The Internet of Things (IoT) paradigm allows the connection and exchange of information between millions of smart devices. This paradigm grows and develops exponentially as do the risks and attacks on IoT infrastructures. Security, privacy, reliability, and autonomy are the most important requirements in IoT Systems. If these issues are not guaranteed, the IoT system could be susceptible to malicious users and malicious use. In centralized IoT systems, attacks and risks are greater, especially when data is transmitted between devices and shared with other organizations. To avoid these types of situations, this work presents a decentralized system that guarantees the autonomy and security of an IoT system. The proposed methodology helps to protect data integrity and availability based on the security advantages provided by blockchain and the use of cryptographic tools. The accuracy of the proposed methodology was measured on a temperature and humidity sensing IoT-based Wireless Sensor Network (WSN). The obtained results prove that the proposal fulfils the main requirements of an IoT system. It is autonomous, secure to share and send information between devices and users, has privacy, it is reliable, and the information is available in the infrastructure. Furthermore, this research demonstrates that the proposal is less susceptible to the most frequent attacks against IoT systems, such as linking attack, man in the middle, and Distributed Denial of Service (DDoS) attack.

Voltage unbalance and mechanical overload generate negative effects on induction motors, producing thermal damages in the stator insulation and a reduction of the motor lifetime. The development of protection devices is crucial as they can help to maintain the integrity of the motor and avoid irreversible damages such as insulation system breakdown, short-circuits, and so on. In this work, a methodology to obtain a time-protection model for induction motors from voltage unbalance is presented. The methodology is based on the thermal impact on the motor produced by mechanical overload and voltage unbalance conditions. In general, it consists of the following steps: i) induce in the motor different overloads and voltage unbalance levels and monitor their thermal profiles at the stator winding, ii) obtain the time-overload curve of the motor, iii) determine both the thermal level according to both the time-overload curve and the overload thermal profile, and iv) estimate the parameters of the time-unbalance model using both the thermal level obtained and the unbalance thermal profiles. The model is validated through its implementation in an online protection scheme, the results show a similar behavior between overload and unbalance protections in the safe thermal level defined by the protection models

Overheating is a negative effect that induction motors suffer under either mechanical or electrical anomalous conditions, which can decrement the motors' useful life or produce catastrophic damage. In this sense, a new approach for assisting in the analysis and solution of problems related to overheating in induction motors is the correlation of thermal effects between the abovementioned conditions. In this study, a methodology for the experimental extraction of mathematical models that correlate the thermal effect on the induction motor stator due to voltage unbalance and mechanical overload is developed. In general, the proposed methodology is based on thermal gradients at different points of an induction motor stator. These thermal gradients are generated from either voltage unbalance or mechanical overload. For voltage unbalance estimation, the definitions of IEEE standard 141, IEEE standard 1159, and NEMA norm are considered. The correlation models are carried out and validated experimentally on a three-phase induction motor of 746 W (1 hp). Results demonstrate effectiveness in the correlation at different stator points of both variables: unbalance voltage and mechanical overload.

Quality assessment of the resistance spot welding process (RSW) is vital during manufacturing. Evaluating the quality without altering the joint material’s physical and mechanical properties has gained interest. This study uses a trained computer vision model to propose a cheap, non-destructive quality-evaluation methodology. The methodology connects the welding input and during-process parameters with the output visual quality information. A manual resistance spot welding machine was used to monitor and record the process input and output parameters to generate the dataset for training. The welding current, welding time, and electrode pressure data were correlated with the welding spot nugget’s quality, mechanical characteristics, and thermal and visible images. Six machine learning models were trained on visible and thermographic images to classify the weld’s quality and connect the quality characteristics (pull force and welding diameter) and the manufacturing process parameters with the visible and thermographic images of the weld. Finally, a cross-validation method validated the robustness of these models. The results indicate that the welding time and the angle between electrodes are highly influential parameters on the mechanical strength of the joint. Additionally, models using visible images of the welding spot exhibited superior performance compared to thermal images.

Due to the negative impact on the equipment, monitoring of electrical disturbances has become a topic of interest for many researches around the world. In this work, a methodology for automatic classification of power quality disturbances (PQD) is proposed. It consists of three stages: first, the empirical mode decomposition for signal processing is applied; second, the entropy and energy are computed as features for pattern recognition and, finally, a neural network performs the automatic classification. The overall methodology is developed using Matlab software. Synthetic signals are used to train and validate de proposal. On the other hand, real measurements using a field programmable gate array (FPGA)-based data acquisition system (DAS) are carried out to test and show its effectiveness under real operating conditions. The obtained results show high accuracy and low computational burden.

Early prediction of epileptic seizures remains an active research area in scalp electroencephalography (EEG) analysis. Current methods focused on this topic often rely on handcrafted features that insufficiently capture the multiscale nonlinear dynamics of preictal activity, process EEG channels independently without modeling brain connectivity, or demand computationally expensive manual hyperparameter tuning. To address these limitations, this study presents a framework integrating multifractal analysis (MFA), graph neural networks (GNNs), and a differential evolution algorithm (DEA) to classify non-overlapping one-minute EEG segments as preictal (within 60 min before onset) or reference (interictal) states. Five complementary MFA techniques extract nonlinear descriptors from each segment, which serve as node attributes in a graph of the 21 EEG channels. Unlike conventional approaches, this graph explicitly encodes neuroanatomical proximity to capture spatial brain dynamics and inter-channel topological dependencies. This graph-based representation allows the GNN to learn from the relational structure of the brain network, capturing spatiotemporal interactions critical for early prediction, while the DEA systematically optimizes the GNN architecture, eliminating subjective manual tuning. Under a segment-level validation protocol on the CHB-MIT database, the framework achieved 96.38% accuracy, 94.36% sensitivity, 98.41% specificity, and an AUC-ROC of 99.37%. These results demonstrate the effectiveness of combining multifractal descriptors, graph-based processing, and evolutionary optimization for segment-level discrimination. Nevertheless, patient-wise validation remains essential for clinical translation, and this work is consequently presented as a proof-of-concept demonstration.