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.

The Interplay between Natural Selection and Susceptibility to Melanoma on Allele 374F of SLC45A2 Gene in a South European Population

We aimed to study the selective pressures interacting on SLC45A2 to investigate the interplay between selection and susceptibility to disease. Thus, we enrolled 500 volunteers from a geographically limited population (Basques from the North of Spain) and by resequencing the whole coding region and intron 5 of the 34 most and the 34 least pigmented individuals according to the reflectance distribution, we observed that the polymorphism Leu374Phe (L374F, rs16891982) was statistically associated with skin color variability within this sample. In particular, allele 374F was significantly more frequent among the individuals with lighter skin. Further genotyping an independent set of 558 individuals of a geographically wider population with known ancestry in the Spanish population also revealed that the frequency of L374F was significantly correlated with the incident UV radiation intensity. Selection tests suggest that allele 374F is being positively selected in South Europeans, thus indicating that depigmentation is an adaptive process. Interestingly, by genotyping 119 melanoma samples, we show that this variant is also associated with an increased susceptibility to melanoma in our populations. The ultimate driving force for this adaptation is unknown, but it is compatible with the vitamin D hypothesis. This shows that molecular evolution analysis can be used as a useful technology to predict phenotypic and biomedical consequences in humans.

Early life history studies of Yellowfin tuna, Thunnus albacares. I. Food selection of Yellowfin tuna, Thunnus albacares, larvae reared in the laboratory. II. Age validation and growth of Yellowfin tuna, Thunnus albacares, larvae reared in the laboratory

English: Food selection of first-feeding yellowfin tuna larvae was studied in the laboratory during October 1992. The larvae were hatched from eggs obtained by natural spawning of yellowfin adults held in sea pens adjacent to Ishigaki Island, Okinawa Prefecture, Japan. The larvae were fed mixed-prey assemblages consisting of size-graded wild zooplankton and cultured rotifers. Yellowfin larvae were found to be selective feeders during the first four days of feeding. Copepod nauplii dominated the diet numerically, by frequency of occurrence and by weight. The relative importance of juvenile and adult copepods (mostly cyclopoids) in the diet increased over the 4-day period. Rotifers, although they comprised 31 to 40 percent of the available forage, comprised less than 2.1 percent of the diet numerically. Prey selection indices were calculated taking into account the relative abundances of prey, the swimming speeds of yellowfin larvae and their prey, and the microscale influence of turbulence on encounter rates. Yellowfin selected for copepod nauplii and against rotifers, and consumed juvenile and adult copepods in proportion to their abundances. Yellowfin larvae may select copepod nauplii and cyclopoid juveniles and adults based on the size and discontinuous swimming motion of these prey. Rotifers may not have been selected because they were larger or because they exhibit a smooth swimming pattern. The best initial diet for the culture of yellowfin larvae may be copepod nauplii and cyclopoid juveniles and adults, due to the size, swimming motion, and nutritional content of these prey. If rotifers alone are fed to yellowfin larvae, the rotifers should be enriched with a nutritional supplement that is high in unsaturated fatty acids. Mouth size of yellowfin larvae increases rapidly within the first few days of feeding, which minimizes limitations on feeding due to prey size. Although yellowfin larvae initiate feeding on relatively small prey, they rapidly acquire the ability to add relatively large, rare prey items to the diet. This mode of feeding may be adaptive for the development of yellowfin larvae, which have high metabolic rates and live in warm mixed-layer habitats of the tropical and subtropical Pacific. Our analysis also indicates a strong potential for the influence of microscale turbulence on the feeding success of yellowfin larvae. --- Experiments designed to validate the periodicity of otolith increments and to examine growth rates of yellowfin tuna larvae were conducted at the Japan Sea-Farming Association’s (JASFA) Yaeyama Experimental Station, Ishigaki Island, Japan, in September 1992. Larvae were reared from eggs spawned by captive yellowfin enclosed in a sea pen in the bay adjacent to Yaeyama Station. Results indicate that the first increment is deposited within 12 hours of hatching in the otoliths of yellowfin larvae, and subsequent growth increments are formed dailyollowing the first 24 hours after hatching r larvae up to 16 days of age. Somatic and otolith gwth ras were examined and compared for yolksac a first-feeding larvae reared at constant water tempatures of 26�and 29°C. Despite the more rapid develo of larvae reared at 29°C, growth rates were nnificaifferent between the two treatments. Howeve to poor survival after the first four days, it was ssible to examine growth rates beyond the onset of first feeding, when growth differences may become more apparent. Somatic and otolith growth were also examined for larvae reared at ambient bay water temperatures during the first 24 days after hatching. timates of laboratory growth rates were come to previously reported values for laboratory-reared yelllarvae of a similar age range, but were lower than growth rates reported for field-collected larvae. The discrepancy between laboratory and field growth rates may be associated with suboptimal growth conditions in the laboratory. Spanish: Durante octubre de 1992 se estudió en el laboratorio la seleccalimento por larvaún aleta amarillmera alimentación. Las larvas provinieron de huevos obtenidosel desove natural de aletas amarillas adultos mantenidos en corrales marinos adyacentes a la Isla Ishigaki, Prefectura de Okinawa (Japón). Se alimentó a las larvas con presas mixtas de zooplancton silvestre clasificado por tamaño y rotíferos cultivados. Se descubrió que las larvas de aleta amarilla se alimentan de forma selectiva durante los cuatro primeros días de alimentación. Los nauplios de copépodo predominaron en la dieta en número, por frecuencia de ocurrencia y por peso. La importancia relativa de copépodos juveniles y adultos (principalmente ciclopoides) en la dieta aumentó en el transcurso del período de 4 días. Los rotíferos, pese a que formaban del 31 al 40% del alimento disponible, respondieron de menos del 2,1% de la dieta en número. Se calcularon índices de selección de presas tomando en cuenta la abundancia relativa de las presas, la velocidad de natación de las larvas de aleta amarilla y de sus presas, y la influencia a microescala de la turbulencia sobre las tasas de encuentro. Los aletas amarillas seleccionaron a favor de nauplios de copépodo y en contra de los rotíferos, y consumieron copépodos juveniles y adultos en proporción a su abundancia. Es posible que las larvas de aleta amarilla seleccionen nauplios de copépodo y ciclopoides juveniles y adultos con base en el tamaño y movimiento de natación discontinuo de estas presas. Es posible que no se hayan seleccionado los rotíferos a raíz de su mayor tamaño o su patrón continuo de natación. Es posible que la mejor dieta inicial para el cultivo de larvas de aleta amarilla sea nauplios de copépodo y ciclopoides juveniles y adultos, debido al tamaño, movimiento de natación, y contenido nutritivo de estas presas. Si se alimenta a las larvas de aleta amarilla con rotíferos solamente, se debería enriquecerlos con un suplemento nutritivo rico en ácidos grasos no saturados. El tamaño de la boca de las larvas de aleta amarilla aumenta rápidamente en los primeros pocos días de alimentación, reduciendo la limitación de la alimentación debida al tamaño de la presa. Pese a que las larvas de aleta amarilla inician su alimentación con presas relativamente pequeñas, se hacen rápidamente capaces de añadir presas relativamente grandes y poco comunes a la dieta. Este modo de alimentación podría ser adaptivo para el desarrollo de larvas de aleta amarilla, que tienen tasa metabólicas altas y viven en hábitats cálidos en la capa de mezcla en el Pacífico tropical y subtropical. Nuestro análisis indica también que la influencia de turbulencia a microescala es potencialmente importante para el éxito de la alimentación de las larvas de aleta amarilla. --- En septiembre de 1992 se realizaron en la Estación Experimental Yaeyama de la Japan Sea- Farming Association (JASFA) en la Isla Ishigaki (Japón) experimentos diseñados para validar la periodicidad de los incrementos en los otolitos y para examinar las tasas de crecimiento de las larvas de atún aleta amarilla. Se criaron las larvas de huevos puestos por aletas amarillas cautivos en un corral marino en la bahía adyacente a la Estación Yaeyama. Los resultados indican que el primer incremento es depositado menos de 12 horas después de la eclosión en los otolitos de las larvas de aleta amarilla, y que los incrementos de crecimiento subsiguientes son formados a diario a partir de las primeras 24 horas después de la eclosión en larvas de hasta 16 días de edad. Se examinaron y compararon las tasas de crecimiento somático y de los otolitos en larvas en las etapas de saco vitelino y de primera alimentación criadas en aguas de temperatura constante entre 26°C y 29°C. A pesar del desarrollo más rápido de las larvas criadas a 29°C, las tasas de crecimiento no fueron significativamente diferentes entre los dos tratamientos. Debido a la mala supervivencia a partir de los cuatro primeros días, no fue posibación, uando las diferencias en el crecimiento podrían hacerse más aparentes. Se examinó también el crecimiento somático y de los otolitos para larvas criadas en temperaturas de agua ambiental en la bahía durante los 24 días inmediatamente después de la eclosión. Nuestras estimaciones de las tasas de crecimiento en el laboratorio fueron comparables a valores reportados previamente para larvas de aleta amarilla de edades similares criadas en el laboratorio, pero más bajas que las tasas de crecimiento reportadas para larvas capturadas en el mar. La discrepancia entre las tasas de crecimiento en el laboratorio y el mar podría estar asociada con condiciones subóptimas de crecimiento en el lab

Human Endogenous Retrovirus HERV-Fc1 Association with Multiple Sclerosis Susceptibility: A Meta-Analysis

Background: Human endogenous retroviruses (HERVs) are repetitive sequences derived from ancestral germ-line infections by exogenous retroviruses and different HERV families have been integrated in the genome. HERV-Fc1 in chromosome X has been previously associated with multiple sclerosis (MS) in Northern European populations. Additionally, HERV-Fc1 RNA levels of expression have been found increased in plasma of MS patients with active disease. Considering the North-South latitude gradient in MS prevalence, we aimed to evaluate the role of HERV-Fc1on MS risk in three independent Spanish cohorts. Methods: A single nucleotide polymorphism near HERV-Fc1, rs391745, was genotyped by Taqman chemistry in a total of 2473 MS patients and 3031 ethnically matched controls, consecutively recruited from: Northern (569 patients and 980 controls), Central (883 patients and 692 controls) and Southern (1021 patients and 1359 controls) Spain. Our results were pooled in a meta-analysis with previously published data. Results: Significant associations of the HERV-Fc1 polymorphism with MS were observed in two Spanish cohorts and the combined meta-analysis with previous data yielded a significant association [rs391745 C-allele carriers: p(M-H) = 0.0005; ORM-H (95% CI) = 1.27 (1.11-1.45)]. Concordantly to previous findings, when the analysis was restricted to relapsing remitting and secondary progressive MS samples, a slight enhancement in the strength of the association was observed [p(M-H) = 0.0003, ORM-H (95% CI) = 1.32 (1.14-1.53)]. Conclusion: Association of the HERV-Fc1 polymorphism rs391745 with bout-onset MS susceptibility was confirmed in Southern European cohorts.

Building TRACE (translations censored) theatre corpus: some methodological questions on text selection

Editores:Micaela Muñoz-Calvo; Carmen Buesa-Gómez