Search

• The paper presents four recurrent and differential artificial neural networks (ANN) structures to construct different versions of dynamic automatic pattern classifiers. • Two different annotated and validated databases of diverse physiological signals were used to evaluate the capacities of all the ANNs proposed in this study. • Two validation methods were used to justify the application of dynamic ANNs as pattern classifiers: generalization-regularization and k-fold cross validation. • The recurrent neural network was also implemented in a 32-bits microcontroller embedded device. In the last few years, recurrent and continuous algorithms have became key factors in the solution of diverse pattern recognition problems. The main goal of this study is to introduce four classes of recurrent and continuous artificial neural networks (ANN) that can be implemented for pattern recognition of electrophysiological signals. Such networks are generally known as dynamic neural networks (DNN). The proposed DNN based pattern recognizer uses biosignals raw data as input. This processing method allows capturing the signal time dynamics, which is considered as an intrinsic characteristic of physiology signals. Therefore, recurrent and differential ANN structures were developed to construct different versions of dynamic automatic pattern recognizer. The first one describes the application of Recurrent Neural Networks (RNN) to enforce the biosignal analysis which evolves over time with a fixed sampling period. Three different DNNs with continuous dynamics are introduced. Differential neural network (DifNN) with the capability of learning the evolution of the signal in continuous time, a time-delay neural network (TDNN) for classification is implemented to consider the time-delayed characteristics of the electrophysiological signals and a complex valued neural network (CVNN) which considered the signals to be classified may be pre-processed with a frequency analysis technique. Two different databases of diverse physiological signals are used in this study to validate the application of dynamic neural networks. A first database considers electromiographic (EMG) signals which are tested using the DifNN, TDNN and CVNN. The second database includes gait in Parkinson's disease database signals which are used in the evaluation procedure of RNN. Two validation methods are used to justify the application of dynamic ANNs as pattern recognizer for the EMG activities and the health level classification of patients suffering from Parkinson's: generalization-regularization and the k -fold cross validation. The accuracy estimation and the confusion matrix evaluation confirm the superiority of the proposed approach compared to classical feed-forward ANN pattern recognizer. The particular case of the RNN is also implemented in a 32-bits micro-controller embedded device. [ABSTRACT FROM AUTHOR]

This study introduces the development of a novel extremum-seeking controller designed to stabilize the tracking trajectory of a fully actuated four-wheeled skid steering vehicle. The controller design employs a class of averaged sub-gradient optimization strategies for a suitable convex function that depends on the enforced tracking trajectory achieved through an integral sliding mode implementation. The application of this controller necessitates a nonlinear coordinate transformation of the skid steering vehicle dynamics, resulting in a perturbed multi-input–multi-output linear system. Using the proposed controller, a multidimensional sliding surface remains remarkably stable despite tracking errors. The surface design defines a manifold that aligns with the sub-gradient of a convex function, contingent upon the integral of the tracking error. This connection establishes a link between the extremum-seeking problem and the sliding mode control design. Employing the cascade design strategy, commonly referred to as backstepping, enables the calculation of torques for the four wheels of the mobile vehicle using a sequence of auxiliary sliding surfaces, each with its corresponding complementary function for every stage. The dynamic formulation for the wheel torques is derived from the integral sliding mode methodology. A series of numerical evaluations are conducted to assess the controller's effectiveness in terms of functional performance. A comparison between the control action based on sliding mode and the traditional state feedback formulation validates the efficacy of the proposed design. This comparison demonstrates advancements in robustness in the face of modeling uncertainties and optimization of the performance function, which are theoretically supported by the suggested control design. Implementing the proposed controller in an experimental platform for a wheeled skid steering vehicle reaffirms the control design methodology presented in this study. This platform includes the application of an image processing algorithm to determine the non-inertial position of the autonomous vehicle using integral sliding mode control. This information completes the necessary data for implementing the on-site version of the proposed controller. • Differential control of a four-wheeled terrestrial vehicle using Average Subgradient Integral Sliding Mode. • A cascade control design formulation proves the ultimate boundedness of the tracking trajectory. • Design of sliding surfaces introduces a sliding control to solve the optimization of the convex function. • Simulations of the terrestrial vehicle confirms the applicability of the average subgradient implementation. • Implementation of the ASG control in a four-wheel vehicle demonstrates the feasibility of the controller [ABSTRACT FROM AUTHOR]

This study aimed to develop a semi non-parametric model of the die casting process of aluminum alloys. This model uses a hierarchical artificial neural network (HANN), with a structure motivated by the relationships of the metals which define the characteristics of the aluminum alloy. These settings depend on the content of seven metals (Sn, Zn, Mn, Cu, Si, Ni, and Mg). The relation between these metals and the alloy characteristics oriented the HANN structure. A distributed back-propagation learning modified with the Levenberg-Marquardt method served to adjust the HANN weights. Two complementary validation methods justified the application of this novel hybrid non-parametric modelling structure. The training set came from standards composition proposed by different international organizations. A set of real aluminum alloys and the experimental results describing their characteristics formed the validation test. An average accuracy value of 3.65% confirmed the ability of the HANN to reproduce the relation between the metal content and the alloy characteristics. These values confirmed how the oriented HANN may predict the aluminum alloy characteristics as function of the metal distribution. This result offers a different alternative to the prediction of aluminum alloy properties using the metal composition as input information. [ABSTRACT FROM AUTHOR]

Edible fungus Lentinula edodes (L. edodes) produces exo-polysaccharides (EPS), which have been obtained from submerged mycelia cultures. EPS are bioactive products which can be obtained more efficiently from submerged cultures compared to regular production methods from endo-polyssacharides from the fruiting bodies of fungus cultured on solid medium. A common manner to characterize the production ability of L. edodes is using the kinetic parameters evaluation of a suitable mathematical model which takes into account the effects of diverse experimental conditions. The aim of this study is characterize the production of exo-polysaccharide extracts from submerged cultures of three strains of L. edodes (commercial. LS and L9) using the estimated parameters of the proposed model. The submerged mycelia cultures have fixed initial pH of 6.5, 4.5 and 3.5. Submerged cultures at an initial pH of 4.5 had maximum amounts of biomass of 10.0-15.4gL-1. The exo-polysaccharide extracts concentrations are in the range of 0.44-0.97 gL-1 The strain L9 obtained a higher yield biomass-substrate (Yx/s = 1.62). At pH 4.5, the commercial strain obtained a higher yield of product-substrate (YP/s = 0.147). If the initial pH is 3.5, the lowest Yx/s is obtained in values ranging from 0.85 to 1.21. The maximum growth rate was higher for strain L9 at pH 4.5 with ηmax values. The obtained exo-polysaccharide extracts from the three strains have the maximum total carbohydrate amounts of 0.5-0.93 gL-1. A soluble proteins percentage range of 0.16-0.39% is obtained. From the hydrolyzed exo-polysaccharide extracts, glucose, mannose, galactose and arabinose can be identified as the main monosaccharides. O--H bonds, ether bonds, C--N bonds and carboxyl bonds are the identified functional groups of the exo-polysaccharides. [ABSTRACT FROM AUTHOR]

This article shows the design of a robust second-order sliding mode controller to solve the trajectory tracking problem of an active orthosis for assisting back physiotherapies. The orthosis was designed in agreement with morphological dimensions and its articulations distribution followed the same designing rules. The orthosis has six articulated arms attached to an articulated column. The orthosis was fully instrumented with actuators and position sensors at each articulation. The controller implemented a class of hybrid/position controller depending on the relative force exerted by the patient and the orthosis movement. The position information provided by each articulation was supplied to a distributed super-twisting differentiator to recover the corresponding angular velocity. A set of twisting controllers was implemented to regulate the position of the robot in agreement to predefined reference trajectories. Reference trajectories were obtained from a biomechanical-based analysis. The hybrid tracking control problem solved the automation of the assisted therapy to the patient, including the force feedback. The performance of the orthosis was tested with different dummy bodies with different resistance. The robust output feedback controller successfully tracked the reference trajectories despite the material of the dummy used during the testing. The orthosis was evaluated with two volunteers using a simple reference trajectory. Graphical Abstract General structure of the active back assisted orthosis. [ABSTRACT FROM AUTHOR]