Quality indices for (practical) clustering evaluation

Clustering quality or validation indices allow the evaluation of the quality of clustering in order to support the selection of a specific partition or clustering structure in its natural unsupervised environment, where the real solution is unknown or not available. In this paper, we investigate the use of quality indices mostly based on the concepts of clusters` compactness and separation, for the evaluation of clustering results (partitions in particular). This work intends to offer a general perspective regarding the appropriate use of quality indices for the purpose of clustering evaluation. After presenting some commonly used indices, as well as indices recently proposed in the literature, key issues regarding the practical use of quality indices are addressed. A general methodological approach is presented which considers the identification of appropriate indices thresholds. This general approach is compared with the simple use of quality indices for evaluating a clustering solution.

Classification of microwatersheds based on morphological characteristics

Three classification techniques, namely, K-means Cluster Analysis (KCA), Fuzzy Cluster Analysis (FCA), and Kohonen Neural Networks (KNN) were employed to group 25 microwatersheds of Kherthal watershed, Rajasthan into homogeneous groups for formulating the basis for suitable conservation and management practices. Ten parameters, mainly, morphological, namely, drainage density (D-d), bifurcation ratio (R-b), stream frequency (F-u), length of overland flow (L-o), form factor (R-f), shape factor (B-s), elongation ratio (R-e), circulatory ratio (R-c), compactness coefficient (C-c) and texture ratio (T) are used for the classification. Optimal number of groups is chosen, based on two cluster validation indices Davies-Bouldin and Dunn's. Comparative analysis of various clustering techniques revealed that 13 microwatersheds out of 25 are commonly suggested by KCA, FCA and KNN i.e., 52%; 17 microwatersheds out of 25 i.e., 68% are commonly suggested by KCA and FCA whereas these are 16 out of 25 in FCA and KNN (64%) and 15 out of 25 in KNN and CA (60%). It is observed from KNN sensitivity analysis that effect of various number of epochs (1000, 3000, 5000) and learning rates (0.01, 0.1-0.9) on total squared error values is significant even though no fixed trend is observed. Sensitivity analysis studies revealed that microwatershecls have occupied all the groups even though their number in each group is different in case of further increase in the number of groups from 5 to 6, 7 and 8. (C) 2010 International Association of Hydro-environment Engineering and Research, Asia Pacific Division. Published by Elsevier B.V. All rights reserved.

Novos métodos determinísticos para gerar centros iniciais dos grupos no algoritmo fuzzy C-Means e variantes

Data clustering is applied to various fields such as data mining, image processing and pattern recognition technique. Clustering algorithms splits a data set into clusters such that elements within the same cluster have a high degree of similarity, while elements belonging to different clusters have a high degree of dissimilarity. The Fuzzy C-Means Algorithm (FCM) is a fuzzy clustering algorithm most used and discussed in the literature. The performance of the FCM is strongly affected by the selection of the initial centers of the clusters. Therefore, the choice of a good set of initial cluster centers is very important for the performance of the algorithm. However, in FCM, the choice of initial centers is made randomly, making it difficult to find a good set. This paper proposes three new methods to obtain initial cluster centers, deterministically, the FCM algorithm, and can also be used in variants of the FCM. In this work these initialization methods were applied in variant ckMeans.With the proposed methods, we intend to obtain a set of initial centers which are close to the real cluster centers. With these new approaches startup if you want to reduce the number of iterations to converge these algorithms and processing time without affecting the quality of the cluster or even improve the quality in some cases. Accordingly, cluster validation indices were used to measure the quality of the clusters obtained by the modified FCM and ckMeans algorithms with the proposed initialization methods when applied to various data sets

Semi-supervised subspace clustering and applications to neuroscience

Machine learning techniques are used for extracting valuable knowledge from data. Nowa¬days, these techniques are becoming even more important due to the evolution in data ac¬quisition and storage, which is leading to data with different characteristics that must be exploited. Therefore, advances in data collection must be accompanied with advances in machine learning techniques to solve new challenges that might arise, on both academic and real applications. There are several machine learning techniques depending on both data characteristics and purpose. Unsupervised classification or clustering is one of the most known techniques when data lack of supervision (unlabeled data) and the aim is to discover data groups (clusters) according to their similarity. On the other hand, supervised classification needs data with supervision (labeled data) and its aim is to make predictions about labels of new data. The presence of data labels is a very important characteristic that guides not only the learning task but also other related tasks such as validation. When only some of the available data are labeled whereas the others remain unlabeled (partially labeled data), neither clustering nor supervised classification can be used. This scenario, which is becoming common nowadays because of labeling process ignorance or cost, is tackled with semi-supervised learning techniques. This thesis focuses on the branch of semi-supervised learning closest to clustering, i.e., to discover clusters using available labels as support to guide and improve the clustering process. Another important data characteristic, different from the presence of data labels, is the relevance or not of data features. Data are characterized by features, but it is possible that not all of them are relevant, or equally relevant, for the learning process. A recent clustering tendency, related to data relevance and called subspace clustering, claims that different clusters might be described by different feature subsets. This differs from traditional solutions to data relevance problem, where a single feature subset (usually the complete set of original features) is found and used to perform the clustering process. The proximity of this work to clustering leads to the first goal of this thesis. As commented above, clustering validation is a difficult task due to the absence of data labels. Although there are many indices that can be used to assess the quality of clustering solutions, these validations depend on clustering algorithms and data characteristics. Hence, in the first goal three known clustering algorithms are used to cluster data with outliers and noise, to critically study how some of the most known validation indices behave. The main goal of this work is however to combine semi-supervised clustering with subspace clustering to obtain clustering solutions that can be correctly validated by using either known indices or expert opinions. Two different algorithms are proposed from different points of view to discover clusters characterized by different subspaces. For the first algorithm, available data labels are used for searching for subspaces firstly, before searching for clusters. This algorithm assigns each instance to only one cluster (hard clustering) and is based on mapping known labels to subspaces using supervised classification techniques. Subspaces are then used to find clusters using traditional clustering techniques. The second algorithm uses available data labels to search for subspaces and clusters at the same time in an iterative process. This algorithm assigns each instance to each cluster based on a membership probability (soft clustering) and is based on integrating known labels and the search for subspaces into a model-based clustering approach. The different proposals are tested using different real and synthetic databases, and comparisons to other methods are also included when appropriate. Finally, as an example of real and current application, different machine learning tech¬niques, including one of the proposals of this work (the most sophisticated one) are applied to a task of one of the most challenging biological problems nowadays, the human brain model¬ing. Specifically, expert neuroscientists do not agree with a neuron classification for the brain cortex, which makes impossible not only any modeling attempt but also the day-to-day work without a common way to name neurons. Therefore, machine learning techniques may help to get an accepted solution to this problem, which can be an important milestone for future research in neuroscience. Resumen Las técnicas de aprendizaje automático se usan para extraer información valiosa de datos. Hoy en día, la importancia de estas técnicas está siendo incluso mayor, debido a que la evolución en la adquisición y almacenamiento de datos está llevando a datos con diferentes características que deben ser explotadas. Por lo tanto, los avances en la recolección de datos deben ir ligados a avances en las técnicas de aprendizaje automático para resolver nuevos retos que pueden aparecer, tanto en aplicaciones académicas como reales. Existen varias técnicas de aprendizaje automático dependiendo de las características de los datos y del propósito. La clasificación no supervisada o clustering es una de las técnicas más conocidas cuando los datos carecen de supervisión (datos sin etiqueta), siendo el objetivo descubrir nuevos grupos (agrupaciones) dependiendo de la similitud de los datos. Por otra parte, la clasificación supervisada necesita datos con supervisión (datos etiquetados) y su objetivo es realizar predicciones sobre las etiquetas de nuevos datos. La presencia de las etiquetas es una característica muy importante que guía no solo el aprendizaje sino también otras tareas relacionadas como la validación. Cuando solo algunos de los datos disponibles están etiquetados, mientras que el resto permanece sin etiqueta (datos parcialmente etiquetados), ni el clustering ni la clasificación supervisada se pueden utilizar. Este escenario, que está llegando a ser común hoy en día debido a la ignorancia o el coste del proceso de etiquetado, es abordado utilizando técnicas de aprendizaje semi-supervisadas. Esta tesis trata la rama del aprendizaje semi-supervisado más cercana al clustering, es decir, descubrir agrupaciones utilizando las etiquetas disponibles como apoyo para guiar y mejorar el proceso de clustering. Otra característica importante de los datos, distinta de la presencia de etiquetas, es la relevancia o no de los atributos de los datos. Los datos se caracterizan por atributos, pero es posible que no todos ellos sean relevantes, o igualmente relevantes, para el proceso de aprendizaje. Una tendencia reciente en clustering, relacionada con la relevancia de los datos y llamada clustering en subespacios, afirma que agrupaciones diferentes pueden estar descritas por subconjuntos de atributos diferentes. Esto difiere de las soluciones tradicionales para el problema de la relevancia de los datos, en las que se busca un único subconjunto de atributos (normalmente el conjunto original de atributos) y se utiliza para realizar el proceso de clustering. La cercanía de este trabajo con el clustering lleva al primer objetivo de la tesis. Como se ha comentado previamente, la validación en clustering es una tarea difícil debido a la ausencia de etiquetas. Aunque existen muchos índices que pueden usarse para evaluar la calidad de las soluciones de clustering, estas validaciones dependen de los algoritmos de clustering utilizados y de las características de los datos. Por lo tanto, en el primer objetivo tres conocidos algoritmos se usan para agrupar datos con valores atípicos y ruido para estudiar de forma crítica cómo se comportan algunos de los índices de validación más conocidos. El objetivo principal de este trabajo sin embargo es combinar clustering semi-supervisado con clustering en subespacios para obtener soluciones de clustering que puedan ser validadas de forma correcta utilizando índices conocidos u opiniones expertas. Se proponen dos algoritmos desde dos puntos de vista diferentes para descubrir agrupaciones caracterizadas por diferentes subespacios. Para el primer algoritmo, las etiquetas disponibles se usan para bus¬car en primer lugar los subespacios antes de buscar las agrupaciones. Este algoritmo asigna cada instancia a un único cluster (hard clustering) y se basa en mapear las etiquetas cono-cidas a subespacios utilizando técnicas de clasificación supervisada. El segundo algoritmo utiliza las etiquetas disponibles para buscar de forma simultánea los subespacios y las agru¬paciones en un proceso iterativo. Este algoritmo asigna cada instancia a cada cluster con una probabilidad de pertenencia (soft clustering) y se basa en integrar las etiquetas conocidas y la búsqueda en subespacios dentro de clustering basado en modelos. Las propuestas son probadas utilizando diferentes bases de datos reales y sintéticas, incluyendo comparaciones con otros métodos cuando resulten apropiadas. Finalmente, a modo de ejemplo de una aplicación real y actual, se aplican diferentes técnicas de aprendizaje automático, incluyendo una de las propuestas de este trabajo (la más sofisticada) a una tarea de uno de los problemas biológicos más desafiantes hoy en día, el modelado del cerebro humano. Específicamente, expertos neurocientíficos no se ponen de acuerdo en una clasificación de neuronas para la corteza cerebral, lo que imposibilita no sólo cualquier intento de modelado sino también el trabajo del día a día al no tener una forma estándar de llamar a las neuronas. Por lo tanto, las técnicas de aprendizaje automático pueden ayudar a conseguir una solución aceptada para este problema, lo cual puede ser un importante hito para investigaciones futuras en neurociencia.

The development and validation of Australian indices of child development - Part II : validity support

The two outcome indices described in a companion paper (Sanson et al., Child Indicators Research, 2009) were developed using data from the Longitudinal Study of Australian Children (LSAC). These indices, one for infants and the other for 4 year to 5 year old children, were designed to fill the need for parsimonious measures of children’s developmental status to be used in analyses by a broad range of data users and to guide government policy and interventions to support young children’s optimal development. This paper presents evidence from Wave 1data from LSAC to support the validity of these indices and their three domain scores of Physical, Social/Emotional, and Learning. Relationships between the indices and child, maternal, family, and neighborhood factors which are known to relate concurrently to child outcomes were examined. Meaningful associations were found with the selected variables, thereby demonstrating the usefulness of the outcome indices as tools for understanding children’s development in their family and socio-cultural contexts. It is concluded that the outcome indices are valuable tools for increasing understanding of influences on children’s development, and for guiding policy and practice to optimize children’s life chances.

The development and validation of Australian Indices of Child Development — Part I: conceptualisation and development

The Longitudinal Study of Australian Children (LSAC) is a major national study examining the lives of Australian children, using a cross-sequential cohort design and data from parents, children, and teachers for 5,107 infants (3–19 months) and 4,983 children (4–5 years). Its data are publicly accessible and are used by researchers from many disciplinary backgrounds. It contains multiple measures of children’s developmental outcomes as well as a broad range of information on the contexts of their lives. This paper reports on the development of summary outcome indices of child development using the LSAC data. The indices were developed to fill the need for indicators suitable for use by diverse data users in order to guide government policy and interventions which support young children’s optimal development. The concepts underpinning the indices and the methods of their development are presented. Two outcome indices (infant and child) were developed, each consisting of three domains—health and physical development, social and emotional functioning, and learning competency. A total of 16 measures are used to make up these three domains in the Outcome Index for the Child Cohort and six measures for the Infant Cohort. These measures are described and evidence supporting the structure of the domains and their underlying latent constructs is provided for both cohorts. The factorial structure of the Outcome Index is adequate for both cohorts, but was stronger for the child than infant cohort. It is concluded that the LSAC Outcome Index is a parsimonious measure representing the major components of development which is suitable for non-specialist data users. A companion paper (Sanson et al. 2010) presents evidence of the validity of the Index.

The WOMAC knee and hip osteoarthritis indices: Development, validation, globafization and influence on the development of the AUSCAN hand osteoarthritis indices

Clinical measurement in both clinical research and clinical practice requires tools and techniques that are valid, reliable and responsive. Patient-centred self-reported measures provide opportunity to evaluate consequences of osteoarthritis, that are important and relevant to patients with the condition. The WOMAC and AUSCAN Indices are health status measurement questionnaires that are valid, reliable and responsive, easy to complete, simple to score and available in multiple language forms and scaling formats. They provide opportunities to capture patient relevant information, relating to the impact of interventions, in clinical research and clinical practice environments. WOMAC data have also contributed to the development of proposed definitions for responder criteria and state-attainment criteria in osteoarthritis.

Motivation, development and validation of a new spectral greenness index : a spectral dimension related to foliage projective cover

A method is presented for the development of a regional Landsat-5 Thematic Mapper (TM) and Landsat-7 Enhanced Thematic Mapper plus (ETM+) spectral greenness index, coherent with a six-dimensional index set, based on a single ETM+ spectral image of a reference landscape. The first three indices of the set are determined by a polar transformation of the first three principal components of the reference image and relate to scene brightness, percent foliage projective cover (FPC) and water related features. The remaining three principal components, of diminishing significance with respect to the reference image, complete the set. The reference landscape, a 2200 km2 area containing a mix of cattle pasture, native woodland and forest, is located near Injune in South East Queensland, Australia. The indices developed from the reference image were tested using TM spectral images from 19 regionally dispersed areas in Queensland, representative of dissimilar landscapes containing woody vegetation ranging from tall closed forest to low open woodland. Examples of image transformations and two-dimensional feature space plots are used to demonstrate image interpretations related to the first three indices. Coherent, sensible, interpretations of landscape features in images composed of the first three indices can be made in terms of brightness (red), foliage cover (green) and water (blue). A limited comparison is made with similar existing indices. The proposed greenness index was found to be very strongly related to FPC and insensitive to smoke. A novel Bayesian, bounded space, modelling method, was used to validate the greenness index as a good predictor of FPC. Airborne LiDAR (Light Detection and Ranging) estimates of FPC along transects of the 19 sites provided the training and validation data. Other spectral indices from the set were found to be useful as model covariates that could improve FPC predictions. They act to adjust the greenness/FPC relationship to suit different spectral backgrounds. The inclusion of an external meteorological covariate showed that further improvements to regional-scale predictions of FPC could be gained over those based on spectral indices alone.

Development and validation of anthropometric prediction equations for estimation of lean body mass and appendicular lean soft tissue in Indian men and women

Lean body mass (LBM) and muscle mass remains difficult to quantify in large epidemiological studies due to non-availability of inexpensive methods. We therefore developed anthropometric prediction equations to estimate the LBM and appendicular lean soft tissue (ALST) using dual energy X-ray absorptiometry (DXA) as a reference method. Healthy volunteers (n= 2220; 36% females; age 18-79 y) representing a wide range of body mass index (14-44 kg/m2) participated in this study. Their LBM including ALST was assessed by DXA along with anthropometric measurements. The sample was divided into prediction (60%) and validation (40%) sets. In the prediction set, a number of prediction models were constructed using DXA measured LBM and ALST estimates as dependent variables and a combination of anthropometric indices as independent variables. These equations were cross-validated in the validation set. Simple equations using age, height and weight explained > 90% variation in the LBM and ALST in both men and women. Additional variables (hip and limb circumferences and sum of SFTs) increased the explained variation by 5-8% in the fully adjusted models predicting LBM and ALST. More complex equations using all the above anthropometric variables could predict the DXA measured LBM and ALST accurately as indicated by low standard error of the estimate (LBM: 1.47 kg and 1.63 kg for men and women, respectively) as well as good agreement by Bland Altman analyses. These equations could be a valuable tool in large epidemiological studies assessing these body compartments in Indians and other population groups with similar body composition.

Development and validation of anthropometric prediction equations for estimation of body fat in Indonesian men

Body composition of 292 males aged between 18 and 65 years was measured using the deuterium oxide dilution technique. Participants were divided into development (n=146) and cross-validation (n=146) groups. Stature, body weight, skinfold thickness at eight sites, girth at five sites, and bone breadth at four sites were measured and body mass index (BMI), waist-to-hip ratio (WHR), and waist-to-stature ratio (WSR) calculated. Equations were developed using multiple regression analyses with skinfolds, breadth and girth measures, BMI, and other indices as independent variables and percentage body fat (%BF) determined from deuterium dilution technique as the reference. All equations were then tested in the cross-validation group. Results from the reference method were also compared with existing prediction equations by Durnin and Womersley (1974), Davidson et al (2011), and Gurrici et al (1998). The proposed prediction equations were valid in our cross-validation samples with r=0.77- 0.86, bias 0.2-0.5%, and pure error 2.8-3.6%. The strongest was generated from skinfolds with r=0.83, SEE 3.7%, and AIC 377.2. The Durnin and Womersley (1974) and Davidson et al (2011) equations significantly (p<0.001) underestimated %BF by 1.0 and 6.9% respectively, whereas the Gurrici et al (1998) equation significantly (p<0.001) overestimated %BF by 3.3% in our cross-validation samples compared to the reference. Results suggest that the proposed prediction equations are useful in the estimation of %BF in Indonesian men.

Field validation of controlled Monte Carlo data generation for statistical damage identification employing Mahalanobis squared distance

This article presents the field applications and validations for the controlled Monte Carlo data generation scheme. This scheme was previously derived to assist the Mahalanobis squared distance–based damage identification method to cope with data-shortage problems which often cause inadequate data multinormality and unreliable identification outcome. To do so, real-vibration datasets from two actual civil engineering structures with such data (and identification) problems are selected as the test objects which are then shown to be in need of enhancement to consolidate their conditions. By utilizing the robust probability measures of the data condition indices in controlled Monte Carlo data generation and statistical sensitivity analysis of the Mahalanobis squared distance computational system, well-conditioned synthetic data generated by an optimal controlled Monte Carlo data generation configurations can be unbiasedly evaluated against those generated by other set-ups and against the original data. The analysis results reconfirm that controlled Monte Carlo data generation is able to overcome the shortage of observations, improve the data multinormality and enhance the reliability of the Mahalanobis squared distance–based damage identification method particularly with respect to false-positive errors. The results also highlight the dynamic structure of controlled Monte Carlo data generation that makes this scheme well adaptive to any type of input data with any (original) distributional condition.

Towards a standard methodology to evaluate internal cluster validity indices

The evaluation and comparison of internal cluster validity indices is a critical problem in the clustering area. The methodology used in most of the evaluations assumes that the clustering algorithms work correctly. We propose an alternative methodology that does not make this often false assumption. We compared 7 internal cluster validity indices with both methodologies and concluded that the results obtained with the proposed methodology are more representative of the actual capabilities of the compared indices.

Prediction of Multi-Target Networks of Neuroprotective Compounds with Entropy Indices and Synthesis, Assay, and Theoretical Study of New Asymmetric 1,2-Rasagiline Carbamates

In a multi-target complex network, the links (L-ij) represent the interactions between the drug (d(i)) and the target (t(j)), characterized by different experimental measures (K-i, K-m, IC50, etc.) obtained in pharmacological assays under diverse boundary conditions (c(j)). In this work, we handle Shannon entropy measures for developing a model encompassing a multi-target network of neuroprotective/neurotoxic compounds reported in the CHEMBL database. The model predicts correctly >8300 experimental outcomes with Accuracy, Specificity, and Sensitivity above 80%-90% on training and external validation series. Indeed, the model can calculate different outcomes for >30 experimental measures in >400 different experimental protocolsin relation with >150 molecular and cellular targets on 11 different organisms (including human). Hereafter, we reported by the first time the synthesis, characterization, and experimental assays of a new series of chiral 1,2-rasagiline carbamate derivatives not reported in previous works. The experimental tests included: (1) assay in absence of neurotoxic agents; (2) in the presence of glutamate; and (3) in the presence of H2O2. Lastly, we used the new Assessing Links with Moving Averages (ALMA)-entropy model to predict possible outcomes for the new compounds in a high number of pharmacological tests not carried out experimentally.

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