Using Particle Swarm Optimization (PSO) Algorithm in Nonlinear Regression Well Test Analysis and Its Comparison with Levenberg-Marquardt Algorithm

Adibifard, Meisam; Bashiri, Gholamreza; Roayaei, Emad; Emad, Mohammad Ali

doi:10.4018/ijamc.2016070101

Cited by 11 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to increase the chances of finding the global or a near-global optimal solution, we used particle swarm optimization algorithm (PSO) which is a global approach to optimization [22]. PSO has been found to produce better results compared to traditional approaches in solving similar non-linear regression problems [23]- [25]. Furthermore, the optimization was run twice starting at randomly chosen n 1 , n 2 , and the solution with the smaller cost was selected to increase the chances of finding the global optimal or a near-global optimal solution.…”

Section: A Methods For Labeling Mrcpsmentioning

confidence: 99%

Automated Labeling of Movement- Related Cortical Potentials Using Segmented Regression

Rashid

Niazi

Jochumsen

et al. 2019

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

The movement-related cortical potential (MRCP) is a brain signal related to planning and execution of motor tasks. From an MRCP, three notable features can be identified: the early Bereitschaftspotential (BP1), the late Bereitschaftspotential (BP2), and the negative peak (PN). These features have been used in past studies to quantify neurophysiological changes in response to motor training. Currently, either manual labeling or a priori specification of time points is used to extract these features. The limitation of these methods is the inability to fully model the features. This paper proposes the segmented regression along with a local peak method for automated labeling of the features. The proposed method derives the onsets, amplitudes at onsets, and slopes of BP1 and BP2 along with time and amplitude of the PN in a typical average MRCP. To choose the most suitable regression technique a bounded segmented regression method, a change point method and multivariate adaptive regression splines were evaluated using the root-mean-square error on a dataset of 6000 simulated MRCPs. The best-performing regression technique combined with the local peak method was then applied to a smaller set of 123 simulated MRCPs. Error in onsets of BP1 and BP2 and time of PN were compared with the errors in manual labeling by an expert. The performance of the proposed method was also evaluated on an experimental dataset of MRCPs derived from electroencephalography (EEG) recorded across two sessions from 22 healthy participants during a lower limb task. The Bland-Altman plots were used to evaluate the absolute reliability of the proposed method. On experimental data, the proposed method was also compared with manual labeling by an expert.

show abstract

Section: A Methods For Labeling Mrcpsmentioning

confidence: 99%

Automated Labeling of Movement- Related Cortical Potentials Using Segmented Regression

Rashid

Niazi

Jochumsen

et al. 2019

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…A detailed tutorial explaining the particle swarm algorithm along with practical examples can be found in [ 65 ]. The advantage of using the particle swarm algorithm over traditional gradient-based methods is that it does not require a good initial guess for the parameters that can be initialised to random values within their bounds, and its results are less sensitive to the initial guess [ 66 , 67 , 68 , 69 , 70 ]. However, optimisation is computationally expensive and it can take a longer time to converge to a solution when compared to a traditional gradient-based algorithm.…”

Section: Materials and Methodsmentioning

confidence: 99%

On Nonlinear Regression for Trends in Split-Belt Treadmill Training

et al. 2020

View full text Add to dashboard Cite

Single and double exponential models fitted to step length symmetry series are used to evaluate the timecourse of adaptation and de-adaptation in instrumented split-belt treadmill tasks. Whilst the nonlinear regression literature has developed substantially over time, the split-belt treadmill training literature has not been fully utilising the fruits of these developments. In this research area, the current methods of model fitting and evaluation have three significant limitations: (i) optimisation algorithms that are used for model fitting require a good initial guess for regression parameters; (ii) the coefficient of determination (R2) is used for comparing and evaluating models, yet it is considered to be an inadequate measure of fit for nonlinear regression; and, (iii) inference is based on comparison of the confidence intervals for the regression parameters that are obtained under the untested assumption that the nonlinear model has a good linear approximation. In this research, we propose a transformed set of parameters with a common language interpretation that is relevant to split-belt treadmill training for both the single and double exponential models. We propose parameter bounds for the exponential models which allow the use of particle swarm optimisation for model fitting without an initial guess for the regression parameters. For model evaluation and comparison, we propose the use of residual plots and Akaike’s information criterion (AIC). A method for obtaining confidence intervals that does not require the assumption of a good linear approximation is also suggested. A set of MATLAB (MathWorks, Inc., Natick, MA, USA) functions developed in order to apply these methods are also presented. Single and double exponential models are fitted to both the group-averaged and participant step length symmetry series in an experimental dataset generating new insights into split-belt treadmill training. The proposed methods may be useful for research involving analysis of gait symmetry with instrumented split-belt treadmills. Moreover, the demonstration of the suggested statistical methods on an experimental dataset may help the uptake of these methods by a wider community of researchers that are interested in timecourse of motor training.

show abstract

“…The algorithm not only seeks the optimal position of individual particles but also keeps tracking the overall optimal value. To estimate reservoir properties, Adibifard [ 39 ] used PSO to implement nonlinear regression in well test analysis. Zhang [ 40 ] used PSO-based BP neural networks to predict reservoir parameters by using dynamic production information.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-Based Kalman Smoothing Method for Uncertain Parameters Processing: Applications in Oil Well-Testing Data Denoising and Prediction

Feng

et al. 2020

Sensors

View full text Add to dashboard Cite

The low-distortion processing of well-testing geological parameters is a key way to provide decision-making support for oil and gas field development. However, the classical processing methods face many problems, such as the stochastic nature of the data, the randomness of initial parameters, poor denoising ability, and the lack of data compression and prediction mechanisms. These problems result in poor real-time predictability of oil operation status and difficulty in offline interpreting the played back data. Given these, we propose a wavelet-based Kalman smoothing method for processing uncertain oil well-testing data. First, we use correlation and reconstruction errors as analysis indicators and determine the optimal combination of decomposition scale and vanishing moments suitable for wavelet analysis of oil data. Second, we build a ground pressure measuring platform and use the pressure gauge equipped with the optimal combination parameters to complete the downhole online wavelet decomposition, filtering, Kalman prediction, and data storage. After the storage data are played back, the optimal Kalman parameters obtained by particle swarm optimization are used to complete the data smoothing for each sample. The experiments compare the signal-to-noise ratio and the root mean square error before and after using different classical processing models. In addition, robustness analysis is added. The proposed method, on the one hand, has the features of decorrelation and compressing data, which provide technical support for real-time uploading of downhole data; on the other hand, it can perform minimal variance unbiased estimates of the data, filter out the interference and noise, reduce the reconstruction error, and make the data have a high resolution and strong robustness.

show abstract

Using Particle Swarm Optimization (PSO) Algorithm in Nonlinear Regression Well Test Analysis and Its Comparison with Levenberg-Marquardt Algorithm

Cited by 11 publications

References 39 publications

Automated Labeling of Movement- Related Cortical Potentials Using Segmented Regression

Automated Labeling of Movement- Related Cortical Potentials Using Segmented Regression

On Nonlinear Regression for Trends in Split-Belt Treadmill Training

Wavelet-Based Kalman Smoothing Method for Uncertain Parameters Processing: Applications in Oil Well-Testing Data Denoising and Prediction

Contact Info

Product

Resources

About