Fuzzy support vector machine for multi-class text categorization

Wang, Tai-Yue; Chiang, Huei-Min

doi:10.1016/j.ipm.2006.09.011

Cited by 97 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier studies (Lin & Wang, 2002;Wang & Chiang, 2007;Tang, 2011) have proposed different membership functions for the FSVM model and substantiated experimental results on the applied datasets. FCM, a known clustering algorithm introduced by Bezdek et al (1984) groups data of similar characteristics by finding the centroid of clusters, and assigns membership values for data points belonging to the respective clusters.…”

Section: Fcm Based Fsvm Modelmentioning

confidence: 83%

See 1 more Smart Citation

Influence of fuzzy index parameter on FSVM classifier performance

Sridevi

Punniyamoorthy

Arasu

2017

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

Support vector machine (SVM), a machine learning algorithm used extensively for pattern analysis and recognition, is found sensitive to outliers and noise. Fuzzy support vector machine (FSVM) has been used in many applications as a most prominent technique by researchers to overcome the sensitivity issue faced by SVM, and for its good generalisation performance. In this research, a method to justify the performance of FSVM classifier by showing the influence of fuzzy index m on membership function of the model has been proposed. In the first phase of the study, an algorithm to find the optimal fuzzy index using fuzzy C-means (FCM) and to avoid testing all fuzzy index values on the FSVM model has been proposed. The operational complexity of the model can be reduced by this process. In the second phase of this study a FSVM algorithm to incorporate new membership function is proposed. The model is tested on six different datasets and kernel functions and the kernel with the highest classification accuracy is identified as an efficient kernel for the applied dataset. The experimental results on the chosen fuzzy index have proven that the proposed alternate methodology enhances classifier accuracy compared to other research findings. Hence, the model could be applied to diverse fields of FSVM applications.

show abstract

Section: Fcm Based Fsvm Modelmentioning

confidence: 83%

“…The FSVM has been found to be very effective in many real time applications like credit risk evaluation (Wang et al, 2005;Zhang et al, 2014), text categorisation (Wang & Chiang, 2007), leukemia diagnosis (Perez et al, 2008), ECG arrhythmia detection (Ozcan & Gurgen, 2010), etc.…”

Section: December 2017mentioning

confidence: 99%

Influence of fuzzy index parameter on FSVM classifier performance

Sridevi

Punniyamoorthy

Arasu

2017

J. Natn. Sci. Foundation Sri Lanka

View full text Add to dashboard Cite

show abstract

“…Thus substituting (13), (14), and (15) into (12), we obtain the following dual problem. Maximize subject to the constraints:…”

Section: The Proposed Emphatic Constraints Support Vector Machinmentioning

confidence: 99%

“…However, method of [11] treats each input as an input of the opposite class with higher membership and it makes full use of the data and achieves better generalization ability. Also, in two different works [12,13], authors try to determine membership function in multi-category data classification.…”

Section: Introductionmentioning

confidence: 99%

Emphatic Constraints Support Vector Machine

Sabzekar¹,

Yazdi²,

Naghibzadeh³

et al. 2010

IJCEE

View full text Add to dashboard Cite

“…It has an unique advantage in solving small sample, nonlinear and high dimensional pattern recognition. SVM has been successfully applied in wide fields, including facial recognition [1], text classification [2], the image recognition [3], information retrieval, intrusion detection, voice recognition.…”

Section: Introductionmentioning

confidence: 99%

LSTSVM-PBT Multi-class Classification

Yu¹,

Wang²

2017

dtetr

View full text Add to dashboard Cite

SVM is used to solve the problem of the binary-class classification. In view of the practical problems encountered in the multi-class classification problem, LSTSVM-PBT (least squares support vector machines partial binary tree) is using partial binary tree to expand the basic category of classifier for multi-class SVM in this paper. Binary tree hierarchy solved the inseparable regional, improved the classification accuracy, reduced the training time. The time advantage is more obvious, especially the data set is large.

show abstract

Fuzzy support vector machine for multi-class text categorization

Cited by 97 publications

References 25 publications

Influence of fuzzy index parameter on FSVM classifier performance

Influence of fuzzy index parameter on FSVM classifier performance

Emphatic Constraints Support Vector Machine

LSTSVM-PBT Multi-class Classification

Contact Info

Product

Resources

About