A Class-Incremental Learning Method Based on One Class Support Vector Machine

نویسندگان

  • Chengfei Yao
  • Jie Zou
  • Yanan Luo
  • Tao Li
  • Gang Bai
چکیده

A method based on one class support vector machine (OCSVM) is proposed for class incremental learning. Several OCSVM models divide the input space into several parts. Then, the 1VS1 classifiers are constructed for the confuse part by using the support vectors. During the class incremental learning process, the OCSVM of the new class is trained at first. Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part. In order to bring more information to the certain support vectors, the support vectors are at the boundary of the distribution of samples as much as possible when the OCSVM is built. Compared with the traditional methods, the proposed method retains the original model and thus reduces memory consumption and training time cost. Various experiments on different datasets also verify the efficiency of the proposed method. Keywords—one class support vector machine; class incremental learning; Gaussian kernel; support vector

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Fault diagnosis in a distillation column using a support vector machine based classifier

Fault diagnosis has always been an essential aspect of control system design. This is necessary due to the growing demand for increased performance and safety of industrial systems is discussed. Support vector machine classifier is a new technique based on statistical learning theory and is designed to reduce structural bias. Support vector machine classification in many applications in v...

متن کامل

پیش بینی ژن‏ های بیماری با استفاده از دسته‏ بند تک‌کلاسی ماشین بردار پشتیبان

Abstract: In disease gene identification and classification, users are only interested in classifying one specific class, disease genes, without considering other classes (non-disease genes). This situation is referred to as one-class classification. Existing machine learning-based methods typically use known disease gene as positive training set and unknown genes as negative training set to bu...

متن کامل

Incremental One-Class Models for Data Classification

In this paper we outline a PhD research plan. This research contributes to the field of one-class incremental learning and classification in case of non-stationary environments. The goal of this PhD is to define a new classification framework able to deal with very small learning dataset at the beginning of the process and with abilities to adjust itself according to the variability of the inco...

متن کامل

A Novel Face Detection Method Based on Over-complete Incoherent Dictionary Learning

In this paper, face detection problem is considered using the concepts of compressive sensing technique. This technique includes dictionary learning procedure and sparse coding method to represent the structural content of input images. In the proposed method, dictionaries are learned in such a way that the trained models have the least degree of coherence to each other. The novelty of the prop...

متن کامل

MULTI CLASS BRAIN TUMOR CLASSIFICATION OF MRI IMAGES USING HYBRID STRUCTURE DESCRIPTOR AND FUZZY LOGIC BASED RBF KERNEL SVM

Medical Image segmentation is to partition the image into a set of regions that are visually obvious and consistent with respect to some properties such as gray level, texture or color. Brain tumor classification is an imperative and difficult task in cancer radiotherapy. The objective of this research is to examine the use of pattern classification methods for distinguishing different types of...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2018