Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

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

A comparative study of codification techniques for clustering heart disease database

  • Barceló Rico, Fátima
  • Diez, José-Luís|||0000-0002-5659-1212
  • Bondía Company, Jorge|||0000-0001-7286-3719
[EN] This paper compares various proposals for codifying categorical attributes in a heart disease database so that numerical clustering algorithms can be applied to them. An approach for the codification of categorical attributes based on polar coordinates is proposed. This is compared with other codifications and methods for clustering mixed databases found in the literature. Our proposal has many advantages: it is relatively easy to understand and apply; the increment in the length of the input matrix is not excessively large; and the committed error is under control. The proposed codification has been combined in this case with the well-known k-means algorithm and has shown a very good performance in a heart disease database benchmark., Partially supported by national project DPI2007-66728-C02-01, regional project GVPRE-2008-108, and the authors’ institution.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Insulin dosage optimization based on prediction of postprandial glucose excursions under uncertain parameters and food intake

  • García Jaramillo, Maira Alejandra
  • Calm, R.
  • Tarin, C.
  • Vehi, J.
  • Bondía Company, Jorge|||0000-0001-7286-3719
Considering the difficulty in selecting correct insulin doses and the problem of hyper- and hypoglycemia episodes in type 1 diabetes, dosage-aid systems are very useful for these patients. A model-based approach to this problem must unavoidably consider uncertainty sources such as large intra-patient variability and food intake. In the present study, postprandial glucose is predicted considering this uncertain information using modal interval analysis. This approach calculates a safer prediction of possible hyper- and hypoglycemia episodes induced by insulin therapy for an individual patient's parameters and integrates this information into a dosage-aid system. Predictions of a patient's postprandial glucose at 5-h intervals are used to predict the risk for a given therapy. Then the insulin dose and injection-to-meal time with the lowest risk are calculated. The method has been validated for three different scenarios corresponding to preprandial glucose values of 100, 180 and 250 mg/dl., This work was partially supported by the Spanish Ministry of Science and Innovation and the European Union through grant DPI-2007-66728 and by the Autonomous Government of Catalonia through SGR00523.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

New possibilistic method for discovering linear local behavior using hyper-Gaussian distributed membership function

  • Barcelo-Rico, F.
  • Diez, José-Luís|||0000-0002-5659-1212
  • Bondía Company, Jorge|||0000-0001-7286-3719
[EN] This paper presents a method to find a model of a system based on the integration of a set of local models. Mainly, properties are sought for the local models: independence of clusters and interpretability of their validity. This has been achieved through the introduction of a possibilistic clustering for the first property and a pre-fixed shape of the membership functions for the second one. A new cost index for the clustering optimization problem has been defined consisting of two terms: one for global error and another for local errors. By giving higher importance to the local errors term, local models valid regionally can be found. To avoid local optima and numerical issues, the parameters of the models are found using global optimization. This new method has been applied to several data sets, and results show how the desired characteristics can be achieved in the resulting models., The authors acknowledge the partial funding of this work by the projects: the national projects DPI2007-66728-C02-01 and DPI2008-06737-C02-01. The first author is recipient of a fellowship from the Spanish Ministry of Education (FPU AP2008-02967). The translation of this paper was funded by the Universidad Politecnica de Valencia, Spain.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Real-Time Continuous Glucose Monitoring in an Intensive Care Unit: Better Accuracy in Patients with Septic Shock

  • Lorencio, Carol
  • Leal, Yenny
  • Bonet Alonso, Alfonso
  • Palerm, César C.
  • Tache, Abdo
  • Sirvent, Josep Maria
  • Vehi, Josep
  • Bondía Company, Jorge|||0000-0001-7286-3719
[EN] Objective: This study assessed the accuracy of real-time continuous glucose monitoring system (RTCGMS) devices in an intensive care unit (ICU) to determine whether the septic status of the patient has any in¿uence on the accuracy of the RTCGMS. Subjects and Methods: In total, 41 patients on insulin therapy were included. Patients were monitored for 72 h using RTCGMS. Arterial blood glucose (ABG) samples were obtained following the protocol established in the ICU. The results were evaluated using paired values (excluding those used for calibration) with the performance assessed using numerical accuracy. Nonparametric tests were used to determine statistically signi¿cant differences in accuracy. Results: In total, 956 ABG/RTCGMS pairs were analyzed. The overall median relative absolute difference (RAD) was 13.5%, and the International Organization for Standardization (ISO) criteria were 68.1%. The median RADs reported for patients with septic shock, with sepsis, and without sepsis were 11.2%, 14.3%, and 16.3%, respectively (P<0.05). Measurements meeting the ISO criteria were 74.5%, 65.6%, and 63.7% for patients with septic shock, with sepsis, and without sepsis, respectively (P<0.05). Conclusions: The results showed that the septic status of patients in¿uenced the accuracy of the RTCGMS in the ICU. Accuracy was signi¿cantly better in patients with septic shock in comparison with the other patient cohorts., This work was supported by the Spanish Ministry of Science and Innovation through grants DPI2007-66728-C02 and DPI-2010-20764-C02, the European Union through FEDER funds, and the Autonomous Government of Catalonia through 2009 SGR 523. Y.L. is grateful for the BR Grants of the University of Girona. The authors thank the Ph.D. candidate student Xavier Berjaga, who helped with the statistical analysis in this work. The authors thank the nursing staff of the ICU of Doctor Josep Trueta Hospital for their work; without them, this study could not have been conducted. Medtronic, Inc. provided some of the devices used in this study.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Calculation of the Best Basal-Bolus Combination for Postprandial Glucose Control in Insulin Pump Therapy

  • Revert, Ana
  • Calm, Remei
  • Vehí, Josep
  • Bondía Company, Jorge|||0000-0001-7286-3719
[EN] Intensive insulin therapy in type 1 diabetes is based on the well-established practice of adjusting basal and bolus insulin independently. Basal insulin delivery is designed to optimize glucose concentrations between meals and overnight, while bolus insulin delivery is designed to optimize postprandial glucose concentrations. However, this strategy shows some limitations in the postprandial glucose control, especially for meals with high carbohydrate content. Strategies based on coordinating basal and bolus insulin in the postprandial period help in overcoming these limitations. An algorithm, based on mathematically guaranteed techniques (interval analysis), is presented in this paper. It determines, given the current glycemic state of the patient and the meal to be ingested, a basal-bolus combination that will yield a tight postprandial glycemic control according to the International Diabetes Federation guidelines. For a given meal, the algorithm reveals which bolus administration mode will enable a good postprandial performance: standard, square-wave, dual-wave, or temporal basal decrement. The algorithm is validated through an in silico study using the 30 subjects in the educational version of the Food and Drug Administration accepted University of Virginia simulator., This work was supported by the Spanish Government under Grants DPI-2007-66728 and DPI-2010-20764-C02, by the FEDER funds from European Union, by the Generalitat de Catalunya under Grant SGR-00296, and by the PAID-05-08 program of the Universidad Politecnica de Valencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A multiple local models approach to accuracy improvement in continuous glucose monitoring

  • Barceló Rico, Fátima
  • Rossetti ., Paolo
  • Bondía Company, Jorge|||0000-0001-7286-3719
  • Diez, José-Luís|||0000-0002-5659-1212
[EN] Background: Continuous glucose monitoring (CGM) devices estimate plasma glucose (PG) from measurements in compartments alternative to blood. The accuracy of currently available CGM is yet unsatisfactory and may depend on the implemented calibration algorithms, which do not compensate adequately for the differences of glucose dynamics between the compartments. Here we propose and validate an innovative calibration algorithm for the improvement of CGM performance. Methods: CGM data from GlucoDay (R) (A. Menarini, Florence, Italy) and paired reference PG have been obtained from eight subjects without diabetes during eu-, hypo-, and hyperglycemic hyperinsulinemic clamps. A calibration algorithm based on a dynamic global model (GM) of the relationship between PG and CGM in the interstitial space has been obtained. The GM is composed by independent local models (LMs) weighted and added. LMs are defined by a combination of inputs from the CGM and by a validity function, so that each LM represents to a variable extent a different metabolic condition and/or sensor-subject interaction. The inputs best suited for glucose estimation were the sensor current I and glucose estimations (G) over cap, at different time instants [I-k, Ik-1, (G) over cap (k-1)] (IIG). In addition to IIG, other inputs have been used to obtain the GM, achieving different configurations of the calibration algorithm. Results: Even in its simplest configuration considering only IIG, the new calibration algorithm improved the accuracy of the estimations compared with the manufacturer's estimate: mean absolute relative difference (MARD) = 10.8 +/- 1.5% versus 14.7 +/- 5.4%, respectively (P = 0.012, by analysis of variance). When additional exogenous signals were considered, the MARD improved further (7.8 +/- 2.6%, P<0.05). Conclusions: The LM technique allows for the identification of intercompartmental glucose dynamics. Inclusion of these dynamics into the calibration algorithm improves the accuracy of PG estimations., The authors acknowledge the partial funding of this work by the Spanish Ministry of Science and Innovation projects DPI2007-66728-C02-01 and DPI2010-20764-C02-01 and by the European Union through FEDER funds and grant FP7-PEOPLE-2009-IEF, Reference 252085. F.B.R. is the recipient of a fellowship (FPU AP2008-02967) from the Spanish Ministry of Education.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Modelling and control of a continuous distillation tower through fuzzy techniques

  • Barceló Rico, Fátima
  • Gozálvez-Zafrilla, José M.|||0000-0003-4419-6765
  • Diez, José-Luís|||0000-0002-5659-1212
  • Santafé Moros, María Asunción|||0000-0002-0933-108X
This paper presents a methodology for the design of a fuzzy controller applicable to continuous processes based on local fuzzy models and velocity linearizations. It has been applied to the implementation of a fuzzy controller for a continuous distillation tower. Continuous distillation towers can be subjected to variations in feed characteristics that cause loss of product quality or excessive energy consumption. Therefore, the use of a fuzzy controller is interesting to control process performance.A dynamic model for continuous distillation was implemented and used to obtain data to develop the fuzzy controller at different operating points. The fuzzy controller was built by integration of linear controllers obtained for each linearization of the system. Simulation of the model with controller was used to validate the controller effectiveness under different scenarios, including a study of the sensibility of some parameters to the control.The results showed that the fuzzy controller was able to keep the target output in the desired range for different inputs disturbances, changing smoothly from a predefined target output to another. The developed techniques are applicable to more complex distillation systems including more operating variables, The authors acknowledge the partial funding of this work by the projects: Regional Government Project GVPRE/2008/108, and National Projects DPI2007-66728-C02-01 and DPI2008-06737-C02-01.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Geometrical codification for clustering mixed categorical and numerical databases

  • Barceló Rico, Fátima
  • Diez, José-Luís|||0000-0002-5659-1212
[EN] This paper presents an alternative to cluster mixed databases. The main idea is to propose a general method to cluster mixed data sets, which is not very complex and still can reach similar levels of performance of some good algorithms. The proposed approach is based on codifying the categorical attributes and use a numerical clustering algorithm on the resulting database. The codification proposed is based on polar or spherical coordinates, it is easy to understand and to apply, the increment in the length of the input matrix is not excessively large, and the codification error can be determined for each case. The proposed codification combined with the well known k-means algorithm showed a very good performance in different benchmarks and has been compared with both, other codifications and other mixed clustering algorithms, showing a better or comparable performance in all cases., The authors acknowledge the partial funding of this work by the National projects DPI2007-66728-C02-01 and DPI2008-06737-C02-01.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

El Páncreas Artificial: Control Automático de Infusión de Insulina en Diabetes Mellitus Tipo 1, Artificial pancreas: automatic control of insulin infusion in type 1 diabetes mellitus

  • Bondía Company, Jorge|||0000-0001-7286-3719
  • Vehí, J.
  • Palerm, C. C.
  • Herrero, P.
[ES] La diabetes mellitus tipo 1 es una enfermedad crónica que afecta aproximadamente a 30 millones de personas en el mundo y se caracteriza por niveles de concentración de glucosa en sangre elevados producidos por una deficiencia absoluta de insulina. Ello produce numerosas complicaciones a largo plazo como retinopatía, nefropatía y neuropatía entre otras. Las terapias actuales basadas en el suministro de insulina exógena (por inyecciones o bomba de insulina), no consiguen normalizar los niveles de glucosa de forma eficiente. Los avances tecnológicos en la última década en sistemas de medición continua de glucosa e infusión de insulina, han impulsado el desarrollo del páncreas artificial, o control automático de infusión de insulina. En este trabajo se presentará, a modo de tutorial, el pasado, presente y futuro de esta tecnología, tan esperada por el paciente diabético. Se revisará el estado actual de la tecnología para la sensorización y actuación, principales desafíos desde el punto de vista de control, las diferentes ``escuelas'' y estudios clínicos del desempeño de controladores, así como herramientas de validación de controladores mediante simulación. Dada la complejidad del problema, el desarrollo del páncreas artificial será de forma escalonada, redundando progresivamente en la mejora de la calidad de vida del paciente. Los grandes avances en los últimos cinco años hacen preveer un horizonte cercano para la primera generación de páncreas artificial., [EN] Type 1 diabetes mellitus is a chronic disease that affects approximately to 30 million people worldwide and is characterized by high blood glucose concentration levels produced by an absolute deficiency of insulin. That produces numerous long-term complications like retinopathy, nephropathy and neuropathy among others. Current therapies based on the exogenous delivery of insulin (through injections or an insulin pump), do not manage to normalize the glucose levels efficiently. Technological advances in the last decade in continuous glucose monitoring and insulin infusion have been a springboard for the development of the artificial pancreas, or automatic control of insulin infusion. In this work, the past, present and future of this technology, so long awaited by the diabetic patient, will be presented in the form of a tutorial. Current technology for sensorization and actuation will be reviewed, as well as main challenges from the control point of view, different “schools of thought” and clinical studies for controllers performance evaluation, and tools for the validation of controllers through simulation. Due to the complexity of the problem, the development of the artificial pancreas will be staggered, resulting progressively in an improvement of the patient’s quality of life. The big advances during last five years foresee a close horizon for a first generation of artificial pancreas., Este trabajo ha sido realizado parcialmente gracias al apoyo del Ministerio de Ciencia e Innovación español, a través del proyecto DPI2007-66728-C02, de la Unión Europea a través de fondos FEDER y de la Wellcome Trust.