Skip to main content

INGENIERIA DEL SOFTWARE AVANZADA PARA LA CONSTRUCCION DE SISTEMAS Y MICROSERVICIOS AUTO-ADAPTATIVOS. INCLUYENDO TECNICAS DE IA Y DE HUMANS-IN-THE-LOOP

PID2020-114480RB-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2020
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Modelling and executing IoT-enhanced business processes through BPMN and microservices

  • Valderas, Pedro|||0000-0002-4156-0675
  • Torres Bosch, Maria Victoria|||0000-0002-2039-2174
  • Serral Asensio, Estefanía
[EN] The Internet of Things enables to connect the physical world to digital business processes (BP) and allows a BP to (1) consider real-world data to take more informed business decisions, (2) automate and/or improve BP tasks, and (3) adapt itself to the physical execution environment. We refer to these processes as IoT-enhanced BPs. Although numerous researchers have studied this subject, there are still some challenges to be faced. For instance, the need of a modelling solution that does not increase the notation complexity to facilitate further analysis and engineering decision making, or an execution approach that provides a high degree of independence between the process and the underlying IoT device technology. The objective of this work is defining an approach that (1) considers important intrinsic characteristics of IoT-enhanced BPs at modelling level without growing the complexity of the modelling language, and (2) facilitates the execution of the IoT-enhanced BPs represented in models independently from IoT devices' technology. To do so, we present a modelling approach that uses standard BPMN concepts to model IoT-enhanced BPs without modifying its metamodel. It applies the Separation of Concern (SoC) design principle: BPMN is used to describe IoT-enhanced BPs while low-level real-world data is captured in an ontology. Finally, a microservice architecture is proposed to execute BPMN models and facilitate its integration with the physical world. This architecture provides high flexibility to support multiples IoT device technologies as well as their evolution and maintenance. The evaluation done allows us to conclude that the application of the SoC principle using BPMN and ontologies facilitates the definition of intrinsic characteristics of IoT-enhanced BPs without increasing the complexity of the BPMN metamodel. Besides, the proposed microservice architecture provides a high degree of decoupling between the created models and the underlying IoT technology. (C) 2021 Published by Elsevier Inc., This work is part of the R&D&I project PID2020-114480RB-I00 funded by MCIN/AEI/10.13039/501100011033
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Recognition of Human Actions through Speech or Voice Using Machine Learning Techniques

  • Peña-Cáceres, Oscar
  • Silva-Marchan, Henry
  • Gil, Miriam
  • Albert Albiol, Manuela|||0000-0003-3747-400X
[EN] The development of artificial intelligence (AI) and smart home technologies has driven the need for speech recognition-based solutions. This demand stems from the quest for more intuitive and natural interaction between users and smart devices in their homes. Speech recognition allows users to control devices and perform everyday actions through spoken commands, eliminating the need for physical interfaces or touch screens and enabling specific tasks such as turning on or off the light, heating, or lowering the blinds. The purpose of this study is to develop a speech-based classification model for recognizing human actions in the smart home. It seeks to demonstrate the effectiveness and feasibility of using machine learning techniques in predicting categories, subcategories, and actions from sentences. A dataset labeled with relevant information about categories, subcategories, and actions related to human actions in the smart home is used. The methodology uses machine learning techniques implemented in Python, extracting features using CountVectorizer to convert sentences into numerical representations. The results show that the classification model is able to accurately predict categories, subcategories, and actions based on sentences, with 82.99% accuracy for category, 76.19% accuracy for subcategory, and 90.28% accuracy for action. The study concludes that using machine learning techniques is effective for recognizing and classifying human actions in the smart home, supporting its feasibility in various scenarios and opening new possibilities for advanced natural language processing systems in the field of AI and smart homes., This work was supported by Generalitat Valenciana with HAAS (CIAICO/2021/03 9) and the Spanish Ministry of Science and Innovation under the Project AVANTIA PID2020-114480RB-I00.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

FloBP: a model-driven approach for developing and executing IoT-enhanced business processes

  • Fedeli, Arianna
  • Fornari, Fabrizio
  • Polini, Andrea
  • Re, Barbara
  • Torres Bosch, Maria Victoria|||0000-0002-2039-2174
  • Valderas, Pedro|||0000-0002-4156-0675
[EN] The capability to integrate Internet of Things (IoT) technologies into business processes (BPs) has emerged as a transformative paradigm, offering unprecedented opportunities for organisations to enhance their operational efficiency and productivity. Interacting with the physical world and leveraging real-world data to make more informed business decisions is of greatest interest, and the idea of IoT-enhanced BPs promises to automate and improve business activities and permit them to adapt to the physical environment of execution. Nonetheless, combining these two domains is challenging, and it requires new modelling methods that do not increase notation complexity and provide independent execution between the process and the underlying device technology. In this work, we propose FloBP, a model-driven engineering approach separating concerns between the IoT and BPs, providing a structured and systematic approach to modelling and executing IoT-enhanced BPs. Applying the separation of concerns through an interdisciplinary team is needed to ensure that the approach covers all necessary process aspects, including technological and modelling ones. The FloBP approach is based on modelling tools and a microservices architecture to deploy BPMN models, and it facilitates integration with the physical world, providing flexibility to support multiple IoT device technologies and their evolution. A smart canteen scenario describes and evaluates the approach's feasibility and its possible adoption by various stakeholders. The performed evaluation concludes that the application of FloBP facilitates the modelling and development of IoT-enhanced BPs by sharing and reusing knowledge among IoT and BP experts., The research underlying this paper has been partially supported by the PNRR MUR Project ECS_00000041-VITALITY. Also, this work is part of the RDI Project PID2020-114480RB-I00 funded by MCIN/AEI/1013039/501100011033.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Microservice Compositions based on the choreography of BPMN fragments. Facing Evolution Issues

  • Ortiz-Amaya, Jesús|||0000-0002-9352-1045
  • Torres Bosch, Maria Victoria|||0000-0002-2039-2174
  • Valderas, Pedro|||0000-0002-4156-0675
[EN] Business Processes (BPs) are commonly used by organizations to describe their goals. However, the existent decentralization found in many organizations forces them to build such BPs by coordinating distributed and fragmented BPs. Within this context, microservices arise as a very interesting and convenient way to address the implementation of such processes due to their low coupling characteristic. In this case, the coordination of such fragmented BPs is usually achieved by means of event-based choreographies. One of the main challenges to be faced by choreographies is their evolution due to the complexity that introduces the need of integrating changes among autonomous and independent partners. We face the challenge of evolving a microservice composition that is globally defined in a BPMN model but executed through a choreography of BPMN fragments. We introduce a protocol to manage the propagation of a change done by one microservice to be integrated into both the BPMN fragments of the rest of the microservices and the global BPMN model. This protocol also supports the negotiation among participants and the automatic suggestion of model adaptations to maintain the functional integrity of the composition. These suggestions are supported by a catalogue of adaptation rules that precisely characterize every possible change and propose actions to be considered by the affected microservices. All the evolution process is done at the modelling level, without managing hard-coded implementations. We have developed specific tools to facilitate the practical adoption of this protocol, and we have validated our work in an experiment with users. We can conclude that the proposed approach is effective to evolve microservice compositions implemented as event-based choreography of BPMN fragments from the local perspective of one partner., This work is part of the R&D&I project PID2020-114480RB-I00 funded by MCIN/AEI. It is also supported by the Research and Development Aid Program (PAID-01-21) of the UPV.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Towards an Interdisciplinary Development of IoT-Enhanced Business Processes

  • Valderas, Pedro|||0000-0002-4156-0675
  • Torres Bosch, Maria Victoria|||0000-0002-2039-2174
  • Serral Asensio, Estefanía
[EN] IoT-enhanced Business Processes make use of sensors and actuators to carry out the process tasks and achieve a specific goal. One of the most important difficulties in the development of IoT-enhanced BPs is the interdisciplinarity that is demanded by this type of project. Defining an interdisciplinary tool-supported development approach that facilitates the collaboration of different professionals, with a special focus on three main facets: business process requirements, interoperability between IoT devices and BPs, and low-level data processing. The study followed a Design Science Research methodology for information systems that consists of a 6-step process: (1) problem identification and motivation; (2) define the objectives for a solution; (3) design and development; (4) demonstration; (5) evaluation; and (6) communication. The paper presents an interdisciplinary development process to support the creation of IoT-enhanced BPs by applying the Separation of Concerns principle. A collaborative development environment is built to provide each professional with the tools required to accomplish her/his development responsibilities. The approach is successfully validated through a case-study evaluation. The evaluation allows to conclude that the proposed development process and the supporting development environment are effective to face the interdisciplinary nature of IoT-enhanced BPs., This work is part of the R&D&I project PID2020-114480RB-I00 funded by MCIN/AEI/1013039/501100011033. Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.