A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine

Cao, Lijuan; Chua, Kok Seng; Chong, Wai Kiong; Lee, H. P.; Gu, Qingming

doi:10.1016/s0925-2312(03)00433-8

Cited by 448 publications

(245 citation statements)

References 22 publications

Supporting

Mentioning

225

Contrasting

Unclassified

Order By: Relevance

“…We performed other experiments, not reported in this paper, without PCA and there is an average decrease of 2% in the accuracy. Our architectural choice is also based on the results published by [43], which shows that there is an improvement when PCA is applied before SVM, and by [44], which shows that PCA before SVM can be used to speed-up training time with no major impact in the accuracy.…”

Section: E Classificationmentioning

confidence: 99%

Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns

Nogueira

Lotufo

Machado

2014

2014 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS) Proceedings

View full text Add to dashboard Cite

Section: E Classificationmentioning

confidence: 99%

Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns

Nogueira

Lotufo

Machado

2014

2014 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS) Proceedings

View full text Add to dashboard Cite

“…In [6], GA was in use for features and parameters selection for intrusion detection model. The Support Vector Machines (SVM) has been applied as an intrusive analysis engine.…”

Section: Related Workmentioning

confidence: 99%

“…PCA purposely is to reduce the dimension of the data while retaining as much as possible of the variation present in the original dataset. It provides a way of identifying patterns in data, and expressing the data in such a way as to highlight their similarities and differences [6,11]. However, PCA here was used to transform the input vectors to the new search space.…”

Section: Gpcs Kmentioning

confidence: 99%

Enhancing MLP Performance in Intrusion Detection using Optimal Feature Subset Selection based on Genetic Principal Components

Ahmad¹

2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

Abstract:Computer and network systems nowadays are facing many security issues, one of which considered important is intrusion. To prevent such intrusion, a mechanism for optimal intrusion detection is deemed necessary. A number of tools and techniques are available, yet most of them still face a main problem that is on performance. The performance, in essence, can be increased by reducing false positives and increasing accurate detection rate. What has made the performance terrible in the existing intrusion detection approaches is due to the use of a raw dataset that includes redundancy and leads the classifier to be confused. To overcome this issue, Principal Component Analysis (PCA) has been used to project a number of raw features on principal feature space and to select the features based on their sensitivity determined by the magnitude of eigenvalues. Here, only the features corresponding to the highest eigenvalues are selected; the remaining features, by contrast, are ignored. Due to the ignorance of many important and sensitive features for the classifier for their lowest eigenvalues, this method comes to be not optimal. Therefore, a suitable method is necessary to select a subset of features, which, in turn, can enhance the classifier performance. The focus of this research is to observe a space of principal features to find a subset of sensitive features to the classifier, which can optimize the detection accuracy. Genetic Algorithm (GA) has been applied to solve an optimization problem. The raw features have, afterwards, been transformed through PCA into principal features space. GA, in this case, was used to search this features space to obtain principal components called genetic principal components (GPC). The feature set obtained through this process was, in turn, presented to the classifier. The Multilayer Perceptron (MLP), meanwhile, was used for classification considering its proven ability. Additionally, Knowledge Discovery and Data mining (KDD) cup dataset was used for the validation of the proposed approach, which is considered as a benchmark to evaluate the intrusion detection approaches. The performance of this approach has been analyzed and compared with a number of existing approaches. The results then show that proposed method outperforms the existing approaches. Not only does it significantly reduce the dimension of the feature space but also improves the detection accuracy.

show abstract

“…ICA is an unsupervised method in which prior knowledge about the class labels is unknown. It is a more advantageous than the PCA [4] because PCA seeks the projection which has maximum variance whereas ICA [5] seeks the projection which has maximum independence. That is the reason in this paper ICA is used for the maximization of independence due to which classification accuracy gets increased.…”

Section: Independent Component Analysismentioning

confidence: 99%

“…Hybrid dimensionality reduction method [1] is the combination of these two approaches which uses both the criteria. In supervised learning LDA [2] and Support Vector Machine [3] are the tow famous dimensionality reduction techniques, whereas in unsupervised learning PCA [4] and Independent Component Analysis [5] and last there is combination supervised and unsupervised approach which is known as Support Vector Machine and Independent Component Analysis.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Hybrid (supervised and unsupervised) method for multiclass data set

Chakre¹,

Naik²

2014

IOSRJCE

View full text Add to dashboard Cite

A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine

Cited by 448 publications

References 22 publications

Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns

Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns

Enhancing MLP Performance in Intrusion Detection using Optimal Feature Subset Selection based on Genetic Principal Components

Performance Analysis of Hybrid (supervised and unsupervised) method for multiclass data set

Contact Info

Product

Resources

About