JSJoaquín Salvachúa

Joaquín Salvachúa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joaquín Salvachúa has a total of 77 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Real-time Spatial Retrieval Augmented Generation for Urban Environments

    by David Nazareno Campo, Javier Conde, Álvaro Alonso, Gabriel Huecas, Joaquín Salvachúa, Pedro Reviriego

    The proliferation of Generative Artificial In t elligence (AI), especially Large Language Models, presents transformative opportunities for urban applications through Urban Foundation Models. However, base models face limitations, as they only contain the knowledge available at the time of training, and updating them is both time-consuming and costly. Retrieval Augmented Generation (RAG) has emerged in the literature as the preferred approach for injecting contextual information into Foundation Models. It prevails over techniques such as fine-tuning, which are less effective in dynamic, real-time scenarios like those found in urban environments. However, traditional RAG architectures, based on semantic databases, knowledge graphs, structured data, or AI-powered web searches, do not fully meet the demands of urban contexts. Urban environments are complex systems characterized by large volumes of interconnected data, frequent updates, real-time processing requirements, security needs, and strong links to the physical world. This work proposes a real-time spatial RAG architecture that defines the necessary components for the effective integration of generative AI into cities, leveraging temporal and spatial filtering capabilities through linked data. The proposed architecture is implemented using FIWARE, an ecosystem of software components to develop smart city solutions and digital twins. The design and implementation are demonstrated through the use case s of a tourism assistant and for the management of traffic lights and luminaires in the city of Madrid. The use case s serve to validate the correct integration of Foundation Models through the proposed RAG architecture. They also enable the analysis of current model limitations, such as their inability to handle large volumes of information, even when it fits within their context window, and the high latency of Large Language Models caused by transformer-based architectures, which generate output token by token.


  • Open Access

    Optimizing machine learning operations in multi-cloud infrastructure: a framework for unified deployment management and topology discovery

    by Hao Wei, Xabiel García Pañeda, Joaquín Salvachúa Rodriguez

    Machine learning (ML) transitioned from a purely academic discipline to an applied field, gaining strategic importance in various industries. Meanwhile, Machine Learning Operations (MLOps) has been widely adopted by enterprises as a comprehensive approach for developing and managing machine learning applications. Despite its advantages, challenges remain. The rising demand for flexibility and scalability has led organizations to embrace multi-cloud and hybrid cloud architectures as preferred solutions. However, the autonomous and distributed nature of modern application development, combined with the complexity of training and deploying machine learning models, makes unified operational management impractical, and this will further affect application quality and efficiency. To address these challenges, this paper proposes a framework to manage model training and deployment in a multi-cloud environment. This framework uses a policy-based resource provisioning approach, agent-based application topology reconstruction, and a visualization dashboard. It aims to provide a cloud provider-neutral solution that enhances the quality of application operations. The framework design is introduced, followed by the implementation of a proof-of-concept prototype. Experiments conducted in various empirical scenarios demonstrate that the proposed framework effectively manages deployment resources while providing clear visibility and control across multiple clouds. The results confirm that this framework enhances control over deployment resources and optimizes model deployment efficiency in multi-cloud infrastructure.


  • Open Access

    Propuesta de implementación de catálogos federados para espacios de datos sobre DataHub

    by Carlos Aparicio de Santiago, Pablo Viñuales Esquinas, Irene Plaza Ortiz, Andres Munoz-Arcentales, Gabriel Huecas, Joaquín Salvachúa, Enrique Barra

    In the digital era, data spaces are emerging as key ecosystems for the secure and controlled exchange of information among participants. To achieve this, components such as metadata catalogs and data space connectors are essential. This document proposes an implementation and integration solution for both elements, considering standardization guidelines for data formats, metadata, and protocols, which ensures interoperability. A hybrid solution is presented: DataHub is used as a federated catalog for robust metadata management, leveraging its advanced ingestion, governance, and lineage capabilities. On the other hand, a custom implementation, Rainbow Catalog, manages ODRL policies for access and usage. This integration makes it possible to query datasets from DataHub and associate them with ODRL policies, facilitating negotiation and transfer flows defined by the Dataspace Protocol. The result is a system that combines the power of DataHub for large-scale cataloging with the policy management of the connector crucial for sovereignty and trust in data spaces.

  • Open Access

    Authentication and authorization in Data Spaces: A relationship-based access control approach for policy specification based on ODRL

    by Irene Plaza-Ortiz, Andres Munoz-Arcentales, Joaquín Salvachúa, Carlos Aparicio, Gabriel Huecas, Enrique Barra

    Data has become a crucial resource in the digital economy, fostering initiatives for secure and sovereign data sharing frameworks such as Data Spaces. However, these distributed environments require fine-grained access control mechanisms that balance openness with sovereignty and security. This paper proposes an extension of the Open Digital Rights Language (ODRL) standard, the ODRL Data Spaces (ODS) profile, aimed at supporting authorization and complementing existing authentication mechanisms throughout the data lifecycle. Additionally, a policy execution engine is introduced to translate ODRL policies into executable formats, enabling effective enforcement. The approach is validated through a use case involving OpenFGA, demonstrating its applicability to relationship-based access control scenarios.

  • Open Access

    Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems

    by Javier Conde, Andrés Munoz-Arcentales, Álvaro Alonso, Joaquín Salvachúa, Gabriel Huecas

    The rise of AI and the Internet of Things is accelerating the digital transformation of society. Mobility computing presents specific barriers due to its real-time requirements, decentralization, and connectivity through wireless networks. New research on edge computing and tiny machine learning (tinyML) explores the execution of AI models on low-performance devices to address these issues. However, there are not many studies proposing agnostic architectures that manage the entire lifecycle of intelligent cyberphysical systems. This article extends a previous architecture based on FIWARE software components to implement the machine learning operations flow, enabling the management of the entire tinyML lifecycle in cyberphysical systems. We also provide a use case to showcase how to implement the FIWARE architecture through a complete example of a smart traffic system. We conclude that the FIWARE ecosystem constitutes a real reference option for developing tinyML and edge computing in cyberphysical systems.


  • Open Access

    Designing Metadata for the Use of Artificial Intelligence in Academia

    by Javier Conde, Gonzalo Martínez, Pedro Reviriego, Joaquín Salvachúa, José Alberto Hernández

    Academic writing is one of the most important tasks in Academia. The pressure to "publish or perish" drives researchers to use all the tools available to try to improve their papers and their impact. Generative artificial intelligence (AI) that can create content such as text, tables, and images can be used for many tasks in academic writing such as summarizing, translating, paraphrasing, data analysis, and presentation. Therefore, AI is expected to be widely used in academic writing in the near future and have a significant impact. Understanding this impact is far from trivial and needs to be carefully studied. The first step in doing so is to be able to identify papers written with the help of AI tools. This can be done by adding metadata on the use of AI in academic results. In this paper, we embark on an initial endeavor to devise such metadata and delineate the potential advantages that the inclusion of AI-related metadata in academic publications may bring forth.


  • Understanding the Impact of Artificial Intelligence in Academic Writing: Metadata to the Rescue

    by Javier Conde, Pedro Reviriego, Joaquín Salvachúa, Gonzalo Martínez, José Alberto Hernández, Fabrizio Lombardi

    This column advocates for including artificial intelligence (AI)-specific metadata on those academic papers that are written with the help of AI in an attempt to analyze the use of such tools for disseminating research.


  • Collaboration of Digital Twins Through Linked Open Data: Architecture With FIWARE as Enabling Technology

    by Javier Conde, Andres Munoz-Arcentales, Alvaro Alonso, Gabriel Huecas, Joaquin Salvachua

    The collaboration of the real world and the virtual world, known as Digital Twin, has become a trend with numerous successful use cases. However, there are challenges mentioned in the literature that must be addressed. One of the most important issues is the difficulty of collaboration of Digital Twins due to the lack of standardization in their implementation. This article continues a previous work that proposed a generic architecture based on the FIWARE components to build Digital Twins in any field. Our work proposes the use of Linked Open Data as a mechanism to facilitate the communication of Digital Twins. We validate our proposal with a use case of an urban Digital Twin that collaborates with a parking Digital Twin. We conclude that Linked Open Data in combination with the FIWARE ecosystem is a real reference option to deploy Digital Twins and to enable the collaboration between Digital Twins.


  • Educational Data Virtual Lab: Connecting the Dots Between Data Visualization and Analysis

    by Sonsoles Lopez-Pernas, Andres Munoz-Arcentales, Carlos Aparicio, Enrique Barra, Aldo Gordillo, Joaquin Salvachua, Juan Quemada

    Educational Data Virtual Lab (EDVL) is an open-source platform for data exploration and analysis that combines the power of a coding environment, the convenience of an interactive visualization engine, and the infrastructure needed to handle the complete data lifecycle. Based on the building blocks of the FIWARE European platform and Apache Zeppelin, this tool allows domain experts to become acquainted with data science methods using the data available within their own organization, ensuring that the skills they acquire are relevant to their field and driven by their own professional goals. We used EDVL in a pilot study in which we carried out a focus group within a multinational company to gain insight into potential users’ perceptions of EDVL, both from the educational and operational points of view. The results of our evaluation suggest that EDVL holds a great potential to train the workforce in data science skills and to enable collaboration among professionals with different levels of expertise.


  • Open Access

    Enabling Context-Aware Data Analytics in Smart Environments: An Open Source Reference Implementation

    by Andres Munoz-Arcentales, Sonsoles López-Pernas, Javier Conde, Álvaro Alonso, Joaquín Salvachúa, Juan José Hierro

    In recent years, many proposals of context-aware systems applied to IoT-based smart environments have been presented in the literature. Most previous works provide a generic high-level structure of how a context-aware system can be operationalized, but do not offer clues on how to implement it. On the other hand, there are many implementations of context-aware systems applied to specific IoT-based smart environments that are context-specific: it is not clear how they can be extended to other use cases. In this article, we aim to provide an open-source reference implementation for providing context-aware data analytics capabilities to IoT-based smart environments. We rely on the building blocks of the FIWARE ecosystem and the NGSI data standard, providing an agnostic end-to-end solution that considers the complete data lifecycle, covering from data acquisition and modeling, to data reasoning and dissemination. In other words, our reference implementation can be readily operationalized in any IoT-based smart environment regardless of its field of application, providing a context-aware solution that is not context-specific. Furthermore, we provide two example use cases that showcase how our reference implementation can be used in a variety of fields.