Soft computing models to identify typical meteorological days

Abstract

Soft computing models are capable of identifying patterns that can characterize a 'typical day' in terms of its meteorological conditions. This multidisciplinary study examines data on six meteorological parameters gathered in a Spanish city. Data on these and other variables were collected for over 6 months, in 2007, from a pollution measurement station that forms part of a network of similar stations in the Spanish Autonomous Region of Castile-Leon. A comparison of the meteorological data allows relationships to be established between the meteorological variables and the days of the year. One of the main contributions of this study is the selection of appropriate data processing techniques, in order to identify typical days by analysing meteorological variables and aerosol pollutants. Two case studies are analysed in an attempt to identify a typical day in summer and in autumn.

Validation of a Hyperspectral Content-Based Information Retrieval (RS-CBIR) System Upon Scarce Data

“…We show an example of its applicability to test a Hyperspectral CBIR system. Further work will address other soft-computing [4,3] approaches to the problem.…”

“…The proposed dissimilarity function can cope with this asymmetry avoiding the combinatorial problem of trying to decide which endmembers can be matched and what to do in case that the number of endmembers is dierent from one image to the oher. 3 The DAMA strategy DAMA is a data-driven thematic map quality assessment strategy suitable for comparative purposes when competing discrete mapping products are provided with little or no ground truth knowledge. It exploits a large number of implicit reference samples extracted from multiple reference cluster maps generated from unlabelled blocks of the input RS image, that are clustered separately to detect genuine, but small, image details at the cost of little human supervision.…”

Using clustering techniques for intelligent camera-based user interfaces

“…Neural networks have been widely deployed in many different areas [20,21]. As in neural networks, the basic idea of SOM has origins in certain brain operations, specifically in projection of multidimensional inputs to onedimensional or two-dimensional neuronal structures on cortex.…”

A Kernel for Time Series Classification: Application to Atmospheric Pollutants

“…Time-series analysis is an important problem with application in domains as diverse as engineering, medicine, astronomy or finance [2,3]. In particular, the problem of time-series classification is attracting a lot of attention among researchers [4].…”