Learn More
Model selection plays a key role in the application of support vector machine (SVM). In this paper, a method of model selection based on the small-world strategy is proposed for least squares support vector regression (LS-SVR). In this method, the model selection is treated as a single-objective global optimization problem in which generalization(More)
With the increase of the training set’s size, the efficiency of support vector machine (SVM) classifier will be confined. To solve such a problem, a novel preextracting method for SVM classification is proposed in this paper. In SVM classification, only support vectors (SVs) have significant influence on the optimization result. We adopt a non-parametric(More)
Unlike animals and humans who are very adept at push recovery, humanoid robots push recovery is difficult for its high dimensional, non-linear, and hybrid features. Existed research results such like Capture points, provide several methods to recover from the push. However when a high magnitude push applies to the humanoid, existed methods are not enough to(More)
In practical engineering, small-scale data sets are usually sparse and contaminated by noise. In this paper, we propose a new sequence of orthogonal polynomials varying with their coefficient, unified Chebyshev polynomials (UCP), which has two important properties, namely, orthogonality and adaptivity. Based on these new polynomials, a new kernel function,(More)
As a novel learning algorithm for single-hidden-layer feedforward neural networks, extreme learning machines (ELMs) have been a promising tool for regression and classification applications. However, it is not trivial for ELMs to find the proper number of hidden neurons due to the nonoptimal input weights and hidden biases. In this paper, a new model(More)
Presently, the data imbalance problems become more pronounced in the applications of machine learning and pattern recognition. However, many traditional machine learning methods suffer from the imbalanced data which are also collected in online sequential manner. To get fast and efficient classification for this special problem, a new online sequential(More)
Because of the high dimensional, non-linear, and hybrid features, humanoid push recovery is very difficult unlike animals and humans who are very adept on this. The topic is currently one of the exciting topics in robotics and existed research results have already provided significant methods to recover from push. However existed researches usually specify(More)