Using chi-square statistics to measure similarities for text categorization

Chen, Yao-Tsung; Chen, Meng Chang

doi:10.1016/j.eswa.2010.08.100

Cited by 95 publications

(44 citation statements)

References 12 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After every accident investigation report has been decomposed using HFACS framework, the frequency and marginal frequency of every factor can be calculated. First, the χ 2 (Chi-square) (Chen, Y., Chen, M. C. 2011) is used to test for independence, where we assume that represents the hypothesis that human factors of HFACS are independent of each other; states the human factors of HFACS are dependent and correlated to each other: N N N N N N N N N N N N N …”

Section: Overview Of Analysis Methods Rationalementioning

confidence: 99%

Routes to Failure and Prevention Recommendations in Work Systems of Hydropower Construction

Zheng

Zhou

Wang

et al. 2018

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

Abstract. There are many types of accidents with their own characteristics in hydropower construction. The accidents are mainly results of human errors. It is important to find out the routes to failure and give recommendations pertinently for different accident types. First, 869 accident investigation reports are collected and the human factors are filtered using the Human Factors Analysis and Classification System (HFACS) framework, the norms which link the accident causes and human factors are also explored, the first three accident types are determined by the frequency statistics. The ranking of the factors and the norms of the three accident types is presented using the frequency statistics. The Chi-square, lambda and odds ratios are used to analyze the interdependences between adjacent level factors of three highest frequency accident types. At last, based on the correlation analysis between different human factors, the routes to failure can be determined; containing the norm frequency of factors, the safety recommendations are given to the different accident types pertinently. The results can be auxiliary and effective information for safety managers to conduct scientific and pertinent safety managements.

show abstract

Section: Overview Of Analysis Methods Rationalementioning

confidence: 99%

Routes to Failure and Prevention Recommendations in Work Systems of Hydropower Construction

Zheng

Zhou

Wang

et al. 2018

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

show abstract

“…Filters are computationally simple and fast. Some of the popular filter approaches are mutual information [14], chisquare [15], and information gain [16].…”

Section: Dimensionality Reductionmentioning

confidence: 99%

“…After features, that well model the problem, have been defined, machine learning algorithms need to be chosen and in the field of miRNA detection supervised methods have been applied widely (see Chapters 10,12,[15][16][17][18].…”

Section: What Are Features?mentioning

confidence: 99%

Introduction to Machine Learning

Baştanlar

Özuysal

2013

Methods in Molecular Biology

348

171

View full text Add to dashboard Cite

The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.

show abstract

“…The information gain of term "w" is: (2) ranges from 1 to 4. 2)Chi-Square Statistic Chi-square statistic ( ) quantify the importance of the feature terms by estimating the correlation between terms and classes [10]. The terms should be selected with the highest correlation.…”

Section: Select the Feature Termsmentioning

confidence: 99%

A Method for Tracking Flu Trends through Weibo

Hu²

2016

IJDTA

View full text Add to dashboard Cite

Using chi-square statistics to measure similarities for text categorization

Cited by 95 publications

References 12 publications

Routes to Failure and Prevention Recommendations in Work Systems of Hydropower Construction

Routes to Failure and Prevention Recommendations in Work Systems of Hydropower Construction

Introduction to Machine Learning

A Method for Tracking Flu Trends through Weibo

Contact Info

Product

Resources

About