Practical training in electrocardiogram (ECG) interpretation remains uneven, particularly in resource-limited settings, despite the central role of ECGs in cardiovascular diagnosis. This work evaluates whether an ECG-focused digital twin that integrates interactive simulation and deep learning guidance can achieve educationally valid realism, improve recognition of patterns and abnormalities through interactivity, and enhance accuracy and learner motivation via predictive feedback. We present ECGTwinMentor, a cross-platform system that synthesizes parameterized ECG waveforms, enables fine-grained control of physiologic variables, and delivers immediate predictive feedback for formative assessment. The diagnostic model supports low-latency inference on modest hardware. Validation with healthcare experts and medical students showed positive evaluations for realism, usability, and integration potential. Experts reported average ratings between 3.5 and 4.5 out of 5, while students rated usability between 4.6 and 4.8 and motivation and realism at 5.0, with most items scoring at least 4. These findings support the conclusion that an interactive, predictive digital twin can narrow the gap between theory and practice in ECG interpretation, offering an accessible, scalable, and reproducible approach to ECG education.

In the digital era, energy efficiency in data centers is crucial due to the exponential growth of data and the increasing demand for technological infrastructures. Power Usage Effectiveness (PUE) is a key indicator for evaluating this energy efficiency, measuring the ratio between the total energy consumption of a data center and the energy used by information technology (IT) equipment. Integrating sensors to monitor key variables provides a detailed and comprehensive view of data center operations. However, analyzing these large volumes of complex data requires advanced processing approaches. In this context, machine learning technologies play a decisive role, as learning algorithms can identify hidden patterns and correlations that would be difficult to detect with traditional methods. This research presents a step-by-step methodology to optimize data center operations by combining advanced sensor technologies and machine learning. It identifies key variables, integrates sensors to monitor them, and analyzes the data to reveal hidden patterns that traditional methods may miss. This approach enables realtime, data-driven decisions, improving efficiency, reducing energy consumption, and optimizing PUE. Validated through a real use case, the methodology demonstrates its potential to enhance energy management and promote sustainability in data centers.

The Internet of Things enhances the quality of life by automating tasks and streamlining human-device interactions. However, manual device management remains time-consuming, especially in multiple or new environments that demand new settings and interactions. Learning systems aid in automating task management, but their learning times hinder personalization and struggle when the system has to interact with multiple IoT environments, impacting user experience. This paper aims to optimize knowledge sharing for IoT environments, proposing a framework that utilizes recommender systems to find optimal and reusable configurations among IoT environments and users. To that end, this work leverages teacher-student relationships in Knowledge Distillation, facilitating knowledge sharing and enhancing knowledge reuse in learning models. In addition, real-time processing eliminates training time. This approach achieves a remarkable 93.15% accuracy.

Federated Learning has emerged as a promising approach for maintaining data privacy across distributed environments, enabling training on a diverse range of devices from high-performance servers to low-power gadgets. Despite its potential, managing numerous data sources can strain these devices, particularly those with limited capabilities, leading to increased latency. This is especially critical in virtual reality, where real-time responsiveness is crucial due to the need for constant data connectivity. Historically, virtual reality systems have relied on tethered computer setups, restricting their flexibility and the benefits of wireless technology. However, recent advancements have enhanced the computational power of VR devices, allowing them to perform certain tasks independently. This work explores the feasibility of training a neural network on VR devices, using a federated learning approach, to develop a collaborative model aggregated and stored in the cloud. The goal is to assess the computational demands and explore the potential and constraints of leveraging VR devices for artificial intelligence applications.

The main goal of the Web of Things (WoT) is to improve people’s quality of life by automating tasks and simplifying human–device interactions with ubiquitous systems. However, the management of devices still has to be done manually, which wastes a lot of time as their number increases. Thus, the expected benefits are not achieved. This management overhead is even greater when users change environments, new devices are added, or existing devices are modified. All this requires time-consuming customization of configurations and interactions. To facilitate this, learning systems help manage automation tasks. However, these require extensive learning times to achieve customization and cannot manage multiple environments so new approaches are needed to manage multiple environments dynamically. This work focuses on knowledge distillation and teacher–student relationships to transfer knowledge between IoT environments in a model-agnostic manner, allowing users to share their knowledge each time they encounter a new environment. This work allowed us to eliminate training times and achieve an average accuracy of 94.70%, making model automation effective from the acquisition in proactive WoT multi-environments.

The Internet of Things (IoT) is more present in our daily lives than ever before, turning everyday physical objects into smart devices. However, these devices often need excessive human interaction before reaching their best performance, making them time-consuming and reducing their usability. Nowadays, Artificial Intelligence (AI) techniques are being used to process data and to find ways to automate different behaviours. However, achieving learning models capable of handling any situation is a challenging task, worsened by time training restrictions. This paper proposes a Federated Learning solution to manage different IoT environments and provide accurate predictions, based on the user’s preferences. To improve the coexistence between devices and users, this approach makes use of other users’ previous behaviours in similar environments, and proposes predictions for newcomers to the federation. Also, for existing participants, it provides a closer personalization, immediate availability and prevents most manual interactions. The approach has been tested with synthetic and real data and identifies the actions to be performed with 94% accuracy on regular users.

The current trend of smart environments is leading towards a world where everything is considered as a service. Internet-connected smart devices make these environments largely manageable and controllable through services. In these environments, not only devices offer services, but lately, people through their smartphones can also offer services such as personal information provided by the name, the preferences, or the location, promoting the offer of almost anything as a service. However, this high supply of services makes it more difficult for IoT systems to identify which services to use to solve a particular need. This paper proposes a solution to characterize services homogeneously and a service selection mechanism is outlined considering the properties of the services and the context in which they are found. With this proposal, services are defined commonly to facilitate a smart selection by IoT applications.

The rate of world population aging is increasing. This situation directly affects all countries socially and economically, increasing their compromise and effort to improve the living conditions of this sector of society. In environments with large influxes of elderly people, such as nursing homes, the use of technology has shown promise in improving their quality of life. The use of smart devices allows people to automate everyday tasks and learn from them to predict future actions. Additionally, smartphones capture a wealth of information that allows to adapt to nearby actuators according to people’s preferences and even detects anomalies in their behaviour. Current works are proposing new frameworks to detect these behaviours and act accordingly. However, these works are not focused on managing multidevice environments where sensor and smartphone data are considered to automate environments with elderly people or to learn from them. Also, most of these works require a permanent Internet connection, so the full benefit of smart devices is not completely achieved. In this work, we present an architecture that takes the data from sensors and smartphones in order to adapt the behaviour of the actuators of the environment. In addition, it uses this data to learn from the environment to predict actions or to extrapolate the actions that should be executed according to similar behaviours. The architecture is implemented through a use case based on a nursing home located in a rural area. Thanks to this work, the quality of life of the elderly is improved in a simple, affordable, and transparent way for them.

Today, an increasing number of systems produce, process, and store personal and intimate data. Such data has plenty of potential for entirely new types of software applications, as well as for improving old applications, particularly in the domain of smart healthcare. However, utilizing this data, especially when it is continuously generated by sensors and other devices, with the current approaches is complex—data is often using proprietary formats and storage, and mixing and matching data of different origin is not easy. Furthermore, many of the systems are such that they should stimulate interactions with humans, which further complicates the systems. In this article, we introduce the Human Data Model—a new tool and a programming model for programmers and end users with scripting skills that help combine data from various sources, perform computations, and develop and schedule computer-human interactions. Written in JavaScript, the software implementing the model can be run on almost any computer either inside the browser or using Node.js. Its source code can be freely downloaded from GitHub, and the implementation can be used with the existing IoT platforms. As a whole, the work is inspired by several interviews with professionals, and an online survey among healthcare and education professionals, where the results show that the interviewed subjects almost entirely lack ideas on how to benefit the ever-increasing amount of data measured of the humans. We believe that this is because of the missing support for programming models for accessing and handling the data, which can be satisfied with the Human Data Model.