Search

The development of machines explores the development of a manufacturing system. This perspective offers challenges adjacent to the materials, the product that wants to be manufactured, the technical considerations that must be covered during implementation and the manner of delivering the products to the user. This article addresses the design and development of machines, on the one hand the redesign of a multifunctional platform, and on the other hand a 3D food printer. The second is emphasised, since its main objective is to help the food problems that exist today. The design phases, aspects considered for its implementation such as food safety, the choice of the substrate, the functionality of the food, transportation and the pre- and post-processes required. In this manner, the selection and innovation of materials constitutes a primary source of innovation and research in the integral development of a 3D food printer. The main source of value of these both cases lie in customisation. The experiences of a multidisciplinary research team in the development processes are compiled and the design and creation process are shown, in order to contribute to deal with design and development to tackle fundamental problems of society. [ABSTRACT FROM AUTHOR]

This study presents the development of an event-driven hybrid control for position and force tracking applied on a mobile robotic manipulator for metal recycling tasks. The suggested controller operates in a sequenced strategy starting from a fixed spot, moving the mobile device towards a targeted zone ($\Omega _i^r$ Ω i r ) from where the i-th piece-to-be-recycled is attainable (considering the arm manipulation). Once the event of entering the zone is completed, the mobile robot is fixed at a position, and the end-effector of the robotic arm is enforced towards the piece-to-be-recycled. When the end-effector touches the piece in a given spot ($\Omega _i^e$ Ω i e ), the hybrid control changes to the force tracking intending to carry the piece towards the spot ($\Omega _i^p$ Ω i p ) where it ill be processed. Each piece location is identified based on a vision-based system that applies deep learning tools using convolutional neural networks. A multi-physics numerical simulation illustrated the application of the developed controller in a realistic scenario, showing all the elements of the event-driven operation. To validate the suggested controller, the comparison with a robust control that works on a wide range of carrying mass confirms the operational improvement of the event-driven hybrid position and force design. [ABSTRACT FROM AUTHOR]

Vehicle safety relies on the capacity of vehicle systems to decrease the likelihood of biomechanical injuries to both vehicle occupants and pedestrians. This can take the form of active or passive measures applied to the materials and their geometry in the event of an impact. Nevertheless, due to the nonlinear behaviour of materials and deformation, a distinct collapse process emerges that requires analysis; this analysis can be virtual or through experimental tests. While observed performance can be ascertained through experimental designs, executing such a design for every parameter combination can be time-consuming and costly. This study employs a Long Short-Term Memory (LSTM) to predict the energy absorbed and crushing force of thin-walled aluminium 6063 T5 tubes subject to different collapse triggers and heat treatments. The LSTM model is constructed using experimental data derived from experiments that consider trigger shape, area, trigger position, furnace duration, cooling temperature, and heat treatment soaking method. The LSTM model achieved a Root Mean Square Error (RSME) of 0.56 and 0.0025 for crushing force and energy absorption, respectively. LSTM proves to be a valuable tool for predicting results in nonlinear analysis, particularly in the context of crush behaviour. Also, a comparison of the LSTM and finite element analysis (FEA) predictive performance is presented. [ABSTRACT FROM AUTHOR]

Summary: In non‐cooperative multi‐player games, an average sub‐gradient (ASG) strategy for finding an ϵ$$ \epsilon $$‐Nash equilibrium. For convex (but not necessarily strictly convex) individual cost functions, the function convergence of the multi‐player game is demonstrated. Applying Tanaka's formula that characterizes the Nash equilibrium leads to finding the strategy for each player. A min‐max formulation defines the corresponding solution for each player. The main result is proving the reachability of the desired regime, obtaining an explicit upper bound for Tanaka's function decrement. Detailed analyses for two‐player and multi‐player games are developed. For a class of two‐player games with a convex performance function, a set of numerical studies shows the applicability of the proposed method. So, the tracking of the arm in 3‐links robot is considered as an illustrative example. [ABSTRACT FROM AUTHOR]

This study investigates the effectiveness of blast furnace slags (BFSs) as catalysts in the ozonation process to degrade complex contaminants such as bezafibrate (BFZ) at different pH levels. The findings reveal that the presence of BFS enhances degradation efficiency, achieving a 10% improvement at pH 10 and a 30% improvement at pH 5.5 compared to simple ozonation. The highest degradation efficiency was observed in the Ozonation–BFS system at pH 10, with 90% decomposition of BFZ. These results were corroborated through ozone consumption analysis, BOD5 measurements, and the identification of oxalic acid as the final decomposition product. Due to the complexity of the reaction system, kinetic characterization was performed using non-parametric modeling based on differential neural networks. The model indicated that the observed reaction rate for BFZ degradation in the presence of ozone and BFS was 4.12 times higher at pH 5.0 and 1.08 times higher at pH 10.0 compared to simple ozonation. These results underscore the potential of using BFS in catalytic ozonation processes for the effective treatment of recalcitrant contaminants in wastewater. [ABSTRACT FROM AUTHOR]

The molecular explanation about why some pancreatic cancer (PaCa) patients die early and others die later is poorly understood. This study aimed to discover potential novel markers and drug targets that could be useful to stratify and extend expected survival in prospective early-death patients. We deployed a deep learning algorithm and analyzed the gene copy number, gene expression, and protein expression data of death versus alive PaCa patients from the GDC cohort. The genes with higher relative amplification (copy number > 4 times in the dead compared with the alive group) were EWSR1, FLT3, GPC3, HIF1A, HLF, and MEN1. The most highly up-regulated genes (>8.5-fold change) in the death group were RPL30, RPL37, RPS28P7, RPS11, Metazoa_SRP, CAPNS1, FN1, H3−3B, LCN2, and OAZ1. None of their corresponding proteins were up or down-regulated in the death group. The mRNA of the RPS28P7 pseudogene could act as ceRNA sponging the miRNA that was originally directed to the parental gene RPS28. We propose RPS28P7 mRNA as the most druggable target that can be modulated with small molecules or the RNA technology approach. These markers could be added as criteria to patient stratification in future PaCa drug trials, but further validation in the target populations is encouraged. [ABSTRACT FROM AUTHOR]

Functional electrical stimulation (FES) has been proven to be a reliable rehabilitation technique that increases muscle strength, reduces spasms, and enhances neuroplasticity in the long term. However, the available electrical stimulation systems on the market produce stimulation signals with no personalized voltage–current amplitudes, which could lead to muscle fatigue or incomplete enforced therapeutic motion. This work proposes an FES system aided by machine learning strategies that could adjust the stimulating signal based on electromyography (EMG) information. The regulation of the stimulated signal according to the patient's therapeutic requirements is proposed. The EMG signals were classified using Long Short-Term Memory (LSTM) and a least-squares boosting ensemble model with an accuracy of 91.87% and 84.7%, respectively, when a set of 1200 signals from six different patients were used. The classification outcomes were used as input to a second regression machine learning algorithm that produced the adjusted electrostimulation signal required by the user according to their own electrophysiological conditions. The output of the second network served as input to a digitally processed electrostimulator that generated the necessary signal to be injected into the extremity to be treated. The results were evaluated in both simulated and robotized human hand scenarios. These evaluations demonstrated a two percent error when replicating the required movement enforced by the collected EMG information. [ABSTRACT FROM AUTHOR]

This paper uses a multi-head neural transformer to present the text-to-text translation/interpretation of Sign Language (SL) in the context of glosses (written SL). A Spanish to Mexican Sign Language (MSL) gloss dataset was built based on simple and compound sentences and the corresponding interpretation in MSL gloss. The interpretation process was achieved by implementing state-of-the-art tools in the natural language processing (NLP) field called neural transformers. We tried different architectures, varying the number of encoder-decoder layers and hyperparameters. The best of our models achieved 0.68 BLEU in the training phase and 0.33 in the validation phase. MSL glosses are crucial as they rule the grammatical order in which MSL has to be executed. All these quantitative and qualitative results confirm the potential applicability of neural transformers to create effective automatic translators for the Spanish language to MSL, with similar effectiveness shown by other automatic translators for other more likely languages. [ABSTRACT FROM AUTHOR]

This research is dedicated to developing a min–max robust control strategy for a dynamic game involving pursuers, evaders, and defenders in a multiple-missile scenario. The approach employs neural dynamic programming, utilizing multiple continuous differential neural networks (DNNs). The competitive controller devised addresses the robust optimization of a joint cost function that relies on the trajectories of the pursuer–evader–defender system, accommodating an uncertain mathematical model while adhering to control restrictions. The dynamic programming min–max formulation facilitates robust control by accounting for bounded modeling uncertainties and external disturbances for each game component. The value function of the Hamilton–Jacobi–Bellman (HJB) equation is approximated by a DNN, enabling the estimation of the closed-loop formulation for the joint dynamic game with state restrictions. The controller’s design is grounded in estimating the state trajectory under the worst possible uncertainties and perturbations, providing a robustness factor through the robust neural controller. The learning law class for the time-varying weights in the DNN is generated by studying the HJB partial differential equation for the missile motion for each player in the dynamic game. The controller incorporates the solution of the obtained learning laws and a time-varying Riccati equation, offering an online solution to the control implementation. A recurrent algorithm, based on the Kiefer–Wolfowitz method, adjusts the initial conditions for the weights to satisfy the final condition of the given cost function for the dynamic game. A numerical example is presented to validate the proposed robust control methodology, confirming the optimization solution based on the DNN approximation for Bellman’s value function. [ABSTRACT FROM AUTHOR]

Differential neural networks (DiNNs) encounter a trade-off between the approximation quality and structural complexity. One promising approach to address this trade-off is incorporating dynamic complexity adjustment as an integral part of the learning process. Taking inspiration from the Fourier approximation theory, this study introduces a novel method for adapting the architecture of DiNNs, when they serve as nonparametric identifiers for dynamic systems with uncertain mathematical models. The structural adaptation process is executed through a recursive algorithm based on a modification structure strategy, which dynamically adjusts the number of neurons within the network's structure. By applying a projection operator to the set of neurons, this method identifies the most relevant sequence of sigmoidal functions, intending to minimize the mean square error in approximating the trajectories of uncertain systems. This simultaneous reduction in overall complexity enhances the quality of the approximations. Moreover, the proposed method can implement a coarse-to-fine approach, wherein selecting necessary neurons occurs in multiple steps. These steps are determined by an adaptive structure strategy that alters the topology of the DiNN. The resulting framework's effectiveness is demonstrated by evaluating the proposed identifier's performance in approximating the evolution of real-life data associated with the ocular response during controlled motions or virtual reality engagement. In both experimental cases, there was a noticeable improvement in the accuracy of eye motion approximation by the DiNN, thanks to the variable structure approximation basis determined by the adaptive structure strategy. Overall, this study presents a formal method to automatically determine a feasible DiNN topology.