Detection Of Changes In Parameters Research Articles

Testing for parameter changes in linear state space models

AbstractLinear state space models (LSSMs) provide a very general framework for multiple time series analysis. We propose a novel statistical procedure for testing validity of a LSSM which is focused on the detection of changes in parameters of the given LSSM. We derive the moments as well as the asymptotic distribution of the test statistic, and investigate the test size and the test power for changes in means, variances, and autoregressive coefficients. In the empirical application we test the validity of LSSMs applied to daily realized volatility time series.

Feasibility Of Open Low-field MRI Measurements In Adolescent Athletes With Spondylolisthesis

Spondylolysis and spondylolisthesis are common findings in adolescent athletes (AA), potentially leading to load-dependent pain and segmental spine instability. In diagnostics, supine MRI is frequently used to visualize the lumbar spine structures. However, upright MRI procedures have been shown to be of clinical value in the detection of load-dependent changes in parameters. PURPOSE: To determine the feasibility of upright compared to supine MRI measurements to determine characteristics of the lumbar spine in AA with spondylolisthesis. METHODS: Ten AA (n=10; m/f: 4/6; 14.5±1.7y; 163±7cm; 52±8kg) from various sports, diagnosed with spondylolisthesis grade I-II Meyerding confirmed by x-ray in standing lateral view, were included. Open low-field MRI images (0.25 Tesla) in upright (82°) and supine (0°) position were evaluated by two observers. Medical imaging software was used to measure the anterior translation (AT, mm), lumbosacral joint angle (LSJA, °) and lordosis angle (LA, °). Reliability was analyzed by the intra-rater correlation coefficient (ICC) and standard error of measurements (SEM). RESULTS: Due to motion artifacts during upright position, measures of three participants had to be excluded. Between observers, AT ranged from 4.2±2.7mm to 5.5±1.9mm (ICC=0.94, SEM=0.6mm) in upright and from 4.9±2.4mm to 5.9±3.0mm (ICC=0.89, SEM=0.9mm) in supine position. LSJA varied from 5.1±2.2° to 7.3±1.5° (ICC=0.54, SEM=1.5°) in upright and from 9.8±2.5° to 10±2.4° (ICC=0.73, SEM=1.1°) in supine position. LA differed from 58.8±14.6° to 61.9±6° (ICC=0.94, SEM=1.19°) in upright and from 51.9±11.7° to 52.6±11.1° (ICC=0.98, SEM=1.59°) in supine position. CONCLUSIONS: Determination of AT and LA showed good to excellent reliability in both, upright and supine position. In contrast, reliability of LSJA had only moderate to good correlation between observers and should therefore be interpreted with caution. However, motion artifacts should be taken into consideration during upright imaging procedures.

A Novel Method for Assessing the Contribution of Harmonic Sources to Voltage Distortion in Power Systems

This paper presents a method for evaluating the harmonic contributions of multiple harmonic sources to voltage distortion at the point of common coupling (PCC). The proposed method quantitatively represents harmonic contributions based on the equivalent voltage models of harmonic sources. The equivalent voltage models can be estimated using the recursive least square (RLS) algorithm and measured voltage and current at the PCC. The assessment of harmonic contribution heavily depends on the accuracy of equivalent model estimation. Many existing studies have assumed that the equivalent model parameters of harmonic sources are not changed. However, because harmonic source parameters and system operating conditions are not constant in real power systems, this assumption can lead large errors in harmonic contribution assessment. In this paper, we propose a new assessment method based on variable forgetting factor RLS and parameter change detection to solve the problem. The proposed method is also effective for evaluating comprehensive harmonic contributions as well as individual harmonic contributions. The case studies show that the proposed method is superior to the previous one even under parameter changing conditions.

An Automatic and early detection of the deterioration of patients in Intensive and Intermediate Care Units

In the Intensive and Intermediate Care Units of healthcare centres, many sensors are connected to patients to measure high frequency physiological data. In order to analyse the state of a patient, the medical staff requires both appropriately presented and easily accessed information. As most medical devices do not support the extraction of digital data in known formats, medical staff need to fill out forms manually. The traditional methodology is prone to human errors due to the large volume of information, with variable origins and complexity. The automatic and real-time detection of changes in parameters, based on known medical rules, will make possible to avoid these errors and, in addition, to detect deterioration early. In this article, we propose and discuss a high-level system architecture, an embedded system that extracts the electrocardiogram signal from an analog output of a medical monitor, and a real-time Big Data infrastructure that integrate Free Software products. We believe that the experimental results, obtained with a simple prototype of the system, demonstrate the viability of the techniques and technologies used, leaving solid foundations for the construction of a reliable system for medical use, able to scale and support an increasing number of patients and captured data.

Evaluation of Echocardiographic Systolic Parameters in Pre-Eclamptics and Normotensives Women.

Early detection of changes in cardiovascular echocardiographic systolic parameters and their comparison with normotensives women. This was a hospital-based prospective case-control study carried out in Department of Obstetrics and Gynaecology in S.M.S Medical College, Jaipur, during the period from February 2013 to December 2014. In total, 100 women were enrolled in the study after applying inclusion and exclusion criteria. All women underwent two-dimensional echocardiography at rest. Cardiac systolic parameters were recorded and studied. Mean LVEDV in the PIH group was 75.71±4.8 versus 71.08±5.6ml in the control group, and the difference was statistically significant. Mean stroke volume was higher in the PIH group as compared to the control group, and the difference was statistically significant (59.83±7.4 vs. 52.48±6.4ml/min). Mean aortic root diameter in the PIH group was 2.188±1.04cm as compared to the 1.866±1.06cm in the control group which was statistically significant. Mean left ventricular outflow tract diameter was slightly higher in the PIH group as compared to the controls although the P value was not significant (2.37±1.06 and 1.99±1.08cm). Mean total vascular resistance was found to be higher in the PIH group as compared to the controls, and the difference was statistically significant (1389±57.04 vs. 1286±45.01 dynes/sec/cm(-5)). Systolic parameters get worsened in pre-eclamptics. Early detection of change in these parameters could help to identify high-risk women who are prone to develop cardiovascular morbidity in later life.

Detection of parametric changes in the Peyrard-Bishop- Dauxois model of DNA using nonlinear Kalman filtering

The derivative-free nonlinear Kalman filter is proposed for state estimation and fault diagnosis in distributed parameter systems of the wave-type and particularly in the Peyrard-Bishop-Dauxois model of DNA dynamics. At a first stage, a nonlinear filtering approach is introduced for estimating the dynamics of the Peyrard-Bishop-Dauxois 1D nonlinear wave equation, through the processing of a small number of measurements. It is shown that the numerical solution of the associated partial differential equation results in a set of nonlinear ordinary differential equations. With the application of a diffeomorphism that is based on differential flatness theory it is shown that an equivalent description of the system is obtained in the linear canonical (Brunovsky) form. This transformation enables to obtain local estimates about the state vector of the DNA model through the application us of the standard Kalman filter recursion. At a second stage, the local statistical approach to fault diagnosis is used to perform fault diagnosis for this distributed parameter system by processing with statistical tools the differences (residuals) between the output of the Kalman filter and the measurements obtained from the distributed parameter system. Optimal selection of the fault threshold is succeeded by using the local statistical approach to fault diagnosis. The efficiency of the proposed filtering approach in the problem of fault diagnosis for parametric change detection, in nonlinear wave-type models of DNA dynamics, is confirmed through simulation experiments.

Sequential change detection in the presence of unknown parameters

It is commonly required to detect change points in sequences of random variables. In the most difficult setting of this problem, change detection must be performed sequentially with new observations being constantly received over time. Further, the parameters of both the pre- and post- change distributions may be unknown. In Hawkins and Zamba (Technometrics 47(2):164–173, 2005), the sequential generalised likelihood ratio test was introduced for detecting changes in this context, under the assumption that the observations follow a Gaussian distribution. However, we show that the asymptotic approximation used in their test statistic leads to it being conservative even when a large numbers of observations is available. We propose an improved procedure which is more efficient, in the sense of detecting changes faster, in all situations. We also show that similar issues arise in other parametric change detection contexts, which we illustrate by introducing a novel monitoring procedure for sequences of Exponentially distributed random variable, which is an important topic in time-to-failure modelling.

Nonparametric particle filtering approaches for identification and inference in nonlinear state-space dynamic systems

Most system identification approaches and statistical inference methods rely on the availability of the analytic knowledge of the probability distribution function of the system output variables. In the case of dynamic systems modelled by hidden Markov chains or stochastic nonlinear state-space models, these distributions as well as that of the state variables themselves, can be unknown or untractable. In that situation, the usual particle Monte Carlo filters for system identification or likelihood-based inference and model selection methods have to rely, whenever possible, on some hazardous approximations and are often at risk. This review shows how a recent nonparametric particle filtering approach can be efficiently used in that context, not only for consistent filtering of these systems but also to restore these statistical inference methods, allowing, for example, consistent particle estimation of Bayes factors or the generalisation of model parameter change detection sequential tests. Real-life applications of these particle approaches to a microbiological growth model are proposed as illustrations.

Design and Implementation of a New Algorithm for Fast Diagnosis of Step Changes in Parameters of Continuous Systems

In this paper special adaptation of modulating functions method MFM for fast detection of step changes in parameters of continuous and linear systems is presented. The modulating functions method is well known for identification of continuous, linear, time-invariant system CLTIS. The characteristic feature of MF method in its application to the problem of identification of step changes in parameters is the existence of fixed time delay in the reconstruction of the new value of parameters after their failure. The aim of this paper is presentation of the substantial modification of MFM which enables optimal identification of parameter faults with minimization of time delay.

Classification of parameter changes in a dynamic system with the use of wavelet analysis and neural networks

In this paper a neural detector of internal parameter changes in a stationary, non-linear SISO dynamic system is considered. A dynamic system is usually described by an input-output relation or by a set of state equations. Each change of parameter values creates a new non-nominal model of a dynamic system (sometimes with different values of parameters, sometimes with different structure and different values of parameters). Thus the detection of parameter changes can be formulated as a multi-model classification. The LVQ (Learning Vector Quantisation) neural network has been proposed as a classifier. Selected aggregated properties of discrete wavelet decomposition coefficients of the system output have been chosen as the inputs of the LVQ classifier. The output of the classifier points out the current model. The proposed approach to classification can be adopted as a fault detection method where faults are represented by changes of values of internal parameters of a system. The algorithm has been evaluated on the example of a non-linear fluid system with a non-ideal pipe which internal state is characterised by one value of a parameter, chosen from the known set.

Monitoring parameter change in time series models

In this paper, we develop a monitoring procedure for an early detection of parameter changes in time series models. We design the monitoring procedure in general time series models and apply it to the changes for the autocovariances of linear processes, GARCH parameters, and underlying distributions. Simulation results are provided for illustration.

Monitoring parameter changes for random coefficient autoregressive models

In this paper, we develop a monitoring procedure for an early detection of parameter changes in random coefficient autoregressive models. It is shown that the stopping rule signaling a parameter change satisfies the desired asymptotic property as seen in Lee, Lee, and Na (submitted for publication). Simulation results are provided for illustration.

Estimation of Future Glucose Concentrations with Subject-Specific Recursive Linear Models

Estimation of future glucose concentrations is a crucial task for diabetes management. Predicted glucose values can be used for early hypoglycemic/hyperglycemic alarms or for adjustment of insulin injections or insulin infusion rates of manual or automated pumps. Continuous glucose monitoring (CGM) technologies provide glucose readings at a high frequency and consequently detailed insight into the subject's glucose variations. The objective of this research is to develop reliable subject-specific glucose prediction models using CGM data. Two separate patient databases collected under hospitalized (disturbance-free) and normal daily life conditions are used for validation of the proposed glucose prediction algorithm. Both databases consist of glucose concentration data collected at 5-min intervals using a CGM device. Using time-series analysis, low-order linear models are developed from patients' own CGM data. The time-series models are integrated with recursive identification and change detection methods, which enables dynamic adaptation of the model to inter-/intra-subject variability and glycemic disturbances. Prediction performance is evaluated in terms of glucose prediction error and Clarke Error Grid analysis (CG-EGA). Prediction errors are significantly reduced with recursive identification of the models, and predictions are further improved with inclusion of a parameter change detection method. CG-EGA analysis results in accurate readings of 90% or more. Subject-specific glucose prediction strategy has been developed. Including a change detection method to the recursive algorithm improves the prediction accuracy. The proposed modeling algorithm with small number of parameters is a good candidate for installation in portable devices for early hypoglycemic/hyperglycemic alarms and for closing the glucose regulation loop with an insulin pump.

Closed-loop model validation based on the two-model divergence method

This paper is concerned with model validation and detection of parameter changes under closed-loop conditions. Two closed-loop model validation algorithms are developed based on the two-model divergence method. The algorithms are only sensitive to the plant changes that affect closed-loop performance. The first algorithm is sensitive to changes in both plant and disturbance dynamics. A novel feature of the second algorithm is that it is only sensitive to the changes in plant dynamics, regardless of changes in disturbance dynamics. Under certain conditions, the proposed algorithms can also be applied for fault detection, e.g. detection of actuator or sensor fault, etc. The developed algorithms are evaluated by simulations as well as experimental applications on a pilot scale process.

Micro‐structured Devices for Chemical Sensing of Flavor and Fragrance

AbstractThe aim of this study was to design, develop and test an integrated micro‐analytical system. Of special interest are micro‐fluidic and micro‐sensor applications in the field of chemical analysis, such as the optical detection of parameter changes, optical recognition of component profiles and technological micro‐reaction applications. For this purpose, a modular system was developed, which enables the realization of various application cases in an uncomplicated manner, and to execute (via serial or parallel combination of components) usually not compatible tasks. Software components were developed to control the measuring procedure as well as to execute the data interpretation up to a chemometrical discriminant analysis. Application is directed to the production and product control in life sciences mainly for food, natural products, cosmetics and pharmaceutics.

SIGEST

Many important practical problems require a control system to be able to automatically, efficiently, and accurately detect changes in dynamical systems that the control system is monitoring. In some instances, public safely is involved. Well-known examples include analysis of seismic data to detect earthquakes, analysis of radar data in aircraft navigation, and monitoring of activities in chemical plants. The SIGEST paper in this issue, “A Nonlinear Filtering Approach to Changepoint Detection Problems: Direct and Differential-Geometric Methods” by M. H. Vellekoop and J. M. C. Clark, from the SIAM Journal on Control and Optimization, significantly advances the state of the art in this area. In particular, it considers the problem of online detection of parameter changes in dynamical systems, when the data are noisy, and when both the time of the change and the size of the change are unknown a priori. The problem of changepoint detection in dynamical systems on the basis of noisy observations has been well studied in cases when only one of these two factors is unknown. It can be solved by the Shiryayev–Wonham equation if the value after the change is known a priori, or by a Kalman filter if the time of the change is known a priori. But when both are unknown, the problem turns out to be much more difficult. Vellekoop and Clark use differential-geometric methods to derive an approximate, suboptimal filter for solving this challenging changepoint detection problem. The method they derive draws upon both of the approaches mentioned above. In their words, their new nonlinear filter can be interpreted as an adaptive version of the Shiryayev–Wonham equation for the detection of a priori known changes, combined with a modified Kalman filer structure to generate estimates of the unknown size of the change. The paper includes excellent mathematics, as well as nicely presented and readily understandable simulation results that compare the performance of the proposed new filters to more exact but computationally expensive approaches. These results indicate that the proposed new filters may be quite useful in practice. We hope that SIAM Review readers enjoy this fascinating glimpse into state-of-the-art research in optimal control.

Slight parameter changes detection in biological models: a multiresolution approach

This paper deals with the automatic detection of slight parameter changes from the analysis of signals generated by nonlinear biological systems. The interest is focused here on investigating particular aspects of the relation between signal analysis and systems dynamics, involving the automatic detection of changes in parameters of nonlinear systems. The continuous multiresolution entropies combine advantages stemming from both entropy (Shannon and parametric q-entropy) and wavelet analysis, have been shown that they are sensitive to dynamical complexity changes. Classical statistical approaches offer a new tool that enables the automatic detection of such changes. In this paper, multiresolution and standard tools for the automatic detection of slight parameter changes in nonlinear dynamical systems from the analysis of the corresponding time series are introduced and compared. The relevance of the multiresolution approach, together with its robustness in the presence of moderate noise, and their comparison are discussed in numerical simulations and they are applied to biological signals.

Detection of abrupt changes of total least squares models and application in fault detection

This paper deals with detection of parameter changes of total least squares and generalized total least squares models and its application in fault detection and isolation. Total least squares and generalized total least squares are frequently used to model processes when all measured process variables are corrupted by disturbances. It is therefore of practical interest to monitor processes and detect faults using the total least squares and generalized total least squares as well. The local approach for detection of abrupt changes is adopted as a computational engine for the change detection. The effectiveness and robustness of the proposed algorithm in fault detection and isolation are demonstrated through Monte Carlo simulations: a pilot-scale experiment and sensor validation of an industrial distillation column.

Multivariable model validation in the presence of time-variant disturbance dynamics

This paper is concerned with dynamic model validation through detection of parameter changes using the local detection approach. The local approach has ability to detect small changes very effectively. To enhance its robustness in the presence of time-variant disturbance dynamics, the local approach based on the output error identification algorithm is proposed. The effectiveness and robustness of the proposed method are illustrated through Monte-Carlo simulations. The result is also extended to multivariable model validation and verified on a multivariable pilot scale process.

Input design for linear dynamic systems using maxmin criteria

This paper considers the problem of input design for maximizing the smallest eigenvalue of the information matrix for linear dynamic systems. The optimization of the smallest eigenvalue is of interest in parameter estimation and parameter change detection problems. We describe a simple cutting plane algorithm to determine the optimal frequency power weights of the input, using successive solutions to linear programs. We present a case study related to estimation of thermal parameters of a building.