariance matrix and initial values of the state.The beginning of this article is devoted to explain the selection of the observed variable. This information is very important in terms of the practical know-how for using technique. It is discovered that the condition number is a practically useful and valid criterion for number is a practically useful and valid criterion for choosing the variable to be observed.Next, when the extended Kalman filter in applied to the online estimation of the specific growth rate, which is directly unmeasurable, criteria for judging the validity of the estimated value from the observed data are proposed. Based on the proposed criterial, the system equation of the specific growth rate is selected and initial value of the state variable and covariance matrix of the system noises are adjusted. From many experiments, it is certified that the specific growth rate in the batch or fed -batch fermentation can be estimated accurately by means of the algorithm proposed here. In these experiments, that is, when the cell concentration is measured directly, the extended Kalman filter using the convariance matrix with a constant element can estimate more accurately values of the specific growth rate than the adaptive extended Kalman filter does.     

Robust and reliable estimation via recursive nonlinear dynamic data reconciliation based on cubature Kalman filter

Since measurements of process variables are subject to measurements errors as well as process variability, data reconciliation is the procedure of optimally adjusting measured date so that the adjusted values obey the conservation laws and constraints. Thus, data reconciliation for dynamic systems is fundamental and important for control, fault detection, and system optimization. Attempts to successfully implement estimators are often hindered by serve process nonlinearities, complicated state constraints, and un-measurable perturbations. As a constrained minimization problem, the dynamic data reconciliation is dynamically carried out to product smoothed estimates with variances from the original data. Many algorithms are proposed to solve such state estimation such as the extended Kalman filter (EKF), the unscented Kalman filter, and the cubature Kalman filter (CKF). In this paper, we investigate the use of CKF algorithm in comparative with the EKF to solve the nonlinear dynamic data reconciliation problem. First we give a broad overview of the recursive nonlinear data dynamic reconciliation (RNDDR) scheme, then present an extension to the CKF algorithm, and finally address the issue of how to solve the constraints in the CKF approach. The CCRNDDR method is proposed by applying the RNDDR in the CKF algorithm to handle nonlinearity and algebraic constraints and bounds. As the sampling idea is incorporated into the RNDDR framework, more accurate estimates can obtained via the recursive nature of the estimation procedure. The performance of the CKF approach is compared with EKF and RNDDR on nonlinear process systems with constraints. The conclusion is that with an error optimization solution of the correction step, the reformulated CKF shows high performance on the selection of nonlinear constrained process systems. Simulation results show the CCRNDDR is an efficient, accurate and stable method for real-time state estimation for nonlinear dynamic processes.     

On parameter estimation in population models III: time-inhomogeneous processes and observation error

Essential to applying a mathematical model to a real-world application is calibrating the model to data. Methods for calibrating population models often become computationally infeasible when the population size (more generally the size of the state space) becomes large, or other complexities such as time-dependent transition rates, or sampling error, are present. Continuing previous work in this series on the use of diffusion approximations for efficient calibration of continuous-time Markov chains, I present efficient techniques for time-inhomogeneous chains and accounting for observation error. Observation error (partial observability) is accounted for by joint estimation using a scaled unscented Kalman filter for state-space models. The methodology will be illustrated with respect to models of disease dynamics incorporating seasonal transmission rate and in the presence of observation error, including application to two influenza outbreaks and measles in London in the pre-vaccination era.     

Endogenous model state and parameter estimation from an extensive batch experiment

In this paper an extensive batch experiment of endogenous process behavior in an aerobic biodegradation process is presented. From these experimental data, comprising measurements of MLVSS (mixed liquor volatile suspended solids) and respiration rate, in a first step the states and unknown parameters in a four-compartmental model are reconstructed analytically. Subsequently, for a selected set of states and parameters, using the results of the previous step, a recursive state estimation procedure, in particular an Extended Kalman filter-based observer, is applied to deal with the noise properties of the data appropriately. From this it appears that the initially proposed model structure, and especially the hydrolysis term, has to be modified.     

Joint estimation in batch culture by using unscented kalman filter

The disturbances caused by uncertain factors are inevitable in microbial fermentation. In this paper, we study the joint estimation problem for state and parameter in the bio-dissimulation process of glycerol to 1,3-PD in batch culture. Based on the nonlinear stochastic dynamic system model, we establish the corresponding iteration equations of Joint Unscented Kalman Filter (UKF) by referring to the Extended Kalman Filter (EKF), which is generally applied in microbial fermentation. Through numerical computation, both the state estimations and the uncertain model parameter estimations are obtained. Furthermore, the results of different parameter identification methods are compared. The results show that Joint UKF is more feasible for the process of controlling the glycerol fermentation.     

Online nonlinear sequential Bayesian estimation of a biological wastewater treatment process

Online estimation of unknown state variables is a key component in the accurate modelling of biological wastewater treatment processes due to a lack of reliable online measurement systems. The extended Kalman filter (EKF) algorithm has been widely applied for wastewater treatment processes. However, the series approximations in the EKF algorithm are not valid, because biological wastewater treatment processes are highly nonlinear with a time-varying characteristic. This work proposes an alternative online estimation approach using the sequential Monte Carlo (SMC) methods for recursive online state estimation of a biological sequencing batch reactor for wastewater treatment. SMC is an algorithm that makes it possible to recursively construct the posterior probability density of the state variables, with respect to all available measurements, through a random exploration of the states by entities called ‘particle’. In this work, the simplified and modified Activated Sludge Model No. 3 with nonlinear biological kinetic models is used as a process model and formulated in a dynamic state-space model applied to the SMC method. The performance of the SMC method for online state estimation applied to a biological sequencing batch reactor with online and offline measured data is encouraging. The results indicate that the SMC method could emerge as a powerful tool for solving online state and parameter estimation problems without any model linearization or restrictive assumptions pertaining to the type of nonlinear models for biological wastewater treatment processes.     

Analysis of endogenous process behavior in activated sludge

In this article, an autonomous four-compartment model that describes the endogenous respiration in an aerobic biodegradation process is proposed and analyzed theoretically. First, the multi-time scale of the system's behavior, to be taken into account in subsequent analyses, is emphasized. Then, an identifiability and observability study, given measurements of MLVSS (mixed liquor volatile suspended solids) and respiration rate, is performed for use under practical circumstances, such as in state and parameter estimation. It appears that the process is observable, but not fully identifiable. Hence, for the identification of some of the model parameters, additional measurements or experiments, also indicated here, have to be performed. Furthermore, it is shown that, under quasi-steady state conditions which, in general, appear shortly after initialization of an endogenous respiration experiment, the model can be reduced significantly. Finally, results of parameter estimation from available data are presented and discussed.     

Signal extraction from long-term ecological data using Bayesian and non-Bayesian state-space models

Emerging ecological time series from long-term ecological studies and remote sensing provide excellent opportunities for ecologists to study the dynamic patterns and governing processes of ecological systems. However, signal extraction from long-term time series often requires system learning (e.g., estimation of true system state) to process the large amount of information, to reconstruct system state, to account for measurement error, and to handle missing data. State-space models (SSMs) are a natural choice for these tasks and thus have received increasing attention in ecological and environmental studies. Data-based learning using SSMs that connect ecological processes to the measurement of system state becomes a useful technique in the ecological informatics toolkit. The present study illustrates the use of the Kalman filter (KF), an estimator of SSMs, with case studies of population dynamics. The examples of the SSM applications include the reconstruction of system state using the KF method and Markov chain Monte Carlo methods, estimation of measurement-error variances in the estimates of animal population abundance using basic structural models (BSMs), and estimation of missing values using the KF and Kalman smoother. Estimation of measurement-error variances by BSMs does not require knowledge of the functional form that generates the time series data. Instead, BSMs approximate the trajectory or deterministic skeleton of a system dynamics in a semi-parametric fashion, and provide a robust estimator of measurement-error variances. The present study also compares Bayesian SSMs with non-Bayesian SSMs. The joint use of the KF method or its extensions and Markov chain Monte Carlo (MCMC) methods is a promising approach to the parameter estimation of SSMs.     

Analysis and implementation of a neural extended Kalman filter for target tracking

Having a better motion model in the state estimator is one way to improve target tracking performance. Since the motion model of the target is not known a priori, either robust modeling techniques or adaptive modeling techniques are required. The neural extended Kalman filter is a technique that learns unmodeled dynamics while performing state estimation in the feedback loop of a control system. This coupled system performs the standard estimation of the states of the plant while estimating a function to approximate the difference between the given state-coupling function model and the behavior of the true plant dynamics. At each sample step, this new model is added to the existing model to improve the state estimate. The neural extended Kalman filter has also been investigated as a target tracking estimation routine. Implementation issues for this adaptive modeling technique, including neural network training parameters, were investigated and an analysis was made of the quality of performance that the technique can have for tracking maneuvering targets.     

Application of an extended kalman filter method for monitoring high density cultivation of Escherichia coli

A real-time, on-line extended Kalman filter was used to describe and monitor the growth of Escherichia coli on glycerol. The growth of E. coli showed an inhibition kinetics with μ_max=0.806/h, K_S=0.68 g/l and K_i=87.4 g/l. As a feeding strategy, the conventional DO-stat with a DDC-PID control method, in which the dissolved oxygen concentration is maintained at a desired level by varying the substrate feedrate, was employed. The Kalman filter was based on an unstructured mathematical model and on-line measured data. The mathematical model comprised of mass balances of the biomass and substrate as well as kinetic and stoichiometric data which were measured prior to the process. For biomass concentration up to 50 g dry weight/l, the estimation of the process was rather accurate. At higher biomass concentration, product formation, indicated by an intense brown coloring of the fermentation broth, occured. Since the effect of this product on biomass production was not included in the mathematical model, the estimated data diverged from the experimental data at biomass concentrations greater than 50 g dry weight/l.     

Dynamic metabolic flux analysis (DMFA): a framework for determining fluxes at metabolic non-steady state

Metabolic flux analysis (MFA) is a key tool for measuring in vivo metabolic fluxes in systems at metabolic steady state. Here, we present a new method for dynamic metabolic flux analysis (DMFA) of systems that are not at metabolic steady state. The advantages of our DMFA method are: (1) time-series of metabolite concentration data can be applied directly for estimating dynamic fluxes, making data smoothing and estimation of average extracellular rates unnecessary; (2) flux estimation is achieved without integration of ODEs, or iterations; (3) characteristic metabolic phases in the fermentation data are identified automatically by the algorithm, rather than selected manually/arbitrarily. We demonstrate the application of the new DMFA framework in three example systems. First, we evaluated the performance of DMFA in a simple three-reaction model in terms of accuracy, precision and flux observability. Next, we analyzed a commercial glucose-limited fed-batch process for 1,3-propanediol production. The DMFA method accurately captured the dynamic behavior of the fed-batch fermentation and identified characteristic metabolic phases. Lastly, we demonstrate that DMFA can be used without any assumed metabolic network model for data reconciliation and detection of gross measurement errors using carbon and electron balances as constraints.     

Monitoring in a Lotka-Volterra model

The problem of monitoring arises when in an ecosystem, in particular in a system of several populations, observing some components, we want to recover the state of the whole system as a function of time. Due to the difficulty to construct exactly this state process, we look for an auxiliary system called an observer. This system reproduces this process with a certain approximation. This means that the solution of the observer tends to that of the original system. An important concept for this work is observability. This means that from the observation it is possible to recover uniquely the state process, however, without determining a constructive method to obtain it. If observability holds for the original system, it guarantees the existence of an auxiliary matrix that makes it possible to construct an observer of the system. The considered system of populations is described by the classical Lotka-Volterra model with one predator and two preys and the construction of its observer is illustrated with a numerical example. Finally, it is shown how the observer can be used for the estimation of the level of an abiotic effect on the population system.     

Microbial production of enzymes: Nonlinear state and kinetic reaction rates estimation

The nonlinearity of the biotechnological processes and the absence of cheap and reliable instrumentation require an enhanced modelling effort and estimation strategies for the state and the kinetic parameters. This work approaches nonlinear estimation strategies for microbial production of enzymes, exemplified by using a process of lipase production from olive oil by Candida rugosa. First, by using a dynamical mathematical model of this process, an asymptotic observer which reconstructs the unavailable state variables is proposed. The design of this kind of observers is based on mass and energy balances without the knowledge of kinetics being necessary; only minimal information concerning the measured concentrations is used. Second, a nonlinear high-gain observer is designed for the estimation of imprecisely known kinetics of the bioprocess. An important advantage of this high-gain estimator is that the tuning is reduced to the calibration of a single parameter. Numerical simulations in various scenarios are provided in order to test the behaviour and performances of the proposed nonlinear estimation strategies.     

Learning to Estimate Dynamical State with Probabilistic Population Codes

Tracking moving objects, including one’s own body, is a fundamental ability of higher organisms, playing a central role in many perceptual and motor tasks. While it is unknown how the brain learns to follow and predict the dynamics of objects, it is known that this process of state estimation can be learned purely from the statistics of noisy observations. When the dynamics are simply linear with additive Gaussian noise, the optimal solution is the well known Kalman filter (KF), the parameters of which can be learned via latent-variable density estimation (the EM algorithm). The brain does not, however, directly manipulate matrices and vectors, but instead appears to represent probability distributions with the firing rates of population of neurons, “probabilistic population codes.” We show that a recurrent neural network—a modified form of an exponential family harmonium (EFH)—that takes a linear probabilistic population code as input can learn, without supervision, to estimate the state of a linear dynamical system. After observing a series of population responses (spike counts) to the position of a moving object, the network learns to represent the velocity of the object and forms nearly optimal predictions about the position at the next time-step. This result builds on our previous work showing that a similar network can learn to perform multisensory integration and coordinate transformations for static stimuli. The receptive fields of the trained network also make qualitative predictions about the developing and learning brain: tuning gradually emerges for higher-order dynamical states not explicitly present in the inputs, appearing as delayed tuning for the lower-order states.     

Computational Algorithm for Least Squares Estimation of Parameters in Compartmental Analysis

This paper presents a new computational algorithm for the estimation of the parameters in multi-compartmental processes. By assuming the initial state of compartmental process known, the Newton-Raphson iterative process is vised to obtain weighted least squares estimates. The estimation procedure considers broad class of structural properties (defined in the sequel) of compartmental models, such as open-closed processes, cyclic pathways, conservative processes, connectivity etc. A computer program, which includes these structural properties is supplied. Two examples of simulated processes illustrate the estimation procedure.     

The extended Kalman filter applied to a continuous culture model

The temperature-dependent endogenous metabolism model of single species continuous culture dynamics is utilized in the computer simulation of the Kalman filter state estimation technique. Parameters of the nonlinear equations can be “tracked” while variance in measured states can be damped. The state estimator is illustrated in, the context of conventional control strategies.     

Identifyability measures to select the parameters to be estimated in a solid‐state fermentation distributed parameter model

Process modeling can lead to of advantages such as helping in process control, reducing process costs and product quality improvement. This work proposes a solid‐state fermentation distributed parameter model composed by seven differential equations with seventeen parameters to represent the process. Also, parameters estimation with a parameters identifyability analysis (PIA) is performed to build an accurate model with optimum parameters. Statistical tests were made to verify the model accuracy with the estimated parameters considering different assumptions. The results have shown that the model assuming substrate inhibition better represents the process. It was also shown that eight from the seventeen original model parameters were nonidentifiable and better results were obtained with the removal of these parameters from the estimation procedure. Therefore, PIA can be useful to estimation procedure, since it may reduce the number of parameters that can be evaluated. Further, PIA improved the model results, showing to be an important procedure to be taken. © 2016 American Institute of Chemical Engineers Biotechnol. Prog., 32:905–917, 2016     

An on-line physiological state recognition system for the lysine fermentation process based on a metabolic reaction model

A metabolic reaction model was developed for the lysine fermentation process by Corynebacterium glutamicum AJ-3462 to estimate the physiological state of the cells-that is, the growth and production activity, and the flux distribution of metabolites-from on-line measurable rates only. First, the extended Kalman filter was applied to eliminate noise in the measured rates. Then, using the metabolic reaction model, the lysine production rate and flux distribution were calculated. The estimation results allowed the physiological state of lysine production to be recognized, and an appropriate measure corresponding to the estimated state, such as intermittent addition of glucose and/or leucine, to be taken to maintain a high level of lysine productivity in batch culture. Finally, application of the recognition system enabled lysine to be produced from glucose at a higher yield than that from glucose- or leucine-limited exponential fed-batch cultures. (c) 1997 John Wiley & Sons, Inc. Biotechnol Bioeng 55: 170-181, 1997.     

Observability in dynamic evolutionary models

In the paper observability problems are considered in basic dynamic evolutionary models for sexual and asexual populations. Observability means that from the (partial) knowledge of certain phenotypic characteristics the whole evolutionary process can be uniquely recovered. Sufficient conditions are given to guarantee observability for both sexual and asexual populations near an evolutionarily stable state.