Learn More
Multiclass SVMs are usually implemented by combining several two-class SVMs. The one-versus-all method using winner-takes-all strategy and the one-versus-one method implemented by max-wins voting are popularly used for this purpose. In this paper we give empirical evidence to show that these methods are inferior to another one-versusone method: one that(More)
Choosing optimal hyperparameters for support vector machines is an important step in SVM design. This is usually done by minimizing either an estimate of generalization error or some other related performance measures. In this paper, we empirically study the usefulness of several simple performance measures that are very inexpensive to compute. The results(More)
This paper gives a new iterative algorithm for kernel logistic regression. It is based on the solution of a dual problem using ideas similar to those of the Sequential Minimal Optimization algorithm for Support Vector Machines. Asymptotic convergence of the algorithm is proved. Computational experiments show that the algorithm is robust and fast. The(More)
Dendritic cells (DCs), monocytes, and macrophages are leukocytes with critical roles in immunity and tolerance. The DC network is evolutionarily conserved; the homologs of human tissue CD141(hi)XCR1⁺ CLEC9A⁺ DCs and CD1c⁺ DCs are murine CD103⁺ DCs and CD64⁻ CD11b⁺ DCs. In addition, human tissues also contain CD14⁺ cells, currently designated as DCs, with an(More)
In this paper, we propose a multi-category classification method that combines binary classifiers through soft-max function. Posteriori probabilities are also obtained. Both, one-versus-all and one-versusone classifiers can be used in the combination. Empirical comparison shows that the proposed method is competitive with other implementations of(More)
During gestation the developing human fetus is exposed to a diverse range of potentially immune-stimulatory molecules including semi-allogeneic antigens from maternal cells, substances from ingested amniotic fluid, food antigens, and microbes. Yet the capacity of the fetal immune system, including antigen-presenting cells, to detect and respond to such(More)
Regulatory B cells (B-reg) produce IL-10 and suppress inflammation in both mice and humans, but limited data on the phenotype and function of these cells have precluded detailed assessment of their contribution to host immunity. In this article, we report that human B-reg cannot be defined based on a phenotype composed of conventional B cell markers, and(More)
Feature selection is a commonly addressed problem in classification. In gene expression-based cancer classification, a large number of genes in conjunction with a small number of samples makes the gene selection problem more important but also more challenging. Support vector machine as a popular classification algorithm, has been successfully used in(More)
We studied two cancer classification problems with mass spectrometry data and used SVM-RFE to select a small subset of peaks as input variables for the classification. Our study shows that, SVM-RFE can select a good small subset of peaks with which the classifier achieves high prediction accuracy and the performance is much better than with the feature(More)