ArtículoPaving the way to collaborative context-aware mobile applications: a case study on preventing worsening of allergy symptomsCaballero Torres, Pablo; Ortiz, Guadalupe; García de Prado Fontela, Alfonso; Boubeta-Puig, Juan. Actas de las XVII Jornadas de Ingeniería de Ciencia e Ingeniería de Servicios (JCIS 2022), 2022-09-05.In recent years, the evolution of smartphones and their software applications has grown exponentially; together with the advance of the Internet of Things and smart cities, it has raised huge demand for services and applications in these domains. Although the wide range of mobile applications is unquestionable, citizens already demand that applications adapt to their specific needs and situations in real time, that is, that they are context-aware. However, context-aware mobile applications are often very limited and miss out on the opportunity of benefiting from feedback provided by citizen collaboration. In order to fill this gap, this paper proposes a context-aware and collaborative software architecture and mobile application. In particular, we have implemented them in the scope of e-health, more specifically in the area of seasonal allergies, which cause allergic people to experience annoying symptoms that could be avoided by having access to pollen information in real time. Furthermore, they will also benefit from citizen collaboration through the knowledge of the symptoms other allergic people with the same allergy and in the same location are experiencing. To this end, users will be able to provide their symptoms at any time through their mobile application and the proposed architecture will constantly process that information in real time, sending notifications to users as soon as reported symptoms are seen to exceed a certain threshold. The architecture’s performance, the application’s resource consumption and a satisfaction survey of the app’s usability and usefulness have been tested; all results have been fully satisfactory. ArtículoSimulateIoT: Domain Specific Language to design, code generation and execute IoT simulation environmentsBarriga Corchero, José Ángel; Clemente Martín, Pedro José; Sosa Sánchez, Encarna; Prieto Ramos, Álvaro E.. Actas de las XVII Jornadas de Ingeniería de Ciencia e Ingeniería de Servicios (JCIS 2022), 2022-09-05.Developing, deploying and testing IoT projects require high investments on devices, fog nodes, cloud nodes, analytic nodes, hardware and software. However, in order to decrease the cost associated to develop and test the IoT system it can be previously simulated. Designing IoT simulation environments has been tackled focusing on low level aspects such as networks, motes and so on more than focusing on the high level concepts related to IoT environments. Model-driven development aims to develop the software systems from domain models which capture at high level the domain concepts and relationships, generating from them the software artefacts by using code-generators. In this paper, a model driven development approach, SimulateIoT, is proposed to define, generate code and deploy IoT systems simulations. Additionally, two case studies, focused on smart building and agriculture IoT systems, are presented to show the simulation expressiveness. ArtículoUsing Federated Learning to achieve Proactive Context-Aware IoT EnvironmentsRentero-Trejo, Rubén; Flores-Martin, Daniel; Galán-Jiménez, Jaime; García Alonso, José Manuel; Murillo Rodríguez, Juan Manuel; Berrocal, José Javier. Actas de las XVII Jornadas de Ingeniería de Ciencia e Ingeniería de Servicios (JCIS 2022), 2022-09-05.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 users 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.