Pasar al contenido principal

SISTEMA ADAPTATIVO BIOINSPIRADO PARA EL CONTROL GLUCEMICO BASADO EN SENSORES Y ACCESORIOS INTELIGENTES

RTI2018-095180-B-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD COMPLUTENSE DE MADRID

Resultados relacionados

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

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

Particle swarm grammatical evolution for energy demand estimation

  • Martínez-Rodríguez, David|||0000-0002-2093-7840
  • Villanueva Micó, Rafael Jacinto|||0000-0002-0131-0532
  • Colmenar, J. Manuel
  • Hidalgo, J. Ignacio
  • Salcedo-Sanz, Sancho
[EN] Grammatical Swarm is a search and optimization algorithm that belongs to the more general Grammatical Evolution family, which works with a set of solutions called individuals or particles. It uses the Particle Swarm Optimization algorithm as the search engine in the evolution of solutions. In this paper, we present a Grammatical Swarm algorithm for total energy demand estimation in a country from macroeconomic variables. Each particle in the Grammatical Swarm encodes a different model for energy demand estimation, which will be decoded by a predefined grammar. The parameters of the model are also optimized by the proposed algorithm, in such a way that the model is adjusted to a training set of real energy demand data, selecting the more appropriate variables to appear in the model. We analyze the performance of the Grammatical Swarm evolution in two real problems of one-year ahead energy demand estimation in Spain and France. The proposal is compared with previous approaches with competitive results., Spanish Ministerial Commission of Science and Technology (MICYT), Grant/Award Number: TIN2017-85887-C2-2-P; Ministerio de Ciencia, Innovacion y Universidades, Grant/Award Number: PGC2018-095322-B-C22 and RTI2018-095180-B-I00; Comunidad de Madrid y Fondos Estructurales de la Union Europea, Grant/Award Number: S2018/TCS-4566 and Y2018/NMT-4668; GenObIA-CM, Grant/Award Number: S2017/BMD-3773; Ministerio de Economia, Industria y Competitividad, Grant/Award Number: MTM2017-89664-P
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Calibration of an agent-based simulation model to the data of women infected by Human Papillomavirus with uncertainty

  • Villanueva Micó, Rafael Jacinto|||0000-0002-0131-0532
  • Cortés, J.-C.|||0000-0002-6528-2155
  • Hidalgo, J.I.
  • Cervigon, Carlos
  • Villanueva-Oller, Javier
[EN] Recently, the transmission dynamics of the Human Papillomavirus (HPV) has been studied. In previous works, we have designed and implemented a computational model (agent-based simulation model) where the contagion of the HPV is described on a network of lifetime sexual partners. The run of a single simulation of this computational model, composed of a network with 500 000 nodes, takes about one hour and a half. In addition to set an adequate model, finding out the model parameters that best fit the proposed model to the available data of prevalence is a crucial goal. Taking into account that the necessary number of simulations to perform the calibration of the model may be very high, the aforementioned goal may become unaffordable. In this paper, we present a procedure to fit the proposed HPV model to the available data and the design of an asynchronous version of the Particle Swarm Optimization (PSO) algorithm adapted to the distributed computing environment. In the process, the number of particles used in PSO should be set carefully looking for a compromise between quality of the solutions and computation time. Another feature of the procedure presented here is that we want to capture the intrinsic uncertainty in the data (data come from a survey) when calibrating the model. To do so, we also propose the design of an algorithm to select the model parameter sets obtained during the calibration that best capture the data uncertainty., This work has been supported by the Spanish Ministerio de Economia y Competitividad grants MTM2017-89664-P, TIN2014-54806-R and RTI2018-095180-B-I00, Grants Y2018/NMT-4668 (Micro-Stres-MAP-CM) and GenObIA-CM (S2017/BMD-3773) financed by the Community of Madrid, Spain and co-financed with EU Structural Funds, Spain, and by GLENO project financed by Fundacion Eugenio Rodriguez Pascual, Spain.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Probabilistic Fitting of Glucose Models with Real-Coded Genetic Algorithms

  • Cervigón, Carlos
  • Velasco, J. Manuel
  • Hidalgo, J. Ignacio
  • Burgos-Simon, Clara|||0000-0001-6385-4263
  • Villanueva Micó, Rafael Jacinto|||0000-0002-0131-0532
[EN] Type 1 Diabetes patients have to control their blood glucose levels using insulin therapy. Numerous factors (such as carbohydrate intake, physical activity, time of day, etc.) greatly complicate this task. In this article we propose a modeling method that will allow us to make predictions of blood glucose level evolution with a time horizon of 24 hours. This may allow the adjustment of insulin doses in advance and could help to improve the living conditions of diabetes patients. Our approach starts from a system of finite difference equations that characterizes the interaction between insulin and glucose (in the field, this is known as a minimal model). This model has several parameters whose values vary widely depending on patient characteristics and time. Thus, in the first phase of our strategy, We will enrich the patient¿s historical data by adding white Gaussian noise, which will allow us to perform a probabilistic fitting with a 95% confidence interval. Then, the model¿s parameters are adjusted based on the history of each patient using a genetic algorithm and dividing the day into 12 time intervals. In the final stage, we will perform a whole-day forecast from an ensemble of the models fitted in the previous phase. Th e validity of our strategy will be tested using the Parkers¿ error grid analysis. Our experimental results based on data from real diabetic patients show that this technique is capable of robust predictions that take into account all the uncertainty associated with the interaction between insulin and glucose., We acknowledge support from Spanish Ministry of Economy and Competitiveness under project RTI2018-095180- B-I00 and Madrid Regional Goverment - FEDER grants B2017/BMD3773 (GenObIA-CM) and Y2018/NMT-4668 (Micro-Stress- MAP-CM). Devices for adquiring data from patients were adquired with the support of Fundacion Eugenio Rodriguez Pascual 2019 grant - Desarrollo de sistemas adaptativos y bioinspirados para el control glucemico con infusores subcutaneos continuos de insulina y monitores continuos de glucosa (Development of adaptive and bioinspired systems for glycaemic control with continuous subcutaneous insulin infusors and continuous glucose monitors).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Modeling breast tumor growth by a randomized logistic model: A computational approach to treat uncertainties via probability densities

  • Burgos-Simon, Clara|||0000-0001-6385-4263
  • Cortés, J.-C.|||0000-0002-6528-2155
  • Martínez-Rodríguez, David|||0000-0002-2093-7840
  • Villanueva Micó, Rafael Jacinto|||0000-0002-0131-0532
[EN] We consider a randomized discrete logistic equation to describe the dynamics of breast tumor volume. We propose a method, that takes advantage of the principle of maximum entropy, to assign reliable distributions to model inputs (initial condition and coefficients) and sample data, respectively. Since the distributions of coefficients depend on certain parameters, we design a computational procedure to determine the above mentioned parameters using the information of the probabilistic distributions. The proposed method is successfully applied to model the breast tumor volume using real data. The approach seems to be flexible enough to be adapted to other stochastic models in future contributions., This work has been supported by the Spanish Ministerio de Economia, Industria y Competitividad (MINECO), the Agencia Estatal de Investigacion (AEI), and Fondo Europeo de Desarrollo Regional (FEDER UE) Grants MTM2017-89664-P and RTI2018-095180-B-I00.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A computational technique to predict the level of glucose of a diabetic patient with uncertainty in the short term

  • Burgos-Simon, Clara|||0000-0001-6385-4263
  • Villanueva Micó, Rafael Jacinto|||0000-0002-0131-0532
  • Cervigón, Carlos
  • Hidalgo, José-Ignacio
[EN] On advanced stages of the disease, diabetic patients have to inject insulin doses to maintain blood glucose levels inside of a healthy range. The decision of how much insulin is injected implies somehow to predict the level of glucose they will have after a certain time. Due to the sudden changes in the glucose levels, their estimation is a very difficult task. If we were able to give reliable estimations in advance, it would facilitate the process of taking therapeutic decisions to control the disease and improve the health of the patient. In this work, we present a technique to estimate the glucose level of a diabetic patient, capturing the measurement errors produced by continuous glucose monitoring systems (CGMSs), smart devices that measure glucose levels. To do that, we will use a model of glucose dynamics and we calibrate it with the aim to capture the glucose level data of the patient in a time interval of 30 minutes and the uncertainty given by the glucose measurement. Then, we use the calibrated parameters to predict the levels of glucose over the next 15 minutes. Repeating this procedure every 15 minutes, we are able to give short¿term accurate predictions., This work has been partially supported by the Spanish Ministerio de Economía y Competitividad under grant MTM2017-89664-P and RTI2018-095180-B-I00 and by Fundación Eugenio Rodriguez Pascual 2019 -GLENO Project