Evaluation of transformation invariant loss function with distance equilibrium in prediction of imaging photoplethysmography characteristics.

Objective. Monitoring changes in human heart rate variability (HRV) holds significant importance for protecting life and health. Studies have shown that Imaging Photoplethysmography (IPPG) based on ordinary color cameras can detect the color change of the skin pixel caused by cardiopulmonary system. Most researchers employed deep learning IPPG algorithms to extract the blood volume pulse (BVP) signal, analyzing it predominantly through the heart rate (HR). However, this approach often overlooks the inherent intricate time-frequency domain characteristics in the BVP signal, which cannot be comprehensively deduced solely from HR. The analysis of HRV metrics through the BVP signal is imperative. APPROACH: In this paper, the transformation invariant loss function with distance equilibrium (TIDLE) loss function is applied to IPPG for the first time, and the details of BVP signal can be recovered better. In detail, TIDLE is tested in four commonly used IPPG deep learning models, which are DeepPhys, EfficientPhys, Physnet and TS_CAN, and compared with other three loss functions, which are mean absolute error (MAE), mean square error (MSE), Neg Pearson Coefficient correlation (NPCC). MAIN RESULTS: The experiments demonstrate that MAE and MSE exhibit suboptimal performance in predicting LF/HF across the four models, achieving the Statistic of Mean Absolute Error (MAES) of 25.94% and 34.05%, respectively. In contrast, NPCC and TIDLE yielded more favorable results at 13.51% and 11.35%, respectively. Taking into consideration the morphological characteristics of the BVP signal, on the two optimal models for predicting HRV metrics, namely DeepPhys and TS_CAN, the Pearson coefficients for the BVP signals predicted by TIDLE in comparison to the gold-standard BVP signals achieved values of 0.627 and 0.605, respectively. In contrast, the results based on NPCC were notably lower, at only 0.545 and 0.533, respectively. SIGNIFICANCE: This paper contributes significantly to the effective restoration of the morphology and frequency domain characteristics of the BVP signal.

Neuroadaptive Control for Active Suspension Systems With Time-Varying Motion Constraints: A Feasibility-Condition-Free Method.

This work is devoted to solving the control problem of vehicle active suspension systems (ASSs) subject to time-varying dynamic constraints. An adaptive control scheme based on nonlinear state-dependent function (NSDF) is proposed to stabilize the vertical displacement of the vehicle body. It provides a reliable guarantee of driving safety, ride comfort, and operational stability. It is commonly known that in the existing work, either the state constraints are ignored which may reduce the stability and safety of the system, or the virtual controller is subjected to some feasibility conditions affecting real system implementation. In this work, it is the first attempt to directly deal with the time-varying displacement and velocity of the vehicle constraints in ASSs without involving any specific feasibility conditions. A novel coordinate transformation based on the NSDF is introduced and integrated into each step of the backstepping design. Thus, the proposed control scheme not only adapts to the time-varying motion (time-varying vertical displacement and velocity) constraints, but also eliminates the feasibility conditions of the virtual controller without the difficulty of obtaining system parameters. Finally, the control scheme for ASSs used in this work is compared with existing control schemes in order to demonstrate its superiority and rationality.

Energy-Saving Robust Saturated Control for Active Suspension Systems via Employing Beneficial Nonlinearity and Disturbance.

This article proposes a novel control framework for active suspension systems by purposely employing beneficial nonlinearity and a useful disturbance effect for control performance enhancement. To this aim, a novel amplitude-limited PD-SMC control scheme is established to ensure a stable performance-oriented tracking control of the overall closed-loop system. Importantly, different from most existing control methods, the designed tracking controller purposely employs beneficial nonlinear stiffness and damping of a novel bioinspired reference model and deliberately utilizes useful disturbance response on the active suspension system, so as to improve the convergence speed and reduce control energy cost simultaneously. The asymptotic stability is theoretically proved by a rigorous Lyapunov-based analysis. To the best of our knowledge, this is a unique control scheme for active suspension systems which can technically take several critical control practice issues into account with guaranteed excellent performance simultaneously, including energy savings, actuator saturation, unexpected disturbances, etc. The superior performance is well validated with a series of experiments, and carefully compared to several existing control methods. The results of this study would definitely present a unique insight and an alternative approach to active controller designs via exploiting beneficial nonlinear and disturbance effects for better control performance and lower energy cost simultaneously.

Online Kernel Learning With Adaptive Bandwidth by Optimal Control Approach.

Online learning methods are designed to establish timely predictive models for machine learning problems. The methods for online learning of nonlinear systems are usually developed in the reproducing kernel Hilbert space (RKHS) associated with Gaussian kernel in which the kernel bandwidth is manually selected and remains steady during the entire modeling process in most cases. This setting may make the learning model rigid and inappropriate for complex data streams. Since the bandwidth appears in a nonlinear term of the kernel model, it raises substantial challenges in the development of learning methods with an adaptive bandwidth. In this article, we propose a novel approach to address this important open issue. By a carefully casted linearization scheme, the nonlinear learning problem is reasonably transformed into a state feedback control problem for a series of controllable systems. Then, by employing optimal control techniques, an effective algorithm is developed, and the parameters in the learning model including kernel bandwidth can be efficiently updated in a real-time manner. By taking advantage of the particular structure of the Gaussian kernel model, a theoretical analysis on the convergence and rationality of the proposed method is also provided. Compared with the kernel algorithms with a fixed bandwidth, our novel learning framework can not only achieve adaptive learning results with a better prediction accuracy but also show performance that is more robust with a faster convergence speed. Encouraging numerical results are provided to demonstrate the advantages of our new method.

A Bioinspired Dynamics-Based Adaptive Fuzzy SMC Method for Half-Car Active Suspension Systems With Input Dead Zones and Saturations.

Active suspension systems are widely used in vehicles to improve ride comfort and handling performance. However, existing control strategies may be limited by various factors, including insufficient consideration of different operation conditions, such as changing in vehicle mass, defects in strategy design leading to incapability for guaranteeing finite-time stability, lack of considering input effects of dead zone and saturation, excessive energy cost, etc. Importantly, very few results considered the energy-saving performance of active suspension systems although a well-perceived issue in practice. An adaptive fuzzy SMC method based on a bioinspired reference model is established in this article, which is to purposely address these problems and be able to provide finite-time convergence and energy-saving performance simultaneously. The proposed control method effectively utilizes beneficial nonlinear stiffness and nonlinear damping properties that the bioinspired reference model could provide. Therefore, superior vibration suppression performance with less energy consumption and improved ride comfort can all be obtained readily. By using a fuzzy-logic system (FLS), the proposed method is beneficial in compensating for system parameter uncertainties, external disturbances, input dead zones, and saturations. Furthermore, based on the adaptive PD-SMC method, the tracking errors can converge to zeros in finite time. The stability of the equilibrium point of all the states in active suspension systems is theoretically proven by Lyapunov techniques. Finally, simulation results are provided to verify the correctness and effectiveness of the proposed control scheme.

Online Identification of Nonlinear Stochastic Spatiotemporal System With Multiplicative Noise by Robust Optimal Control-Based Kernel Learning Method.

In this paper, we propose a novel kernel method for the online identification of stochastic nonlinear spatiotemporal dynamical systems using the robust control approach. By the difference method, the stochastic spatiotemporal (SST) systems driven by multiplicative noise are first transformed into a class of multi-input-multi-output-partially linear kernel models (PLKMs) with heterogeneous random terms. With the help of techniques established for reproducing kernel Hilbert space, the online learning problem is reasonably considered as an output feedback control problem for a group of time varying linear dynamical systems. We develop an effective algorithm to address the learning problem of PLKM and SST systems by employing the model predictive control theory. Compared with the existing learning methods, the new one can achieve adaptive, robust, and fast convergent online modeling performance for the spatiotemporal dynamics with multiplicative noise, which greatly facilitates the characterization of physical characteristics of the system. Moreover, this investigation for the first time addresses the learning problems for SST systems with novel robust control techniques, which can provide some novel insights into the design of kernel machine learning methods from the perspective of optimal control theory. Numerical studies for benchmark systems are presented to illustrate the effectiveness and efficiency of our new method.

A tracked robot with novel bio-inspired passive "legs".

For track-based robots, an important aspect is the suppression design, which determines the trafficability and comfort of the whole system. The trafficability limits the robot's working capability, and the riding comfort limits the robot's working effectiveness, especially with some sensitive instruments mounted on or operated. To these aims, a track-based robot equipped with a novel passive bio-inspired suspension is designed and studied systematically in this paper. Animal or insects have very special leg or limb structures which are good for motion control and adaptable to different environments. Inspired by this, a new track-based robot is designed with novel "legs" for connecting the loading wheels to the robot body. Each leg is designed with passive structures and can achieve very high loading capacity but low dynamic stiffness such that the robot can move on rough ground similar to a multi-leg animal or insect. Therefore, the trafficability and riding comfort can be significantly improved without losing loading capacity. The new track-based robot can be well applied to various engineering tasks for providing a stable moving platform of high mobility, better trafficability and excellent loading capacity.

Identification of Nonlinear Spatiotemporal Dynamical Systems With Nonuniform Observations Using Reproducing-Kernel-Based Integral Least Square Regulation.

The identification of nonlinear spatiotemporal dynamical systems given by partial differential equations has attracted a lot of attention in the past decades. Several methods, such as searching principle-based algorithms, partially linear kernel methods, and coupled lattice methods, have been developed to address the identification problems. However, most existing methods have some restrictions on sampling processes in that the sampling intervals should usually be very small and uniformly distributed in spatiotemporal domains. These are actually not applicable for some practical applications. In this paper, to tackle this issue, a novel kernel-based learning algorithm named integral least square regularization regression (ILSRR) is proposed, which can be used to effectively achieve accurate derivative estimation for nonlinear functions in the time domain. With this technique, a discretization method named inverse meshless collocation is then developed to realize the dimensional reduction of the system to be identified. Thereafter, with this novel inverse meshless collocation model, the ILSRR, and a multiple-kernel-based learning algorithm, a multistep identification method is systematically proposed to address the identification problem of spatiotemporal systems with pointwise nonuniform observations. Numerical studies for benchmark systems with necessary discussions are presented to illustrate the effectiveness and the advantages of the proposed method.

Vibration isolation by exploring bio-inspired structural nonlinearity.

Inspired by the limb structures of animals/insects in motion vibration control, a bio-inspired limb-like structure (LLS) is systematically studied for understanding and exploring its advantageous nonlinear function in passive vibration isolation. The bio-inspired system consists of asymmetric articulations (of different rod lengths) with inside vertical and horizontal springs (as animal muscle) of different linear stiffness. Mathematical modeling and analysis of the proposed LLS reveal that, (a) the system has very beneficial nonlinear stiffness which can provide flexible quasi-zero, zero and/or negative stiffness, and these nonlinear stiffness properties are adjustable or designable with structure parameters; (b) the asymmetric rod-length ratio and spring-stiffness ratio present very beneficial factors for tuning system equivalent stiffness; (c) the system loading capacity is also adjustable with the structure parameters which presents another flexible benefit in application. Experiments and comparisons with existing quasi-zero-stiffness isolators validate the advantageous features above, and some discussions are also given about how to select structural parameters for practical applications. The results would provide an innovative bio-inspired solution to passive vibration control in various engineering practice.

Fuzzy sampled-data control for uncertain vehicle suspension systems.

This paper investigates the problem of sampled-data H∞ control of uncertain active suspension systems via fuzzy control approach. Our work focuses on designing state-feedback and output-feedback sampled-data controllers to guarantee the resulting closed-loop dynamical systems to be asymptotically stable and satisfy H∞ disturbance attenuation level and suspension performance constraints. Using Takagi-Sugeno (T-S) fuzzy model control method, T-S fuzzy models are established for uncertain vehicle active suspension systems considering the desired suspension performances. Based on Lyapunov stability theory, the existence conditions of state-feedback and output-feedback sampled-data controllers are obtained by solving an optimization problem. Simulation results for active vehicle suspension systems with uncertainty are provided to demonstrate the effectiveness of the proposed method.

Robust adaptive learning of feedforward neural networks via LMI optimizations.

Feedforward neural networks (FNNs) have been extensively applied to various areas such as control, system identification, function approximation, pattern recognition etc. A novel robust control approach to the learning problems of FNNs is further investigated in this study in order to develop efficient learning algorithms which can be implemented with optimal parameter settings and considering noise effect in the data. To this aim, the learning problem of a FNN is cast into a robust output feedback control problem of a discrete time-varying linear dynamic system. New robust learning algorithms with adaptive learning rate are therefore developed, using linear matrix inequality (LMI) techniques to find the appropriate learning rates and to guarantee the fast and robust convergence. Theoretical analysis and examples are given to illustrate the theoretical results.

Understanding neuronal systems in movement control using Wiener/Volterra kernels: a dominant feature analysis.

Although Volterra kernels have been extensively applied in modelling and analysis of biological systems, the relationship between the kernel characteristics and physiologically important features under study is still not revealed clearly. In this study, the link between Volterra kernels and dynamic response of neural systems which control animal movements was investigated and demonstrated using a dominant feature analysis. The new results show an effective but simplified method to use Volterra or Wiener kernels to understand and classify the neural systems which are responsible for the fundamental movements such as flexion and extension of animal limbs, and importantly demonstrate how the neuron pathways in locusts control joint activities of low and high frequency and perform fundamental joint movements such as position, velocity and acceleration. These results provide a useful insight into the nonlinear characteristics of neural systems in movement control and show a useful approach to the analysis of physiological systems using Volterra/Wiener kernels.

Online identification of nonlinear spatiotemporal systems using kernel learning approach.

The identification of nonlinear spatiotemporal systems is of significance to engineering practice, since it can always provide useful insight into the underlying nonlinear mechanism and physical characteristics under study. In this paper, nonlinear spatiotemporal system models are transformed into a class of multi-input-multi-output (MIMO) partially linear systems (PLSs), and an effective online identification algorithm is therefore proposed by using a pruning error minimization principle and least square support vector machines. It is shown that many benchmark physical and engineering systems can be transformed into MIMO-PLSs which keep some important physical spatiotemporal relationships and are very helpful in the identification and analysis of the underlying system. Compared with several existing methods, the advantages of the proposed method are that it can make full use of some prior structural information about system physical models, can realize online estimation of the system dynamics, and achieve accurate characterization of some important nonlinear physical characteristics of the system. This would provide an important basis for state estimation, control, optimal analysis, and design of nonlinear distributed parameter systems. The proposed algorithm can also be applied to identification problems of stochastic spatiotemporal dynamical systems. Numeral examples and comparisons are given to demonstrate our results.

An H(∞) control approach to robust learning of feedforward neural networks.

A novel H(∞) robust control approach is proposed in this study to deal with the learning problems of feedforward neural networks (FNNs). The analysis and design of a desired weight update law for the FNN is transformed into a robust controller design problem for a discrete dynamic system in terms of the estimation error. The drawbacks of some existing learning algorithms can therefore be revealed, especially for the case that the output data is fast changing with respect to the input or the output data is corrupted by noise. Based on this approach, the optimal learning parameters can be found by utilizing the linear matrix inequality (LMI) optimization techniques to achieve a predefined H(∞) "noise" attenuation level. Several existing BP-type algorithms are shown to be special cases of the new H(∞)-learning algorithm. Theoretical analysis and several examples are provided to show the advantages of the new method.