• Integration of ML techniques into DigiMoCA, a T-MoCA-based conversational agent. • Models yielded an R 2 of 0.81 and RMSE of 1.84 in predictive validity. • MCI detection showed an AUC of 0.98, with 100% sensitivity and 93% specificity. • DigiMoCA offers a self-administered, accessible, and cost-effective alternative. • The integration of ML techniques significantly outperforms previous related work. Background: This study investigates the feasibility of integrating machine learning techniques into DigiMoCA, a T-MoCA-based conversational agent for the early screening of cognitive impairment in senior adults. Method: A sample of 46 participants with varying cognitive decline levels, age, and gender was recruited. Each participant undertook several gold standard tests as well as two administrations of DigiMoCA. Then, a data processing architecture was designed and implemented to test different Machine Learning (ML) algorithms. Results: Predictive validity testing using the Telephone Montreal Cognitive Assessment (T-MoCA) yielded promising results, with the best-performing algorithm achieving an R 2 = 0.81 and RMSE of 1.84. Criterion validity testing for discerning between individuals suffering from mild cognitive impairment (MCI) and non-MCI individuals showed an area under the ROC curve of 0.98 in the best case, with 100% sensitivity and 93% specificity. Thus, the inclusion of machine learning allows to exploit more effectively the information captured with DigiMoCA, improving its MCI screening potential. Conclusions: Integrating machine learning techniques into DigiMoCA showed promising predictive and criterion validity, indicating the efficacy of the approach in discerning cognitive decline levels and facilitating timely interventions for individuals at risk of cognitive decline. Despite limitations in sample size and heterogeneity, the findings notably outperform previous related work, laying a foundation for future research and showcasing the potential of conversational agents for this purpose.

The limitations of current cognitive impairment screening instruments, combined with the widespread adoption of smart speakers, highlight the need for an easy-to-use and accessible cognitive assessment tool. This study introduces DigiMoCA, a conversational agent for the detection of cognitive impairment, and presents its diagnostic, convergent and content validity. DigiMoCA was tested with 46 senior adults, and standard statistical analysis was utilized to determine its validity. We used T-MoCA as the gold standard. In the best scenario, we obtained a Pearson correlation of r=0.88 with the gold standard, and an area under the ROC curve of AUC=0.79 for the detection of cognitive impairment. Additionally, linear regression was applied to predict the gold standard outcomes from DigiMoCA’s, obtaining a coefficient of determination R2=0.77. This demonstrates the potential of DigiMoCA as a digital screening tool for the early detection of cognitive impairment among senior adults.

ABSTRACT Introduction The popularization of blockchain‐based applications made evident a critical challenge, namely the inherent isolation of these decentralized systems, akin to the disconnected and technologically diverse local area networks of the 1970s. This lack of interoperability limits the potential for widespread adoption and innovation in the blockchain space. While various initiatives aim to bridge this gap, many remain nascent. Methods This article addresses this issue by proposing a robust architecture and practical implementation to interconnect two Ethereum‐based blockchains, enabling seamless smart contract interactions across these chains, and facilitating the exchange of complex information beyond mere token transfers. Results Our work explores the emerging landscape of inter‐blockchain communication, highlighting their current maturity and potential, and providing insights on how to overcome the technical hurdles associated with these protocols, particularly in the context of transmitting complex data and executing cross‐chain function calls. Additionally, we illustrate with a case study the challenges posed by linking private blockchains with public ones, ensuring secure and efficient data exchange. Conclusion This article aims to inspire blockchain researchers and practitioners, presenting a foundational framework for enhancing blockchain interoperability, including detailed, practical steps for its implementation. By laying the groundwork for more connected blockchain ecosystems, we intend to support the continued evolution and widespread adoption of blockchain technology.

Abstract Background: early detection of dementia and Mild Cognitive Impairment (MCI) have an utmost significance nowadays, and smart conversational agents are becoming more and more capable. DigiMoCA, an Alexa-based voice application for the screening of MCI, was developed and tested. Objective: to evaluate the acceptability and usability of DigiMoCA, considering the perception of end-users and cognitive assessment administrators, through standard evaluation questionnaires. Method: a sample of 46 individuals and 24 evaluators participated in this study. End-users were fairly heterogeneous considering demographic and neuro-psychological characteristics. Evaluators were mostly health and social care professionals, relatively well-balanced in terms of gender, career background and years of experience. Results: end-users acceptability ratings were generally positive (rating above 3 in a 5-point scale for all dimensions) and it improved significantly after the interaction with DigiMoCA. Administrators also rated the usability of DigiMoCA, with an average score of 5.86/7 and with high internal consistency ( $$\alpha $$ α = 0.95). Conclusion: although there is still room for improvement in terms of user satisfaction and voice interface, DigiMoCA is perceived as an acceptable, accessible and usable cognitive screening tool, both by individuals being tested and test administrators. Graphical abstract

Abstract Smart assistants are among the most popular technological devices at home. With a built‐in voice‐based user interface, they provide access to a broad portfolio of online services and information, and constitute the central element of state‐of‐the‐art home automation systems. This work discusses the challenges addressed and the solutions adopted for the design and implementation of scripted conversations by means of off‐the‐shelf smart assistants. Scripted conversations play a fundamental role in many application fields, such as call center facilities, retail customer services, rapid prototyping, role‐based training or the management of neuropsychiatric disorders. To illustrate this proposal, an actual implementation of the phone version of the Montreal cognitive assessment test as an Amazon's Alexa skill is described as a proof‐of‐concept.

Blockchain technologies are attracting the interest of different actors in various sectors and, among them, the education field, which is also studying how to apply these technologies to improve the traceability, accountability, and integrity of its information. Although different initiatives and projects were launched and are being developed, there are still issues not fully resolved, such as privacy, compliance with data protection regulations and scalability. This research proposes a novel design of a system to issue, store and verify different types of academic information, which allows complying with applicable regulations, protecting the privacy of users' personal data, as well as addressing the problem of scalability and performance.

OBJECTIVE: To design, implement, and test a solution to provide social and health services for the elderly at home based on smart TV technologies and access to all services. METHODS: The architecture proposed is based on an open software platform and standard personal computing hardware. This provides great flexibility to develop new applications over the underlying infrastructure or to integrate new devices, for instance to monitor a broad range of vital signs in those cases where home monitoring is required. RESULTS: An actual system as a proof-of-concept was designed, implemented, and deployed. Applications range from social network clients to vital signs monitoring; from interactive TV contests to conventional online care applications such as medication reminders or telemedicine. CONCLUSION: In both cases, the results have been very positive, confirming the initial perception of the TV as a convenient, easy-to-use technology to provide social and health care. The TV set is a much more familiar computing interface for most senior users, and as a consequence, smart TVs become a most convenient solution for the design and implementation of applications and services targeted to this user group. SIGNIFICANCE: This proposal has been tested in real setting with 62 senior people at their homes. Users included both individuals with experience using computers and others reluctant to them.

The Open Educational Resource concept was proposed several years ago as a way to develop the Open Movement principles in the educational domain. Despite the open and participative view underlying this proposal, there has not been a significant adoption of this concept by users. Many problems and barriers have been considered and analyzed. Nevertheless, we consider that a main issue is the contradiction among the definitions proposed and the real support provided by platforms. In addition, there exist also different approaches to the concept by users and organizations. In this paper we call for a real open approach to the Open Educational Resource concept and introduce a platform where specific functionalities have been introduced to support its development.

Open educational resources are a key instrument in the promotion of learning and social appropriation of knowledge in the digital world. Providing access to existing learning resources in a way that teachers, students and parents are able to discover, acquire, discuss and adapt them to their own learning scenarios will also promote the development of values and attitudes that play a fundamental role in the educational process, such as team work, collaboration and critical thinking. In turn, this will foster the development of learning networks and communities. In this context, teachers play an instrumental role as facilitators, as their expertise enables them to assess the quality of content and to design and adapt learning activities according to individual learners' profiles. However, we wanted to find out how the interaction with open educational resources would enhance teachers' activities, if digital resources could be easily integrated in their actual educational curricula, or if teachers felt that the introduction of these resources would improve the educational experience of their students. This paper addresses the usage and usability of open educational resources from teachers' perceptions. For this, we utilized the Open Discovery Space portal, a socially-powered and multilingual open educational resources' repository intended to support teachers, students and parents to intuitively identify, share, reuse and revise digital learning resources. This analysis was performed taking into account both actual content and ancillary services offered by the portal (e.g., content sharing, content discussion, community building), and was methodologically organized as a streamlined cognitive walkthrough that included two evaluation workshops in late 2013 and early 2014, and a further debriefing survey in mid 2014. The first workshop included a brief course to teachers on the functionalities and aims of the Open Discovery Space portal and an assessment survey. The second workshop was devoted to answer the questions posed by the teachers participating after a 6-week period of usage and reflection. Again, the workshop was completed with an assessment survey on the portal's content and services. Finally, in mid 2014 a final evaluation, survey-based session was (will be at the time of writing this abstract) carried out after continuing interaction with the portal's content and services during several months.

Usability is widely acknowledged in the ICT-related literature as one of the most important factors that can directly affect the overall acceptance and success of any ICT application, tool, software, and platform. Ensuring usability is one of the main challenges of e-learning system developers. This paper describes two case studies designed to (i) evaluate the usability and (ii) assess the impact on school learning of the newly designed ODS Portal. The paper presents the development of the testing/evaluation methodology, the evaluation exercise, and the analysis of the results from an extensive "use and usability" evaluation of the Open Discovery Space educational online platform.

With the popularization of online repositories and content management systems, digital resources available to organize educational activities proliferate. Digital resources include many different possibilities besides content, like events, people, or hardware devices and software applications. We propose a conceptualization of the educational domain by means of an ontology aimed to comprehensively classify educational resources. This ontology may serve as the foundation of complex knowledge-based systems to assist teachers in the categorization, selection and retrieval of the most suitable resources for any educational activity in any educational scenario they wish to design and implement.

This article discusses a modular, accessible platform that provides a computing environment for people with disabilities accessible through adapted control devices and the television set at users’ homes. Relying on a standard television set as the presentation device allows dependent individuals, especially people with disabilities, to introduce new technological advances in communication and information management in their everyday lives. As a proof-of-concept, the solution presented offers a collection of educational and training services related to teleworking and the search of employment targeted to people with disabilities. A smart job advisor included among these services, which was designed to help our target users to locate job offers that best suit the abilities and disabilities of a particular individual, is also discussed to illustrate how semantic technologies can be applied to increase the perceived accessibility and inclusion by reducing the dependence from other persons. The platform developed, the introduction of semantic technologies, and the way adapted interfacing and presentation devices were integrated may also serve as inspiration to provide services to people with disabilities.

This paper describes a multi-device Learning Management System based on Moodle with alternative interfaces providing accessibility for people with disabilities. The software architecture built over Moodle is described as well as the interface created to offer access through a TV. An initial user focus group has been used to test and get feedback for further developments of the system.

This paper introduces the iTEC SDE (Scenario Development Environment), a recommendation system to assist teachers in the creation of lesson plans. A key functionality of the SDE is the recommendation of people. Basically, taking into account new pedagogical approaches, this system manages information about potential lesson plan contributors and provides recommendations on the best available people to participate in specific learning activities. The SDE has been developed as a multi-criteria recommender focused on supporting learning activities in particular technological and educational contexts. In this way, it manages information about the devices and applications available in the classroom and the features of the students, such as educational level, language, age, location, etc. The final goal of this system is to support teachers creating lesson plans in which they can develop new pedagogical approaches involving new technologies and external resources, such as people from outside the school. Eventually, this will contribute to engage students and improve learning.

Game·Tel is an open source software system that supports personalized learning, focusing on serious games and simulations, making these and traditional content accessible and adaptive to the student and educational context. In this paper we discuss about its design and functionalities, its modular architecture and the multi-environment approach.

This paper focuses on automated content update for MHP applications. Some of the authors have been involved in the first MHP trials of TVG, the TV channel of Galicia, NW Spain (three million population). It has a 30% share at regional level, competing with national channels. However, the initial MHP trials have raised the problem of manual content update cost, since in many key applications, like news and weather forecasts, contents vary on a daily basis. We have reviewed the status of MHP deployment in similar TV channels, and we have determined that the problem is currently relevant. We describe our solutions for automated content update with minimal human intervention, and our practical experience with them.

Web Content Management Systems support both access to content and content management using a Web interface. However, navigation-based access to content is not ideal for some tasks, like content analysis and assessment, report generation, education, filing or third-party distribution. This paper discusses a cost-effective approach to the generation of high-quality printed versions of content held in a Web Content Management System using typesetting software. This approach is illustrated with two case studies. Copyright © 2005 John Wiley & Sons, Ltd.

E-learning takes advantage of the new features offered by Web services: integration of heterogeneous applications, publicity of available services, etc. As the adoption of this new technology increases it will become necessary to offer intermediary platforms that make it easier to find and locate services, and composing new services from the existing ones. Additionally, it will also be necessary to provide value-added services like auditing, security or management. We present a proposal for a standard-based intermediary framework for Web services.

The learning technology standardization process is taking one of the leading roles in the research efforts into computer-based education. Institutions like the IEEE, the US Department of Defense and the European Commission have set up committees to deliver recommendations and specifications on this area. Their goal is to provide interoperability among heterogeneous systems and reuse of learning objects. From this standardization work, we propose am open and distributed architecture that identifies some common software services for the e-learning domain. Our aim is to contribute to this standardization process from the software perspective.

This paper presents a layered component model to support Web-based interactive and collaborative applications. It is intended to let programmers focus on the particular logic of their applications, avoiding most of the issues related to collaboration, access control and networking management. A Web-based educational application has been developed over this framework. This tele-education system, which follows the recommendations by the main institutions involved in the learning technology standardization process, is the second contribution presented by the authors.

We present a layered component model to support Web-based collaborative applications. We show how this model lets programmers focus on the particular logic of their applications, avoiding most of the issues related to collaboration, access control, and network management. The proposed model is organized into three layers on top of a foundation composed of commercial-off-the-shelf services and standard Internet protocols. The service level provides a network-transparent communications layer, database access, and distributed data interchange. The component level offers typical collaborative services, like user management, auditing, user-oriented messaging, higher-level events, project management, and a bulletin board. The application level supports actual applications constructed using the services offered by the underlying layers. A Web-based educational application has been developed over this framework to illustrate the process. This tele-education system, which follows the recommendations of the main institutions involved in the learning technology standardization process, is the second contribution presented by the authors.

Abstract This paper describes a layered framework to support WWW‐based interactive and collaborative applications. Using some commercial‐off‐the‐shelf (COTS) software, three basic services are built: virtual rooms, virtual file systems, and database connectivity. These services are used at a second layer, which actually provides the functionality of the framework. The components that have been described at this level can be embedded in WWW‐based business applications in an easy and direct way. Therefore, programmers can focus on the particular logic of their applications, avoiding most of the issues related to collaboration, networking, and access control. In order to test the developed framework a WWW‐based educational application has been implemented. This tele‐education system, with innovative features in the field of WWW‐based practical training, is the second contribution presented by the authors. Copyright © 2001 John Wiley & Sons, Ltd.

Abstract The Internet and the WWW have encouraged the adoption of a three‐tiered architectural style as the general framework for distributed computing. The thin client concept associated with this model is the most suitable for the WWW, because it can be easily mapped to the browser concept. Additionally, the separation of business logic (middle tier) and back‐end services enable further flexibility for the design of this kind of service. Nevertheless, the advent of platform‐independent software models like Java and the availability of common off‐the‐shelf services, like FTP or HTTP, offer new opportunities to more classical distributed computing models. In this paper we revisit the two‐tiered model for Internet environments, and show that the fat client (user interface plus business logic) may still be valid, at least in some environments. We propose two solutions to provide full FTP access from a Java applet. Copyright © 2001 John Wiley & Sons, Ltd.

The authors present DelfosnetX, an information retrieval (IR) system intended to evaluate different relevance analysis and ranking techniques for metadata-enabled IR, and more specifically, XML based IR. The theoretical background that supports the proposed model is also discussed.