This study presents a sustainable digital transformation framework to integrate sustainable practices into digital transformation initiatives within Small and Medium Enterprises (SMEs). The methodology includes a literature review, a framework creation, and a case study with passive participation. The framework was structured to help industries implement responsible digitalization initiatives in five key stages: setting objectives, fostering stakeholder-focused engagement, defining sustainable objectives and dimensions, creating a sustainable model, and executing the project. Validating the proposal in the context of an SME allowed us to discern the tangible benefits of sustainability practices for the organization, further reinforcing the relevance and applicability of the framework. In conclusion, this research offers valuable information for SMEs considering starting a sustainable digitalization process.

Industry 5.0 introduces a shift toward human-centric, sustainable, and resilient industrial ecosystems, emphasizing intelligent automation, collaboration, and adaptive operations. Predictive Maintenance (PdM) plays a critical role in this transition, addressing the limitations of traditional maintenance approaches in increasingly complex and data-driven environments. The convergence of Artificial Intelligence and the Industrial Internet of Things, referred to as the Artificial Intelligence of Things (AIoT), enables real-time sensing, learning, and decision-making for advanced fault detection, Remaining Useful Life estimation, and prescriptive maintenance actions. This study provides a systematic and structured review of AIoT-enabled PdM aligned with Industry 5.0 objectives. It presents a unified taxonomy integrating AI models, Industrial Internet of Things (IIoT) infrastructures, and AIoT architectures; reviews AI-driven techniques, sector-specific implementations in manufacturing, transportation, and energy; and analyzes emerging paradigms such as Edge–Cloud collaboration, federated learning, self-supervised learning, and digital twins for autonomous and privacy-preserving maintenance. Furthermore, this paper synthesizes strengths, limitations, and cross-industry challenges, and outlines future research directions centered on explainability, data quality and heterogeneity, resource-constrained intelligence, cybersecurity, and human–AI collaboration. By bridging technological advancements with Industry 5.0 principles, this review contributes a comprehensive foundation for the development of scalable, trustworthy, and next-generation AIoT-based predictive maintenance systems.

Mobile electrocardiogram (ECG) monitoring is an emerging area that has received increasing attention in recent years, but still real-life validation for elderly residing in low and middle-income countries is scarce. We developed a wearable ECG monitor that is integrated with a self-designed wireless sensor for ECG signal acquisition. It is used with a native purposely designed smartphone application, based on machine learning techniques, for automated classification of captured ECG beats from aged people. When tested on 100 older adults, the monitoring system discriminated normal and abnormal ECG signals with a high degree of accuracy (97%), sensitivity (100%), and specificity (96.6%). With further verification, the system could be useful for detecting cardiac abnormalities in the home environment and contribute to prevention, early diagnosis, and effective treatment of cardiovascular diseases, while keeping costs down and increasing access to healthcare services for older persons.

In this paper, we addressed the problem of dataset scarcity for the task of network intrusion detection. Our main contribution was to develop a framework that provides a complete process for generating network traffic datasets based on the aggregation of real network traces. In addition, we proposed a set of tools for attribute extraction and labeling of traffic sessions. A new dataset with botnet network traffic was generated by the framework to assess our proposed method with machine learning algorithms suitable for unbalanced data. The performance of the classifiers was evaluated in terms of macro-averages of F1-score (0.97) and the Matthews Correlation Coefficient (0.94), showing a good overall performance average.

Attacks, such as port scans, DDoS and worms, threaten the functionality and reliability of IP networks. Early and accurate detection is crucial to mitigate their impact. We use the Method of Remaining Elements (MRE) to detect anomalies based on the characterization of traffic features through a proportional uncertainty measure. MRE has the functionality and performance to detect abnormal behavior and serve as the foundation for next generation network intrusion detection systems.