1,721,046 research outputs found
Exploiting coding theory for classification: An LDPC-based strategy for multiclass-to-binary decomposition
Full text linkA powerful strategy for the classification of multiple classes is to create a classifier ensemble that decomposes the polychotomy into several dichotomies. The central issue when designing a multiclass-to-binary decomposition scheme is the definition of both the coding matrix and the decoding algorithm. In this study, we propose a new classification system based on low-density parity-check codes, which is a very effective class of binary block codes. The main idea is to exploit the algebraic properties of the codes to generate the codewords for the coding matrix and to define two decoding approaches, which allow us to detect and recover possible errors or rejects produced by the dichotomizers. Experiments based on benchmark datasets demonstrated that the proposed approach provides a statistically significant improvement in terms of the classification performance compared with state-of-the-art decomposition strategies
Exploiting AUC for Optimal Linear Combination of Dichotomizers
No full textThe combination of classifiers is an established technique to improve the classification performance. The possible combination rules proposed up to now generally try to decrease the classification error rate, which is a performance measure not suitable in many real situations and particularly when dealing with two-class problems. In this case, a good alternative is given by the area under the receiver operating characteristic curve (AUC), whose effectiveness in measuring the classification quality has been proved in many recent papers.
In this paper, we propose a method to achieve the optimal linear combination of two dichotomizers based on the maximization of the AUC of the resulting classification system. The effectiveness of the approach has been confirmed by the tests performed on standard datasets
A multi-context CNN ensemble for small lesion detection
No full textIn this paper, we propose a novel method for the detection of small lesions in digital medical images. Our approach is based on a multi-context ensemble of convolutional neural networks (CNNs), aiming at learning different levels of image spatial context and improving detection performance. The main innovation behind the proposed method is the use of multiple-depth CNNs, individually trained on image patches of different dimensions and then combined together. In this way, the final ensemble is able to find and locate abnormalities on the images by exploiting both the local features and the surrounding context of a lesion. Experiments were focused on two well-known medical detection problems that have been recently faced with CNNs: microcalcification detection on full-field digital mammograms and microaneurysm detection on ocular fundus images. To this end, we used two publicly available datasets, INbreast and E-ophtha. Statistically significantly better detection performance were obtained by the proposed ensemble with respect to other approaches in the literature, demonstrating its effectiveness in the detection of small abnormalities
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Proteomic analysis of platelets treated with gamma irradiation versus a commercial photochemical pathogen reduction technology.
No full textBACKGROUND: Several strategies are currently being tested to reduce the risk of pathogen transmission associated with platelet (PLT) transfusion. Within the framework of the Italian Platelet Technology Assessment Study, we investigated the variations of the protein profiles (proteomics) of apheresis PLT concentrates (PCs) upon treatment with riboflavin and ultraviolet (UV) light (Mirasol; 6.24J/mL; 280-400nm).
STUDY DESIGN AND METHODS: Control, gamma-irradiated, and Mirasol-treated apheresis PCs were assayed on Days 1 and 5 of storage by means of gel-based analytical approaches (two-dimensional gel electrophoresis) and mass spectrometry-based identification of significant (p<0.05 analysis of variance) differential proteins. Supernatants were then assayed for metabolism and oxidative stress-related metabolites through multiple reaction monitoring mass spectrometry.
RESULTS: Only a handful of modifications could be observed in the PLT proteome profiles in response to the Mirasol treatment, which included proteins involved in oxidative stress responses, PLT metabolism, and activation. Results confirmed increased metabolic rate and oxidative stress in the supernatants of treated PLTs (both gamma irradiated and Mirasol treated).
CONCLUSION: From this investigation, it emerges that, from a proteomics standpoint, gamma irradiation results in the acceleration of PLT storage lesions and the Mirasol treatment only moderately exacerbates these phenomena
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Addressing class imbalance in deep learning for small lesion detection on medical images
No full textDeep learning methods utilizing Convolutional Neural Networks (CNNs) have led to dramatic advances in automated understanding of medical images. However, in many medical image classification tasks, lesions occupy only a few pixels of the image. This results in a significant class imbalance between lesion and background. From recent literature, it is known that class imbalance may negatively affect the performance of CNN classification. However, very few research exists in the context of lesion detection. In this work, we propose a two-stage deep learning framework able to deal with the high class imbalance encountered during training of small lesion detectors. First, we train a deep cascade (DC) of long sequences of decision trees with an algorithm designed to handle unbalanced data that also drastically reduces the number of background samples reaching the final stage. The remaining samples are fed to a CNN, whose training benefits from both rebalance and hard mining done by the DC. We evaluated DC-CNN on two severely unbalanced classification problems: microcalcification detection and microaneurysm detection. In both cases, DC-CNN outperformed the CNNs trained with commonly used methods for addressing class imbalance such as oversampling, undersampling, hard mining, cost sensitive learning, and one-class classification. The DC-CNN was also ∼10x faster than CNN at test time
- …
