Dynamic ensemble selection systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. This is achieved by defining a criterion to measure the level of competence of a base classifier, such as, its accuracy in local regions of the feature space around the query instance. However, using only one criterion about the behavior of a base classifier is not sufficient to accurately estimate its level of competence. In this paper, we present a novel dynamic ensemble selection framework using meta-learning. We propose five distinct sets of meta-features, each one corresponding to a different criterion to measure the level of competence of a classifier for the classification of input samples. The meta-features are extracted from the training data and used to train a meta-classifier to predict whether or not a base classifier is competent enough to classify an input instance. During the generalization phase, the meta-features are extracted from the query instance and passed down as input to the meta-classifier. The meta-classifier estimates, whether a base classifier is competent enough to be added to the ensemble. Experiments are conducted over several small sample size classification problems, i.e., problems with a high degree of uncertainty due to the lack of training data. Experimental results show the proposed meta-learning framework greatly improves classification accuracy when compared against current state-of-the-art dynamic ensemble selection techniques.
Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this paper, we present a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way. Previous deep learning-based methods apply the same convolutional filters on wellexposed and saturated pixels, creating ambiguity during training and leading to checkerboard and halo artifacts. To overcome this problem, we propose a feature masking mechanism that reduces the contribution of the features from the saturated areas. Moreover, we adapt the VGG-based perceptual loss function to our application to be able to synthesize visually pleasing textures. Since the number of HDR images for training is limited, we propose to train our system in two stages. Specifically, we first train our system on a large number of images for image inpainting task and then fine-tune it on HDR reconstruction. Since most of the HDR examples contain smooth regions that are simple to reconstruct, we propose a sampling strategy to select challenging training patches during the HDR fine-tuning stage. We demonstrate through experimental results that our approach can reconstruct visually pleasing HDR results, better than the current state of the art on a wide range of scenes.
With the publication of the sequence of the human genome, we are challenged to identify the functions of an estimated 70,000 human genes and the much larger number of proteins encoded by these genes. Of particular interest is the identification of gene products that play a role in human disease pathways, as these proteins include potential new targets that may lead to improved therapeutic strategies. This requires the direct measurement of gene function on a genomic scale in cell-based, functional assays. We have constructed and validated an individually arrayed, replication-defective adenoviral library harboring human cDNAs, termed PhenoSelect library. The adenoviral vector guarantees efficient transduction of diverse cell types, including primary cells. The arrayed format allows screening of this library in a variety of cellular assays in search for gene(s) that, by overexpression, induce a particular disease-related phenotype. The great majority of phenotypic assays, including morphological assays, can be screened with arrayed libraries. In contrast, pooled-library approaches often rely on phenotype-based isolation or selection of single cells by employing a flow cytometer or screening for cell survival. An arrayed placental PhenoSelect library was screened in cellular assays aimed at identifying regulators of osteogenesis, metastasis, and angiogenesis. This resulted in the identification of known regulators, as well as novel sequences that encode proteins hitherto not known to play a role in these pathways. These results establish the value of the PhenoSelect platform, in combination with cellular screens, for gene function discovery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.