Search

Fault diagnosis plays an indispensable role in prognostics and health management of rotating machines. In recent years, intelligent fault diagnosis methods based on domain adaptation technology have attracted the attention of researchers. However, a more extensive application scenario of fault diagnosis − partial domain adaptation (PDA) − has not been well-resolved. In this article, for the first time, a novel stacked auto-encoder based partial adversarial domain adaptation (SPADA) model is proposed to solve the fault diagnosis problem in PDA situations. Two deep stack auto-encoders are first designed to extract representative features from the training data (source domain) and test data (target domain), respectively. Then, a weighted classifier based on Softmax is used to weight the features from the source and target domains. Meanwhile, another domain discriminator and label predictor using the Softmax classifier are adopted to simultaneously implement domain adaptation and fault diagnosis. Comprehensive analysis is performed on real data to test the performance of the SPADA model and detailed comparisons are provided; the extensive experimental results show that the diagnosis performance of SPADA outperforms the existing deep learning and domain adaptation methods in dealing with the PDA problem.

A novel $d$ -axis variable-structure control (VSC) current regulator is proposed for realizing fast and accurate sensorless control in the surface-mounted permanent magnet synchronous motor (SPMSM) in this article. In this proposed regulator, the sigmoid function is employed as a switching control law to reduce the chattering effect and increase the degrees of freedom in tuning the regulator. The sensorless control performance under the $d$ -axis VSC current regulator is testified by using the model reference adaptive system (MRAS) and sliding-mode control (SMC) method. In the MRAS observer, the adaptive law of speed and resistance is designed so that resistance, speed, and position can be estimated simultaneously, which can eliminate the influence of the resistance variations theoretically. In the sliding-mode observer, the back electromotive force observer is employed to estimate the speed and position of PMSM so that the estimation can cover a relative low-speed range because pure integration is not employed. Furthermore, the dead-time compensation voltages (DTCV) strategy is employed to online estimate disturbance voltage in a feed-forward manner, which can improve the sensorless control performance of PMSM. Experimental results obtained from an SPMSM drive system validate the superiority of the proposed $d$ -axis VSC current regulator.

Fault diagnosis of rolling bearings is an essential process for improving the reliability and safety of the rotating machinery. It is always a major challenge to ensure fault diagnosis accuracy in particular under severe working conditions. In this article, a deep adversarial domain adaptation (DADA) model is proposed for rolling bearing fault diagnosis. This model constructs an adversarial adaptation network to solve the commonly encountered problem in numerous real applications: the source domain and the target domain are inconsistent in their distribution. First, a deep stack autoencoder (DSAE) is combined with representative feature learning for dimensionality reduction, and such a combination provides an unsupervised learning method to effectively acquire fault features. Meanwhile, domain adaptation and recognition classification are implemented using a Softmax classifier to augment classification accuracy. Second, the effects of the number of hidden layers in the stack autoencoder network, the number of neurons in each hidden layer, and the hyperparameters of the proposed fault diagnosis algorithm are analyzed. Third, comprehensive analysis is performed on real data to validate the performance of the proposed method; the experimental results demonstrate that the new method outperforms the existing machine learning and deep learning methods, in terms of classification accuracy and generalization ability.

Rotating machinery is important to industrial production. Any failure of rotating machinery, especially the failure of rolling bearings, can lead to equipment shutdown and even more serious incidents. Therefore, accurate residual life prediction plays a crucial role in guaranteeing machine operation safety and reliability and reducing maintenance cost. In order to increase the forecasting precision of the remaining useful life (RUL) of the rolling bearing, an advanced approach combining elastic net with long short-time memory network (LSTM) is proposed, and the new approach is referred to as E-LSTM. The E-LSTM algorithm consists of an elastic mesh and LSTM, taking temporal-spatial correlation into consideration to forecast the RUL through the LSTM. To solve the over-fitting problem of the LSTM neural network during the training process, the elastic net based regularization term is introduced to the LSTM structure. In this way, the change of the output can be well characterized to express the bearing degradation mode. Experimental results from the real-world data demonstrate that the proposed E-LSTM method can obtain higher stability and relevant values that are useful for the RUL forecasting of bearing. Furthermore, these results also indicate that E-LSTM can achieve better performance.

Bo Lian,1,* Hua Wei,2,* Ruiyan Pan,3,* Jingui Sun,4 Bo Zhang,3 Jingliang Wu,1 Xiujie Li,1 Guixiang Tian1 1School of Bioscience and Technology, Weifang Medical University, Weifang 261053, People’s Republic of China; 2Department of Endocrinology, ShouGuang Peoples’ Hospital, Weifang 262700, People’s Republic of China; 3School of Pharmacy, Weifang Medical University, Weifang 261053, People’s Republic of China; 4Department of Oncology, ShouGuang Peoples’ Hospital, Weifang 262700, People’s Republic of China*These authors contributed equally to this workCorrespondence: Xiujie Li Email lixiujie@wfmc.edu.cnGuixiang TianSchool of Bioscience and Technology, Weifang Medical University, Weifang 261053, People’s Republic of ChinaEmail gxtian2008@163.comBackground: Tumor angiogenesis plays a crucial role in tumor development, and recent efforts have been focused on combining proapoptotic and antiangiogenic activities to enhance antitumor therapy.Methods: In this study, galactose-modified liposomes (Gal-LPs) were prepared for co-delivery of doxorubicin (DOX) and combretastatin A4 phosphate (CA4P). The co-cultured system composed of BEL-7402 and human umbilical vein endothelial cells (HUVEC) cells was established to effectively evaluate in vitro anti-tumor activity through cell viability and cell migration assay. Furthermore, both in vivo bio-distribution and anti-hepatoma effect of DOX&CA4P/Gal-LPs were investigated on H22 tumor cell-bearing mice.Results: The results showed that DOX&CA4P/Gal-LPs were spherical with a mean particle size of 143 nm, and could readily be taken up by BEL-7402 cells. Compared with a mixture of free DOX and CA4P, the DOX&CA4P/Gal-LPs were more effective in inhibiting cell migration and exhibited stronger cytotoxicity against BEL-7402 cells alone or a co-cultured system. The in vitro studies showed that the co-cultured system was a more effective model to evaluate the anti-tumor activity of combination therapy. Moreover, DOX&CA4P/Gal-LPs exhibited a greater anti-hepatoma effect than other drug formulations, indicating that Gal-LPs could promote drug accumulation in the tumor region and improve the anti-tumor activity.Conclusion: Gal-LPs co-loaded with chemotherapeutic and antiangiogenic drugs are a promising strategy for anti-hepatoma therapy.Keywords: liposomes, anti-hepatoma, co-delivery, combination therapy

Electroencephalogram (EEG) signal analysis plays an essential role in detecting and understanding epileptic seizures. It is\ud known that seizure processes are nonlinear and nonstationary, discriminating between rhythmic discharges and dynamic\ud change is a challenging task in EEG based seizure detection. In this paper, a new time-varying (TV) modeling framework,\ud based on an autoregressive (AR) model structure, is proposed to characterize and analyze EEG signals. The TV parameters\ud of the AR model are approximated through a multi-wavelet basis function expansion (MWBF) approach. An effective ultraregularized orthogonal forward regression (UROFR) algorithm is employed to significantly reduce and refine the resulting\ud expanded model. Given a time-varying process, the proposed TVAR-MWBF-UROFR method can generate a parsimonious\ud TVAR model, based on which a high-resolution power spectrum density (PSD) estimation can be obtained. Informative features are then defined and extracted from the PSD estimation. The TVAR-MWBF-UROFR method is applied to a number of\ud real EEG datasets; features obtained from these datasets are then used for seizure detection and classification. To make the\ud results more accurate and reliable, a PCA algorithm is adopted to select the optimal feature subset, and a Bayesian optimization technique based on the Gaussian process (GP) is performed to determine the coefficients associated with each of the\ud classifiers. Experimental results of the proposed approach outperform the compared state-of-the-art classifiers on two\ud benchmark datasets. Moreover, the results produced by the proposed time-frequency analysis scheme are more reliable for\ud seizure detection based on the noisy EEG datasets used in our case studies.

The use of the multiscale generalized radial basis function (MSRBF) neural networks for image feature extraction and medical image analysis and classification is proposed for the first time in this work. The MSRBF networks hold a simple and flexible architecture that has been successfully used in forecasting and model structure detection of input-output nonlinear systems. In this work instead, MSRBF networks are part of an integrated computer-aided diagnosis (CAD) framework for breast cancer detection, which holds three stages: an input-output model is obtained from the image, followed by a high-level image feature extraction from the model and a classification module aimed at predicting breast cancer. In the first stage, the image data is rendered into a multiple-input-single-output (MISO) system. In order to improve the characterisation, the nonlinear autoregressive with exogenous inputs (NARX) model is introduced to rearrange the available input-output data in a nonlinear way. The forward regression orthogonal least squares (FROLS) algorithm is then used to take advantage of the previous arrangement by solving the system as a model structure detection problem and finding the output layer weights of the NARX-MSRBF network. In the second stage, once the network model is available, the feature extraction takes place by stimulating the input to produce output signals to be compressed by the discrete cosine transform (DCT). In the third stage, we leverage the extracted features by using a clustering algorithm for classification to integrate a CAD system for breast cancer detection. To test the method performance, three different and well-known public image repositories were used: the mini-MIAS and the MMSD for mammography, and the BreaKHis for histopathology images. A comparison exercise was also made between different database partitions to understand the mammogram breast density effect in the performance since there are few remarks in the literature on this factor. Classification results show that the new CAD method reached an accuracy of 93.5% in mini-Mammo graphic image analysis society (mini-MIAS), 93.99% in digital database for screening mammography (DDSM) and 86.7% in the BreaKHis. We found that the MSRBF networks are able to build tailored and precise image models and, combined with the DCT, to extract high-quality features from both black and white and coloured images.

A three-dimensional (3D) composite consisting of nickel-cobalt (Ni-Co) dual hydroxide nanoneedles (NCDHNs) grown on a carbon nanotube (CNT) material, denoted as CNTs@NCDHNs, was designed using a facile one-step hydrothermal method. This composite was further fabricated into electrodes, which exhibited high rate capability and long cycle life. Comparative analysis of the electrochemical performance between 3D CNTs@NCDHNs electrodes and Ni-Co hydroxide electrodes revealed that the high rate capability and long cycle life of the CNTs@NCDHNs are due to a synergistic effect. The CNTs@NCDHNs exhibited a high specific capacitance of 1823 F g-1 at a current density of 1 A g-1, and more than 77.6% of the capacitance was retained at a charge-discharge rate of 20 A g-1. To evaluate the functional behavior of the CNTs@NCDHNs, quasi-solid-state cells using CNTs@NCDHNs as the positive electrode and rGO-Fe2O3 as the negative electrode were assembled and tested. These devices presented ultrafast charge-discharge rates of up to 20 A g-1 with high rate capabilities and excellent long-term cyclic stability. The corresponding quasi-solid-state device presented a high energy density of up to 54.6 Wh kg-1 at a power density of 1.13 kW kg-1 and an energy density of 35.8 Wh kg-1 at 12.4 kW kg-1 when a voltage in the range 0-1.6 V was applied. Moreover, the device exhibited optimal flexibility, stability, and safety under different extreme conditions.

Bilevel optimization has been recognized as one of the most difficult and challenging tasks to deal with because a solution to the upper level problem may be feasible only if it is also an optimal solution to the lower level problem. In recent years, evolutionary bilevel optimization has attracted increasing interest. In this paper, an efficient self-adaptive bilevel differential evolution (SABiLDE) with k-nearest neighbors (kNN) based interpolation is proposed to solve bilevel optimization problems. The kNN approximation is applied to estimate the optimal lower level variables for any newly generated upper candidates to improve the computational efficiency. A similarity based self-adaptive strategy for the dynamic control of lower level population size and search radius is introduced to further enhance the efficiency of the lower level function evaluations. A test set with 10 standard test problems and the SMD suite with controllable complexities are used to evaluate the performance of the proposed approach. Compared with four recent state-of-the-art methods, the numerical results produced by the proposed method are promising and show great potential for solving generic bilevel optimization problems.

Fisheye images with a far larger Field of View (FOV) have severe radial distortion, with the result that the associated image feature matching process cannot achieve the best performance if the traditional feature descriptors are used. To address this challenge, this paper reports a novel distorted Binary Robust Independent Elementary Feature (BRIEF) descriptor for fisheye images based on a spherical perspective model. Firstly, the 3D gray centroid of feature points is designed, and the position and direction of the feature points on the spherical image are described by a constructed feature point attitude matrix. Then, based on the attitude matrix of feature points, the coordinate mapping relationship between the BRIEF descriptor template and the fisheye image is established to realize the computation associated with the distorted BRIEF descriptor. Four experiments are provided to test and verify the invariance and matching performance of the proposed descriptor for a fisheye image. The experimental results show that the proposed descriptor works well for distortion invariance and can significantly improve the matching performance in fisheye images.

Multi-person pose estimation is a fundamental and challenging problem to many computer vision tasks. Most existing methods can be broadly categorized into two classes: top-down and bottom-up methods. Both of the two types of methods involve two stages, namely, person detection and joints detection. Conventionally, the two stages are implemented separately without considering their interactions between them, and this may inevitably cause some issue intrinsically. In this paper, we present a novel method to simplify the pipeline by implementing person detection and joints detection simultaneously. We propose a Double Embedding (DE) method to complete the multi-person pose estimation task in a global-to-local way. DE consists of Global Embedding (GE) and Local Embedding (LE). GE encodes different person instances and processes information covering the whole image and LE encodes the local limbs information. GE functions for the person detection in top-down strategy while LE connects the rest joints sequentially which functions for joint grouping and information processing in A bottom-up strategy. Based on LE, we design the Mutual Refine Machine (MRM) to reduce the prediction difficulty in complex scenarios. MRM can effectively realize the information communicating between keypoints and further improve the accuracy. We achieve the competitive results on benchmarks MSCOCO, MPII and CrowdPose, demonstrating the effectiveness and generalization ability of our method.

Time-varying (TV) nonlinear systems widely exist in various fields of engineering and science. Effective identification and modeling of TV systems is a challenging problem due to the nonstationarity and nonlinearity of the associated processes. In this paper, a novel parametric modeling algorithm is proposed to deal with this problem based on a TV nonlinear autoregressive with exogenous input (TV-NARX) model. A new class of multiple beta wavelet (MBW) basis functions is introduced to represent the TV coefficients of the TV-NARX model to enable the tracking of both smooth trends and sharp changes of the system behavior. To produce a parsimonious model structure, a locally regularized ultraorthogonal forward regression (LRUOFR) algorithm aided by the adjustable prediction error sum of squares (APRESS) criterion is investigated for sparse model term selection and parameter estimation. Simulation studies and a real application to EEG data show that the proposed MBW-LRUOFR algorithm can effectively capture the global and local features of nonstationary systems and obtain an optimal model, even for signals contaminated with severe colored noise.

A global parameter estimation method for a permanent magnet synchronous machines (PMSM) drive system is proposed, where the electrical parameters, mechanical parameters, and voltage-source-inverter (VSI) nonlinearity are regarded as a whole and parameter estimation is formulated as a single parameter optimization model. A dynamic learning estimator is proposed for tracking the electrical parameters, mechanical parameters, and VSI of PMSM drive by using dynamic self-learning particle swarm optimization (DSLPSO). In DSLPSO, a novel movement modification equation with dynamic exemplar learning strategy is designed to ensure its diversity and achieve a reasonable tradeoff between the exploitation and exploration during the search process. Moreover, a nonlinear multiscale based interactive learning operator is introduced for accelerating the convergence speed of the $Pbest$ particles; meanwhile a dynamic opposition-based learning strategy is designed to facilitate the $gBest$ particle to explore a potentially better region. The proposed algorithm is applied to parameter estimation for a PMSM drive system. The results show that the proposed method has better performance in tracking the variation of electrical parameters, and estimating the immeasurable mechanical parameters and the VSI disturbance voltage simultaneously.

In model identification, the existence of uncertainty normally generates negative impact on the accuracy and performance of the identified models, especially when the size of data used is rather small. With a small data set, least squares estimates are biased, the resulting models may not be reliable for further analysis and future use. This study introduces a novel robust model structure selection method for model identification. The proposed method can successfully reduce the model structure uncertainty and therefore improve the model performances. Case studies on simulation data and real data are presented to illustrate how the proposed metric works for robust model identification.

The Atlantic meridional overturning circulation (AMOC), an important component of the climate system, has only been directly measured since the RAPID array’s installation across the Atlantic at 26°N in 2004. This has shown that the AMOC strength is highly variable on monthly timescales; however, after an abrupt, short-lived, halving of the strength of the AMOC early in 2010, its mean has remained ~ 15% below its pre-2010 level. To attempt to understand the reasons for this variability, we use a control systems identification approach to model the AMOC, with the RAPID data of 2004–2017 providing a trial and test data set. After testing to find the environmental variables, and systems model, that allow us to best match the RAPID observations, we reconstruct AMOC variation back to 1980. Our reconstruction suggests that there is inter-decadal variability in the strength of the AMOC, with periods of both weaker flow than recently, and flow strengths similar to the late 2000s, since 1980. Recent signs of weakening may therefore not reflect the beginning of a sustained decline. It is also shown that there may be predictive power for AMOC variability of around 6 months, as ocean density contrasts between the source and sink regions for the North Atlantic Drift, with lags up to 6 months, are found to be important components of the systems model.

This paper is concerned with the model selection and model averaging\ud problems in system identification and data-driven modelling for nonlinear\ud systems. Given a set of data, the objective of model selection is to evaluate\ud a series of candidate models and determine which one best presents the data.\ud Three commonly used criteria, namely, Akaike information criterion (AIC),\ud Bayesian information criterion (BIC) and an adjustable prediction error sum\ud of squares (APRESS) are investigated and their performance in model\ud selection and model averaging is evaluated via a number of case studies\ud using both simulation and real data. The results show that APRESS\ud produces better models in terms of generalization performance and model\ud complexity.

In this paper, an accurate parameter estimation model of surface permanent magnet synchronous machines (SPMSMs) is established by taking into account voltage-source-inverter (VSI) nonlinearity. A fast dynamic particle swarm optimization (DPSO) algorithm combined with a receptor editing (RE) strategy is proposed to explore the optimal values of parameter estimations. This combination provides an accelerated implementation on graphics processing unit (GPU), and the proposed method is, therefore, referred to as G-DPSO-RE. In G-DPSO-RE, a dynamic labor division strategy is incorporated into the swarms according to the designed evolutionary factor during the evolution process. Two novel modifications of the movement equation are designed to update the velocity of particles. Moreover, a chaotic-logistic-based immune RE operator is developed to facilitate the global best individual ( gBest particle) to explore a potentially better region. Furthermore, a GPU parallel acceleration technique is utilized to speed up parameter estimation procedure. It has been demonstrated that the proposed method is effective for simultaneous estimation of the PMSM parameters and the disturbance voltage ( $V_{\mathrm { {dead}}})$ due to VSI nonlinearity from experimental data for currents and rotor speed measured with inexpensive equipment. The influence of the VSI nonlinearity on the accuracy of parameter estimation is analyzed.

The fruit fly optimization algorithm (FOA) is a global optimization algorithm inspired by the foraging behavior of a fruit fly swarm. In this study, a novel stochastic fractal model based fruit fly optimization algorithm is proposed for multiobjective optimization. A food source generating method based on a stochastic fractal with an adaptive parameter updating strategy is introduced to improve the convergence performance of the fruit fly optimization algorithm. To deal with multiobjective optimization problems, the Pareto domination concept is integrated into the selection process of fruit fly optimization and a novel multiobjective fruit fly optimization algorithm is then developed. Similarly to most of other multiobjective evolutionary algorithms (MOEAs), an external elitist archive is utilized to preserve the nondominated solutions found so far during the evolution, and a normalized nearest neighbor distance based density estimation strategy is adopted to keep the diversity of the external elitist archive. Eighteen benchmarks are used to test the performance of the stochastic fractal based multiobjective fruit fly optimization algorithm (SFMOFOA). Numerical results show that the SFMOFOA is able to well converge to the Pareto fronts of the test benchmarks with good distributions. Compared with four state-of-the-art methods, namely, the non-dominated sorting generic algorithm (NSGA-II), the strength Pareto evolutionary algorithm (SPEA2), multi-objective particle swarm optimization (MOPSO), and multiobjective self-adaptive differential evolution (MOSADE), the proposed SFMOFOA has better or competitive multiobjective optimization performance.

System identification and data-driven modeling techniques have seen ubiquitous applications in the past decades. In particular, parametric modeling methodologies such as linear and nonlinear autoregressive with exogenous input models (ARX and NARX) and other similar and related model types have been preferably applied to handle diverse data-driven modeling problems due to their easy-to-compute linear-in-the-parameter structure, which allows the resultant models to be easily interpreted. In recent years, several variations of the NARX methodology have been proposed that improve the performance of the original algorithm. Nevertheless, in most cases, NARX models are applied to regression problems where all output variables involve continuous or discrete-time sequences sampled from a continuous process, and little attention has been paid to classification problems where the output signal is a binary sequence. Therefore, we developed a novel classification algorithm that combines the NARX methodology with logistic regression and the proposed method is referred to as logistic-NARX model. Such a combination is advantageous since the NARX methodology helps to deal with the multicollinearity problem while the logistic regression produces a model that predicts categorical outcomes. Furthermore, the NARX approach allows for the inclusion of lagged terms and interactions between them in a straight forward manner resulting in interpretable models where users can identify which input variables play an important role individually and/or interactively in the classification process, something that is not achievable using other classification techniques like random forests, support vector machines, and k-nearest neighbors. The efficiency of the proposed method is tested with five case studies.

A dynamic particle swarm optimization with learning strategy (DPSO-LS) is proposed for key parameter estimation for permanent magnet synchronous machines (PMSMs), where the voltage-source inverter (VSI) nonlinearities are taken into account in the parameter estimation model and can be estimated simultaneously with other machine parameters. In the DPSO-LS algorithm, a novel movement modification equation with variable exploration vector is designed to effectively update particles, enabling swarms to cover large areas of search space with large probability and thus the global search ability is enhanced. Moreover, a Gaussian-distribution-based dynamic opposition-based learning strategy is developed to help the pBest jump out local optima. The proposed DPSO-LS can significantly enhance the estimator model accuracy and dynamic performance. Finally, the proposed algorithm is applied to multiple parameter estimation including the VSI nonlinearities of a PMSM. The performance of DPSO-LS is compared with several existing PSO algorithms, and the comparison results show that the proposed parameters estimation method has better performance in tracking the variation of machine parameters effectively and estimating the VSI nonlinearities under different operation conditions.

Influenza and influenza-like illnesses are one of the leading causes of death in the world, resulting in heavy losses to individual families and nations. Accurate and timely forecasts of seasonal influenza would therefore crucially important to inform and facilitate public health decision-making for presenting and intervening influenza epidemics. System identification and data-driven modelling approaches play an indispensable role in analyzing and understanding complex processes including medical, healthcare and environmental time series. This paper aims to present a type of sparse, interpretable and transparent (SIT) model, which cannot only be used for future behavior prediction but more importantly for understanding the dependent relationship between the response variables of a system on potential independent variables (also known as input variables or predictors). An ideal candidate for such a SIT representation is the well-known NARMAX (nonlinear autoregressive moving average with exogenous inputs) model, which can be established based on input and output data of the system of interest, and the final refined model is usually simple, parsimonious and easy to interpret. The general framework of the NARMAX model is presented, and the state-of-the-art algorithms for such a SIT model estimation are described. Two case studies are provided to illustrate how well the SIT-NARMAX model can work for medical, healthcare and related data.

Objective: This study proposes a new parametric TF (time frequency) CGC (conditional Granger causality) method for high precision connectivity analysis over time and frequency in multivariate coupling nonstationary systems, and applies it to scalp and source EEG signals to reveal dynamic interaction patterns in oscillatory neocortical sensorimotor networks. Methods: The Geweke spectral measure is combined with the TVARX (time varying autoregressive with exogenous input) modelling approach, which uses multiwavelets and ultra regularized orthogonal least squares (UROLS) algorithm aided by APRESS (adjustable prediction error sum of squares), to obtain high resolution time varying CGC representations. The UROLS APRESS algorithm, which adopts both the regularization technique and the ultra least squares criterion to measure not only the signal data themselves but also the weak derivatives of them, is a novel powerful method in constructing time varying models with good generalization performance, and can accurately track smooth and fast changing causalities. The generalized measurement based on CGC decomposition is able to eliminate indirect influences in multivariate systems. Results: The proposed method is validated on two simulations and then applied to multichannel motor imagery (MI) EEG signals at scalp and source level, where the predicted distributions are well recovered with high TF precision, and the detected connectivity patterns of MI EEG data are physiologically and anatomically interpretable and yield new insights into the dynamical organization of oscillatory cortical networks. Conclusion: Experimental results confirm the effectiveness of the proposed TF CGC method in tracking rapidly varying causalities of EEG based oscillatory networks. Significance: The novel TF CGC method is expected to provide important information of neural mechanisms of perception and cognition.

Solvent-based post combustion capture (PCC) is a well-developed technology for CO2 capture from power plants and industry. A reliable model that captures the dynamics of the solvent-based capture process is essential to implement suitable control design. Typically, first principle models are used, however they usually require comprehensive knowledge and deep understanding of the process. System identification approach is adopted to obtain a model that accurately describes the dynamics between key variables in the process. The nonlinear auto-regressive with exogenous (NARX) inputs model is employed to represent the relationship between the input variables and output variables as two Multiple-Input Single-Output (MISO) sub-models. The forward regression with orthogonal least squares (FROLS) algorithm is implemented to select an accurate model structure that best describes the dynamics within the process. The prediction performance of the identified NARX models is promising and shows that the models capture the underlying dynamics of the CO2 capture process.

In recent years, regression trackers have drawn increasing attention in the visual-object tracking community due to their favorable performance and easy implementation. The tracker algorithms directly learn mapping from dense samples around the target object to Gaussian-like soft labels. However, in many real applications, when applied to test data, the extreme imbalanced distribution of training samples usually hinders the robustness and accuracy of regression trackers. In this paper, we propose a novel effective distractor-aware loss function to balance this issue by highlighting the significant domain and by severely penalizing the pure background. In addition, we introduce a full differentiable hierarchy-normalized concatenation connection to exploit abstractions across multiple convolutional layers. Extensive experiments were conducted on five challenging benchmark-tracking datasets, that is, OTB-13, OTB-15, TC-128, UAV-123, and VOT17. The experimental results are promising and show that the proposed tracker performs much better than nearly all the compared state-of-the-art approaches.

Data-driven modelling approaches play an indispensable role in analyzing and understanding complex processes. This study proposes a type of sparse, interpretable and transparent (SIT) machine learning model, which can be used to understand the dependent relationship of a response variable on a set of potential explanatory variables. An ideal candidate for such a SIT representation is the well-known NARMAX (nonlinear autoregressive moving average with exogenous inputs) model, which can be established from measured input and output data of the system of interest, and the final refined model is usually simple, parsimonious and easy to interpret. The performance of the proposed SIT models is evaluated through two real healthcare datasets.

This paper addresses nonlinear time series modelling and prediction problem using a type of wavelet neural networks. The basic building block of the neural network models is a ridge type function. The training of such a network is a nonlinear optimization problem. Evolutionary algorithms (EAs), including genetic algorithm (GA) and particle swarm optimization (PSO), together with a new gradient-free algorithm (called coordinate dictionary search optimization – CDSO), are used to train network models. An example for real speed wind data modelling and prediction is provided to show the performance of the proposed networks trained by these three optimization algorithms.

Rotating machinery working under changing operation conditions is prone to failure. In recent years, domain adaptation has been successfully used for fault diagnosis. However, the existing fault diagnosis methods based on domain adaptation have two main disadvantages: 1) with these methods, it is difficult to precisely measure and estimate the differences between the source and target domains and 2) they only consider the discrepancies in the feature space, but not in the label space. In this article, a new optimal transport (OT)-based deep domain adaptation model is proposed for rotating machine fault diagnosis. The framework of the proposed method comprises three main components. First, an autoencoder network is designed to extract compact and class discriminative features from the raw data. Second, the domain-invariant representation features are trained by searching an OT plan with a predefined cost function between source and target domains and by minimizing the discrepancies of a joint distribution of the feature and label spaces based on OT. Finally, the classifier trained with data in the source domain is directly used to perform the classification task in the target domain. In addition, the optimal selection of the model hyper-parameters is verified through empirical analysis, and the transfer ability of the proposed model is visually illustrated in a reduced feature space. The experimental results show that the proposed method outperforms the existing machine learning and domain adaptation fault diagnosis methods, in terms of, e.g., classification accuracy and generalization ability.

Severe geomagnetic disturbances can be hazardous for modern technological systems. The reliable forecast of parameters related to the state of the magnetosphere can facilitate the mitigation of adverse effects of space weather. This study is devoted to the modeling and forecasting of the evolution of the Kp index related to global geomagnetic disturbances. Throughout this work the Nonlinear AutoRegressive with eXogenous inputs (NARX) methodology is applied. Two approaches are presented: i) a recursive sliding window approach, and ii) a direct approach. These two approaches are studied separately and are then compared to evaluate their performances. It is shown that the direct approach outperforms the recursive approach, but both tend to produce predictions slightly biased from the true values for low and high disturbances.

Although visual surveillance has emerged as an effective technolody for public security, privacy has become an issue of great concern in the transmission and distribution of surveillance videos. For example, personal facial images should not be browsed without permission. To cope with this issue, face image scrambling has emerged as a simple solution for privacy- related applications. Consequently, online facial biometric verification needs to be carried out in the scrambled domain thus bringing a new challenge to face classification. In this paper, we investigate face verification issues in the scrambled domain and propose a novel scheme to handle this challenge. In our proposed method, to make feature extraction from scrambled face images robust, a biased random subspace sampling scheme is applied to construct fuzzy decision trees from randomly selected features, and fuzzy forest decision using fuzzy memberships is then obtained from combining all fuzzy tree decisions. In our experiment, we first estimated the optimal parameters for the construction of the random forest, and then applied the optimized model to the benchmark tests using three publically available face datasets. The experimental results validated that our proposed scheme can robustly cope with the challenging tests in the scrambled domain, and achieved an improved accuracy over all tests, making our method a promising candidate for the emerging privacy-related facial biometric applications.

A new ultra-least squares (ULS) criterion is introduced for system identification. Unlike the standard least squares criterion which is based on the Euclidean norm of the residuals, the new ULS criterion is derived from the Sobolev space norm. The new criterion measures not only the discrepancy between the observed signals and the model prediction but also the discrepancy between the associated weak derivatives of the observed and the model signals. The new ULS criterion possesses a clear physical interpretation and is easy to implement. Based on this, a new Ultra-Orthogonal Forward Regression (UOFR) algorithm is introduced for nonlinear system identification, which includes converting a least squares regression problem into the associated ultra-least squares problem and solving the ultra-least squares problem using the orthogonal forward regression method. Numerical simulations show that the new UOFR algorithm can significantly improve the performance of the classic OFR algorithm.

With the increase of multimedia traffic, the implementation of fast and accurate classification has become an important issue. Besides, a manually captured dataset contains certain noise and mislabeled instances, which influences the accuracy of classifier to some extent. Motivated by these observations, a novel feature selection and instance purification (FSI that is because it is an unsupervised method in terms of data purification. 3) through data purification, it is able to obtain a minimal feature subset on condition of maintaining accuracy. In addition, the proposed method can be used to discover a new discriminative feature based on linking behaviors called the flow fragment ( F − F r a g ), which can reflect important information among the complex and multitudinous packet communication behaviors. The experimental results over six different datasets demonstrate the advantages of the proposed technique compared to six existing methods, and the discriminative power of the new flow fragment feature.

The use of the multiscale generalized radial basis function (MSRBF) network for image feature extraction is proposed for the first time. The MSRBF network holds a simple but flexible structure capable to modelling complex systems. However MSRBF is originally designed to identify observational-type input-output systems. We aim to use this efficient network to get to concise but accurate models of digital images thanks to: a) the use of multiple scales in the RBF kernel width, and b) the adoption of the forward regression orthogonal least squares (FROLS) algorithm to refine the model structure selection. Thereafter the new tailored model is excited to produce output signals aimed at be compressed by the discrete cosine transform (DCT), adopted in this work to compact signals' energy into a few coefficients. To recognise images as MSRBF networks, a mathematical modelling was done by considering the first ones as multiple-input single-output systems. Based on the new methodology a novel computer aided diagnosis (CAD) system for cancer detection in X-ray mammograms was designed. Classification results show that the new CAD method helped reach a competitive diagnostic accuracy of 93.5%. It was similarly found that the MSRBF network is able to construct tailored and precise image models.

A normal cloud model based fruit fly optimization algorithm is extended for multi-objective optimization. The normal cloud model is used to produce new food positions for the fruit flies in the osphresis-based search, and a parameter self-adaptive strategy is proposed to adjust the search space dynamically. The concept of Pareto domination is incorporated into the vision-based search and a cloud model based multi-objective fruit fly optimization algorithm (CMMOFOA) is then developed. To have a good diversity of the member in the elitist archive, a normalized nearest neighbor distance based diversity maintenance strategy is adopted. The UF test set in CEC2009 is used to test the performance of CMMOFOA. Numerical simulation results demonstrate that CMMOFOA can converge to the Pareto fronts of the test problems with good accuracy and distribution, and has better or competitive performance compared with six popular state-of-the-art algorithms.

A new transient Granger causality detection method is proposed based on a time-varying\ud parametric modelling framework, and is applied to real EEG signals to reveal the causal information flow\ud during motor imagery (MI) tasks. The time-varying parametric modelling approach employs a nonlinear\ud autoregressive with external input (NARX) model, whose parameters are approximated by a set of multiwavelet\ud basis functions. A regularized orthogonal least squares (ROLS) algorithm is then used to produce\ud a parsimonious or sparse regression model and estimate the associated model parameters. The time-varying\ud Granger causality between nonstationary signals can be detected accurately by making use of both the good\ud approximation properties of multi-wavelets and the good generalization performance of the ROLS in the\ud presence of high-level noise. Two simulation examples are presented to demonstrate the effectiveness of\ud the proposed method for both linear and nonlinear causal detection respectively. The proposed method is\ud then applied to real EEG signals of MI tasks. It follows that transient causal information flow over the\ud time course between various sensorimotor related channels can be successfully revealed during the whole\ud reaction processes. Experiment results from these case studies confirm the applicability of the proposed\ud scheme and show its utility for the understanding of the associated neural mechanism and the potential\ud significance for developing MI tasks based brain-computer interface (BCI) systems.

A new iOFR-MF iterative orthogonal forward regression--modulating function algorithm is proposed to identify continuous-time models from noisy data by combining the MF method and the iOFR algorithm. In the new method, a set of candidate terms, which describe different dynamic relationships among the system states or between the input and output, are first constructed. These terms are then modulated using the MF method to generate the data matrix. The iOFR algorithm is next applied to build the relationships between these modulated terms, which include detecting the model structure and estimating the associated parameters. The relationships between the original variables are finally recovered from the model of the modulated terms. Both nonlinear state-space models and a class of higher order nonlinear input–output models are considered. The new direct method is compared with the traditional finite difference method and results show that the new method performs much better than the finite difference method. The new method works well even when the measurements are severely corrupted by noise. The selection of appropriate MFs is also discussed.

The identification of nonlinear time-varying systems using linear-in-the-parameter models is investigated. An efficient common model structure selection CMSS algorithm is proposed to select a common model structure, with application to EEG data modelling. The time-varying parameters for the identified common-structured model are then estimated using a sliding-window recursive least squares SWRLS approach. The new method can effectively detect and adaptively track and rapidly capture the transient variation of nonstationary signals, and can also produce robust models with better generalisation properties. Two examples are presented to demonstrate the effectiveness and applicability of the new approach including an application to EEG data.

Models of transcriptional regulatory networks (TRN) have benefited a wide range of biological and biomedical research. Several system theoretical modelling approaches are available in literature including those that divide TRNs into subnet-works for computational advantages, estimate and recombine them. However, the problem of updating an existing model has not gained much attention. Such a situation is not rare in biological research where new protein-gene interactions are discovered on a regular basis. In such cases, existing models must be discarded and new system-wide models must be estimated. This may result in estimates that are inconsistent with previously validated models. This can be avoided by appending a previously validated model with a new subnetwork. In this paper, an optimisation based approach is developed to address this challenge. With the help of an experimental data set obtained from literature, it is shown that a convex combination of subnetworks can model system-wide data with signal reconstruction error comparable to that obtained with a modelling technique available in literature.

Demographic indicators linked to general health have been strongly linked to economic development. However, change in such indicators is also associated with other factors such as climate, water availability, and diet. Here, we use a systems modelling approach, bringing together a range of environmental, economic, dietary, and health factors, to seek possible dominant causes of demographic change across Africa. A continent-wide, north-south transect of countries allows for the exploration of a range of climates, while a longitudinal transect from the Atlantic to the Red Sea provides a range of socio-economic factors within the similar climatic regime of Sahelian Africa. While change in national life expectancy and death rate since 1960 is modelled to be linked to a varying number and type of factors across the transects, the dominant factor in improving these demographic indicators across the continent is food availability. This has been strongly modulated by HIV infection rates in recent decades in some countries.

Digital image processing is shifting the information analysis paradigms in a variety of systems whereas that it is becoming highly viable. Medicine has made the most of image processing by enhancing decision-making through computer-aided diagnosis (CAD) systems. CAD image models support medical inferences by extracting key visual features and classifying regions of interest. Linear parametric system identification models, typically used for time series forecasting such as the auto regressive moving average (ARMA) model have been adopted as CAD image procedures with encouraging results. But this perspective can be enhanced by incorporating flexible-order system identification models capable to detect corrupting features that might be shortly described by linear models. In this way, the polynomial nonlinear autoregressive with exogenous inputs (NARX) model is presented along with the forward regression orthogonal least squares (FROLS) algorithm and the k-means clustering method. For the first time the polynomial NARX is presented as a system identification method for digital images and as a CAD procedure for breast cancer detection in images. Experiments with a public database of mammograms show that the method actually detected nonlinearities within images and attained competitive performance measures compared to previous similar methods.

In this paper, a new similar stock prices patterns extraction method is proposed for short-term stock trend forecasting. Different from Euclidean distance and conventional dynamic time warping (DTW) based historical features extraction, the new feature extraction method is developed based on a modified DTW approach, which allows the length of historical sub-sequences to be in a suitable range and integrates the actual distance with the drift between aligned points. To demonstrate the performance of this proposed method, 20 stock prices containing the price information in the last 10 years are collected from Shanghai Stock Exchange and used to predict the stock price change trends. The experimental results show that prediction accuracy of the trends, on the randomly selected testing sequences of stock prices, can reach to 79%, which is promising.

Model selection is a crucial step in choosing a best model from a series of candidate models for data based modelling problems. The commonly used Akaike information criterion (AIC) and Bayesian information criteria (BIC) may not be effective for many real-world modelling problems when the true system model structure is unknown and therefore not included in the candidate model set. This study investigates the model selection issue using AIC, BIC and an adjustable prediction error sum of squares (APRESS) for nonlinear dynamic predictive modelling. Results from simulation and real data modelling case studies show that both BIC and APRESS produce good models for nonlinear modelling problems. The APRESS works slightly better than BIC in achieving a parsimonious representation of the studied system. In addition, a model averaging method is introduced, which is capable to provide an averaged model that is more robust in generalization (i.e. in representing future data) than any single model.

A new parametric approach is proposed for nonlinear and non-stationary system identification based on a time-varying nonlinear autoregressive with exogenous input (TV-NARX) model. The time-varying coefficients of the TV-NARX model are expanded using multi- wavelet basis functions and the model is thus transformed into a time-invariant regression problem.\ud An ultra-orthogonal forward regression (UOFR) algorithm aided by mutual information (MI) is designed to identify a parsimonious model structure and estimate the associated model parameters. The UOFR-MI algorithm which uses not only the observed data themselves but also weak derivatives of the signals is more powerful in model structure detection. The proposed approach combining the advantages of both the basis function expansion method and the UOFR-MI algorithm is proved to be capable of tracking the change of time-varying parameters effectively in both numerical simulations and the real EEG data.

The severity of global magnetic disturbances in Near-Earth space can crucially affect human life. These geomagnetic disturbances are often indicated by a Kp index, which is derived from magnetic field data from ground stations, and is known to be correlated with solar wind observations. Forecasting of Kp index is important for understanding the dynamic relationship between the magnetosphere and solar wind. This study presents 3 hours ahead prediction for Kp index using the NARMAX model identified by a novel robust model structure detection method. The identified models are evaluated using 4 years of Kp data. Overall, the models with robust structure can produce very good Kp forecast results and provide transparent and compact representations of the relationship between Kp index and solar wind variables. The robustness and conciseness of the models can highly benefit the space weather forecast tasks.

In this paper, a new global time series averaging method is proposed for improving k-means clustering performance for observed signals or time series data. The proposed method is different from most commonly used time series averaging methods, such as pairwise averaging method (PA), nonlinear alignment and averaging filter (NLAAF), prioritized shape averaging (PSA) and dynamic time warping (DTW) barycentre averaging (DBA). The implementation mechanism of the new method is as follows: i) Choose an initial cluster centre sequence based on the within-cluster distance; ii) Compute the weight values and extract the optimal matching path according to the dynamic time warping distance between the centre sequence and all the rest sequences, and iii) Calculate the average sequence using the rest sequences, the optimal matching paths and the weight values. To demonstrate the performance of the proposed method, the aforementioned four existing averaging methods, along with the proposed method, are applied to a benchmark time series dataset containing 600 sequences. The experimental results show that the proposed method outperforms all the four compared methods, in terms of the sum of within-cluster distance and adjusted Rand index.

The problem of parameter estimation of permanent-magnet synchronous machines (PMSMs) can be formulated as a nonlinear optimization problem. To obtain accurate machine parameters, it is necessary to develop easily applicable but efficient optimization algorithms to solve the parameter estimation models. This paper proposes a novel dynamic differential evolution with adaptive mutation operator (AMDDE) algorithm for the multiparameter simultaneous estimation of a nonsalient pole PMSM. The dynamic updating of population enables AMDDE to responds to any improved changes of the population immediately and thus generates better optimization solutions compared with the static mechanism used in original differential evolution. Two mutation strategies, namely DE/rand/1 and DE/best/1, are adaptively employed to balance the global exploration and local exploitation. The effectiveness of the proposed AMDDE is demonstrated on the multiparameter estimation for a nonsalient pole PMSM. Experimental results indicate that the proposed method significantly outperforms the existing peer algorithms in efficiency, accuracy, and robustness. Furthermore, the new algorithm can be potentially realized in digital microcontroller due to its simple structure and lower memory requirement. The proposed algorithm can also be applied to other parameter estimation and optimization problems.

A new maximum relevanceminimum multicollinearity (MRmMC) method is proposed.The proposed MRmRC algorithm was applied to a number of real-life datasets; experimental results are reported and compared with several state-of-the-art methods.Numerical analysis results confirmed the promising performance of the proposed method. A substantial amount of datasets stored for various applications are often high dimensional with redundant and irrelevant features. Processing and analysing data under such circumstances is time consuming and makes it difficult to obtain efficient predictive models. There is a strong need to carry out analyses for high dimensional data in some lower dimensions, and one approach to achieve this is through feature selection. This paper presents a new relevancy-redundancy approach, called the maximum relevanceminimum multicollinearity (MRmMC) method, for feature selection and ranking, which can overcome some shortcomings of existing criteria. In the proposed method, relevant features are measured by correlation characteristics based on conditional variance while redundancy elimination is achieved according to multiple correlation assessment using an orthogonal projection scheme. A series of experiments were conducted on eight datasets from the UCI Machine Learning Repository and results show that the proposed method performed reasonably well for feature subset selection.

Handwritten signature verification is a classical technology. Which uses features extracted from signatures. The purpose of signature verification is to identify whether a testing signature image is the same as a template. In this study, a new off-line signature verification method based on symbolic representation and dynamic time warping is proposed. In the proposed symbolic representation, the distances between symbols are defined according to the average value of each segment rather than the distance calculated based on Gaussian distribution, which is used in traditional symbolic representations. The proposed dynamic time warping (DTW) method is used to detect the optimal path and an optimal verification result can then be obtained by comparing the fitting errors of all matching paths. To demonstrate the performance the proposed approach, the following experiment is carried out: firstly, a signature image was created by a person and this is used as the template. Secondly, a total of 100 signature images written by the same person were collected, and the false rejected rate (FRR) and false acceptance rate (FAR) are calculated using the proposed method. Thirdly, a total of 100 signature images written by 100 different people were collected, based on which the false acceptance rate is calculated. The experimental results show that the performance of the proposed method is very promising, and the FRR and FAR values for the two group tests are 3% and 2% respectively.

This study presents a new method for walking gesture representation and recognition based on a symbolic representation. The symbolic representation is used to represent images which can be decomposed into a number of time series and the distance between time series can be characterized based on the distances between symbols. In this work, the distances between symbols are defined according to the average value of each segment rather than the distance calculated based on Gaussian distribution as used in traditional symbolic representations. The proposed method is applied to a short template video containing a number of walking steps (gestures). In the case studies we consider a database containing 104 test videos, taken from 101 people, and our objective is to identify whether a person in the testing video is the same person as in the template video (i.e. the training video), and the identification accuracy of the method is around 98%.

This study aims to analyse the relationship between lifestyle and life satisfaction in the UK using a class of transparent and nonlinear parametric models, based on which the dependency of the response variable (happiness or life satisfaction) on a set of independent (or explanatory) variables relating to life styles can easily be interpreted. A forward regression orthogonal least square (FROLS) algorithm, initially developed in control and systems engineering area, is employed to build the transparent models. Based on over 10000 surveyed samples with 42 variables from UK Understanding Society Data, a number of significant variables of lifestyle have been selected first according to the rank of their contribution to explaining life satisfaction. As an example, a reduced simple nonlinear model with only 12 model terms is presented. This model is meaningful in that it provides a parsimonious representation of the relationship between happiness and lifestyle, reveals how life satisfaction quantitatively depends on lifestyle, and how the lifestyle variables interactively affect life satisfaction.

Given an observed data set, there are different methods that can be used to impute missing data. While excellent work has been done in this field, most available approaches are focused on some particular applications, such as static data and univariate time series. The primary aim of the two papers Part I VAR-IM algorithm v.s. traditional methods and Part II VAR-IM algorithm v.s. modern algorithms — is to introduce an algorithm for handling missing data in multivariate time series based on vector autoregressive (VAR) model by combining an expectation and minimization (EM) algorithm with the prediction error minimization (PEM) method. In the first part, we conduct two cases studies (one for simulation data and another for real ECG data) to compare the proposed algorithm with three traditional methods for imputing missing data: Mean substitution, list-wise deletion and linear regression substitution. In the second part, the proposed method is compared with more powerful modern techniques: MARRS Package, nearest neighbour, and the full information maximum likelihood (FIML) method. Furthermore, we demonstrate the use of the proposed method together with an empirical example of multivariate time series to ECG data and discuss its advantages and limitations.