The analysis of gait is a field of study whose popularity has grown due to its broad range of applications. Consequently, the development of tools for capturing gait has also seen a significant increase. This article presents the development of a system for gait analysis named STEPIO, which consists of four portable wireless modules, each equipped with a board comprised of a microcontroller and an inertial sensor. The system includes an intuitive graphical user interface that allows the acquisition, visualization, processing, and storage of the signals. The system offers a low-cost solution and the possibility of conducting studies in different environments and implementing innovative tools like the Internet of Things. To evaluate the performance of the system, 15 subjects without any diagnosed neuromusculoskeletal pathologies participated in the experimental protocol in which the range of motion of the knee and hip articulations was measured and compared with a reference optical system, resulting in a root mean square error of 2.7 degrees and a mean deviation of 2.44 degrees.

This work describes the development and control of a robotic lower limb exoskeleton (LLE) for the mobilization of pediatric users. The structural design of the LLE considers the anthropometric dimensions aside from the range of motion required to execute a normal gait cycle of pediatric users. The proposed system considers six degrees of freedom, three for each leg, corresponding to the flexion/extension of the hip, flexion/extension of the knee, and dorsiflexion/plantar flexion on the ankle. The system’s manufacturing materials include aluminum profiles, aside from 3D printing segments of polylactic acid. Regarding the electronic instrumentation of the LLE, a set of six brushless motors was considered to provide movement of each joint. All the actuators are controlled by a Texas Instrument LAUNCHXL-F28379D microcontroller in which a first-order sliding mode control is embedded to regulate the trajectory tracking of the LLE. The results showed that the LLE can perform trajectory tracking considering an RMSE less than 0.0863 rad.

This paper describes the development of a portable system to measure surface electromyo-graphical (EMG) signals based on the Internet of Things. The system comprises eight modules designed to allow the wireless transmission of the surface EMG signals through a self-designed board to a graphical user interface (GUI). The GUI has three main stages: the configuration that enables the online adjustment of acquisition parameters; the acquisition stage for the visualization and storage of the data, as well as the upload or download to the cloud, contemplating encryption for data security, and finally, a rehabilitation video game that can be programmed according to the users’ needs. The system was tested on ten healthy participants, five men and five women, using a protocol for measuring signals during gait. The system showed a maximum data loss of $2.21 \%$ in a public network and $0.48 \%$ in a private network, a maximum stable frequency of 4700 Hz, and an autonomy of 128 minutes. Finally, it was compared with one commercial device and one clinical system.

This article focuses on designing a neural identifier for non-linear systems using an Integral Sliding Mode (ISM) approach. A Differential Neural Network (DNN) structure identifies a non-linear system; meanwhile, the learning laws for stabilizing the identification error are obtained from the Lyapunov Stability analysis. An integral sliding surface is proposed to provide the convergence of the system identifier weights to the ideals to approximate the non-linear system. The results for identifying the Van Der Poll Oscillator and the Inverted Pendulum show better identification error reduction performance than a traditional DNN.

This work presents the development of the ArMexo, an upper limb assistive rehabilitation system with four degrees of freedom (DoF) to assist the user in wrist radial/ulnar deviation, flexion/extension, pronation/supination, and elbow flexion/extension movements. The ArMexo is a self-designed exoskeleton manufactured mainly using a tridimensional printing system with polylactic acid (PLA) as the primary manufacturing material. As part of the actuation system, the proposed device considers four brushless motors model AK60 of CubeMars coupled to a microcontroller Launchpad F28379xD of Texas Instruments™, where a first-order sliding mode (FOSM) serves as the control algorithm to regulate the trajectory tracking of each DoF of the ArMexo. A proportional-derivative (PD) controller was also implemented as part of the obtained results to prove the proposed FOSM’s superior performance. Then, the experimental results show that the proposed controller guaranteed the trajectory tracking of reference trajectories with an error norm of less than six degrees.

This work describes the acquisition of kinematic and surface electromyography (sEMG) data from young and older adults during the execution of wrist movements using an upper limb rehabilitation robot (ULRR), along with a wristband equipped with inertial measurement units (IMUs) and sEMG sensors. These devices enable the observation of electrical muscle activation in the forearm during movement execution, providing valuable insights into the neuromuscular dynamics involved in motor control and movement mechanics. The description covers the robot configuration, sensor array, graphical user interfaces (GUIs) for visualizing robot data and biosignals, the experimental protocol, the database structure, and the signal processing and evaluation procedures. For the experimental protocol, 20 participants, 10 young and 10 older adults, were recruited. The test consisted of four basic wrist movements: radial deviation, ulnar deviation, flexion, and extension, which were performed in random order under the guidance of the ULRR GUI. The sEMG analysis indicated that older adults tend to overuse specific muscles and exhibit a higher percentage of compensatory movements $(38.5 \%)$ than younger participants $(24.25 \%)$. The study’s findings enable the identification of age-related differences in muscle activation and compensation, aiding the design of personalized rehabilitation programs and improved devices to enhance motor function in older adults.

This manuscript analyses the performance of different machine learning models classifying hand gestures from electromyography (EMG) signals. The EMG information is obtained from the WyoFlex armband, a wearable bracelet with four sensors that capture the EMG of the forearm. This study considers four different models, the K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Long Short-Term Memories (LSTM) for classifying four and six hand gestures. The methodology comprises different scenarios, including the application of the Synthetic Minority Over-Sampling (SMOTE) algorithm to increase the cardinality of the dataset and the Minimum-Redundancy-Maximum-Relevance (MRMR) technique to reduce computational costs. These models are compared considering the classification of four and six different hand gestures in three different scenarios: a) including the SMOTE technique, b) including the MRMR procedure without SMOTE, and c) including both MRMR and SMOTE. The results show an overall accuracy between 79.32% to 94.90% on the four gestures classification and from 75.14% to 92.80% for six gestures classification, with the SVM classifier producing the best performance in training time and accuracy. The application of the MRMR algorithm yields a reduction of the training time in all models applying the K-fold and Leave-One-Subject-Out (LOSO) cross validation methods, the accuracy is not strongly affected reducing the number of features in almost all the models.

This work presents the development of a joystick with two degrees of freedom. The joystick is designed considering a cable-capstan mechanism allowing the movement of the central axis for Pitch and Roll angles, where the central axis has a workspace in a plane (XY). The joystick design and instrumentation consider future haptic tasks and applications in practical engineering education courses. This device was designed based on fast prototype manufacturing, including 3D printed parts. The design is small and portable, and the development of the joystick includes a user interface to display and save data and graphs of different signals such as angular positions, central axis position, control signals, current of the motors, and errors, and allows tuning different parameters for the control implementation. In order to show the functionality of the designed mechanism, we show its performance in tracking trajectory tasks implementing a proportional, integral, derivative controller (PIDC) with a Super Twisting algorithm (STA). The results showed the joystick with the complete instrumentation and communication with the user interface in a personal computer. We compared the PIDC using an Euler's derivative vs. the PIDC with the STA's derivative estimated. The results of the trajectory tracking control with the PIDC-STA algorithm showed a better performance of the joystick with an average error norm of 2.73 degrees, taking the Pitch and Roll errors, compared with the PIDC- Euler controller with an average error norm of 3.22 degrees.

This work presents the design of a control trajec-tory algorithm based on Barrier Lyapunov functions (BLF) for a class of third-order electro-mechanical systems. The method considers unknown control gains and uncertain plant parame-ters, a common problem in control engineering applications. In order to deal with the uncertain parameters, this study proposes a backstepping adaptive strategy applying Nussbaum functions to know the sign of the control gains. The BLF imposes partial constraints to keep the trajectories of the system inside a safe operation set. The proposed controller is tested in a virtual one-link robotic manipulator including actuator dynamics to develop an adequate trajectory tracking. The maximum tracking error norm was 0.02, which fulfilled the maximum constrained bound of 0.5.

This work deals with the design of a millimetric electrospinning device (MED) controlled with the implemen-tation of a sliding mode controller taking into account states constraints or constraint sliding mode controller (CSM C). The proposed MED is integrated by two cartesian robots with two (injector system) and three (collector system) degrees of freedom, respectively. These two cartesian robots work in a coordinated manner to regulate the deposition processes for the generation of polymeric micro and nanofibers. This strategy addresses one of the most common problems of classic MEDs, guaranteeing that the fibers are deposited in a specific zone (aiming to create 3D polymeric structures). The suggested CSM C successfully restricts the motions of the MED to a predefined working space that led to the production of aligned polymer fibers, ensuring the convergence of the tracking error to the sliding surface in finite-time, while the state constraints are satisfied. Experimental results validate the effectiveness of the proposed CSMC by using the least mean square evaluation of the tracking error and the integral of the control signal. The evaluation is also done following a comparative analysis concerning the performance forced with respect to a state feedback form. The evaluation confirmed the effectiveness of the CDMC strategy compared to the state feedback form.

This manuscript proposes the design of a speech synthesis algorithm based on measured electroencephalographic (EEG) signals previously classified by a class of neural network with continuous dynamics. A novel multilayer differential neural network (MDNN) classifies a database with the EEG studies of 20 volunteers. The database contains information described by input-output pairs corresponding to EEG signals and a corresponding word imagined by the volunteer. The suggested MDNN estimates the unknown relationship between the information instances and suggests the most-likely word that the user wants mentioning. The proposed MDNN satisfactory classifies over 95% a set of words obtained from the suggested EEG study in which, the users have to watch four different geometric figures on a screen.

This manuscript presents the design of a deep differential neural network (DDNN) for pattern classification. First, we proposed a DDNN topology with three layers, whose learning laws are derived from a Lyapunov analysis, justifying local asymptotic convergence of the classification error and the weights of the DDNN. Then, an extension to include an arbitrary number of hidden layers in the DDNN is analyzed. The learning laws for this general form of the DDNN offer a contribution to the deep learning framework for signal classification with biological nature and dynamic structures. The DDNN is used to classify electroencephalographic signals from volunteers that perform an identification graphical test. The classification results show exponential growth in the signal classification accuracy from 82 percent with one layer to 100 percent with three hidden layers. Working with DDNN instead of static deep neural networks (SDNN) represents a set of advantages, such as processing time and training period reduction up to almost 100 times, and the increment of the classification accuracy while working with less hidden layers than working with SDNN, which are highly dependent on their topology and the number of neurons in each layer. The DDNN employed fewer neurons due to the induced feedback characteristic.

This manuscript presents an algorithm to classify continuously electroencephalographic (EEG) signals based on deep differential neural networks (DDNNs). The learning laws are obtained by the second stability method of Lyapunov that requires the solution of a set of matrix differential equations. The robustness of this technique allows the analysis and classification of bio-signals like EEG signals. The EEG signals have complex dynamics and they are strongly affected by noises in the measurements and a high degree of variability between different studies in patients. The main strength of DDNNs is their feedback property, which allows them to work with the time-dependent variation of the EEG signals. The DDNNs are tested in a database constituted of EEG signals acquired from a study made in ten volunteers. The study consisted of the acquisition of EEG measurements of the volunteers recognizing geometrical figures appearing in a graphic user interface. The DDNN obtained better performance than a single layer differential neural network and a convolutional neural network.

This manuscript deals with the problem of controlling a virtualized humanoid robot with 16 degrees of freedom (DOF). The aim of this study was to design an output feedback discontinuous controller which must resolve the sequence of articulation movements to walk over disjoint stepping objects placed in front of the humanoid robot. The suggested controller considers the state restrictions, via a nonstandard strong Lyapunov function, corresponding to the angular displacements and velocities at each articulation. This study implements an extended state terminal second order sliding mode controller with time dependent gains, to ensure the finite-time tracking trajectory of each articulation of the humanoid robot. The terminal sliding mode (TSM) is implemented in a virtual platform developed in a computer-aided design software. For comparison purposes, the controller was compared with a state feedback and a first order sliding mode algorithms.

This manuscript deals with the problem of controlling a virtualized humanoid robot with 16 degrees of freedom (DOF), each corresponding to the articulation in a real human being. That is, three DOF for each leg in the sagittal plane and one for the abduction movement; three DOF for each arm in the sagittal plane and one for the waist. The tracking trajectory problem of any humanoid robot like the classical biped robots requires a control algorithm with robustness against parametric uncertainties, fast response and even with finite-time convergence. These main characteristics are easily covered by sliding mode controllers. This manuscript implements a terminal second order sliding mode (TSOSM) controller to ensure the finite-time tracking trajectory of each articulation of the humanoid robot to the ones that define a classical walking pattern obtained by bio-mechanical studies. The TSOSM is implemented in a virtual platform developed in a computer-aided design software.