Table of Contents

Current Research Projects

GenObIA­-CM

Absys is a member of the GenObIA project: Design, by means of artificial intelligence, of predictive algorithms for the identification of individuals at risk of developing overweight/obesity and their associated pathologies: contribution of genetic analysis – Diseño, mediante inteligencia artificial, de algoritmos predictivos para la identificación de individuos en riesgo de desarrollar sobrepeso/obesidad y sus patologías asociadas: Aportación del análisis genético. (GenObIA­CM) B2017/BMD­3773. More Info

COST Action CA15140

Absys is actively participating in COST Action CA15140 Improving Applicability of Nature-Inspired Optimisation by Joining Theory and Practice (ImAppNIO). More Info . Nature-inspired search and optimisation heuristics are easy to implement and apply to new problems. However, in order to achieve good performance it is usually necessary to adjust them to the problem at hand. Theoretical foundations for the understanding of such approaches have been built very successfully in the past 20 years but there is a huge disconnect between the theoretical basis and practical applications. The development of powerful analytical tools, significant insights in general limitations of different types of nature-inspired optimisation methods and the development of more practically relevant perspectives for theoretical analysis have brought impressive advances to the theory-side of the field. However, so far impact on the application-side has been limited and few people in the diverse potential application areas have benefitted from these advances.

The main objective of the COST Action is to bridge this gap and improve the applicability of all kinds of nature-inspired optimisation methods. It aims at making theoretical insights more accessible and practical by creating a platform where theoreticians and practitioners can meet and exchange insights, ideas and needs; by developing robust guidelines and practical support for application development based on theoretical insights; by developing theoretical frameworks driven by actual needs arising from practical applications; by training Early Career Investigators in a theory of nature-inspired optimisation methods that clearly aims at practical applications; by broadening participation in the ongoing research of how to develop and apply robust nature-inspired optimisation methods in different application areas.

Project TIN2014-54806-R

Our Project “Development of Adaptive and Bioinspired Systems for Glycemic Control using Insulin Pumps and Continuous Glucose Monitors in Patients with Diabetes Mellitus” has been granted for the next 3 years by the Spanish Goverment. April 16th, 2015. More Info

Related Publications

glUCModel

glUCModel is a web application, available in internet with a double purpose: improving the control of diabetes and helping both diabetics and physicians to manage the disease. The requirement was to make glUCModel multi-platform, so that the type of device was not a restriction. To this end, we have tested it in several devices, like smartphones, tablets, laptops or personal computers with different operating systems (Windows, GNU/Linux, iOS), and with different web browsers (Internet Explorer, Google Chrome, Mozilla Firefox, Opera and Safari). glUCModel is composed of five different modules, that is, a data interface, a database, and the three novel contributions in this field: a recommender system, an e-learning course and the glucose model:

  1. Data interface: It is the core module of the application, connecting all the modules. It is used to allow diabetics to query and update all necessary data for the control of their illness. On the other hand, physicians can track the evolution of the patient.
  2. Database: In the database glUCModel stores the information about users (patients and physicians), medical tests and diabetic measurements (glycemias, sport activities, food intakes, etc.). Furthermore, the recommender system and the e-learning course also store this data here.
  3. glUCModel Recommender System (g-RS): The function of g-RS is to evaluate the patient data. With this information, the system creates suggestions about how the diabetic can improve his control about the diabetes and what habits he should modify to improve his quality of life. g-RS includes an Inbox, where the patient receives recommendations in an e-mail message format.
  4. E-learning module: A virtual e-learning space where the patient has all the necessary information about diabetes. In this environment, there are documents with theoretical concepts to resolve the patient doubts. It also presents several tools to help on the education, like tests, calendar, forum and glossary.
  5. Glucose model module: Supported by evolutionary computation techniques, this module obtains a customized model the each patient’s glucose blood levels using the information available in the database.

Plan Avanza i+D+I

Plan INNPACTO