Topic
Statistical learning theory
About: Statistical learning theory is a research topic. Over the lifetime, 1618 publications have been published within this topic receiving 158033 citations.
Papers published on a yearly basis
Papers
More filters
•
TL;DR: The method of modulation identification for communication signals based on SVMs is introduced and the classification and identification of communication signals modulation mode can be performed well with the method.
Abstract: Support vector machines(SVMs) is a new pattern recongnition technology, which is based on the statistical learning theory. SVMs has not only simpler structure, but also better performances, especially better generalization ability. The method of modulation identification for communication signals based on SVMs is introduced. The classification and identification of communication signals modulation mode can be performed well with the method.
1 citations
01 Jan 2012
TL;DR: This essay introduces Regularized Optimal Affine Discriminant (ROAD), a high dimensional classification method explicitly using covariance information and studies the problem of information aggregation in social networks, where the focus is to determine aggregate learning status in any finite population network.
Abstract: Yes or no is perhaps the most common answer we provide each day. Indeed, binary answers to well structured questions are the building blocks of our knowledge. I started my research career in drafting such answers in various circumstances within the domains of statistics and machine learning. From statisticians and computer scientists' point of view, classification is a well defined field. But more broadly, discretization is a powerful convention to help us understand the real-world social, economic and scientific situations. Also, the clean and tractable finite sample results from classification literature motivates me to investigate the explicit interplay among parameters in other fields. In this essay, I include my selected works regarding binary status in high dimensional statistics, statistical learning theory and social networks. In the first chapter, I introduce Regularized Optimal Affine Discriminant (ROAD), a high dimensional classification method explicitly using covariance information. In the second chapter, novel performance bounds of oracle type for asymmetric errors under the Neyman-Pearson context are derived. In the third chapter, I study the problem of information aggregation in social networks, where the focus is to determine aggregate learning status in any finite population network.
1 citations
••
TL;DR: As modeling and prediction methods are introduced into the experiment of microwave preparing partially stabilized zirconia (PSZ) and built the stability prediction model, the better prediction accuracy and the better fitting results are verified and analyzed.
Abstract: Support vector machines (SVMs) are a promising type of learning machine based on structural risk minimization and statistical learning theory, which can be divided into two categories: support vector classification (SVC) machines and support vector regression machines (SVR). The basic elements and algorithms of SVR machines are discussed. As modeling and prediction methods are introduced into the experiment of microwave preparing partially stabilized zirconia (PSZ) and built the stability prediction model, the better prediction accuracy and the better fitting results are verified and analyzed. This is conducted to elucidate the good generalization performance of SVMs, specially good for dealing with nonlinear data.
1 citations
•
TL;DR: This paper studies the speaker identification problem using support vector machine, and presents a SVM training method on large-scale training data according to the speech signal, which has good ability on solving binary classification problems.
Abstract: Support vector machine (SVM) is an important learning method of statistical learning theory, and is also a powerful tool for pattern recognition problems. This paper studies the speaker identification problem using support vector machine, and presents a SVM training method on large-scale training data according to the speech signal. Two decision methods are used to apply binary classification problems into multi-classes classification problems for SVM has a good ability on solving binary classification problems. A text-independent speaker identification system based on SVMs was implemented and the results showed good performance.
1 citations
•
TL;DR: The classification algorithm of support vector machine and its application in fault diagnosis are discussed and the result of fault diagnosis by using different kernel function is compared with that by using BP neural network, which shows that the SVM has higher classification ability thanBP neural network in the case of fewer samples.
Abstract: Shortage of fault samples is one of the main reasons that restricting the developing of fault diagnosis. The support vector machine (SVM) is a machine-learning algorithm based on the statistical theory (SLT), which has desirable classification ability even if with fewer samples, SVM provides us a new method to develop the intelligent fault diagnosis. In this paper, the classification algorithm of support vector machine and its application in fault diagnosis are discussed. The result of fault diagnosis by using different kernel function is compared with that by using BP neural network, which shows that the SVM has higher classification ability than BP neural network in the case of fewer samples.
1 citations