Feature Selection for Speech Emotion Recognition in Spanish and Basque: On the Use of Machine Learning to Improve Human-Computer Interaction

Study of emotions in human-computer interaction is a growing research area. This paper shows an attempt to select the most significant features for emotion recognition in spoken Basque and Spanish Languages using different methods for feature selection. RekEmozio database was used as the experimental data set. Several Machine Learning paradigms were used for the emotion classification task. Experiments were executed in three phases, using different sets of features as classification variables in each phase. Moreover, feature subset selection was applied at each phase in order to seek for the most relevant feature subset. The three phases approach was selected to check the validity of the proposed approach. Achieved results show that an instance-based learning algorithm using feature subset selection techniques based on evolutionary algorithms is the best Machine Learning paradigm in automatic emotion recognition, with all different feature sets, obtaining a mean of 80,05% emotion recognition rate in Basque and a 74,82% in Spanish. In order to check the goodness of the proposed process, a greedy searching approach (FSS-Forward) has been applied and a comparison between them is provided. Based on achieved results, a set of most relevant non-speaker dependent features is proposed for both languages and new perspectives are suggested.

Changes in social inequalities in disability-free life expectancy in Southern Europe: the case of the Basque Country

Background: Health expectancy is a useful tool to monitor health inequalities. The evidence about the recent changes in social inequalities in healthy expectancy is relatively scarce and inconclusive, and most studies have focused on Anglo-Saxon and central or northern European countries. The objective of this study was to analyse the changes in socioeconomic inequalities in disability-free life expectancy in a Southern European population, the Basque Country, during the first decade of the 21st century. Methods: This was an ecological cross-sectional study of temporal trends on the Basque population in 1999-2003 and 2004-2008. All-cause mortality rate, life expectancy, prevalence of disability and disability free-life expectancy were calculated for each period according to the deprivation level of the area of residence. The slope index of inequality and the relative index of inequality were calculated to summarize and compare the inequalities in the two periods. Results: Disability free-life expectancy decreased as area deprivation increased both in men and in women. The difference between the most extreme groups in 2004-2008 was 6.7 years in men and 3.7 in women. Between 1999-2003 and 2004-2008, socioeconomic inequalities in life expectancy decreased, and inequalities in disability-free expectancy increased in men and decreased in women. Conclusions: This study found important socioeconomic inequalities in health expectancy in the Basque Country. These inequalities increased in men and decreased in women in the first decade of the 21st century, during which the Basque Country saw considerable economic growth.

Literary portraits of basque-american women from shadow to presence

268 p.

Breaking verbs. From event structure to syntactic categories in Basque

445 p.

Genotypes, Recombinant Forms, and Variants of Norovirus GII.4 in Gipuzkoa (Basque Country, Spain), 2009-2012

Background: Noroviruses (NoVs) are genetically diverse, with genogroup II-and within it-genotype 4 (GII.4) being the most prevalent cause of acute gastroenteritis worldwide. The aim of this study was to characterize genogroup II NoV causing acute gastroenteritis in the Basque Country (northern Spain) from 2009-2012. Methods: The presence of NoV RNA was investigated by reverse transcriptase-polymerase chain reaction (RT-PCR) in stool specimens from children younger than 15 years old with community-acquired acute gastroenteritis, and from hospitalized adults or elderly residents of nursing homes with acute gastroenteritis. For genotyping, the open reading frames ORF1 (encoding the polymerase) and ORF2 (encoding the major capsid protein) were partially amplified and sequenced. Recombinant strains were confirmed by PCR of the ORF1/ORF2 junction region. Results: NoV was detected in 16.0% (453/2826) of acute gastroenteritis episodes in children younger than 2 years, 9.9% (139/1407) in children from 2 to 14 years, and 35.8% (122/341) in adults. Of 317 NoVs characterized, 313 were genogroup II and four were genogroup I. The GII.4 variants Den Haag-2006b and New Orleans-2009 predominated in 2009 and 2010-2011, respectively. In 2012, the New Orleans-2009 variant was partially replaced by the Sydney-2012 variant (GII.Pe/GII.4) and New Orleans-2009/Sydney-2012 recombinant strains. The predominant capsid genotype in all age groups was GII.4, which was the only genotype detected in outbreaks. The second most frequent genotype was GII.3 (including the recently described recombination GII.P16/GII.3), which was detected almost exclusively in children. Conclusion: Nine different genotypes of NoV genogroup II were detected; among these, intergenotype recombinant strains represented an important part, highlighting the role of recombination in the evolution of NoVs. Detection of new NoV strains, not only GII.4 strains, shortly after their first detection in other parts of the world shows that many NoV strains can spread rapidly.

Análisis de la desigualdad económica en los municipios del País Vasco agrupados por tamaño de la población. Economic Inequality in the municipalities of the Basque Country aggregated by population size.

This paper analyses the economic inequality in the municipalities of the Basque Country during the period 1996 and 2010. We have used dates from the Udalmap database mainly the GDP per capita. We have drawn Lorenz Curves and also we have computed Gini indexes to analyse the evolution of inequality during this period. Therefore, we have concluded that there has been an increase of the economic inequality in the municipalities of the Basque Country during this period of time.

Analysis of the housing market in the autonomous community of the Basque country: the adjustment after the burst of the housing bubble

In this project study the characteristic and dynamics of the residential housing market in the Basque country. When strong expansion and colapsing emerged in 2007,studied the differents adjustment.

Entrepreneurship in the University of the Basque Country (UPV/EHU)

Currently entrepreneurship is a basic pillar in the socioeconomic area of any country since it contributes to attain the government objectives of job creation and boost of dynamism and competitiveness of the business network. These aspects are even more crucial nowadays due to the global economic crisis. This paper attempts to provide some new insights about the scientific field entrepreneurship in the Basque Country analyzing some aspects related to the entrepreneurial activity, the profile of the entrepreneur and the characteristics of the entrepreneurial businesses. It also aims to provide empirical evidence that proves the good features of the spin-offs and TBF groups as job creators, technology transferors to the society and important actors in the growth and development of the economies for both the business network and its surrounding society. To this aim, a descriptive study has been performed of the firms belonging to the Zitek Program of Bizkaia Campus of the University of the Basque Country (UPV/EHU).

Factors behind the wage in the Basque Country

[EN]This project aims to determine the factors which influence workers’ wages in the Basque Country, taking data from the INE (Spanish Statistical Office). In first place, I will decide which variables to choose and describe them. Then they will be used to build a wage model. At this point I will observe their behaviour according to their values and the possible differences between them. Once these variables are described, they will be used to develop an econometric model that will allow to see the different effects of the variables on the endogenous variable, in this case the gross annual wage. Finally, all the analysed data will be taken and examined to draw the final conclusions and see how workers’ age, training or gender affect their salary. [EN]

The labour market in the Basque Country: University Employment Centers

This project is a study of the Labour Market in the Basque Country. First of all, we have analysed the position of the Basque Country in the European Union employment situation by gender and age. Secondly, we have studied the educational level of the Basque Country from the European Union perspective. Thirdly, we have showed the importance of labour orientation in educational level, especially in higher education. Finally, the design of new employment policies to promote the creation of jobs and stability of the labour market depends on: new industries and university employment policies.

Wage factors in the Basque Economy

[EN] This project aims to determine the factors which influence workers’ wages in the Basque Country, taking data from the INE (Spanish Statistical Office). In first place, I will decide which variables to choose and describe them. Then they will be used to build a wage model. At this point I will observe their behaviour according to their values and the possible differences between them. Once these variables are described, they will be used to develop an econometric model that will allow to see the different effects of the variables on the endogenous variable, in this case the gross annual wage. Finally, all the analysed data will be taken and examined to draw the final conclusions and see how workers’ age, training or gender affect their salary. [EN]

Integrated assessment of environmental pollution using diverse sentinel organisms within Basque marine environments

294 p.

Ebaluatoia: crowd evaluation of English-Basque machine translation

[EU]Lan honetan Ebaluatoia aurkezten da, eskala handiko ingelesa-euskara itzulpen automatikoko ebaluazio kanpaina, komunitate-elkarlanean oinarritua. Bost sistemaren itzulpen kalitatea konparatzea izan da kanpainaren helburua, zehazki, bi sistema estatistiko, erregeletan oinarritutako bat eta sistema hibrido bat (IXA taldean garatuak) eta Google Translate. Emaitzetan oinarrituta, sistemen sailkapen bat egin dugu, baita etorkizuneko ikerkuntza bideratuko duten zenbait analisi kualitatibo ere, hain zuzen, ebaluazio-bildumako azpi-multzoen analisia, iturburuko esaldien analisi estrukturala eta itzulpenen errore-analisia. Lanak analisi hauen hastapenak aurkezten ditu, etorkizunean zein motatako analisietan sakondu erakutsiko digutenak.

Basque legacy in the New World: on the surnames of Latin American presidents

[EN] In this article we explain the etymology of the surnames of Basque origin that some presidents of Latin American countries have or have had in the past. These family names were created in the language called Euskara, in the Basque Country (Europe), and then, when some of the people who bore them emigrated to America, they brought their surnames with them. Most of the family names studied here are either oiconymic or toponymic, but it must be kept in mind that the oiconymic ones are, very often, based on house-nicknames, that is, they are anthroponymic in the first place. As far as possible, we have related the surname, when its origin is oiconymic or toponymic, to its source, i.e. to the house or place where it was created.