Bearings are one of the main components of induction motors, machines widely employed in today’s industries, making their monitoring a primordial task; however, most systems focus on measuring one physical magnitude to detect one kind of fault at a time. This research tackles the combination of two common faults, grease contamination and outer race damage, as lubricant contamination significantly impacts the life of the bearing and the emergence of other defects; as a contribution, this paper proposes a methodology for the diagnosis of this combination of faults based on a proprietary data acquisition system measuring vibration and current signals, from which time domain statistical and fractal features are computed and then fused using LDA for dimensionality reduction, ending with an SVM model for classification, achieving 97.1% accuracy, correctly diagnosing the combination of the contamination with different severities of the outer race damage, improving the classification results achieved when using vibration and current signals individually by 7.8% and 27.2%, respectively.

Bearings are one of the most essential elements in an induction motor, and they are built with different materials and constructions according to their application. These components are usually one of the most failure-prone parts of an electric motor, so correct and accurate measurements, instrumentation, and processing methods are required to prevent and detect the presence of different failures. This work develops a methodology based on the fusion of current and magnetic stray flux signals, calculation of statistical and non-statistical indicators, genetic algorithms (GAs), linear discriminant analysis (LDA), and neural networks. The proposed approach achieves a diagnostic effectiveness of 99.8% for detecting various damages in the outer race at 50 Hz frequency and 96.6% at 60 Hz. It also demonstrates 99.8% effectiveness for detecting damages in the presence of contaminants in lubrication at 50 Hz and 97% at 60 Hz. These results apply across metallic, ceramic, and hybrid bearings.

Electromyographic (EMG) signals are increasingly used in wearable cyber–physical systems (CPS), where reliable movement recognition must be achieved under limited computational resources. In this study, we present a compact EMG processing framework that integrates signal acquisition, preprocessing, segmentation, and movement classification within a unified pipeline designed for embedded-oriented applications. The proposed approach combines a multi-channel EMG acquisition system with a lightweight one-dimensional convolutional neural network (1D CNN) developed according to TinyML principles, withprocessing input windows of size 32 × 3 and low computational complexity and memory requirements. Experimental evaluation was conducted on a dataset collected from 15 participants performing squat, walking, and running activities under realistic acquisition conditions. The proposed model achieved an accuracy of 0.9135, an F1-score of 0.9124, and a ROC AUC of approximately 0.96, demonstrating reliable classification performance. Following 8-bit quantization, the model size was reduced to approximately 2 KB, supporting deployment on resource-constrained embedded platforms. The results show that compact CNN architectures can effectively classify EMG-based movement patterns while maintaining a small computational footprint, providing a practical foundation for future wearable CPS and TinyML-enabled applications.

Background/Objectives: Lower-limb exoskeletons require reliable movement recognition mechanisms to support adaptive locomotor assistance and rehabilitation. Electromyographic (EMG) signals provide valuable information on muscle activation and user intention, enabling safe and responsive human–exoskeleton interaction. This study aims to develop and experimentally validate an EMG-based platform for intelligent lower-limb movement recognition and locomotor assistance applications. Methods: The proposed platform integrates multichannel EMG acquisition, embedded signal processing, and artificial intelligence for movement classification. EMG signals associated with six movement classes (left/right kneeling, stepping, and dash) were acquired from ten healthy male participants aged 19–24 years. Signal preprocessing, normalization, dataset generation, and model training were performed using a dedicated processing framework. Continuous EMG acquisition without threshold-based segmentation was employed to preserve complete neuromuscular information and improve dataset consistency. Movement classification was implemented using a lightweight one-dimensional convolutional neural network (1D-CNN). Model performance was evaluated using Stratified 5-Fold Cross-Validation and Leave-One-Subject-Out (LOSO) protocols. Results: A dataset containing 608 multichannel EMG recordings was generated for training and validation. The proposed 1D-CNN model achieved an accuracy of 92.43 ± 1.69% and a macro F1-score of 0.9093 ± 0.0247 under Stratified 5-Fold Cross-Validation. LOSO evaluation yielded an accuracy of 62.11 ± 23.26%, highlighting the significant impact of inter-subject variability on classification performance. Conclusions: The developed platform provides an effective framework for EMG-based lower-limb movement recognition in intelligent exoskeleton systems. The results demonstrate the feasibility of integrating multichannel EMG sensing and AI-based inference into adaptive locomotor assistance systems while emphasizing the importance of improving subject-independent generalization. The proposed platform also establishes a foundation for future research on multimodal sensing and real-time adaptive exoskeleton control.

Background/Objectives: Hand loss or severe impairment significantly reduces quality of life by restricting essential daily activities and professional tasks. Despite advances in prosthetics, challenges remain in affordability, accessibility, and usability. This study aimed to design and develop a low-cost, ergonomic bionic hand prototype that integrates sustainable fabrication, intuitive control, and modular electronics. Methods: A user-centred design process guided by iterative prototyping, anatomical modelling, and functional validation. The prototype was manufactured using 3D printing techniques and assembled with modular electronic components. The design included segmented fingers, independent thumb articulation, and a tendon-like actuation system driven by micro-motors. Control was implemented through an ESP32-based board and a Bluetooth-enabled mobile application. Durability was preliminarily assessed through 500 grasp–release cycles. Results: Experimental validation confirmed the feasibility of both precision and power grips. The pinch grip successfully lifted objects to 120 g, and the power grip up to 85 g, corresponding to effective output forces of approximately 1.2 N and 0.83 N, respectively. The final prototype weighed ~350 g and maintained reliable performance during 500 grasp–release cycles. Conclusions: The developed bionic hand demonstrates that an affordable, ergonomic, and functional prosthetic can be achieved through sustainable 3D printing and accessible electronics. Future work will focus on enhancing actuation strength, long-term durability, and integration of sensory feedback, with the long-term objective of clinical testing and scalable production.