Jose Angel Taboada Gonzalez

Using Data-Mining for Short-Term Rainfall Forecasting

Weather forecasting [12] has been one of the most scientifically and technologically challenging problems around the world in the last century. This is due mainly to two factors: firstly, the great value of forecasting for many human activities; secondly, due to the opportunism created by the various technological advances that are directly related to this concrete research field, like the evolution of computation and the improvement in measurement systems. This paper describes several techniques belonging to the paradigm of artificial intelligence which try to make a short-term forecast of rainfalls (24 hours) over very spatially localized regions. The objective is to compare four different data-mining [1] methods for making a rainfall forecast [7], [10] for the next day using the data from a single weather station measurement.

Common Data Model in AmI Environments

Ambient Intelligence environments involve a wide range of different devices typically associated to protocols not compatible with each other. This is probably one of the possible problems to reach the full explosion of the internet of things because of the lack of standards for sensor data exchanging. This paper proposes a solution for the exchange and storage of information developing a generic model to be used with different sources of data. The model is light enough to be used in low-cost and low performance hardware. The paper also describes how the model is used in a scenario supporting different contexts, as industrial devices or environmental data.

Anti-Icing Decision Support System Based on a Multi-agent System and Data-Mining

This paper presents a system to improve decision support to prevent the ice formation or snow accumulation on the road surface (anti-icing). The main part of the system has the task of predicting the weather parameters [1] involved in the problem. To do that, the system uses data-mining techniques for the prediction process and uses a multi-agent system that is responsible for controlling the flow of information throughout the system and decides the most appropriate actions in each case to address the problem.