Text Classification Based on Nonlinear Dimensionality Reduction Techniques and Support Vector Machines

Shi, Lukui; Zhang, Jun; Liu, Enhai; He, Pinjia

doi:10.1109/icnc.2007.706

Cited by 11 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Support vector machine is one of the most successful classifiers in many applications including text classification. Hence, many researchers used SVM with dimensionality reduction to improve their studies [29][30][31]. Random forest is also a famous classification method for text classification [32].…”

Section: Performance Of Ga On Tfidf and Latent Dimension Spacementioning

confidence: 99%

Java Bytecode Control Flow Classification: Framework for Guiding Java Decompilation

Sateanpattanakul

Jetpipattanapong

Mathulaprangsan

2021

JMM

View full text Add to dashboard Cite

Decompilation is the main process of software development, which is very important when a program tries to retrieve lost source codes. Although decompiling Java bytecode is easier than bytecode, many Java decompilers cannot recover originally lost sources, especially the selection statement, i.e., if statement. This deficiency affects directly decompilation performance. In this paper, we propose the methodology for guiding Java decompiler to deal with the aforementioned problem. In the framework, Java bytecode is transformed into two kinds of features called frame feature and latent semantic feature. The former is extracted directly from the bytecode. The latter is achieved by two-step transforming the Java bytecode to bigram and then term frequency-inverse document frequency (TFIDF). After that, both of them are fed to the genetic algorithm to reduce their dimensions. The proposed feature is achieved by converting the selected TFIDF to a latent semantic feature and concatenating it with the selected frame feature. Finally, KNN is used to classify the proposed feature. The experimental results show that the decompilation accuracy is 93.68 percent, which is obviously better than Java Decompiler.

show abstract

Section: Performance Of Ga On Tfidf and Latent Dimension Spacementioning

confidence: 99%

Java Bytecode Control Flow Classification: Framework for Guiding Java Decompilation

Sateanpattanakul

Jetpipattanapong

Mathulaprangsan

2021

JMM

View full text Add to dashboard Cite

show abstract

“…A number of methods are suggested for reducing the dimensionality of text documents. Some of them are: nonlinear dimension reduction techniques 14 , discretizing high-dimensional data 15 , latent semantic indexing (LSI) 21 and Document Frequency (DF) 16 etc. We have proposed a lexical approach, where we identify tokens or lexemes in the document.…”

Section: Introductionmentioning

confidence: 99%

A Lexical Approach for Text Categorization of Medical Documents

Jindal

Taneja²

2015

Procedia Computer Science

View full text Add to dashboard Cite

This research proposes a novel lexical approach to text categorization in the bio-medical domain. We have proposed LKNN (Lexical KNN) algorithm, in which lexemes (tokens) are used to represent the medical documents. These tokens are used to classify the abstracts by matching them with the standard list of keywords specified as MESH (Medical Subject Headings). It automatically classifies journal articles of medical domain into specific categories. We have used the collection of medical documents, called Ohsumed, as the test data for evaluating the proposed approach. The results show that LKNN outperforms the traditional KNN algorithm in terms of standard F-measure.

show abstract

“…Generally, both unsupervised and (semi-)supervised DR approaches devote to capturing a new pattern representation through mapping original data into a lower-dimensional latent space. Thereby, from a more general point of view, DR is in fact a data preprocessor and has widely given services to practical applications such as classification [23], clustering [10] and metric learning [20].…”

Section: Introductionmentioning

confidence: 99%

SSPS: A Semi-Supervised Pattern Shift for Classification

Yin

Wang

et al. 2010

Neural Process Lett

View full text Add to dashboard Cite

Recently, a great amount of efforts have been spent in the research of unsupervised and (semi-)supervised dimensionality reduction (DR) techniques, and DR as a preprocessor is widely applied into classification learning in practice. However, on the one hand, many DR approaches cannot necessarily lead to a better classification performance. On the other hand, DR often suffers from the problem of estimation of retained dimensionality for real-world data. Alternatively, in this paper, we propose a new semi-supervised data preprocessing technique, named semi-supervised pattern shift (SSPS). The advantages of SSPS lie in the fact that not only the estimation of retained dimensionality can be avoided naturally, but a new shifted pattern representation that may be more favorable to classification is obtained as well. As a further extension of SSPS, we develop its fast and out-of-sample versions respectively, both of which are based on a shape-preserved subset selection trick. The final experimental results demonstrate that the proposed SSPS is promising and effective in classification application.

show abstract

Text Classification Based on Nonlinear Dimensionality Reduction Techniques and Support Vector Machines

Cited by 11 publications

References 4 publications

Java Bytecode Control Flow Classification: Framework for Guiding Java Decompilation

Java Bytecode Control Flow Classification: Framework for Guiding Java Decompilation

A Lexical Approach for Text Categorization of Medical Documents

SSPS: A Semi-Supervised Pattern Shift for Classification

Contact Info

Product

Resources

About