Abstract Smart classrooms leverage advanced technologies to create interactive, data-driven learning environments that enhance educational experiences. However, interoperability remains a significant challenge, as many of these systems operate independently. This paper presents the Smart Classroom Ontology (SClassO), the very first holistic model designed to unify the key components of smart classroom environments, including people, context, and resources. By providing a semantic framework, SClassO enables seamless integration across heterogeneous systems, bridging gaps between sensing devices, learning management platforms, and classroom analytics. A proof of concept implementation demonstrates its ability to collect and integrate real-world data from both sensor devices and information systems using standard protocols such as MQTT and RESTful APIs. Data is stored both in OWL/RDF format and in a relational database to evaluate performance trade-offs. Finally, the study explores key architectural challenges, focusing on storage capacity, system performance, security, and data privacy.

With the technological developments of recent years, the concept of the “Smart Classroom” has gained in importance and is increasingly becoming a plausible reality. This refers to a classroom in which real-time data collection facilitates decision-making to improve teaching and learning processes. This article presents a proposal for the smart classroom infrastructure that utilises based on the Internet of Things and Cognitive and Intelligent Systems. It consists of a number of perception units that focus on monitoring environmental variables such as light, air quality and noise, as well as variables related to the actors involved (students and teachers), especially those about emotions (which play a crucial role in educational processes). The information extracted from the data is stored and analysed by the classroom agent, which provides teachers with relevant information and suggestions in a timely manner. It is important to further develop our smart classroom infrastructure and test it in real environments to evaluate its potential and benefits in terms of the teaching and learning process, as well as to identify possible drawbacks and obstacles to implementation.

Abstract As society experiences accelerated ageing, understanding the complex biological processes of human ageing, which are affected by a large number of variables and factors, becomes increasingly crucial. Artificial intelligence (AI) presents a promising avenue for ageing research, offering the ability to detect patterns, make accurate predictions, and extract valuable insights from large volumes of complex, heterogeneous data. As ageing research increasingly leverages AI techniques, we present a timely systematic literature review to explore the current state-of-the-art in this field following a rigorous and transparent review methodology. As a result, a total of 77 articles have been identified, summarised, and categorised based on their characteristics. AI techniques, such as machine learning and deep learning, have been extensively used to analyse diverse datasets, comprising imaging, genetic, behavioural, and contextual data. Findings showcase the potential of AI in predicting age-related outcomes, developing ageing biomarkers, and determining factors associated with healthy ageing. However, challenges related to data quality, interpretability of AI models, and privacy and ethical considerations have also been identified. Despite the advancements, novel approaches suggest that there is still room for improvement to provide personalised AI-driven healthcare services and promote active ageing initiatives with the ultimate goal of enhancing the quality of life and well-being of older adults. Graphical abstract Overview of the literature review.

The advent of decentralised systems and the continuous collection of personal data managed by public and private entities require the application of measures to guarantee the privacy of individuals. Due to the necessity to preserve both the privacy and the utility of such data, different techniques have been proposed in the literature. Microaggregation, a family of data perturbation methods, relies on the principle of k-anonymity to aggregate personal data records. While several microaggregation heuristics exist, those based on the Travelling Salesman Problem (TSP) have been shown to outperform the state of the art when considering the trade-off between privacy protection and data utility. However, TSP-based heuristics suffer from scalability issues. Intuitively, methods that may reduce the computational time of TSP-based heuristics may incur a higher information loss. Nevertheless, in this article, we propose a method that improves the performance of TSP-based heuristics and can be used in both small and large datasets effectively. Moreover, instead of focusing only on the computational time perspective, our method can preserve and sometimes reduce the information loss resulting from the microaggregation. Extensive experiments with different benchmarks show how our method is able to outperform the current state of the art, considering the trade-off between information loss and computational time.

The proper exploitation of vast amounts of event data by means of process mining techniques enables the discovery, monitoring and improvement of business processes, allowing organizations to develop more efficient business intelligence systems. However, event data often contain personal and/or confidential information that, unless properly managed, may jeopardize people’s privacy while conducting process mining analysis. Despite its relevance, privacy aspects have barely been considered within process mining, and the field of privacy-preserving process mining is still in an embryonic stage. With the aim to protect people’s privacy, this article presents a novel privacy-preserving process mining method based on microaggregation techniques, called k-PPPM, that increases privacy in process mining through k-anonymity. Contrary to current solutions, mostly based on pseudonyms and encryption, this method averts the re-identification of targeted individuals from attacks based on the analysis of process models in combination with location-oriented attacks, such as Restricted Space Identification and Object Identification attacks. The proposed method provides adjustable parameters to tune different anonymization aspects. Six real-life event logs have been employed to evaluate the method in terms of process models quality and information loss.

Abstract Due to society aging, age-related issues such as mild cognitive impairments (MCI) and dementia are attracting the attention of health professionals, scientists and governments. Seniors suffering from such impairments notice a slight deterioration in their cognitive abilities, which may lead to memory loss and behavioural disorders. In consequence, such seniors refrain from doing their everyday outdoor activities. Technology, e.g. smartphones, wearables and artificial intelligence, can provide seniors and their relatives with a variety of monitoring tools. In a nutshell, locations are analysed and, under specific situations, alarms are raised so that caregivers urgently informed. In this context, the discovery and prediction of trajectories and behaviours play a key role in deploying effective monitoring solutions. In this paper, we present a real-time smartphone-based monitoring system, called SafeMove, to discover and predict elderly people behaviours by analyzing outdoor trajectories. This is achieved by firstly analysing the elder’s mobility data previously collected using the proposed model called SpaceTime-Convolutional Neural Network (ST-CNN) in order to predict the most popular locations he/she might visit in the next time. Based on the predicted locations, the elder can be monitored in bounded region. Time and space-related variables, such as the distance traversed, the direction of the movements and the time spent, are analyzed in our abnormal behaviour detection (ABD) model that takes advantage of recurrent neural networks (RNNs). The effectiveness and the efficiency of our system for predicting the next location and detection the abnormal behaviors are evaluated using different datasets comprising real-world GPS trajectories.

The understanding of human ageing contributes to the overall improvement of healthcare and opens the door to the increase of life expectancy and quality of life. Studies on human ageing, which are evidence-based, require data. Although some efforts have been put to concentrate datasets in single reference points, many datasets remain hidden in articles, studies and research projects websites.In this paper, we aim at identifying those datasets that have been used for the study of human ageing and make them easy to find to researchers in the field. To do so, we have analysed well-known literature databases, previous reviews, and specialised sources. We have reviewed the available data and, as a result, we have identified and discussed 28 datasets. Hence, this article provides an organised reference point to datasets for researchers interested in the study of human ageing and contributes to their visibility.

Age-related diseases are becoming more prominent due to life expectancy increase in developed countries. Mild cognitive impairment and several types of dementia like Alzheimer's disease are gaining importance both socially and economically. Patients suffering from these diseases have different degrees of autonomy and, thus, different needs. Often, relatives or friends take care of those patients. However, during the first stages of the disease, they still have a high degree of autonomy and frown on the supervision of others. Despite their autonomy, patients could get lost and disoriented. Rapidly determining the location of a lost patient is paramount to reduce the risk of suffering serious injuries. Current solutions to this problem are based on the continuous monitoring of the patient. Such continuous control might be seen by most people as a privacy invasion, and it may discourage patients from using these solutions. In this article we present the concept of m-Carer as a smart mobile device able to privately monitor the movements of patients having diverse degrees of mobility and autonomy. After justifying the need for privacy-aware m-carers due to social and economical reasons, we propose a complete architecture aimed at fulfilling the needs of patients, relatives and healthcare services. Moreover, we show a real implementation of our proposal so as to confirm that it is technically sound and feasible.

In this paper, we present the concept of double-phase microaggregation as an improvement of classical microaggregation for the protection of privacy in distributed scenarios without fully trusted parties. We apply this new concept in the context of mobile health and we show that a distributed architecture consisting of patients and several intermediate entities can apply it to protect the privacy of patients, whose data are released to third parties for secondary use. After recalling some fundamental concepts of statistical disclosure control and microaggregation, we detail the distributed architecture that allows the private gathering, storage, and sharing of biomedical data. We show that double-phase multivariate microaggregation properly fits the needs for privacy preservation of biomedical data in the distributed context of mobile health. Moreover, we show that double-phase microaggregation performs similarly to classical microaggregation in terms of information loss, disclosure risk, and correlation preservation, while avoiding the limitations of a centralized approach.

Automated data collection has fostered the use of data mining for intrusion and crime detection. Indeed, banks, large corporations, insurance companies, casinos, etc. are increasingly mining data about their customers or employees in view of detecting potential intrusion, fraud or even crime. Mining algorithms are trained from datasets which may be biased in what regards gender, race, religion or other attributes. Furthermore, mining is often outsourced or carried out in cooperation by several entities. For those reasons, discrimination concerns arise. Potential intrusion, fraud or crime should be inferred from objective misbehavior, rather than from sensitive attributes like gender, race or religion. This paper discusses how to clean training datasets and outsourced datasets in such a way that legitimate classification rules can still be extracted but discriminating rules based on sensitive attributes cannot.

Microaggregation is a Statistical Disclosure Control (SDC) technique that aims at protecting the privacy of individual respondents before their data are released. Optimally microaggregating multivariate data sets is known to be an NP-hard problem. Thus, using heuristics has been suggested as a possible strategy to tackle it. Specifically, Genetic Algorithms have been shown to be serious candidates that can find good solutions on small data sets. However, due to the very nature of these algorithms and the coding of the microaggregation problem, GA can hardly cope with large data sets. In order to apply them to large data sets, the latter have to be previously partitioned into smaller disjoint subsets that the GA can handle. In this article we summarise several proposals for partitioning data sets, in order to use GA to microaggregate them. In addition, we suggest a new partitioning strategy based on the variable-MDAV algorithm, and we compare it with the most relevant previous proposals. The experimental results show that our method outperforms the previous ones in terms of information loss.

Protecting personal data is essential to guarantee the rule of law1. Due to the new Information and Communication Technologies (ICTs) unprecedented amounts of personal data can be stored and analysed. Thus, if the proper measures are not taken, individual privacy could be in jeopardy. Being the aim to protect individual privacy, a great variety of statistical disclosure control (SDC) techniques has been proposed. Amongst many others, k-anonymity is a promising property that, if properly achieved, can help protect individual privacy. In this paper, we propose a new post-processing method that can be applied after a k-anonymity algorithm, being the aim to lessen the errors resulting from the aggregation of data. We show that our method can be extended to work with many other SDC techniques and we provide some experimental results which emphasise the usefulness of our proposal.

Checking data possession in networked information systems such as those related to critical infrastructures (power facilities, airports, data vaults, defense systems, etc.) is a matter of crucial importance. Remote data possession checking protocols permit to check that a remote server can access an uncorrupted file in such a way that the verifier does not need to know beforehand the entire file that is being verified. Unfortunately, current protocols only allow a limited number of successive verifications or are impractical from the computational point of view. In this paper, we present a new remote data possession checking protocol such that: i) it allows an unlimited number of file integrity verifications; ii) its maximum running time can be chosen at set-up time and traded off against storage at the verifier.

Blocking is a well-known technique used to partition a set of records into several subsets of manageable size. The standard approach to blocking is to split the records according to the values of one or several attributes (called blocking attributes). This paper presents a new blocking method based on 2/sup d/-trees for intelligently partitioning very large data sets for micro aggregation. A number of experiments has been carried out in order to compare our method with the most typical univariate one.