One of the main challenges when working with time series captured online using sensors is the appearance of noise or null values, generally caused by sensor failures or temporary disconnections. These errors compromise data reliability and can lead to incorrect decisions. Particularly in the treatment of diabetes mellitus, where medical decisions depend on continuous glucose monitoring (CGM) systems provided by modern sensors, the presence of corrupted data can pose a significant risk to patient health. This work presents an approach that encompasses online detection and imputation of anomalous data using physiological inputs (insulin and carbohydrate intake), which enables decision-making in automatic glucose monitoring systems or for glucose control purposes. Four deep neural network architectures are proposed: CNN-LSTM, GRU, 1D-CNN, and Transformer-LSTM, under a controlled fault injection protocol and compared with the ARIMA model and the Temporal Convolutional Network (TCN). The obtained performance is compared using regression (MAE, RMSE, MARD) and classification (accuracy, precision, recall, F1-score, AUC) metrics. Results show that the CNN-LSTM network is the most effective for fault detection, achieving an F1-score of 0.876 and an accuracy of 0.979. Regarding data imputation, the 1D-CNN network obtained the best performance, with an MAE of 2.96 mg/dL and an RMSE of 3.75 mg/dL. Then, validation on the OhioT1DM dataset, containing real CGM data with natural sensor disconnections, showed that the CNN–LSTM model accurately detected anomalies and reliably imputed missing glucose segments under real-world conditions.

Financial stability in interconnected markets is increasingly challenged by nonlinear interactions that amplify local disturbances into systemic crises. This study models a financial system as a complex network of coupled chaotic nodes, where each node represents a nonlinear macroeconomic subsystem governed by endogenous feedback dynamics. In contrast to traditional centralized interventions, a pinning control strategy is proposed to stabilize a network through selective control of a small subset of influential nodes. Numerical simulations show how local crises propagate through coupling links, generating systemic instability, and how the proposed impulsive control scheme effectively suppresses chaos and restores synchronization across an entire network. Results highlight the efficiency of localized interventions for achieving global stability, offering new theoretical insights into mechanisms of financial correlation and design of control-based resilience strategies for complex economic systems.

This paper introduces the design and development of an adaptive hand prosthesis that incorporates flexible materials and advanced sensors to improve user functionality and comfort. This prosthesis is designed for individuals with partial hand amputations, enabling better control and ergonomic integration with the natural hand anatomy. The methodology used for the design, simulation, and validation of the prototype is presented, as well as preliminary tests carried out in controlled environments.

People with speech disabilities face significant communication challenges, especially those with motor impairments that prevent them from using sign language. To address this issue, eye movement-based communication systems like Blink to Speak (BTS) have been developed, allowing users to convey messages through eight eye movement alphabets. This study evaluates the clas- sification of BTS alphabets using electrooculography (EOG) signals, comparing two approaches: within-subject (WS) and between-subject (BS). A dataset of EOG signals from 38 subjects was used to train and test a Random Forest model, selected for its superior performance in BS classification. Results show that WS classification generally outperforms BS, with F1-score improvements in 33 out of 38 subjects and across all alphabets. Alphabets with lower inter-subject similarity, such as “Wink”, “Roll” and “Left” achieved the most significant improvements in WS, while those with high similarity, like «Down» and «Blink,» showed less enhancement. Despite the superior performance of the WS approach, it requires an extensive data collection and calibration process, which may hinder practical implementation. Future work should consider balancing quick adaptability (favoring BS classification) and model accuracy (favoring WS classifica- tion), depending on user needs and application context.

Continuous arterial blood pressure (ABP) prediction is relevant to cardiovascular monitoring and development of adaptive patient-specific digital twins. This study presents an adaptive data-driven ABP prediction framework inspired by cardiovascular digital-twin principles for causal one-step-ahead prediction using a single physiological signal modality. The proposed methodology combines a seven-sample causal ABP representation, a compact 7–5–1 multilayer perceptron, recursive Extended Kalman Filter (EKF) adaptation of all neural-network weights and biases, and offline evolutionary optimization of EKF covariance hyperparameters. Model development and evaluation used invasive ABP recordings from five CHARIS subjects available in PhysioNet, with five non-overlapping 100 s windows per subject. A rotating 3/1/1 subject-wise protocol assigned three subjects to supervised MLP training, one independent subject to covariance-hyperparameter selection, and one completely unseen subject to final testing in each fold. A fixed MLP achieved a mean test RMSE of 3.4123 mmHg. Recursive EKF adaptation using identical manually selected covariance hyperparameters across folds reduced mean RMSE to 3.0033 mmHg, corresponding to an average improvement of 11.98%. Offline optimization of $P_0$, $Q_0$, and $R_0$ further reduced mean RMSE to 2.1546 mmHg with Differential Evolution, 2.1548 mmHg with Particle Swarm Optimization, and 2.1546 mmHg with Genetic Algorithm, representing an overall improvement of approximately 35.9% relative to the fixed-MLP baseline. Despite differences in selected covariance values, all three evolutionary methods produced nearly identical final predictive performance. These results show that recursive neural-parameter adaptation and systematic covariance tuning provide complementary improvements in causal ABP prediction while preserving strict subject-level separation among training, hyperparameter selection, and final evaluation.

Impresión 3D con Software Libre es una guía práctica y completa para quienes desean adentrarse en el mundo de la fabricación aditiva. A lo largo de sus páginas, aprenderás desde los conceptos básicos de la impresión 3D, el modelado en software libre como Blender, hasta los diferentes tipos de impresoras y materiales que puedes utilizar en tus proyectos. Escrito por un equipo de expertos en tecnología y educación este libro no solo te enseñará las técnicas fundamentales, sino que también te ayudará a entender el impacto de la impresión 3D en diversas industrias, desde la ingeniería hasta la medicina. Este manual es ideal tanto para estudiantes, profesionales y entusiastas, que buscan aprovechar el poder del software libre en la creación de prototipos, productos personalizados y soluciones innovadoras.