Proposed Estimation Method Research Articles

Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework

3D human pose estimation using monocular images is an important yet challenging task. Existing 3D pose detection methods exhibit excellent performance under normal conditions however their performance may degrade due to occlusion. Recently some occlusion aware methods have also been proposed however, the occlusion handling capability of these networks has not yet been thoroughly investigated. In the current work, we propose an occlusion-guided 3D human pose estimation framework and quantify its occlusion handling capability by using different protocols. The proposed method estimates more accurate 3D human poses using 2D skeletons with missing joints as input. Missing joints are handled by introducing occlusion guidance that provides extra information about the absence or presence of a joint. Temporal information has also been exploited to better estimate the missing joints. A large number of experiments are performed for the quantification of occlusion handling capability of the proposed method on three publicly available datasets in various settings including random missing joints, fixed body parts missing, and complete frames missing using mean per joint position error criterion. In addition to that, the quality of the predicted 3D poses is also evaluated using action classification performance as a criterion. 3D poses estimated by the proposed method achieved significantly improved action recognition performance in the presence of missing joints. Our experiments demonstrate the effectiveness of the proposed framework for handling the missing joints as well as quantification of the occlusion handling capability of the deep neural networks.

A Two-Stage GA-Based sEMG Feature Selection Method for User-Independent Continuous Estimation of Elbow Angles

Surface electromyography (sEMG) has great application potential in upper extremity rehabilitation exoskeleton. The accurate identification of elbow motion angle is crucial for the sEMG-controlled upper limb exoskeleton rehabilitation system. However, the existing high inter-subject variability in sEMG limits the generality of the model built through learning algorithms among different subjects. Aiming at the above problem, a feature selection method based on a two-stage genetic algorithm (GA) is proposed for the accurate user-independent estimation of continuous movements. And the information theory-based minimum redundancy maximum relevance criterion serves as the fitness function to evaluate the goodness of subsets. The effectiveness of the proposed method is verified by estimating the motion angle of the elbow joint using the collected sEMG data of 6 participants. The prediction performance is compared with that before the two-stage GA-based feature selection, and different metrics and statistical analyses are adopted to evaluate the results. The estimation angle error calculated after two-stage GA-based feature selection is controlled within 10°, which shows the feasibility of the proposed method for the accurate user-independent estimation of continuous joint movements.

Mapping Individual Motor Unit Activity to Continuous Three-DoF Wrist Torques: Perspectives for Myoelectric Control.

The surface electromyography (EMG) decomposition techniques provide access to motor neuron activities and have been applied to myoelectric control schemes. However, the current decomposition-based myoelectric control mainly focuses on discrete gestures or single-DoF continuous movements. In this study, we aimed to map the motor unit discharges, which were identified from high-density surface EMG, to the three degrees of freedom (DoFs) wrist movements. The 3-DoF wrist torques and high-density surface EMG signals were recorded concurrently from eight non-disabled subjects. The experimental protocol included single-DoF movements and their various combinations. We decoded the motor unit discharges from the EMG signals using a segment-wise decomposition algorithm. Then the neural features were extracted from motor unit discharges and projected to wrist torques with a multiple linear regression model. We compared the performance of two neural features (twitch model and spike counting) and two training schemes (single-DoF and multi-DoF training). On average, 145 ± 33 motor units were identified from each subject, with a pulse-to-noise ratio of 30.8 ± 4.2 dB. Both neural features exhibited high estimation accuracy of 3-DoF wrist torques, with an average [Formula: see text] of 0.76 ± 0.12 and normalized root mean square error of 11.4 ± 3.1%. These results demonstrated the efficiency of the proposed method in continuous estimation of 3-DoF wrist torques, which has the potential to advance dexterous myoelectric control based on neural information.

High Maneuvering Target Long-time Coherent Integration and Motion Parameters Estimation Based on Bayesian Compressive Sensing

This paper intends to address the long-time coherent integration (LTCI) of high maneuvering targets in low signal-to-noise (SNR) environments with high computational efficiency and accuracy. The high-order motion parameters estimation, considering the acceleration and jerk, is modeled as the under-estimated linear regression and the complex-field Bayesian compressive sensing (BCS) algorithm is introduced to resolve the sparse recovery. To correct the high-order range migration (RM) and reduce the order of Doppler frequency migration (DFM), the adjacent cross correlation (ACCF) is applied. An effective method based on non-coherent integration is proposed to extract the self-term from ACCF result. Further, with the proper design of sensing matrix, the acceleration and jerk motion parameters are estimated by sparse reconstruction based on the complex-field BCS. Compared with the traditional methods based on time-frequency transform, like Lv's distribution (LVD), the proposed BCS algorithm is free from the interference of cross-terms and maintains the super-resolution ability, which provides better performance in parameters estimation and multi-targets discrimination. Finally, the numerical experiments validate the advantages of the proposed method in motion parameters estimation, super-resolution ability and computational efficiency.

Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting

Massive electrical load exhibits many patterns making it difficult for forecast algorithms to generalise well. Most learning algorithms produce a better forecast for dominant patterns in the case of weekday consumption and otherwise for less dominant patterns in weekend and holiday consumption. In view of this, there is the need to cluster the load patterns, so learning algorithms can focus on the patterns independently to produce forecasts with better accuracy for all cases. However, clustering time-series data breaks the time-series dependency, making model training difficult. This paper presents a novel sequence-to-sequence cluster framework to reform time-series dependency after clustering; this enables independent clusters to be modelled using Convolutional Neural Network-Gated Recurrent Unit, which learns spatiotemporal features for future forecasts. A real-world dataset by the Korea Power Exchange composed of nationwide consumption is used for case studies and experiments. Experimental results verify that the proposed study effectively improves the accuracy of electric load forecasting by about 50%, with a WAPE of 0.67%. The proposed method also speeds up the training process of the forecast algorithm by about 35%, given that only a subset of the dataset is trained due to clustering. Korea Water Resources Corporation has implemented the proposed method for load forecasting and system marginal price estimation.

Deep Learning Aided State Estimation for Guarded Semi-Markov Switching Systems With Soft Constraints

This paper investigates the problem of state estimation for guarded semi-Markov switching systems with soft constraints. We first construct the switching system in a multiple model manner and derive the recursive Bayesian filter compatible with the sojourn time and base state dependent mode transitions. To solve the intractable conditioned mode transition probabilities, we develop deep learning based classifiers with long short-term memory networks capturing the temporal dependencies. Various network structures are designed to handle different situations where knowledge of the transition probability matrix is available or deficient. Furthermore, we incorporate sequential Monte Carlo techniques into the multiple model framework to resolve the local filtering task. A novel particle refinement procedure exploiting the constraint information is proposed to improve the efficiency of particle propagation and prevent the exponential increase of particle number simultaneously. Simulations on a robotic manipulator and an autonomous vehicle tracking task validate the effectiveness of the proposed state estimation method.

Stress-strength reliability estimation for the inverted exponentiated Rayleigh distribution under unified progressive hybrid censoring with application

<abstract> <p>In this paper, we studied the estimation of a stress-strength reliability model ($R = P(X>Y)$) based on inverted exponentiated Rayleigh distribution under the unified progressive hybrid censoring scheme (unified PHCS). The maximum likelihood estimates of the unknown parameters were obtained using the stochastic expectation-maximization algorithm (stochastic EMA). The asymptotic confidence intervals were also created. Under squared error and Linex and generalized entropy loss functions, the Gibbs sampler together with Metropolis-Hastings algorithm was provided to compute the Bayes estimates and the credible intervals. Extensive simulations were performed to see the effectiveness of the proposed estimation methods. Also, parallel to the development of reliability studies, it is necessary to study its application in different sciences such as engineering. Therefore, droplet splashing data under two nozzle pressures were proposed to exemplify the theoretical outcomes.</p> </abstract>

A comprehensive estimation method of phase error in the frequency‐interleaving digital‐to‐analog converter

This letter studied the phase error in the frequency-interleaving digital-to-analog converter (FI-DAC) and proposed a comprehensive phase estimation method. Firstly, the model of the FI-DAC system was established, and the phase error was considered that consists of three parts: time delay error, initial phase error and non-linear phase error. By analyzing the phase function characteristics of the system, the least squares (LS) was used to linearly fit the phase functions of the non-overlapping bands to estimate both the time delay and the initial phase of each sub-band channel. Then, the non-linear phase error of the system was estimated by the difference between the system phase function and the estimated linear phase function. Finally, the effectiveness of the proposed estimation method was verified by the built FI-DAC test bench.

Joint CD, DGD, and PDL Estimation Enabled by FrFT based Time-Frequency Reconstruction

A high-precision optical performance monitoring (OPM) scheme is proposed to achieve chromatic dispersion estimation (CDE), differential group delay (DGD) estimation, and polarization-dependent loss (PDL) estimation simultaneously for the long haul coherent optical fiber communication system. A time-frequency analysis method based on the fractional Fourier transformation (FrFT) is applied to the optical signal under different channel impairments to reconstruct the two-dimensional distribution images. Multi-task convolutional neural network (MT-CNN) is then adopted to extract the corresponding features of impairments and establish a solid relationship between the images and impairment quantities, thus can jointly estimate CD, DGD, and PDL. We validate in simulation the proposed estimation using 50GBaud PDM-16QAM, the mean absolute error (MAE) for CD, DGD, and PDL estimation is 114ps/nm, 0.26ps, and 0.072dB, and the monitoring window ranges from 1600∼48000ps/nm, 4∼100ps, and 0∼2dB, respectively. Simulation verification indicates that the proposed estimation method achieves high precision and robustness to ASE noise and fiber nonlinearity of self-phase modulation (SPM).

Estimation of the Cholesky Multivariate Stochastic Volatility Model Using Iterated Filtering

Aim: The paper aims to propose a new estimation method for the Cholesky Multivariate Stochastic Volatility Model based on the iterated filtering algorithm (Ionides et al., 2006, 2015). Methodology: The iterated filtering method is a frequentist-based technique that through multiple repetitions of the filtering process, provides a sequence of iteratively updated parameter estimates that converge towards the maximum likelihood estimate. Results: The effectiveness of the proposed estimation method was shown in an empirical example in which the Cholesky Multivariate Stochastic Volatility Model was used in a study on safe-haven assets of one market index: Standard and Poor’s 500 and three safe-haven candidates: gold, Bitcoin and Ethereum. Implications and recommendations: In further research, the iterating filtering method may be used for more advanced multivariate stochastic volatility models that take into account, for example, the leverage effect (as in Ishihara et al., 2016) and heavy-tailed errors (as in Ishihara and Omori, 2012). Originality/Value: The main contribution of the paper is the proposition of a new estimation method for the Cholesky Multivariate Stochastic Volatility Model based on iterated filtering algorithm This is one of the few frequentist-based statistical inference methods for multivariate stochastic volatility models.

Modeling and Adaptive Parameter Estimation for a Piezoelectric Cantilever Beam

This paper proposes a new adaptive estimation approach to online estimate the model parameters of a piezoelectric cantilever beam. The beam behavior is firstly modeled using partial differential equations (PDE) considering the Kelvin-Voigt damping. To facilitate the estimation of unknown model parameters, the Galerkin’s method is introduced to extract desired vibration modes by separating the time and space variables of the PDE. Then, considering two major vibration modes, the corresponding system model can be represented by a fourth-order ordinary differential equation (ODE). Finally, by using measured input and output information, a novel adaptive parameter estimation strategy is introduced to estimate the unknown parameters of the derived ODE model in real time. For the purpose of driving the parameter updating law, the estimation error is extracted by using an auxiliary variable and a time-varying gain. Consequently, the convergence of the parameter estimation error is rigorously proved based on the Lyapunov theory. Simulations and experimental results show the validity and practicability of the proposed estimation method.

Data- and theory-guided learning of partial differential equations using SimultaNeous basis function Approximation and Parameter Estimation (SNAPE)

Full-field discrete measurements of the continuous spatiotemporal response of physical processes often generate large datasets. Such continuous spatiotemporal dynamic models are represented by partial differential equations (PDEs). In the past, attempts have been made to identify the PDE models from the measured response by inferring its parameters via regression or deep learning-based techniques. But the previously presented regression-based methods fail to estimate the parameters of the higher-order PDE models in the presence of moderate noise. Likewise, the deep learning-based methods lack the much-needed property of repeatability and robustness in the identification of PDE models from the measured response. The proposed method of SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE) addresses such drawbacks by simultaneously fitting basis functions to the measured response and estimating the parameters of both ordinary and partial differential equations. The domain knowledge of the general multidimensional process is used as a constraint in the formulation of the optimization framework. The alternating direction method of multipliers (ADMM) algorithm is used to simultaneously optimize the loss function over the parameter space of the PDE model and coefficient space of the basis functions. The proposed method not only infers the parameters but also estimates a continuous function that approximates the solution to the PDE model. SNAPE not only demonstrates its applicability on various complex dynamic systems that encompass wide scientific domains including Schrödinger equation, chaotic duffing oscillator, and Navier–Stokes equation but also estimates an analytical approximation to the process response. The method systematically combines the knowledge of well-established scientific theories and the concepts of data science to infer the properties of the process from the observed data.

Simultaneous Confidence Intervals for All Pairwise Differences between the Coefficients of Variation of Multiple Birnbaum–Saunders Distributions

In situations where several positive random variables cannot be described using symmetrical distributions, a positively asymmetric distribution which has garnered much attention for studying them is the Birnbaum-Saunders (BS) distribution. This distribution was originally proposed to study fatigue over time in materials and has become widely employed for reliability and fatigue studies. In statistics, the coefficient of variation (CV) is employed to measure relative variation. Furthermore, comparing the CVs of several samples from BS distributions is an important approach to assess the variation among them. Herein, we propose estimation methods for the simultaneous confidence intervals (SCIs) for all pairwise differences between the CVs of multiple BS distributions based on the percentile bootstrap, the generalized confidence interval (GCI), the method of variance estimates recovery (MOVER) based on the asymptotic confidence interval (ACI) and GCI, Bayesian credible interval, and the highest posterior density (HPD) interval. The coverage probabilities and average lengths of the proposed methods were examined via a simulation study to determine their performance. The results demonstrate that GCI and the MOVER based on the GCI method provided satisfactory performances in almost every case studied. Particulate matter ≤ 2.5 μm (PM2.5) concentration datasets from three areas in northern Thailand were used to illustrate the effectiveness of the proposed methods.

Estimation of Respiratory Rate from Functional Near-Infrared Spectroscopy (fNIRS): A New Perspective on Respiratory Interference

Respiration is recognized as a systematic physiological interference in functional near-infrared spectroscopy (fNIRS). However, it remains unanswered as to whether it is possible to estimate the respiratory rate (RR) from such interference. Undoubtedly, RR estimation from fNIRS can provide complementary information that can be used alongside the cerebral activity analysis, e.g., sport studies. Thus, the objective of this paper is to propose a method for RR estimation from fNIRS. Our primary presumption is that changes in the baseline wander of oxygenated hemoglobin concentration (O2Hb) signal are related to RR. fNIRS and respiratory signals were concurrently collected from subjects during controlled breathing tasks at a constant rate from 0.1 Hz to 0.4 Hz. Firstly, the signal quality index algorithm is employed to select the best O2Hb signal, and then a band-pass filter with cut-off frequencies from 0.05 to 2 Hz is used to remove very low- and high-frequency artifacts. Secondly, troughs of the filtered O2Hb signal are localized for synthesizing the baseline wander (S1) using cubic spline interpolation. Finally, the fast Fourier transform of the S1 signal is computed, and its dominant frequency is considered as RR. In this paper, two different datasets were employed, where the first one was used for the parameter adjustment of the proposed method, and the second one was solely used for testing. The low mean absolute error between the reference and estimated RRs for the first and second datasets (2.6 and 1.3 breaths per minute, respectively) indicates the feasibility of the proposed method for RR estimation from fNIRS. This paper provides a novel view on the respiration interference as a source of complementary information in fNIRS.

State Estimation and Remaining Useful Life Prediction of PMSTM Based on a Combination of SIR and HSMM

The permanent magnet synchronous traction motor (PMSTM) is the core equipment of urban rail transit. If a PMSTM fails, it will cause serious economic losses and casualties. It is essential to estimate the current health state and predict remaining useful life (RUL) for PMSTMs. Directly obtaining the internal representation of a PMSTM is known to be difficult, and PMSTMs have long service lives. In order to address these drawbacks, a combination of SIR and HSMM based state estimation and RUL prediction method is introduced with the multi-parameter fusion health index (MFHI) as the performance indicator. The proposed method’s advantages over the conventional HSMM method were verified through simulation research and examples. The results show that the proposed state estimation method has small error distribution results, and the RUL prediction method can obtain accurate results. The findings of this study demonstrate that the proposed method may serve as a new and effective technique to estimate a PMSTM’s health state and RUL.

Sensor fault detection and isolation based on zonotopic Kalman Filter for accelerometer system in drilling tools

Sensor faults of the accelerometer system impact the efficiency and security of the drilling process, so the sensor fault detection and isolation are significant. However, there are insufficient relevant studies on the accelerometer system affected by time-varying disturbances with unknown bounds. This paper proposes a residual generator based on the Zonotopic Kalman Filter with the process disturbance estimation, and the bounds of parametric uncertainties and measurement noises are obtained by calibration. Then, a fault detection test is realized by time-varying residual bounds regarded as the combinations of residuals and dynamic thresholds. Moreover, a fault isolation decision is developed by analyzing fault directions. Finally, simulation and experiment results demonstrate the effectiveness of the proposed method. The proposed method estimates time-varying process disturbances and performs better than existing methods. This paper provides a reference for the reliable application of the accelerometer system.

Saliency-Based Rotor Spatial Position Displacement Self-Sensing for Self-Bearing Machines.

Self-bearing machines do not contain physical bearings but magnetic bearings. Both rotor rotary and spatial positions displacement are required in these types of machines to control the rotor position while it is levitating. Self-bearing machines often use external sensors for x (horizontal) and y (vertical) spatial position measurement, which will result in additional cost, volume, complexity, and number of parts susceptible to failure. To overcome these issues, this paper proposes a xy-position estimation self-sensing technique based on both main- and cross-inductance variation. The proposed method estimates x and y position based on inductive saliency between two sets of three-phase coils. The proposed idea is applied on a combined winding self-bearing machine which does not require additional suspension force winding. No additional search coil placement for xy-position estimation is required. Therefore, the proposed algorithm can result in a compact size self-bearing machine that does not require external sensors for xy-position measurement and suspension force winding.

Estimation of First Order Plus Dead Time and Second Order Plus Dead Time models from noisy step response data

SummaryThis paper proposes the estimation of first‐order‐plus‐dead‐time (FOPDT) and second‐order‐plus‐dead‐time (SOPDT) models from noisy step response data. The model parameters are estimated by computation of areas, which makes it robust in the presence of stochastic disturbances in the step response data. The efficiency of the methodology is extensively tested in various numerical examples as well as in real‐life experimental tests. The results—comparing our proposed estimation method with some other methods—suggest that the novel algorithm can be used with noisy step response data and adequately approximates high‐order systems. Moreover, it does not require any system identification expertise, making it readily accessible for the nonexperienced user in industrial practice. The method is successfully validated for overdamped, reasonably underdamped, as well as highly oscillatory processes, hence offering a comprehensive estimation method.

Lindley procedure and MCMC technique in Bayesian estimation for Kumaraswamy Weibull distribution

In this study, a comparison between three methods for estimating unknown parameters of the Kumaraswamy Weibull distribution for different sample sizes of type II censoring data is presented. Specifically, we compare the behaviors of maximum likelihood estimates, Lindley and Markov chain Monte Carlo (MCMC) estimates as Bayesian estimates. We have not found any work on this topic after reviews of the literature except one with little information about the inference of this important distribution. The simplest form for Lindley approximation of the posterior mean is proposed and approximate closed forms of acceptable Bayes estimates for the models of multi-parameters such as Kumaraswamy Weibull distribution is derived. A Monte Carlo simulation is conducted to investigate the performances of the proposed estimators. Finally, three real data examples are analyzed to illustrate the application possibility of the different proposed estimation methods. The results reveal that, although, good performance of the approximate forms of Lindley estimators, the estimators resulting in the MCMC technique are better in the sense of the mean squared errors.

Training Free In-Service Chromatic Dispersion Estimation Using Power Spectrum Analysis for MZM Based IM/DD Optical Communication Systems

In high-speed optical fiber communications, chromatic dispersion (CD) estimation is essential for the monitoring and compensation of CD-induced impairments. Compared with coherent detection, in short-reach optical communication systems, intensity modulation/direct detection (IM/DD) is more widely used, and the existing dispersion estimation techniques usually require training signals or a large amount of data for curve fitting or machine learning. However, these methods cannot provide in-service estimation. This paper presents a novel technique for in-service CD estimation in IM/DD short-reach optical communication systems based on our derived analytical model. With the analytical model, the in-service CD estimation is realized via the direct power spectrum analysis of the received signal. Unlike previous studies that only work with single-frequency sinusoidal signals, the practical random data with the rectangular type of base waveform is considered in our model. Therefore, our method can be applied to the dispersion estimation of various pulse amplitude modulation (PAM) based systems. Our proposed training free in-service CD estimation method is verified and investigated, where results show that better than 0.5% accuracy in dispersion estimation can be achieved in optical communication systems with up to 40 GBaud data rate and 100 km transmission distance.