SciTePress - Affiliation Profile

Affiliation

Select a Subject
Refine Ontology Subject

University of Cantabria, Spain

Context (please use complete words only)

Field

Sort by

17 Papers

Bridging AutoML and LLMs: Towards a Framework for Accessible and Adaptive Machine Learning

Topics: Accessibility and Usability; Models and Frameworks; Natural Language Interfaces to Intelligent Systems; Machine Learning in HCI

Authors: Rafael Duque ¹ , Cristina Tîrnăucă ¹ , Camilo Palazuelos ¹ , Abraham Casas ² , Alejandro López ² and Alejandro Pérez ²

Affiliations: ¹ Department of Mathematics Statistics and Computer Science, University of Cantabria, Avenida de los Castros S/N, Santander, Spain , ² Centro Tecnológico CTC, Parque Científico y Tecnológico de Cantabria, Santander, Spain

Digital Object Identifier: 10.5220/0013448500003929

Proceedings of ICEIS 2025, ISBN: 978-989-758-749-8

Quick Abstract

This paper introduces a framework architecture that integrates Automated Machine Learning with Large Language Models to facilitate machine learning tasks for non-experts. The system leverages natural language processing to help users describe datasets, define problems, select models, refine results through iterative feedback, and manage the deployment and ongoing maintenance of models in production environments. By simplifying complex machine learning processes and ensuring the continued performance and usability of deployed models, this approach empowers users to effectively apply machine learning solutions without deep technical knowledge.

Automating the Customization of Model-Driven Software Engineering Environments

Topics: Workflow Management Systems; Domain-Specific Modeling; Frameworks for Model-Driven Development; Software Process Modeling, Enactment and Execution

Authors: César Cuevas Cuesta , Patricia López Martínez and José M. Drake

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0006130903370344

Proceedings of MODELSWARD 2017, ISBN: 978-989-758-210-3

Quick Abstract

This paper presents a strategy to facilitate the customization of MDSE software development environments, which aims at providing the software engineers who design, implement and maintain those environments with capacity to automate the generation of tools supporting new development processes. A generic conception for the design of software development environments based on the MDSE paradigm, called MDDE (Model-Driven Development Environment), has been defined as basis of the proposed strategy. In MDDE, the definition of the processes that determine the functionality of an environment as well as their options regarding interaction, supervision and control by the users are completely formulated as models. To support this capability, the MDDE reference model includes a meta-model that formalizes such models. A sample implementation called MDDE-MinMAST2 is presented for illustrative purposes.

Related Ontology Subjects/Areas/Topics (13)

Business and Social Applications	Languages, Tools and Architectures	Software Engineering
Domain-Specific Modeling and Domain-Specific Languages	Methodologies, Processes and Platforms	Software Process Modeling, Enactment and Execution
e-Business	Model-Driven Software Development	Web Information Systems and Technologies
Enterprise Information Systems	Society, e-Business and e-Government	Workflow Management Systems
Frameworks for Model-Driven Development

Automating the Construction of Models based on Domain Views

Topics: Domain-Specific Modeling; Model Transformations and Generative Approaches; Frameworks for Model-Driven Development

Authors: César Cuevas Cuesta , Patricia López Martínez and José M. Drake

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0005688202410249

Proceedings of MODELSWARD 2016, ISBN: 978-989-758-168-7

Quick Abstract

This work addresses the automatic generation of the resources required for the assisted creation of domain models according to specialized views of their meta-model. The task of a designer who builds models compliant to a complex domain meta-model is eased if the model editor requests the information according to a specific view of the meta-model based on the conceptualization or the specific construction strategy that the designer uses. With that aim, this work presents 1) the meta-model with which a domain expert formulates the model creation strategy that he envisions, 2) the tool that, from that strategy information, generates the meta-model that drives data introduction and 3) the M2M transformation that generates the final model compliant to the original domain meta-model and that contains the newly introduced data.

Related Ontology Subjects/Areas/Topics (7)

Domain-Specific Modeling and Domain-Specific Languages	Methodologies, Processes and Platforms	Model-Driven Software Development
Frameworks for Model-Driven Development	Model Transformations and Generative Approaches	Software Engineering
Languages, Tools and Architectures

Model-driven Approach for Verifying Conformity of Models in the Presence of Constraints

Topics: Domain-Specific Modeling; Model Transformations and Generative Approaches; Frameworks for Model-Driven Development

Authors: César Cuevas Cuesta , Patricia López Martínez and José M. Drake

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0005744504550466

Proceedings of MODELSWARD 2016, ISBN: 978-989-758-168-7

Quick Abstract

This paper presents a model-driven approach for the systematic development of tools for checking the conformity of models when the domain formalization does not only consist of a meta-model but also on a set of constraints enhancing it. The strategy is built on top of the idea of representing the result of the verification as a model which gathers all the constraint violations found in the model, formulating them in a way that allows their later detailed manifestation, automatic correction or any other potential processing. With that aim, a meta-model for supporting those models describing constraints violations has been designed. The verification is applied by means of an M2M transformation that takes as input the model to verify and generates a model conforming to the designed meta-model. This methodology constitutes the way to accomplish the final objective: designing a strategy for the development of a generic tool for verification, regardless any particular meta-model or constraints set. This is performed through the duality of a model transformation as a processing program but also as a processed artefact (model), by means of the Higher Order Transformation (HOT) technique.

Related Ontology Subjects/Areas/Topics (7)

Domain-Specific Modeling and Domain-Specific Languages	Methodologies, Processes and Platforms	Model-Driven Software Development
Frameworks for Model-Driven Development	Model Transformations and Generative Approaches	Software Engineering
Languages, Tools and Architectures

Fault Modeling of Implantable MEMS Sensors

Topics: Biomedical Sensors; Implantable Electronics; MEMS; Biomechanical Devices

Authors: Jose A. Miguel , Y. Lechuga , M. Martinez and J. R. Berrazueta

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0005278801620167

Proceedings of BIODEVICES 2015/BIOSTEC, ISBN: 978-989-758-071-0

Quick Abstract

The aim of this work is to analyse the fault-injection problem of implantable capacitive micro-electro-mechanical pressure sensors intended to be used as a part of smart stents for in-stent restenosis monitoring. The development of accurate fault models is mandatory in order to create a Design-for-Test methodology compatible with MEMS-based sensors as well as with its related CMOS electronic circuitry. Rigorous behavioural descriptions of both circular and square-shaped fault-free pressure sensors can be obtained from analytical expressions and numerical approximations. However, the deflection vs. pressure response of faulty sensors, suffering from contamination-based defects growth during the fabrication process, require the use of finite-elements analysis to be modelled, allowing the fulfilment of a realistic fault model library.

Related Ontology Subjects/Areas/Topics (8)

Biomechanical Devices	Biomedical Sensors	MEMS
Biomedical Engineering	Hardware	Sensor Networks
Biomedical Instruments and Devices	Implantable Electronics

A Sharp Fitness Function for the Problem of Finding Roots of Polynomial Equations Systems

Topics: Genetic Algorithms; Evolution Strategies; Swarm/Collective Intelligence

Authors: Cruz E. Borges ¹ , José L. Montaña ² and Luis M. Pardo ²

Affiliations: ¹ Universidad de Deusto, Spain , ² Universidad de Cantabria, Spain

Digital Object Identifier: 10.5220/0005140002940301

Proceedings of ECTA 2014/IJCCI, ISBN: 978-989-758-052-9

Quick Abstract

We experiment with several evolutionary algorithms for solving systems of polynomial equations with real coefficients. As a main difference with previous work, our algorithms can certify the correctness of the solutions they provide. This achievement is made possible by incorporating results from the field of numerical analysis to their fitness functions. We have performed an experimental comparison between the various proposed algorithms. The results of this comparison show that evolutionary and other local search algorithms can deal with the problem of solving systems of polynomial equations even for systems having many variables and high degree. Our main contribution is a nontrivial fitness function adjusted to the problem to be solved. This function is not based on any heuristics but on the fundamentals of numerical computation.

Related Ontology Subjects/Areas/Topics (9)

Artificial Intelligence	Evolutionary Computing	Intelligent Control Systems and Optimization
Computational Intelligence	Genetic Algorithms	Soft Computing
Evolution Strategies	Informatics in Control, Automation and Robotics	Swarm/Collective Intelligence

Analysis of Fault Injection in Implantable Capacitive Blood-pressure Sensors

Topics: Biomedical Sensors; Microelectronics; Implantable Electronics; MEMS

Authors: J. A. Miguel , Y. Lechuga and M. Martinez

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0004241701530158

Proceedings of BIODEVICES 2013/BIOSTEC, ISBN: 978-989-8565-34-1

Quick Abstract

This work explores the fault injection problem in the particular case of an implantable capacitive micro-electromechanical pressure sensor for blood-flow measurement applied to the detection of in-stent restenosis. In order to develop a MEMS testing method for this sensor and its related electronic circuitry, an accurate and realistic fault model is essential. A behavioural description of the equivalent capacitance in the fault-free case can be obtained from the analytical and numerical solutions of the deflection of a circular diaphragm under a uniformly distributed pressure. However, the deflection problem for faulty conditions due to, for example, contamination-based defects or partially released structures must be solved and modelled using finite-element analysis.

Related Ontology Subjects/Areas/Topics (8)

Biomedical Engineering	Hardware	Microelectronics
Biomedical Instruments and Devices	Implantable Electronics	Sensor Networks
Biomedical Sensors	MEMS

Model Complexity Control in Straight Line Program Genetic Programming

Topics: Genetic Algorithms; Machine Learning; Evolution Strategies

Authors: César L. Alonso ¹ , José Luis Montaña ² and Cruz Enrique Borges ³

Affiliations: ¹ Universidad de Oviedo, Spain , ² Universidad de Cantabria, Spain , ³ Universidad de Deusto, Spain

Digital Object Identifier: 10.5220/0004554100250036

Proceedings of ECTA 2013/IJCCI, ISBN: 978-989-8565-77-8

Quick Abstract

In this paper we propose a tool for controlling the complexity of Genetic Programming models. The tool is supported by the theory of Vapnik-Chervonekis dimension (VCD) and is combined with a novel representation of models named straight line program. Experimental results, implemented on conventional algebraic structures (such as polynomials) and real problems, show that the empirical risk, penalized by suitable upper bounds for the Vapnik-Chervonenkis dimension, gives a generalization error smaller than the use of statistical conventional techniques such as Bayesian or Akaike information criteria.

Related Ontology Subjects/Areas/Topics (12)

Artificial Intelligence	Genetic Algorithms	Knowledge-Based Systems
Computational Intelligence	Informatics in Control, Automation and Robotics	Machine Learning
Evolution Strategies	Intelligent Control Systems and Optimization	Soft Computing
Evolutionary Computing	Knowledge Discovery and Information Retrieval	Symbolic Systems

BEHAVIOURAL ANALYSIS OF AN IMPLANTABLE FLOW AND PRESSURE SENSING DEVICE

Topics: Biomedical Sensors; Health Monitoring Devices; Implantable Electronics

Authors: J. A. Miguel , R. Mozuelos and M. Martinez

Affiliation: University of Cantabria, Spain

Digital Object Identifier: 10.5220/0003873902690273

Proceedings of BIODEVICES 2012/BIOSTEC, ISBN: 978-989-8425-91-1

Quick Abstract

This paper presents a simplified MatLab model of an implantable device for pulmonary artery blood flow velocity measurement. A comparative review of the most popular blood flow measurement techniques has been carried out, showing the better suitability of pressure-sensing approaches to provide useful information to cardiovascular diseases monitorization. Different possible grades of stenosis in the pulmonary artery have been simulated in order to obtain an early estimation of the device behavior under real conditions.

Related Ontology Subjects/Areas/Topics (8)

Biomedical Engineering	Devices	Implantable Electronics
Biomedical Instruments and Devices	Health Monitoring Devices	Physiological Computing Systems
Biomedical Sensors	Human-Computer Interaction

FILTERING ASSOCIATION RULES WITH NEGATIONS ON THE BASIS OF THEIR CONFIDENCE BOOST

Topics: Data Reduction and Quality Assessment; Pre-Processing and Post-Processing for Data Mining

Authors: José L. Balcázar , Cristina Tîrnăucă and Marta E. Zorrilla

Affiliation: Universidad de Cantabria, Spain

Digital Object Identifier: 10.5220/0003095802630268

Proceedings of KDIR 2010/IC3K, ISBN: 978-989-8425-28-7

Quick Abstract

We consider a recent proposal to filter association rules on the basis of their novelty: the confidence boost. We develop appropriate mathematical tools to understand it in the presence of negated attributes, and explore the effect of applying it to association rules with negations. We show that, in many cases, the notion of confidence boost allows us to obtain reasonably sized output consisting of intuitively interesting association rules with negations.

Related Ontology Subjects/Areas/Topics (6)

Artificial Intelligence		Knowledge Discovery and Information Retrieval		Pre-Processing and Post-Processing for Data Mining
Data Reduction and Quality Assessment		Knowledge-Based Systems		Symbolic Systems

Context (please use complete words only)

Field

Sort by

Topic(s):

Filter listed results, by

Publication date

From:

To:

Author

Locate Author in list below

Data pager
Data pager
1 2 3 4 5 Page 1 of 5, items 1 to 10 of 45.

Add Author(s) to filter:

Cruz Borges (3)

Patricia López Martínez (3)

José Luis Montaña (3)

César L. Alonso (3)

José Drake (3)

J. A. Miguel (3)

M. Martinez (3)

Cesar Cuesta (3)

Marta Zorrilla (2)

Y. Lechuga (2)

Conference

Locate Conference in list below

Data pager
Data pager
1 2 Page 1 of 2, items 1 to 10 of 11.

Add Conference(s) to filter:

BIODEVICES(3)

MODELSWARD(3)

WEBIST(2)

ICEC(2)

ICEIS(1)

ICINCO(1)

ICSOFT(1)

CSEDU(1)

ECTA(1)

FCTA(1)

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject: