The classification of surface myoelectric signals (sEMG) remains a great challenge when focused on its implementation in an electromechanical hand prosthesis, due to its nonlinear and stochastic nature, as well as the great difference between models applied offline and online. In this work, the selection of the set of the features that allowed us to obtain the best results for the classification of this type of signals is presented. In order to compare the results obtained, the Nina PRO DB2 and DB3 databases were used, which contain information on 50 different movements of 40 healthy subjects and 11 amputated subjects, respectively. The sEMG of each subject was acquired through 12 channels in a bipolar configuration. To carry out the classification, a convolutional neural network (CNN) was used and a comparison of four sets of features extracted in the time domain was made, three of which have shown good performance in previous works and one more that was used for the first time to train this type of network. Set one is composed of six features in the time domain (TD1), Set two has 10 features also in the time domain (TD2) including the autoregression model (AR), the third set has two features in the time domain derived from spectral moments (TD-PSD1), and finally, a set of five features also has information on the power spectrum of the signal obtained in the time domain (TD-PSD2). The selected features in each set were organized in four different ways for the formation of the training images. The results obtained show that the set of features TD-PSD2 obtained the best performance for all cases. With the set of features and the formation of images proposed, an increase in the accuracies of the models of 8.16% and 8.56% was obtained for the DB2 and DB3 databases, respectively, compared to the current state of the art that has used these databases.

A fiber optic curvature sensor based on a tapered single-mode optical fiber coated with a polyester polymer (T-SMF-CPP) is proposed and experimentally demonstrated. Fabrication of the tapered optical fibers was realized by heating and stretching by a flame, and an airbrush was used to coat the surface of the tapered fiber with the polymer. The operating principle of the sensor was based on the interaction of the evanescent wave with the polyester polymer deposited on the tapered fiber. By adopting intensity demodulation in experiments, average sensitivities of -5.017 dB/m-1 and 5.862 dB/m-1 in the curvature ranges from 1.23 to 4.44 m-1 and from 4.64 to 7.54 m-1, respectively, were obtained for a fixed wavelength of $\lambda =1572.45$ nm. The curvature of the sensor did not show a temperature dependence in the range [24-90 °C].

The implementation of embedded systems for myoelectric signal classification is key to the development of prosthetic and other real-time assistive technologies. This work presents a hand gesture classification system based on an artificial neural network (ANN) deployed on an ESP32 microcontroller. In contrast to approaches that require multiple acquisition channels or complex configurations, the proposed system uses a single surface electromyography (sEMG) channel, reducing cost and complexity. Data were collected from eight participants performing eight hand and wrist gestures. The system achieved classification accuracies of up to 93.05% for six gestures, including rest. Furthermore, the ESP32 implementation demonstrated inference times compatible with real-time operation, achieving an average inference time of 0.17 ms. When using a majority voting strategy, classification accuracy increased to 99%, confirming the feasibility of implementing efficient and accurate gesture recognition on low-cost embedded hardware. These results support its integration into portable and autonomous systems for prosthetic control and other interactive applications.

Sargassum has become an “ecological disaster” on most beaches in the Caribbean Sea, causing serious health, safety, economic and environmental problems. The objective of this study was to valorize sargassum for the extraction of sodium alginate, cellulose and cellulose nanocrystals. Cellulose was also used in the manufacture of a separator for an energy storage device (ESD) based on expanded graphite and activated carbon. Sargassum was characterized physicochemically; the results of this characterization are very relevant for the generation of bioenergy and removal of toxic contaminants. The extracted materials were identified by FT-IR; the spectra were very similar to the IR spectra of commercial samples, which corroborated that the materials extracted were sodium alginate, cellulose and cellulose nanocrystals. The performance of the ESD/cellulose-based separator was determined using cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS). Additionally, an RC circuit and an oscilloscope were used to perform a charge/discharge test. The voltammograms obtained for the ESD showed a rectangular shape with redox peaks characteristic of a pseudocapacitor and a battery, and the Nyquist plot showed a typical electrochemical performance of such ESD. Likewise, the developed devices have the capacity to store and release energy in seconds.

El descubrimiento y uso de nuevos métodos y técnicas matemática-computacionales permite que los humanos puedan desarrollar herramientas prácticas para facilitar las tareas cotidianas día con día, naturalmente se busca que las áreas de interés más importantes como la salud se beneficien de estas aplicaciones con premura, pero al mismo tiempo con un nivel de precisión adecuado al realizar dichas tareas. El objetivo de este estudio es crear un programa de cómputo que sea capaz de interpretar y sugerir un posible diagnóstico de lesiones pigmentada en la piel a través del análisis de una imagen con un modelo de redes neuronales convolucionales entrenado con la base de datos “HAM10000”. Además, en este trabajo se propone un nuevo filtro de vellos para las imágenes con el fin de evaluar su repercusión en el rendimiento de la clasificación, el filtro se basa en el uso de cambio de canal, transformaciones morfológicas y reconstrucción de la imagen a través del relleno de pixeles faltantes y finalmente surge el diseño de un programa con interfaz de usuario para que los dermatólogos puedan utilizar la herramienta con imágenes dermatoscópicas. El modelo propuesto en este artículo tiene un porcentaje de precisión al momento de ser evaluado del 88.21%.