Error Cost Function Research Articles

Inverse Kinematics Analysis of Novel 6-Dof Robotic Arm Manipulator for Oil and Gas Welding Using Grey Wolf Algorithm

his paper presents a grey-wolf algorithm for solving the inverse kinematics of a newly designed 6-degree-of-freedom robotic arm for oil and gas pipeline welding which has not been used in the literature. Consequently, due to the robot’s multiple joints with compounding combinatory possibilities of joint angles, analysis of the inverse kinematics is relatively complex. In this research, grey-wolf algorithm, a swarm-based meta-heuristic algorithm, has been used to solve for the inverse kinematics of the robotic arm with respect to tracking a rectangular trajectory with six sets of waypoints in the 3D [X, Y, Z] space. The results were further analyzed in terms of the accuracy of the position of end effector from the accurate position of the rectangular target trajectory via a mean squared error cost function. Furthermore, results of comparison between the grey-wolf algorithm and the particle swarm optimisation, an alternate swarm algorithm with respect to position error from the inverse kinematics task is also presented. The results obtained via simulation clearly demonstrates the superior performance of the grey-wolf algorithm compared to particle swarm optimisation with respect to the solving an inverse kinematics task

Optimal design of fuzzy-PID controller for automatic generation control of multi-source interconnected power system

This paper suggests a fuzzy logic controller (FLC) structure from seven membership functions (MFs) and its input–output relationship rules to design a secondary controller to reduce load frequency control (LFC) issues. The FLC is coupled to a proportional–integral–derivative (PID) controller as the proposed FPID controller, which is tuned by an optimized water cycle algorithm (WCA). The proposed WCA: FPID scheme was implemented with two models from the literature under the integral time absolute error cost function. Initially, a two-area non-reheat unit was implemented, and the gains of PID and FPID controllers were adjusted to verify the suitability of WCA in solving LFC issues. Then, in order to identify the robustness of the closed-loop system, sensitivity analysis is carried out. Additionally, a two-area non-reheat unit was tested under the governor dead band nonlinearity. To guarantee the suitability of the proposed FPID controller, a model with a mixture of power plants, such as reheat, hydro, and gas unit in each area was carried out with and without the HVDC link, which can increase practical issues with LFC. The proposed controller's robustness was studied for all models under numerous scenarios, step load perturbations (SLP), and different objective functions. Simulation results proved that the proposed FPID controller provided superior performance compared to recently reported techniques in terms of peaks and settling time.

Adaptive Synergetic Motion Control for Wearable Knee-Assistive System: A Rehabilitation of Disabled Patients

In this study, synergetic-based adaptive control design is developed for trajectory tracking control of joint position in knee-rehabilitation system. This system is often utilized for rehabilitation of patients with lower-limb disabilities. However, this knee-assistive system is subject to uncertainties when applied to different persons undertaking exercises. This is due to the different masses and inertias of different persons. In order to cope with these uncertainties, an adaptive scheme has been proposed. In this study, an adaptive synergetic control scheme is established, and control laws are developed to ensure stable knee exoskeleton system subjected to uncertainties in parameters. Based on Lyapunov stability analysis, the developed adaptive synergetic laws are used to estimate the potential uncertainties in the coefficients of the knee-assistive system. These developed control laws guarantee the stability of the knee rehabilitation system controlled by the adaptive synergetic controller. In this study, particle swarm optimization (PSO) algorithm is introduced to tune the design parameters of adaptive and non-adaptive synergetic controllers, in order to optimize their tracking performances by minimizing an error-cost function. Numerical simulations are conducted to show the effectiveness of the proposed synergetic controllers for tracking control of the exoskeleton knee system. The results show that compared to classical synergetic controllers, the adaptive synergetic controller can guarantee the boundedness of the estimated parameters and hence avoid drifting, which in turn ensures the stability of the controlled system in the presence of parameter uncertainties.

Variable Tap-Length Algorithm Based on a Mixed Error Cost Function

Variable Tap-Length Algorithm Based on a Mixed Error Cost Function

Combined Use of Glucose-Specific Model Identification and Alarm Strategy Based on Prediction-Funnel to Improve Online Forecasting of Hypoglycemic Events.

Advanced decision support systems for type 1 diabetes (T1D) management often embed prediction modules, which allow T1D people to take preventive actions to avoid critical episodes like hypoglycemia. Real-time prediction of blood glucose (BG) concentration relies on a subject-specific model of glucose-insulin dynamics. Model parameter identification is usually based on the mean square error (MSE) cost function, and the model is usually used to predict BG at a single prediction horizon (PH). Finally, a hypo-alarm is raised if the predicted BG crosses a threshold. This work aims to show that real-time hypoglycemia forecasting can be improved by leveraging: a glucose-specific mean square error (gMSE) cost function in model's parameters identification, and a "prediction-funnel," that is, confidence intervals (CIs) for multiple PHs, within the hypo-alarm-raising strategy. Autoregressive integrated moving average with exogenous input (ARIMAX) models are selected to illustrate the proposed solution (use of gMSE and prediction-funnel) and its assessment against the conventional approach (MSE and single PH). The gMSE penalizes the model misfit in unsafe BG ranges (e.g., hypoglycemia), and the prediction-funnel allows raising an alarm by monitoring if the CIs cross a suitable threshold. The algorithms were evaluated by measuring precision (P), recall (R), F1-score (F1), false positive per day (FP/day), and time gain (TG) on a real dataset collected in 11 T1D individuals. The best performance is achieved exploiting both the gMSE and the prediction-funnel: P = 65%, R = 88%, F1 = 75%, FP/day = 0.29, and mean TG = 15 minutes. The combined use of a glucose-specific metric and an alarm-raising strategy based on the prediction-funnel allows achieving a more effective and reliable hypoglycemia prediction algorithm.

Predicting the energy and exergy performance of F135 PW100 turbofan engine via deep learning approach

In the present study, the effects of flight-Mach number, flight altitude, fuel types, and intake air temperature on thrust specific fuel consumption, thrust, intake air mass flow rate, thermal and propulsive efficiecies, as well as the exergetic efficiency and the exergy destruction rate in F135 PW100 engine are investigated. Based on the results obtained in the first phase, to model the thermodynamic performance of the aforementioned engine cycle, Flight-Mach number and flight altitude are considered to be 2.5 and 30,000 m, respectively; due to the operational advantage of supersonic flying at high altitude flight conditions, and the higher thrust of hydrogen fuel. Accordingly, in the second phase, taking into account the mentioned flight conditions, an intelligent model has been obtained to predict output parameters (i.e., thrust, thrust specific fuel consumption, and overall exergetic efficiency) using the deep learning method. In the attained deep neural model, the pressure ratio of the high-pressure turbine, fan pressure ratio, turbine inlet temperature, intake air temperature, and bypass ratio are considered input parameters. The provided datasets are randomly divided into two sets: the first one contains 6079 samples for model training and the second set contains 1520 samples for testing. In particular, the Adam optimization algorithm, the cost function of the mean square error, and the active function of rectified linear unit are used to train the network. The results show that the error percentage of the deep neural model is equal to 5.02%, 1.43%, and 2.92% to predict thrust, thrust specific fuel consumption, and overall exergetic efficiency, respectively, which indicates the success of the attained model in estimating the output parameters of the present problem.

Implementation of a Human Motion Capture System Based on the Internet of Things Machine Vision

The classification of the stereo matching comprehensive analysis related algorithm model can be subdivided into local stereo matching based on the entire acquisition and global stereo matching based on the entire local. But it can have a higher capture efficiency because the log-likelihood variance cost calculation function can have a faster feature convergence capture speed than the ordinary log-mean-square error cost function. Through the combination of gray channel and frame difference channel, a better network structure and parameters on the KTH data set are obtained, which can ensure the classification effect while greatly reducing the number of parameters, improving training efficiency and improving classification accuracy. The article uses dual-channel 3D convolutional human neural network technology to achieve 92.5% accuracy of human feature capture, which is significantly better than many traditional feature extraction techniques proposed in the literature.

Modeling of Thermal Traces Using Fractional Order, a Discrete, Memory-Efficient Model

In the paper, the problem of modeling of thermal traces is addressed. The proposed model allows prediction of the behaviour of a thermal mark left by a warm body on cooler ground. In the model, a fractional order (FO) approach is employed. This allows consideration of an inital function (not only a condition in one, initial time instant). The proposed model uses a scalar FO differential equation approximated with the use of Continuous Fraction Expansion (CFE) approximation. This allows maintenance of a relatively small size of the model with good accuracy in the sense of a Mean Square Error (MSE) cost function. Experimental verification confirms good accuracy of the proposed model in modeling of thermal traces.

Robust classification via clipping-based kernel recursive least lncosh of error

Classification as a supervised machine learning method predicts the class label from the features distribution and the training process. The traditional classifier algorithms are not robust in the presence of outliers and noisy features. In this study, we suggest a novel robust classifier using kernel recursive least lncosh (RC-KRLL), in which the clipping concept is used to ignore the effect of large noises. Instead of the conventional mean square error cost function, the suggested RC-KRLL method is derived from the lncosh loss function, being more suitable for non-Gaussian noise. The mean, mean-square convergence, and learning curve of the RC-KRLL are discussed theoretically. The simulation results show that the proposed method outperforms the other robust state-of-the-art classification algorithms in the presence of synthetic non-Gaussian noise over UCI data sets, such as the mixture of Gaussian noise with different variances, impulse, and Alpha–Beta noises. The obtained results over 500px data sets on social media with real outliers and mislabeled samples confirmed the acceptable performance of the proposed method.

On the consistency and asymptotic normality of discrete-time LTI models identified from concatenated data sets

Even-though data concatenation is a well-known technique for identifying Linear Time-Invariant models from multiple records, the study of the asymptotic properties of the estimator continues to be limited. Therefore, we investigated consistency and asymptotic normality as the number or records tend to infinity, with focus on the identification of discrete-time parametric models for single-input single-output systems operating in open loop. This paper presents the results of a consistency and asymptotic normality study based on the analysis of the prediction error cost function and Monte Carlo simulations. We show that for persistently exciting input signals (filtered white noise), model structures such as Output-Error, AR and ARX are consistently estimated, and the estimated parameters are asymptotically normally distributed. On the other hand, ARMA, ARMAX and Box–Jenkins present a bias on the estimated parameters. However, this bias asymptotically disappears for longer records

Kernel Least Logarithmic Absolute Difference Algorithm

Kernel adaptive filtering (KAF) algorithms derived from the second moment of error criterion perform very well in nonlinear system identification under assumption of the Gaussian observation noise; however, they inevitably suffer from severe performance degradation in the presence of non-Gaussian impulsive noise and interference. To resolve this dilemma, we propose a novel robust kernel least logarithmic absolute difference (KLLAD) algorithm based on logarithmic error cost function in reproducing kernel Hilbert spaces, taking into account of the non-Gaussian impulsive noise. The KLLAD algorithm shows considerable improvement over the existing KAF algorithms without restraining impulsive interference in terms of robustness and convergence speed. Moreover, the convergence condition of KLLAD algorithm with Gaussian kernel and fixed dictionary is presented in the mean sense. The superior performance of KLLAD algorithm is confirmed by the simulation results.

Application of Generalized Frequency Response Functions and Improved Convolutional Neural Network to Fault Diagnosis of Heavy-duty Industrial Robot

The combination of nonlinear spectrum and convolutional neural network (CNN) is efficient for fault diagnosis of nonlinear system . However, in traditional method, the nonlinear spectrum calculation was accomplished by identification algorithm outside the CNN, which reduced the diagnosis efficiency. To solve this problem, a novel CNN with the function of spectrum calculation and fault diagnosis is designed, in which the spectrum calculation network and the fault diagnosis network are connected in series. By extracting the optimized parameters of network, the nonlinear spectrum based on generalized frequency response function (GFRF) is obtained in the former network. Then, the GFRF spectrum is automatically put into the latter network for feature extraction and diagnosis. Hence, after determining the structure of the CNN, only by system input and output, the fault diagnosis can be realized, which avoids the complex process in traditional method. What's more, a new error cost function model is designed to guide the network parameters optimization in the direction of feature classification , which is conductive to improve the diagnosis accuracy. The proposed network model is applied to the heavy-duty industrial robot system, and the best performance is demonstrated by several experiments.

Deep learning-based convolutional neural network for intramodality brain MRI synthesis.

PurposeThe existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state‐of‐the‐art deep learning convolutional neural network (CNN) for image‐to‐image translation across three standards MRI contrasts for the brain.MethodsBRATS’2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1‐weighted (T1), T2‐weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U‐Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean‐squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic‐MR images were evaluated against the ground‐truth images by computing the MSE, mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), and structural similarity index (SSIM).ResultsThe generated synthetic‐MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44–33.25 dB, 0.0005–0.0012, 0.0086–0.0149, and 0.932–0.946, respectively. Our results were as good as the best‐reported results by other deep learning models on BRATS datasets.ConclusionsOur U‐Net model exhibited that it can accurately perform image‐to‐image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision‐making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.

EFFECT OF RISK-SENSITIVE STOCHASTIC OPTIMAL CONTROL WITH TRACKING IN AN EVAPORATOR

This work presents an application of the Risk-Sensitive (R-S) control with tracking applied to a stochastic nonlinear system which models the operation of an electronic expansion valve (EEV) in a conventional evaporator. A novel dynamical stochastic equation represents the mathematical model of the evaporator system. The R-S stochastic optimal problem consists of the design of an optimal control u(t) such that the state reaches setpoint values (SP) and minimizes the exponential quadratic cost function. The presence of disturbances and errors in the sensor measurements is represented by Gauss white noise in the state equation, with the coefficient v(e/(2?^2 )) . One novel characteristic in this proposal is that the coefficient of the control into the state equation contains the state term. The error and exponential quadratic cost function show that the R-S control has a better performance versus the classical PID (Proportional, Integral Derivative) control. Key Words: Optimal Risk-Sensitive control with tracking, modelling of the evaporator.

A Class of Pareto Optimal Binaural Beamformers

The objective of binaural multi-microphone speech enhancement algorithms can be viewed as a multi-criteria design problem as there are several requirements to be met. The objective is not only to extract the target speaker without distortion, but also to suppress interfering sources (e.g., competing speakers) and ambient background noise, while preserving the auditory impression of the complete acoustic scene. Such a multi-objective problem (MOP) can be solved using a Pareto frontier, which provides a useful trade-off between the different criteria. In this paper, we propose a unified Pareto optimization framework, which is achieved by defining a generalized mean squared error (MSE) cost function, derived from a MOP. The solution to the multi-criteria problem is grounded on a solid mathematical foundation. The MSE cost function consists of a weighted sum of speech distortion (SD), partial interference reduction (IR), and partial noise reduction (NR) terms with scaling parameters that control the amount of IR and NR. The filter minimizing this generalized cost function, denoted Pareto optimal binaural multichannel Wiener filter (Pareto-BMWF), constitutes a generalization of various binaural MWF-based and binaural MVDR-based beamformers. This solution is optimal for any set of parameters. The improved speech enhancement capabilities are experimentally demonstrated using real-signal recordings when estimation errors are present and the binaural cue preservation capabilities are analyzed.

Scalable Optimal Control Allocation: Linear and Quadratic Programming Methods Applied to Active Capacitor Balancing in Modular Multilevel Converters

The paper introduces a novel, scalable control allocation (CA) formulation for active capacitor balancing of the Modular Multilevel Converter (MMC). The formulation is obtained by introducing a converter arm model that is also scalable and accommodates an MMC with any number of phases and any number of submodules (SM). The CA algorithm involves the fast real-time minimization of an error cost function formalized as linear programming (LP) and quadratic programming (QP) problems. The real-time coding is implemented in both cases using an interior-point method. A hardware-in-the-loop (HIL) test procedure is used to demonstrate the ability of the CA to perform active capacitor voltage balancing. The influence of QP vs LP on the system behavior is also evaluated, and tracking errors using QP are found to be more evenly distributed than with LP.

Design of fractional order PID controller for AVR system using whale optimization algorithm

In this paper a robust fractional order PID (FOPID) controller is proposed to control the automatic voltage regulator (AVR) system, the tuning of the controller gains are done using whale optimization algorithm (WOA) and integral time absolute error (ITAE) cost function is adopted to achieve an efficient performance. The transient analysis was done and compared with conventional PID in terms of overshoot, settling time, rise time, and peak time to explain the superiority of the proposed controller. Finally, a robustness analysis is done by adding external disturbances to the system and changing the system parameters by ±20% from its original value, the controller overcomes the disturbances signals with less than 0.25 s and faces the changes of the system values and returning the response within (0.7-1) sec and led the system to the desired response efficiently. The numerical simulations showed that the smart WOA offers satisfying results and faster response reflected clearly on the robust and stable performance of the proposed controller in improving the transient analysis of AVR system response.

Frequentist parameter estimation with supervised learning

Recently, there has been a great deal of interest surrounding the calibration of quantum sensors using machine learning techniques. This work explores the use of regression to infer a machine-learned point estimate of an unknown parameter. Although the analysis is necessarily frequentist—relying on repeated estimates to build up statistics—the authors clarify that this machine-learned estimator converges to the Bayesian maximum a posteriori estimator (subject to some regularity conditions). When the number of training measurements is large, this is identical to the well-known maximum-likelihood estimator (MLE), and using this fact, the authors argue that the Cramér–Rao sensitivity bound applies to the mean-square error cost function and can therefore be used to select optimal model and training parameters. The machine-learned estimator inherits the desirable asymptotic properties of the MLE, up to a limit imposed by the resolution of the training grid. Furthermore, the authors investigate the role of quantum noise in the training process and show that this noise imposes a fundamental limit on the number of grid points. This manuscript paves the way for machine-learning to assist the calibration of quantum sensors, thereby allowing maximum-likelihood inference to play a more prominent role in the design and operation of the next generation of ultra-precise sensors.

Assessing the performance of artificial neural networks to predict ionospheric TEC over Nigeria during different space weather events

The ionosphere model is essential to satellite-based systems to accurately correct the ionospheric error encountered by satellite signals en route. The Levenberg–Marquardt backpropagation (LMBP) algorithm in the artificial neural network (ANN) was used in this work to predict the total electron content (TEC) within the trough of equatorial ionization anomaly (EIA) over Nigeria. Two sets of data were used over the period of three consecutive years (2011–2013) of high solar activity. The first set was used as an input to the ANN model and the second set of data was used as a target. Seventy percent of the data sets were used to train the network, 15% of the data were used for validation, and 15% used for testing. The performance of the model was assessed during specific quiet and disturbed geomagnetic conditions. The regression analysis of the model output was optimized by minimizing a cost function of the mean square error (MSE). The results of the errors, regression, and comparative analyses have revealed that the ANN model is able to predict accurate and reliable TEC that compares well with the actual experimental data at any geophysical conditions. Hence, this model would be useful to forecast TEC over Nigeria to a reliable threshold.

Epileptic Seizure Recognition Using Reduced Deep Convolutional Stack Autoencoder and Improved Kernel RVFLN From EEG Signals.

In this paper, reduced deep convolutional stack autoencoder (RDCSAE) and improved kernel random vector functional link network (IKRVFLN) are combined to recognize the epileptic seizure using both the multichannel scalp and single-channel electroencephalogram (EEG) signals. The novel RDCSAE structure is designed to extract the most discriminative unsupervised features from EEG signals and fed into the proposed supervised IKRVFLN classifier to train efficiently by reducing the mean-square error cost function for recognizing the epileptic seizure activity with promising accuracy. The proposed RDCSAE-IKRVFLN algorithm is tested over the benchmark Boston Children's Hospital multichannel scalp EEG (sEEG) and Boon University, Germany single-channel EEG databases. The less computational complexity, higher learning speed, better model generalization, accurate epileptic seizure recognition, remarkable classification accuracy, negligible false positive rate per hour (FPR/h) and short event recognition time are the main advantages of the proposed RDCSAE-IKRVFLN method over reduced deep convolutional neural network (RDCNN), RDCSAE and RDCSAE-KRVFLN methods. The proposed RDCSAE-IKRVFLN method is implemented in a high-speed reconfigurable field-programmable gate array (FPGA) hardware environment to design a computer-aided-diagnosis (CAD) system for automatic epileptic seizure diagnosis. The simplicity, feasibility, and practicability of the proposed method validate the stable and reliable performances of epilepsy detection and recognition.