Ensemble learning-based Interactive Machine Learning (IML) offers significant potential for enhancing user-adaptive healthcare monitoring in resource-constrained environments, where preserving privacy and minimizing interaction burden are crucial. This work presents a novel cascade strategy that uses discriminative models to integrate personalization into interactive learning pipelines. It enables lightweight, adaptive activity recognition systems suited for deployment in edge and home-based healthcare scenarios (i.e., local devices and in-home systems). To achieve this, the proposed cascade dynamically adjusts confidence thresholds to match user engagement, triggering selective interaction only when prediction certainty is low. User-labeled data is then used to incrementally retrain the models, enabling personalized adaptation over time. We evaluate the approach on a hydration-related activity dataset as an example of routines relevant to smart health monitoring. Results show that even limited user participation yields measurable improvements, with personalized models achieving higher accuracy than generic ones using only a few additional annotations. This demonstrates the feasibility of combining low-effort interaction with edge-compatible Artificial Intelligence (AI) to enhance real-time, personalized decision-making. Thus, the method supports the development of efficient, adaptive, and human-aware health solutions.

The adoption of IoT technology to improve wellness and health awareness in workplace environments is increasingly vital. However, the acceptance of such e-health interventions largely depends on employees' perceptions of their value versus the privacy and security risks associated with data usage. Hence, addressing these concerns is paramount for fostering trust and ensuring the successful integration of technology. For this reason, this work explores the critical role of privacy in the workplace and examines how concepts of data control and ownership can improve the acceptance and effectiveness of IoT solutions. Leveraging insights from an online questionnaire with 524 participants from European countries, the obtained findings contribute to the existing literature by expanding the understanding of data control in workplace contexts and providing valuable insights for designing IoT-mediated e-health interventions that effectively address employees' privacy concerns.

Abstract Knowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add $$l_1$$ l 1 regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.

As the number of interconnected devices increases and more artificial intelligence (AI) applications upon the Internet of Things (IoT) start to flourish, so does the environmental cost of the computational resources needed to send and process all the generated data. Therefore, promoting the optimization of AI applications is a key factor for the sustainable development of IoT solutions. Paradigms such as Edge Computing are progressively proposed as a solution in the IoT field, becoming an alternative to delegate all the computation to the Cloud. However, bringing the computation to the local stage is limited by the resources’ availability of the devices hosted at the Edge of the network. For this reason, this work presents an approach that simplifies the complexity of supervised learning algorithms at the Edge. Specifically, it separates complex models into multiple simpler classifiers forming a cascade of discriminative models. The suitability of this proposal in a human activity recognition (HAR) context is assessed by comparing the performance of three different variations of this strategy. Furthermore, its computational cost is analyzed in several resource-constrained Edge devices in terms of processing time. The experimental results show the viability of this approach to outperform other ensemble methods, i.e., the Stacking technique. Moreover, it substantially reduces the computational cost of the classification tasks by more than 60% without a significant accuracy loss (around 3.5%). This highlights the potential of this strategy to reduce resource and energy requirements in IoT architectures and promote more efficient and sustainable classification solutions.

Interactive live streaming is a key feature of applications and platforms in which the actions of the viewers affect the content of the stream. In those, a minimal capture-display delay is critical. Though recent technological advances have certainly made it possible to provide web-based interactive live-streaming, little research is available that compares the real-world performance of the different web-based schemes. In this paper we use educational remote laboratories as a case study. We analyze the restrictions that web-based interactive live-streaming applications have, such as a low delay. We also consider additional characteristics that are often sought in production systems, such as universality and deployability behind institutional firewalls. The paper describes and experimentally compares the most relevant approaches for the study. With the provided descriptions and real-world experimental results, researchers, designers and developers can: a) select among the interactive live-streaming approaches which are available for their real-world systems, b) decide which one is most appropriate for their purpose, and c) know what performance and results they can expect.

Developing educational apps that cover a wide range of learning contexts and languages is a challenging task. In this paper, we introduce the AppComposer Web app to address this issue. The AppComposer aims at empowering teachers to easily translate and adapt existing apps that fit their educational contexts. Developers do not need to provide extensive translations and configurations of their apps and can simply follow certain guidelines to make their apps translatable and adaptable by the AppComposer. Since the AppComposer makes use of the standard internationalization specification used by OpenSocial, even external apps can be translated without contacting the original developer.

The lack of tracking and storing capabilities for the results of web-based learning activities is an issue that remains unsolved. Transitions or interactions defined by teachers through a set of conditions still require programming skills that stay far beyond the desired final results. In addition to this, authoring tools should be powerful enough to let lecturers generate contents which are high-quality, interactive, and tuned to each student's cognitive preferences and progress. Availability and processing capabilities, or motivation, relevance, etc., must also be aspects to address in this context. For these reasons, this paper aims to review the existing web application authoring toolkits focusing on distance education. In particular, we analize their main features, requirements and issues, as well as the most promising areas for future improvemenst in this field.

A remote laboratory is a software and hardware tool which enables students to use real equipment -located in an educational institution- through the Internet. This way, students can experiment as if they were using the laboratories with their own hands. And, depending on the design, instructors can later see the results of these students. During the last decade, federation protocols to share remote laboratories have emerged. The focus of these protocols is to be make remote laboratories of one institution available in other in an automated manner, through institutional contracts. And these federation protocols usually rely on existing Remote Laboratory Management Systems (RLMS), which usually provide APIs for tracking student usage. At the same time, the interest on Learning Analytics is increasing. Learning Analytics focuses on the measurement and analysis of data about learners in their context. In the particular context of federated remote laboratories, new challenges arise: on the one hand, remote laboratories must be prepared to track insightful information from the student session so as to extract patterns, and on the other hand, the usage of a federated environment requires different degrees of anonymity. This contribution describes the new Learning Analytics dashboard of WebLab-Deusto, detailing what information can be extracted and how the usage of a RLMS simplifies the development of such tools in a federated environment.

Educational remote laboratories are software and hardware tools that allow students to remotely access real equipment located in universities as if they were in a hands-on-lab session. Federations of these remote laboratories have existed for years, focused on allowing two universities to share their equipment. Additionally, the integration of remote laboratories in Learning Tools-LT-(Learning Management Systems, Content Management Systems or Personal Learning Environments) has been achieved in the past in order to integrate remote laboratories as part of the learning curricula, being part of the practice exercises or even as a tool of evaluation. An cross-institutional initiative called gateway4labs has been created to perform this integration through federation protocols. In this contribution, this initiative adds support for OpenSocial as a new protocol for Learning Tools (in particular, for EPFL Graasp), as well as for the iLab Shared Architecture (in addition to WebLab-Deusto and UNR FCEIA laboratories already supported). Supporting OpenSocial opens a number of new technical and organizational challenges since public labs should be supported without registering students, teachers or schools. The focus of this contribution is to show these challenges and how they are tackled in the proposed open source implementation.

Nowadays, a large number of online laboratories are available and deployed throughout the world. Most of them are sponsored by universities and often only used by their home institution, because they tend to be dedicated to the needs of their creators. However, in many cases these labs provide successful experiences and other teachers would wish to incorporate them into their classroom activities and to embrace Learning-by-Experience methodologies. Currently, they cannot do that effectively without first tailoring the lab experience to their own teaching style and the educational background of their students. This can be a complicated affair, due the closed nature of many online labs and the steep learning curve of the few tools that allow customization. This paper describes the work on an application builder, named App Composer, which aims to make it easy for school teachers to create their own customized applications from existing ones. Different customization levels are provided, each one powered by a different type of composer. For instance, teachers will be able to easily translate an application into a new language, or to start with a template and create a customized version of an application. The App Composer makes use of Graasp and Open Social - a widely-used, interoperable and open technology.

In the last few years, an ecosystem of devices and heterogeneous services has emerged with a huge variety of capacities and characteristics. These new devices, along with applications and services, must be used to enhance the quality of life, making the users daily activities easier, as well as increasing their personal autonomy. In this sense, there is a clear need for creating interfaces that adapt themselves taking into account characteristics of the user, context, application and device. One of the aspects to consider when adapting interfaces is the set of preferences of the user. When using different applications or devices, each user has different preferences, mainly related to their limitations. For that, we have developed a system that discovers users preferences related to different devices and applications. The system discovers set-up parameters, as well as normal performance parameters.

Abstract Recent advances on sensor network technology provide the infrastructure to create intelligent environments on physical places. One of the main issues of sensor networks is the large amount of data they generate. Therefore, it is necessary to have good data analysis techniques with the aim of learning and discovering what is happening on the monitored environment. The problem becomes even more challenging if this process is performed following an unsupervised way (without having any a priori information) and applied over a long‐term timeline with many sensors. In this work, topic models are employed to learn the latent structure and dynamics of sensor network data. Experimental results using two realistic datasets, having over 50 weeks of data, have shown the ability to find routines of activity over sensor network data in office environments.

Adaptive user interfaces involves the design of dynamic interfaces, the main purpose of which is to present an adapted alternative to the user to ease the interaction. User’s preferences, context situation, and device’s capabilities help these systems to adapt the interface to make the interaction more adequate to the current situation. Being aware of different characteristics of these entities is vital for reaching the main goals of these systems efficiently. To collect knowledge from these entities, it is necessary to design several formal models to help to organize and give meaning to the gathered data. This article analyzes several literature solutions for modeling users, context, and devices considering different approaches. The article identifies their advantages and drawbacks to finally propose a new ontology model that addresses the identified limitations.

This special issue of the Interacting with Computers journal is devoted to papers selected from the Fifth International Symposium on Ubiquitous Computing and Ambient Intelligence (UCAmI 2011) and the Third International Workshop on Ambient Assisted Living (IWAAL 2011), held in Riviera Maya, Mexico, 5–9 December 2011. UCAmI focuses on the Ambient Intelligence (AmI) research discipline, which represents a new generation of user-centred computing environments aiming to find new ways to obtain a better integration of information technology in everyday life devices and activities. IWAAL focuses on Ambient Assisted Living (AAL), an important application domain of AmI that aims to contribute with ICT research applied to enabling assistive living environments. The AmI paradigm brings about one important challenge, i.e. to make environments adaptive, responsive or reactive to users’ current contextual situation. To meet this goal, it is important to enable interaction mechanisms among all those entities so that they can address users’ needs. Following this premise, a key aspect of user interaction with Smart Environments (i.e. ICT instrumented environments designed to offer services to end-users) is to acquire, model and reason upon users’ and environments’ contextual information in an implicit and transparent manner. Only then it will be possible for the environments to intelligently react and personalize their behaviour to facilitate users’ daily activities.

The MUGGES mobile service prosuming platform aims at enabling user-aware service provision and consumption from the very mobile devices in a true peer-to-peer manner, still providing centralized support to user- and location-aware micro-service searching. Thus, users will not only provide contents but also launch and host services from their own mobile devices. Explorative field trials in Spain and Finland assessing the potential of the ‘prosuming concept' were carried out for several weeks with students and IT professionals. The feedback gathered from end-users showed that the MUGGES proposed location concept eases service creation and consumption, although service provisioning from mobile devices is still in its infancy.

A vast number of learning content and tools can be found over Internet. Currently, most of them are ad-hoc solutions which are developed for a particular learning platform or environment. New concepts, such as Widgets, Smart devices, Internet of Thing and learning Clouds, are ideas whose goals is the creation of shareable online learning scenarios over different devices and environments.

An educational remote laboratory is a software and hardware tool that allows students to remotely access real equipment located in universities or educational centers. Federations of remote laboratories have existed for years: students of one university transparently access laboratories of other university through software systems that enable these contracts. However, traditionally these contracts have been defined in a “one to one” basis and both universities using the same remote laboratory management system. The focus of this contribution is to present different interoperable bridges among different remote laboratory systems and explore how they can be chained to build complex ecosystems of remote laboratories. The impact of this chaining is that, if successful, it would definitely contribute to the adoption of remote laboratories.

Educational remote laboratories are a software and hardware tool that allows students to remotely access real equipment located in universities as if they were in a hands-on-lab session. Their integration in Content and Learning Management Systems (CMSs or LMSs) has been an active research topic for years, supporting mainly ad hoc solutions. A notable exception has been the use of federation protocols -commonly used for sharing laboratories from one university to other-, for actually sharing laboratories from a remote laboratory system to a C/LMS. This approach opened new doors in the simplification of the process, since it did not require the remote laboratories to make any type of change. The focus of this contribution is to provide a solution to decrease the number of functionalities required for creating an integration by providing a software component that reuses them. As shown in the contribution, this component has been implemented and two remote laboratory management systems (which provide access to multiple remote laboratories) are already supported, and a third one is under development. In the C/LMS side, all the LMSs supporting IMS LTI are supported, and HTTP APIs are provided for being supported by other systems. Indeed, the contribution describes its support in the Joomla CMS and in the Moodle 1.9 and dotLRN LMSs which do not support IMS LTI. The solution, called gateway4labs, is an open source initiative which targets to be used in production.

LabVIEW is a development environment from National Instruments, focused on the automation of processing and measuring equipment, and it is and has been for years a crucial tool in Educational Remote Laboratories. Three features are key for this success: a) a visual programming language called G, so developers don't need to work with traditional “text” programming languages, therefore achieving a wider range of experiment developers; b) a strong industrial support and c) the “Remote Panels”, where the developer publishes the application automatically in a web browser. However, Remote Panels require a plug-in to run, not available for mobile devices neither all browsers in operating systems, and it clearly breaks with the ongoing web development trends, more interested in HTML5. This contribution shows how LabVIEW Remote Panels are used in Remote Laboratories, describing its inclusion in the WebLab-Deusto platform, and it describes the advantages and disadvantages of its use, comparing it with other existing approaches.

An educational remote laboratory is a software and hardware tool that allows students to remotely access real equipment located in the university as if they were in a hands-on-lab session. Federations of remote laboratories have existed for years: they are based on enabling two universities to exchange remote laboratories directly, without registering students of the latter on the former university. Integration of remote laboratories on Learning Management Systems (LMS) or Content Management Systems (CMS) have also been addressed in the past, enabling institutions to delegate the authentication or authorization of the experiments to the LMS/CMS. However, these integrations are usually achieved in an ad hoc way, integrating each particular laboratory to a LMS/CMS. This contribution studies the use of federation models to integrate remote laboratory management systems in LMS/CMSs, since both approaches (integrating a laboratory on an a external electronic learning tool, and integrating a laboratory on other laboratory) are essentially equivalent. The contribution defines two case studies to evaluate this approach, showing how this integration is achieved on a LMS (Moodle) and on a CMS (Joomla).

An educational remote laboratory is a software and hardware tool that enables students to remotely access real equipment located in the university as if they were in a hands-on-lab session. In order to be able to increase the curricula of universities, software infrastructures and toolkits that make the development and maintenance of remote laboratories easier arose, such as the MIT iLab project, the Labshare Sahara project, or WebLab-Deusto. Making different systems collaborate at infrastructure level is highly desirable so as to successfully share laboratories with different characteristics. This contribution summarizes the integration of WebLab-Deusto laboratories inside the iLab Shared Architecture, as well as the integration of iLab batch laboratories inside WebLab-Deusto.

Current state of the art of mobile devices allow visitors to be connected to sources of information in an anytime/anywhere manner. However, finding useful information as a tourist in an unknown place is not easy due to the lack of familiarity with the location on the one hand and to the interaction restrictions with mobile devices on the other. This paper presents a specific Intelligent Tourism Information Dissemination approach that comprehends the particular characteristics and requirements of knowledge management in tourism and thus, contextualizes the visitor and the visitor’s situation. The experiments carried out have focused on proving that digital broadcasting is an appropriate technology to disseminate tourism information and it can be processed by means of semantic-based rules with a lexicographic order. However, due to the high memory requirements and low performance of the CPU further research is needed in order to reduce the size of the ontology, and therefore, reduce the requirements in terms of memory and resource consumptions to perform the reasoning.

There are several toolkits in order to develop context-aware systems. Most of them are for programmers, providing high-level APIs in order to manage context data. Therefore, people that do not have programming skills but have the necessary knowledge about the application domain where the system is going to be deployed cannot participate in the development process. One of the main tasks in the development of context-aware systems is the definition of user situations, which are best defined by people with expertise in the application domain. The involvement of domain experts can improve the final product and it can speed up the development process. This article presents the theoretical foundations for a toolkit in order to promote the involvement of domain experts in the development of context-aware systems. Based on these requirements, a platform to develop such systems has been implemented and it has been validated with domain experts of the tourism domain.

The development of services that use context data to personalize their behaviour is complex. Data coming from distributed and heterogeneous sources have to be acquired, processed and managed. One of the main tasks in the development process is the definition of user situations, which are best defined by people with expertise in the application domain that usually do not have technical skills. The existing context-aware development toolkits are for programmers, so nontechnical domain experts cannot participate in the development process. In order to solve this gap, this article presents a web-based platform to ease the development of context-aware services. The web front-end provides several dialogs in order to manage context data, involving the creation of the context model, the access to the defined context data sources and the definition of situations based on rules. A situation-driven methodology is also proposed in order to guide the development process based in the collaboration among programmers and domain experts. The paper describes the main functionalities of the platform, the development methodology and presents the results of the user evaluation tests that have been carried out.

The paper shows the results of an integration of the remote laboratory WebLab-Deusto-PLD at the "Programmable Logic" course of the Faculty of Engineering of the University of Deusto (Spain). Presented herein is a technical overview of the laboratory, a description of access to it, and an analysis of the user experience derived from conducted surveys since 2004. The surveys' analysis shows a correlation between two advantages of the remote experimentation: efficiency/usefulness and immersion/control. The prospective work includes an improving the WebLab-Deusto usability, an extension of the capabilities of the overall system and further its implementation in curricula.

The remote labs or WebLabs promote the experimentation in the studies of engineering allowing the access and control of real laboratory equipment through Internet. In general a WebLab is a client-server application where the client application can only be used from a PC, and it is not considered the use of mobile devices as potential clients. This is due to the fact that the WebLabs are designed from the hardware point of view, and not from the software engineering point of view. Any WebLab can be designed and implemented to be accessed using a mobile device, but only the AJAX technology can provide a unique solution for a wide range of platforms, including mobile devices. This work compares the different strategies to include mobile devices in remote labs and describes the benefits of using the AJAX approach.

The design of WebLabs has traditionally been focused on the hardware rather than the software side. However, paying more importance to the software side can bring about important improvements: richer collaboration among group members, better scalability, securer access and more natural anywhere at anytime access to the remote lab. Regarding this latter issue, enabling a user to access a remote WebLab not only through standard internet-connected PCs but also by means of their mobile devices can be very interesting and potentially advantageous. The core of this paper is to discuss the transformation of DeustoWebLab into a Web 2.0-compatible application accessible from mobile devices.

Automatic adaptation of the environment to user preferences results in personalized ambient that fulfil user interaction requirements in a more suitable way. However, the problem of environment adaptation has been traditionally solved via ad-hoc context-specific solutions. In this paper we present the WebProfiles model, a negotiation mechanism for ubiquitous computing, based on Web technology extensions, that enables user preferences awareness capability in surrounding devices and services, so that the environment meets the user and knows him as if specifically designed for that purpose.