The aid of machine learning to overcome the classification of real health discharge reports written in Spanish

Hospitals attached to the Spanish Ministry of Health are currently using the International Classification of Diseases 9 Clinical Modification (ICD9-CM) to classify health discharge records. Nowadays, this work is manually done by experts. This paper tackles the automatic classification of real Discharge Records in Spanish following the ICD9-CM standard. The challenge is that the Discharge Records are written in spontaneous language. We explore several machine learning techniques to deal with the classification problem. Random Forest resulted in the most competitive one, achieving an F-measure of 0.876.

Agua, derecho de uso y utilidad en el regadío de tradición andalusí del Reino de Valencia

El origen de la normativa escrita sobre el uso de las aguas en el territorio peninsular levantino plantea diversas incógnitas. Las primera de ellas sobre los quienes fueron los protagonistas en la redacción y determinación de ese derecho. La segunda sobre el papel que la costumbre de los sarracenos desempeñó en la preservación de tradiciones jurídicas, mantenimiento de infraestructuras y gestión del agua. La tercera tiene que ver con el modo de aunar intereses de comunidades distintas desde el punto de vista religioso y jurídico sobre el derecho de uso de forma equitativa y proporcional a necesidades no necesariamente coincidentes. Lo cierto es que las fuentes conservadas sobre el proceso de reconquista y población siguen siendo una de las mejores referencias para despejar incógnitas y justificar la tradición y pervivencia de un derecho inmemorial y vigente en algunas de sus formas y manifestaciones, no solo en el marco levantino sino en otros muchos espacios de la cuenca mediterránea con idénticas características medioambientales y geo-climáticas.

Spectrally tunable light source based on light-emitting diodes for custom lighting solutions

This study describes a novel spectral LED-based tunable light source used for customized lighting solutions, especially for the reconstruction of CIE (Commission Internationale de l’Éclairage) standard illuminants. The light source comprises 31 spectral bands ranging from 400 to 700 nm, an integrating cube and a control board with a 16-bit resolution. A minimization algorithm to calculate the weighting values for each channel was applied to reproduce illuminants with precision. The differences in spectral fitting and colorimetric parameters showed that the reconstructed spectra were comparable to the standard, especially for the D65, D50, A and E illuminants. Accurate results were also obtained for illuminants with narrow peaks such as fluorescents (F2 and F11) and a high-pressure sodium lamp (HP1). In conclusion, the developed spectral LED-based light source and the minimization algorithm are able to reproduce any CIE standard illuminants with a high spectral and colorimetric accuracy able to advance available custom lighting systems useful in the industry and other fields such as museum lighting.