technology

TECHNOLOGY

The following code was mostly developed in the context of EU projects hosted by the AI Lab at the Jozef Stefan Institute where I work at the moment. A large part of it is publicly available through GitHub under the tab code and received by request.

InfluenzaLab

Using persistence we are able to analyze the Influenzanet data identifying several topological features relevant to the epidemiological study. In particular, we can identify data noise, distinguish higher dimension features and look at join spaces between countries. This is done both in terms of the overall structure of a disease as well as its evolution. Finally, it provides a way to test agreement at a global scale arising from standard local models. Influenzanet is a system to monitor the activity of influenza-like-illness (ILI) with the aid of volunteers via the internet. It has been operational for more than 10 years at the EU level since 2008. The data includes a profile questionnaire for each participant, and a symptom questionnaire at every week during the flu season for each participant. The data covers Belgium and the Netherlands 2003-2013, and Portugal 2005-2013, provided for further research by Gabriela Gomes and Sander Van Noort. The study of Epidemiology is a great source of problems that focus aspects of such nature. Moreover, persistence can provide such research with high dimension techniques for medical data analysis. In particular, persistence diagrams are a clear and practical tool that allows us the detection of outliers and to capture the dynamics of the system. During further reseach we will investigate if those exceptional points evident for the Mahalanobis metric are distinct under other metrics, and learn the appropriate metric such that those outliers are close enough. We shall also use kernels and SVMs on these features, enabling a machine learning approach over this data. To this work was developed together with Primož Škraba and to it contributed discussions with the following: Daniela Paolotti, Gabriela Gomes, Sander Van Noort, Graham Ellis, Maeusz Juda, Anita Kolaržik and Luis Rei.

AquaLab

The EU project aquaSmart uses state of the art technologies and global data access to reveal how the environment, fish feeding, production management and practices affects your production. My contribution in this project focused Big Data Analytics towards the cost optimisation of the aquaculture industry through the improvement of feed conversion ratio models. The raw data includes the daily data typical for the aquaculture production - such as average weight, water temperature, feeder - and the aim of our model was to evaluate the feeding process of the fish and permit predictions regarding the production. These methods use artificial intelligence algorithms to extrapolate the data and permit polinomial approximation modelling. To this work was developed together with Matjaž Rihtar and to it contributed discussions with the following: Primož Škraba, Luka Stopar and Giannis Zarifis.

PersistenceLab

Topological data analysis is interested in problems relating to nonlinear systems, large scale data and development of more accurate models, that contribute to a high level research. To this work was developed together with Primož Škraba and Luka Stopar and to it contributed discussions with the following: Mikael Vejdemo Johansson, Luis Rei.