Browsing by Keyword "Information Systems"
Now showing 1 - 20 of 155
Results Per Page
Sort Options
Item 3D convolutional neural networks initialized from pretrained 2D convolutional neural networks for classification of industrial parts(2021-02-04) Merino, Ibon; Azpiazu, Jon; Remazeilles, Anthony; Sierra, Basilio; ROBOTICA_FLEX; Medical TechnologiesDeep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone.Item ADAPTATION TO FLOODING EVENTS THROUGH VULNERABILITY MAPPING IN HISTORIC URBAN AREAS(2018-03-06) Gandini, Alessandra; Prieto, Iñaki; Garmendia, Leire; San-José, José Tomás; Egusquiza, Aitziber; LABORATORIO DE TRANSFORMACIÓN URBANA; Tecnalia Research & InnovationHistoric urban areas are complex and inter-reliant systems, vulnerable to natural hazards. Over the recent years, the increase frequency in extreme precipitation events and sea-level rise, have impacted on a large number of historic areas, growing concern over disaster mitigation related to climate change. Most of the changes in the climatological indicators may have adverse impacts on historic areas, leading to physical, social and cultural consequences and should be included in urban planning practice. The importance of addressing cultural heritage in disaster risk has also been included in The Sendai Framework, considering the dimensions of vulnerability, adaptive capacity and exposure through systematic evaluation. Urban planning decisions involve an understanding of complex interactions between different aspects of the city, in its constructive, social, economic, environmental and cultural system. The analysis of these interactions requires a systemic approach as the components operate on different spatial and temporal scales and generate a large amount of data. This information can be used to determine the vulnerability of historic areas by assessing it at the building level, through the creation of typologies representing the building stock, often characterized by similarities and common constructive elements. The comprehension of the information can be supported and homogenized by a multi-scale urban model, to facilitate the understanding of interactions and the link among the different disciplines involved. This paper describes the methodology proposed for vulnerability mapping in historic urban areas, by using a categorization method supported by an information strategy and a multiscale urban model.Item Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions(2021-11) Diez-Olivan, Alberto; Ortego, Patxi; Ser, Javier Del; Landa-Torres, Itziar; Galar, Diego; Camacho, David; Sierra, Basilio; Tecnalia Research & Innovation; IAIndustrial prognosis refers to the prediction of failures of an industrial asset based on data collected by Internet of Things sensors. Prognostic models can experience the undesired effects of concept drift, namely, the presence of nonstationary phenomena that affects the data collected over time. Consequently, fault patterns learned from data become obsolete. To overcome this issue, contextual and operational changes must be detected and managed, triggering rapid model adaptation mechanisms. This article presents an adaptive learning approach based on a dendritic cell algorithm for drift detection and a deep neural network model that dynamically adapts to new operational conditions. A kernel density estimator with drift-based bandwidth is used to generate synthetic data for a faster adaptation, focusing on fine-tuning the lowest neural layers. Experimental results over a real-world industrial problem shed light on the outperforming behavior of the proposed approach when compared to other drift detectors and classification models.Item Advanced IC tools for maximising virtual team creativity and innovation in manufacturing environments(Institute of Electrical and Electronics Engineers Inc., 2007) Sorli, Mikel; Stokic, Dragan; Mendikoa, Íñigo; Armijo, Alberto; Tecnalia Research & InnovationDuring the last years (basically since 1999), the author and his research team are and have been involved in several research projects within the Held of Product Life-Cycle Knowledge Management in the manufacturing domain. The key idea behind these projects is to develop means supporting the collection of all useful knowledge on product and process throughout the extended enterprise, all along the product Life-Cycle from Conception to Disposal and eventual Reuse. Keeping and re-using knowledge is of capital importance for the companies' competitivity to be used in continuous improvement of existing product/processes as well as in new developments. In a further step, the knowledge will then be developed into a means of fostering industrial innovations. Innovation is a critical factor in the success of manufacturing companies and it will mainly arise by combining ideas and feedback from all phases of the product life cycle.Item The AFarCloud ECSEL Project(IEEE, 2019-10) Castillejo, Pedro; Curuklu, Baran; Fresco, Roberto; Johansen, Gorm; Bilbao-Arechabala, Sonia; Martinez-Rodriguez, Belen; Pomante, Luigi; Martinez-Ortega, Jose-Fernan; Santic, Marco; Konofaos, Nikos; Kitsos, Paris; Tecnalia Research & Innovation; BIGDATAFarming is facing many economic challenges in terms of productivity and cost-effectiveness. Labor shortage partly due to depopulation of rural areas, especially in Europe, is another challenge. Domain specific problems such as accurate identification and proper quantification of pathogens affecting plant and animal health are key factors for minimizing economical risks, and not risking human health. The ECSEL AFarCloud (Aggregate FARming in the CLOUD) project will provide a distributed platform for autonomous farming that will allow the integration and cooperation of agriculture Cyber Physical Systems in real-time in order to increase efficiency, productivity, animal health, food quality and reduce farm labour costs. This platform will be integrated with farm management software and will support monitoring and decision-making solutions based on big data and real-time data mining techniques.Item Affect-aware behaviour modelling and control inside an intelligent environment(2010-10) Leon, Enrique; Clarke, Graham; Callaghan, Victor; Doctor, Faiyaz; Tecnalia Research & InnovationThe evidence suggests that human actions are supported by emotional elements that complement logic inference in our decision-making processes. In this paper an exploratory study is presented providing initial evidence of the positive effects of emotional information on the ability of intelligent agents to create better models of user actions inside smart-homes. Preliminary results suggest that an agent incorporating valence-based emotional data into its input array can model user behaviour in a more accurate way than agents using no emotion-based data or raw data based on physiological changes.Item Ambient intelligence based system for life-cycle management of complex manufacturing and assembly lines(Institute of Electrical and Electronics Engineers Inc., 2007) Stokic, Dragan; Neves-Silva, Rui; Marques, Maria; Reimer, Philip; Ibarbia, Jon Agirre; GENERALThe key idea of the work presented is to explore how a combination of advanced Ambient Intelligence (AmI) and Knowledge Management (KM) technologies can be used to assure a sustainable and safe use of Manufacturing and Assembly Lines (MAL) and their infrastructure over their life-cycle. The specific intention is to reduce the whole service-life operational costs and impact of MAL, providing new ways to monitor on-line Life-Cycle Parameters (LCP) of MAL and improved services to support MAL throughout its whole life-cycle. The paper presents a new system for effective life cycle management of complex MAL, including computation of LCP based on information obtained from AmI systems within MAL, and delivery of improved services around MAL.Item Analysing Edge Computing Devices for the Deployment of Embedded AI(2023-12) Garcia-Perez, Asier; Miñón, Raúl; Torre-Bastida, Ana I.; Zulueta-Guerrero, Ekaitz; HPAIn recent years, more and more devices are connected to the network, generating an overwhelming amount of data. This term that is booming today is known as the Internet of Things. In order to deal with these data close to the source, the term Edge Computing arises. The main objective is to address the limitations of cloud processing and satisfy the growing demand for applications and services that require low latency, greater efficiency and real-time response capabilities. Furthermore, it is essential to underscore the intrinsic connection between artificial intelligence and edge computing within the context of our study. This integral relationship not only addresses the challenges posed by data proliferation but also propels a transformative wave of innovation, shaping a new era of data processing capabilities at the network’s edge. Edge devices can perform real-time data analysis and make autonomous decisions without relying on constant connectivity to the cloud. This article aims at analysing and comparing Edge Computing devices when artificial intelligence algorithms are deployed on them. To this end, a detailed experiment involving various edge devices, models and metrics is conducted. In addition, we will observe how artificial intelligence accelerators such as Tensor Processing Unit behave. This analysis seeks to respond to the choice of a device that best suits the necessary AI requirements. As a summary, in general terms, the Jetson Nano provides the best performance when only CPU is used. Nevertheless the utilisation of a TPU drastically enhances the results.Item Analysis of the Refined Mean-Field Approximation for the 802.11 Protocol Model(2022-11) Ispizua, Begoña; Doncel, Josu; IAMean-field approximation is a method to investigate the behavior of stochastic models formed by a large number of interacting objects. A new approximation was recently established, i.e., the refined mean-field approximation, and its high accuracy when the number of objects is small has been shown. In this work, we consider the model of the 802.11 protocol, which is a discrete-time model and show how the refined mean-field approximation can be adapted to this model. Our results confirm the accuracy of the refined mean-field approximation when the model with N objects is in discrete time.Item AnHitz, development and integration of language, speech and visual technologies for Basque(2008) Arrieta, Kutz; Leturia, Igor; Iturraspe, Urtza; De Ilarraza, Arantza Diaz; Sarasola, Kepa; Hernáez, Inma; Navas, Eva; HPAAnHitz is a project promoted by the Basque Government to develop language technologies for the Basque language. The participants in AnHitz are research groups with very different backgrounds: text processing, speech processing and multimedia. The project aims to further develop existing language, speech and visual technologies for Basque: up to now its fruit is a set of 7 different language resources, 9 NLP tools, and 5 applications.. But also, in the last year of this project we are integrating, for the first time, such resources and tools (both existing and generated in the project) into a content management application for Basque with a natural language communication interface. This application consists of a Question Answering and a Cross Lingual Information Retrieval system on the area of Science and Technology. The interaction between the system and the user will be in Basque (the results of the CLIR module that are not in Basque will be translated through Machine Translation) using Speech Synthesis, Automatic Speech Recognition and a Visual Interface. The various resources, technologies and tools that we are developing are already in a very advanced stage, and the implementation of the content management application to integrate them all is in work and is due to be completed by October 2008.Item Architecting SOA solutions from enterprise models: A model driven framework to architect SOA solutions from enterprise models(2006) Larrucea, Xabier; Benguria, Gorka; Tecnalia Research & Innovation; HPAThe improvement of the operational efficiency is an important concern in the several kinds of enterprises, but it involves the management of a multitude of elements. To be able to cope with such as complexity several enterprises are relaying in the use of enterprise modelling tools. This usually becomes a starting point for business process automation initiatives towards the improvement of the organisation. However, there is still a large gap from these enterprise models to the infrastructure systems. The current paper presents a MDA (Model Driven Architectures) framework over eclipse platform to address this gap for SOA (Service Oriented Architecture) based solutions and more in deep the notation and transformation aspects of the framework. The framework provides a systematic approach for deriving SOA solutions from enterprises models, ensuring that the information systems really implements the models developed by the business experts and no partial interpretations from IT experts.Item Assurance and certification of cyber–physical systems: The AMASS open source ecosystem(2021-01) de la Vara, Jose Luis; Ruiz, Alejandra; Blondelle, Gaël; QuantumMany cyber–physical systems (CPS) are subject to rigorous assurance and certification processes to provide confidence that undue risks are not posed and thus the systems are trustworthy. These processes are complex and time-consuming and tool support can greatly aid in their execution. In line with other trends for systems and software engineering, the need for and interest in open source tools for assurance and certification is growing and different initiatives have been launched. As a concrete example, we report on our experience in developing the AMASS open source ecosystem. This ecosystem includes (1) an open source tool platform that supports the main CPS assurance and certification activities, (2) external tools with added-value features, and (3) an open community of developers and users. The platform integrates existing solutions for system modelling, process engineering, and compliance and argumentation management. We also present the application of the AMASS tool platform in 11 industrial case studies from five different application domains. The results show that the platform is a feasible means for CPS assurance and certification and that practitioners find benefits in assurance-oriented system modelling and in integrated system assurance information, among other areas. Nonetheless, improvement opportunities also exist, most notably regarding tool interoperability and usability.Item Blockchain-based refurbishment certification system for enhancing the circular economy(2024-03) Regueiro, Cristina; Gómez-Goiri, Aitor; Pedrosa, Nuno; Semertzidis, Christos; Iturbe, Eider; Mansell, Jason; CIBERSEC&DLTAs the global population continues to grow, the enormous stress on our environment and resources is becoming impossible to ignore. A focus on producing and consuming as cheaply as possible has created an economy in which objects are briefly used and then discarded as waste, featuring a linear lifecycle that creates an enormous amount of waste. The alternative to the linear economy “take-make-waste” is called the “circular economy”. Under this paradigm, materials are recycled to build new products or components that are designed and built to promote their reuse and refurbishment. This assures the continuous (re-)exploitation of existing resources, reducing the extraction of new raw materials. However, customers often reject these reused or refurbished products under the suspicion that they do not meet the same usability, safety, or performance levels of new products. In this sense, trustworthy records of historical details of refurbished products could increase consumers’ confidence in products and components of the “circular economy”, prioritizing trustworthiness, reliability, and transparency. This work presents a new certification tool based on blockchain technology to guarantee trusted, accurate, transparent, and traceable lifecycle information of products and their components and to generate trustworthy certificates to probe refurbished product historical details. This tool aims to enhance refurbished product visibility by creating the basis for making the circular economy a reality in any domain.Item Blockchain-Based Threat Registry Platform(Institute of Electrical and Electronics Engineers Inc., 2019-10) De DIego, Santiago; Goncalves, Carlos; Lage, Oscar; Mansell, Jason; Kontoulis, Michael; Moustakidis, Serafeim; Guerra, Barbara; Liapis, Angelos; Chakrabarti, Satyajit; Saha, Himadri Nath; CIBERSEC&DLTThis document presents a reference architecture for a Blockchain-based Threat Registry platform, named BBTR, to share information about treats among different actors. The design of the BBTR guarantees integrity and availability of the data stored in it and is also compatible with privacy requirements, allowing different actors to participate as users of this shared BaaS (Blockchain as a Service). The paper also shows how this approach can be combined with AI techniques to extract valuable information from the threats directly from the Blockchain, empowering the final solution with a decision-making engine. It also includes its validation in a use case in the Health care domain.Item A Bluetooth sensor network based on the IEEE 1451 standard: A sensor network solution to evaluate the wellbeing of the passenger and improve safety in cars(2010) Larrauri, Jesus Murgoitio; Larrinaga, Beñat Arejita; Lopez, Maider Larburu; Cubillo, Javier Sanchez; CCAM; POWERTRAIN; Tecnalia Research & InnovationThe use of sensors is very widespread in a lot of different environments and applications. Each situation needs a different solution and for that reason the use of a scalable and easily manageable sensor network is a must as applications are becoming increasingly complex. In many cases the perfect solution is the one based on a wireless sensor network; it provides flexibility, ease of management of the system and expandability. But in order to provide interoperability between different sensor manufacturers and to give a transparent and independent interface, the use of a standard is mandatory. This standard system is provided by the IEEE 1451 family of standard protocols. In this project a Bluetooth based sensor network has been implemented using the IEEE 1451 family of standard protocols. The goal of this network is to aid data acquisition from a number of sensors within a car, in order to monitor the wellbeing of the passengers and improve safety and comfort.Item Business process interoperability towards quality models(Springer International Publishing, 2012) Jaekel, Frank Walter; Benguria, Gorka; Tarsitano, Giuseppe; Aceto, Giacomo; HPAQuality models are in many domains an important mean to ensure the interoperability of the processes of the contracted organisation with the requirements of the contracting party. The syncronization of the organisation processes with the requirements of the quality model is in many cases a challeging activity, this is even more challenging in those situations where organisations have to deal with multiple development processed and multiple quality models at the same time. The FACIT SME project addresses SMEs operating in the ICT domain in the management of their development processes together with their quality models. The goals are to facilitate the use of Software Engineering (SE) methods and to systematize their application integrated with the business processes, to provide efficient and affordable certification of these processes according to internationally accepted standards, and to securely share best practices, tools and experiences with development partners and customers. The paper focuses on the interrelating of different methods and best practices to create a knowledge base not only for knowledge exchange but also to support its usage. A related interoperability challenge is the correlation between different models and a semantic approach to handle this correlation.Item Bypassing Current Limitations for Implementing a Credential Delegation for the Industry 4.0(Science and Technology Publications, Lda, 2022) de Diego, Santiago; Lage, Óscar; Regueiro, Cristina; Anguita, Sergio; Maciá-Fernández, Gabriel; De Capitani di Vimercati, Sabrina; Samarati, Pierangela; CIBERSEC&DLT; Tecnalia Research & InnovationIndustry 4.0 is set to modernize industrial processes as we know them today. This modernization goes hand in hand with the digitalization of industry and the need to digitally identify the different devices involved in the manufacturing process. Verifiable credentials and Decentralized Identifiers, which are part of the self-sovereign identity (SSI) concept, allow decentralized identification and characterization of the devices (commonly IIoT devices) that make up Industry 4.0. However, some use cases in the Industry 4.0 cannot be modelled with standard SSI schemes. Despite the fact that delegated credentials have been defined in the W3C standard for verifiable credentials, current technologies present some important limitations that make them non-implementable. This paper analyses these limitations in the context of the problem of building delegated credentials for the Industry 4.0, and proposes an alternative based on an Hyperledger Aries RFC, bypassing these limitations. Finally, some implementation tests have been conducted in order to demonstrate that the Aries RFC does not add extra complexity in terms of performance to the normal SSI flow.Item Can Shared Control Improve Overtaking Performance? Combining Human and Automation Strengths for a Safer Maneuver(2022-12) Marcano, Mauricio; Tango, Fabio; Sarabia, Joseba; Chiesa, Silvia; Pérez, Joshué; Díaz, Sergio; CCAMThe Shared Control (SC) cooperation scheme, where the driver and automated driving system control the vehicle together, has been gaining attention through the years as a promising option to improve road safety. As a result, advanced interaction methods can be investigated to enhance user experience, acceptance, and trust. Under this perspective, not only the development of algorithms and system applications are needed, but it is also essential to evaluate the system with real drivers, assess its impact on road safety, and understand how drivers accept and are willing to use this technology. In this sense, the contribution of this work is to conduct an experimental study to evaluate if a previously developed shared control system can improve overtaking performance on roads with oncoming traffic. The evaluation is performed in a Driver-in-the-Loop (DiL) simulator with 13 real drivers. The system based on SC is compared against a vehicle with conventional SAE-L2 functionalities. The evaluation includes both objective and subjective assessments. Results show that SC proved to be the best solution for assisting the driver during overtaking in terms of safety and acceptance. The SC’s longer and smoother control transitions provide benefits to cooperative driving. The System Usability Scale (SUS) and the System Acceptance Scale (SAS) questionnaire show that the SC system was perceived as better in terms of usability, usefulness, and satisfaction.Item A case analysis of enabling continuous software deployment through knowledge management(2018-06) Colomo-Palacios, Ricardo; Fernandes, Eduardo; Soto-Acosta, Pedro; Larrucea, Xabier; Tecnalia Research & InnovationContinuous software engineering aims to accelerate software development by automating the whole software development process. Knowledge management is a cornerstone for continuous integration between software development and its operational deployment, which must be implemented using sound methodologies and solid tools. In this paper, the authors present and analyse a case study on the adoption of such practices by a software company. Results show that, beyond tools, knowledge management practices are the main enablers of continuous software engineering adoption and success.Item Cloud modernization assessment framework: Analyzing the impact of a potential migration to Cloud(2013) Alonso, Juncal; Orue-Echevarria, Leire; Escalante, Marisa; Gorroñogoitia, Jesús; Presenza, Domenico; HPA; Tecnalia Research & Innovation; CIBERSEC&DLTMany software companies have in mind jumping into the Cloud in order to take advantage of this technical paradigm as well as the innovative business models associated (such as SaaS). However, taking this leap becomes a hard task since it implies a high uncertainty and a raised risk without knowing when or even if the investment will be recovered. This paper presents the solution proposed by the ARTIST project to assess companies which are considering the migration of their products to Cloud, and provide estimations of the costs, ROI, efforts and migration tasks that this process could imply. The envisioned solution comprises a pre-migration phase through which 1) the maturity (to migrate to Cloud) of the application and the company will be measured, 2) a feasibility analysis both at technical and business level will be performed. In addition to the general approach of the proposed solution, this paper presents the first results obtained by means of a theoretical exercise conducted with the PetStore Java application.