Search results for "selection"
showing 10 items of 1940 documents
Effect of somatic cell count level on functional longevity in Valle del Belice dairy sheep assessed using survival analysis.
2009
The objectives of this study were to evaluate the effect of somatic cell count (SCC) on functional longevity and to estimate the heritability of functional longevity using survival analysis in Valle del Belice dairy sheep. A total of 4,880 lactations of 2,190 ewes from 11 flocks were used. In this study, SCC was considered as an indication of subclinical mastitis. In case of clinical cases, identified by the technicians at milking time, test-day weights and milk samples of those ewes were not considered. Somatic cells were analyzed as counts, without any transformation, and were grouped in 3 classes based on the observed SCC maximum (mxSCC). The mxSCC classes, expressed as 103 cells/mL, wer…
Time-to-event analysis of mastitis at first-lactation in Valle del Belice ewes
2007
A time-to-event study for mastitis at first-lactation in Valle del Belice ewes was conducted, using survival analysis with an animal model. The goals were to evaluate the effect of lambing season and level of milk production on the time from lambing to the day when a ewe experienced a test-day with a recorded SCC greater than or equal to 750,000 cells/ml, and to estimate, for this trait, its heritability and the percentage of variation explained by the flock-year of lambing effect. A dataset with 2468 first-lactation records, collected from 1998 to 2003 in Valle del Belice ewes allocated in 17 flocks, was used. The Cox model used included lambing season and total milk yield adjusted for lac…
Convolutional architectures for virtual screening
2020
Abstract Background A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% …
Filtered circular fingerprints improve either prediction or runtime performance while retaining interpretability.
2016
Background Even though circular fingerprints have been first introduced more than 50 years ago, they are still widely used for building highly predictive, state-of-the-art (Q)SAR models. Historically, these structural fragments were designed to search large molecular databases. Hence, to derive a compact representation, circular fingerprint fragments are often folded to comparatively short bit-strings. However, folding fingerprints introduces bit collisions, and therefore adds noise to the encoded structural information and removes its interpretability. Both representations, folded as well as unprocessed fingerprints, are often used for (Q)SAR modeling. Results We show that it can be prefer…
A Probabilistic Classification Procedure Based on Response Time Analysis Towards a Quick Pre-Diagnosis of Student's Attention Deficit
2019
[EN] A classification methodology based on an experimental study is proposed towards a fast pre-diagnosis of attention deficit. Our sample consisted of school-aged children between 8 and 12 years from Valencia, Spain. The study was based on the response time (RT) to visual stimuli in computerized tasks. The process of answering consecutive questions usually follows an ex-Gaussian distribution of the RTs. Specifically, we seek to propose a simple automatic classification scheme of children based on the most recent evidence of the relationship between RTs and ADHD. Specifically, the prevalence percentage and reported evidence for RTs in relation to ADHD or to attention deficit symptoms were t…
Feature selection: A multi-objective stochastic optimization approach
2020
The feature subset task can be cast as a multiobjective discrete optimization problem. In this work, we study the search algorithm component of a feature subset selection method. We propose an algorithm based on the threshold accepting method, extended to the multi-objective framework by an appropriate definition of the acceptance rule. The method is used in the task of identifying relevant subsets of features in a Web bot recognition problem, where automated software agents on the Web are identified by analyzing the stream of HTTP requests to a Web server.
Identifying legitimate Web users and bots with different traffic profiles — an Information Bottleneck approach
2020
Abstract Recent studies reported that about half of Web users nowadays are intelligent agents (Web bots). Many bots are impersonators operating at a very high sophistication level, trying to emulate navigational behaviors of legitimate users (humans). Moreover, bot technology continues to evolve which makes bot detection even harder. To deal with this problem, many advanced methods for differentiating bots from humans have been proposed, a large part of which relies on supervised machine learning techniques. In this paper, we propose a novel approach to identify various profiles of bots and humans which combines feature selection and unsupervised learning of HTTP-level traffic patterns to d…
Didáctica (lengua y literatura)
2017
La diversidad siempre ha estado presente en nuestro alumnado, no obstante, la incorporación de culturas poco presentes en España, fue un revulsivo en los años 90 para la revitalización de la educación intercultural. Pero a nuestro parecer, existe una carencia importante de estudios acerca de cómo esta nueva multiculturalidad ha hecho mella en la sociedad, y en especial en los materiales no curriculares entre los cuales la Literatura Infantil y Juvenil (LIJ) es un componente fundamental. Es importante, pues, y necesario comprobar qué tratamiento se ha hecho de la multiculturalidad en la LIJ y el estereotipo es, sin duda, uno de los aspectos más sensibles que se reflejan en las obras.Nuestro …
A New Neighbour Selection Strategy for Group-Based Wireless Sensor Networks
2008
In any type of networks a neighbour selection method is needed to form the topology of the network and to know which node the information has to be sent to reach a destination. Nowadays, several selection strategies exist that are based on different aspects and mainly designed to work in common networks. In this paper we will show our study about those different methods and, then we show the development of a suitable neighbour selection strategy for group-based wireless sensor networks (WSN) that is based on a capacity parameter defined by us and the new neighbour distance. We also present the proposal architecture for WSNs and the protocol when a new node joins a group and has to select it…
Energy efficient and distributed resource allocation for wireless powered OFDMA multi-cell networks
2017
In this paper, we investigate the energy efficient resource allocation problem for the wireless powered OFDMA multi-cell networks. In the considered system, the users who have data to transmit in the uplink can only be empowered by the wireless power obtained from multiple base stations (BSs) with a large scale of multiple antennas in the downlink. A time division protocol is considered to divide the time of wireless power transfer (WPT) in the downlink and wireless information transfer (WIT) in the uplink into separate time slot. With the objective to improve the energy efficiency (EE) of the system, we propose the antenna selection, time allocation, subcarrier and power allocation schemes…