Classification Rule for Small Samples: A Bootstrap Approach. Rahman, M., M., Hossain, M., M., & Majumder, A., K. International Journal of Advanced Scientific and Technical Research Issue, 3(1):337-344, 2013. ![Classification Rule for Small Samples: A Bootstrap Approach [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex In a recent year, classification is computer implemented and most popular data mining technique. Thus in this paper, we address the issue of classification errors over small samples and propose a new Bootstrap based approach for quantifying the level of classification errors. We investigate the performances of classification techniques and observed that, Bootstrap based classification techniques significantly reduce the classification errors than the usual techniques of small samples. Thus, this paper proposes to apply classification techniques under Bootstrap approach for classifying objects in case of small samples. INTRODUCTION Classification is perhaps the most familiar and most popular data mining technique (M. H. Dunham) [1]. Examples of classification applications include image and pattern recognition, medical diagnosis, loan approval, detecting faults in industry applications, and classifying financial market trends. Estimation and prediction may be viewed as types of classification. When someone estimates your age or guesses the number of marbles in a jar, these are actually classification problems. Before the use of current data mining techniques, classification was frequently performed by simply applying knowledge of the data. Statistical classification is a procedure in which individual items are placed into groups based on quantitative information on one or more characteristics inherent in the items (referred to as traits, variables, characters, etc) and based on a training set of previously labeled items. We still do not have single classifier that can reliably outperform all others on a given data set. The accuracy of a particular parametric classifier on a given data set will clearly depend on the relationship between the classifier and the data (C. M. Van Der Walt and E. Barnard) [2]. By developing statistical classification methods we can asses the performance of the assignment rule, the relative sizes of the classes can be measured formally the differences between classes can also be tested (D. J. Hand) [3].
@article{
title = {Classification Rule for Small Samples: A Bootstrap Approach},
type = {article},
year = {2013},
keywords = {Bootstrap Approach,Fisher's Linear Classification,Neural Network Classification,Quadratic Classification,Small Sample},
pages = {337-344},
volume = {3},
id = {ec2cb174-c7a9-3734-a672-b95274b63084},
created = {2020-11-12T21:53:38.476Z},
file_attached = {true},
profile_id = {3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f},
last_modified = {2021-05-05T18:26:55.141Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
private_publication = {false},
abstract = {In a recent year, classification is computer implemented and most popular data mining technique. Thus in this paper, we address the issue of classification errors over small samples and propose a new Bootstrap based approach for quantifying the level of classification errors. We investigate the performances of classification techniques and observed that, Bootstrap based classification techniques significantly reduce the classification errors than the usual techniques of small samples. Thus, this paper proposes to apply classification techniques under Bootstrap approach for classifying objects in case of small samples. INTRODUCTION Classification is perhaps the most familiar and most popular data mining technique (M. H. Dunham) [1]. Examples of classification applications include image and pattern recognition, medical diagnosis, loan approval, detecting faults in industry applications, and classifying financial market trends. Estimation and prediction may be viewed as types of classification. When someone estimates your age or guesses the number of marbles in a jar, these are actually classification problems. Before the use of current data mining techniques, classification was frequently performed by simply applying knowledge of the data. Statistical classification is a procedure in which individual items are placed into groups based on quantitative information on one or more characteristics inherent in the items (referred to as traits, variables, characters, etc) and based on a training set of previously labeled items. We still do not have single classifier that can reliably outperform all others on a given data set. The accuracy of a particular parametric classifier on a given data set will clearly depend on the relationship between the classifier and the data (C. M. Van Der Walt and E. Barnard) [2]. By developing statistical classification methods we can asses the performance of the assignment rule, the relative sizes of the classes can be measured formally the differences between classes can also be tested (D. J. Hand) [3].},
bibtype = {article},
author = {Rahman, M M and Hossain, M M and Majumder, A K},
journal = {International Journal of Advanced Scientific and Technical Research Issue},
number = {1}
}
Downloads: 0
{"_id":"Ps3QexMREESHzAiKu","bibbaseid":"rahman-hossain-majumder-classificationruleforsmallsamplesabootstrapapproach-2013","author_short":["Rahman, M., M.","Hossain, M., M.","Majumder, A., K."],"bibdata":{"title":"Classification Rule for Small Samples: A Bootstrap Approach","type":"article","year":"2013","keywords":"Bootstrap Approach,Fisher's Linear Classification,Neural Network Classification,Quadratic Classification,Small Sample","pages":"337-344","volume":"3","id":"ec2cb174-c7a9-3734-a672-b95274b63084","created":"2020-11-12T21:53:38.476Z","file_attached":"true","profile_id":"3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","last_modified":"2021-05-05T18:26:55.141Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"private_publication":false,"abstract":"In a recent year, classification is computer implemented and most popular data mining technique. Thus in this paper, we address the issue of classification errors over small samples and propose a new Bootstrap based approach for quantifying the level of classification errors. We investigate the performances of classification techniques and observed that, Bootstrap based classification techniques significantly reduce the classification errors than the usual techniques of small samples. Thus, this paper proposes to apply classification techniques under Bootstrap approach for classifying objects in case of small samples. INTRODUCTION Classification is perhaps the most familiar and most popular data mining technique (M. H. Dunham) [1]. Examples of classification applications include image and pattern recognition, medical diagnosis, loan approval, detecting faults in industry applications, and classifying financial market trends. Estimation and prediction may be viewed as types of classification. When someone estimates your age or guesses the number of marbles in a jar, these are actually classification problems. Before the use of current data mining techniques, classification was frequently performed by simply applying knowledge of the data. Statistical classification is a procedure in which individual items are placed into groups based on quantitative information on one or more characteristics inherent in the items (referred to as traits, variables, characters, etc) and based on a training set of previously labeled items. We still do not have single classifier that can reliably outperform all others on a given data set. The accuracy of a particular parametric classifier on a given data set will clearly depend on the relationship between the classifier and the data (C. M. Van Der Walt and E. Barnard) [2]. By developing statistical classification methods we can asses the performance of the assignment rule, the relative sizes of the classes can be measured formally the differences between classes can also be tested (D. J. Hand) [3].","bibtype":"article","author":"Rahman, M M and Hossain, M M and Majumder, A K","journal":"International Journal of Advanced Scientific and Technical Research Issue","number":"1","bibtex":"@article{\n title = {Classification Rule for Small Samples: A Bootstrap Approach},\n type = {article},\n year = {2013},\n keywords = {Bootstrap Approach,Fisher's Linear Classification,Neural Network Classification,Quadratic Classification,Small Sample},\n pages = {337-344},\n volume = {3},\n id = {ec2cb174-c7a9-3734-a672-b95274b63084},\n created = {2020-11-12T21:53:38.476Z},\n file_attached = {true},\n profile_id = {3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f},\n last_modified = {2021-05-05T18:26:55.141Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {In a recent year, classification is computer implemented and most popular data mining technique. Thus in this paper, we address the issue of classification errors over small samples and propose a new Bootstrap based approach for quantifying the level of classification errors. We investigate the performances of classification techniques and observed that, Bootstrap based classification techniques significantly reduce the classification errors than the usual techniques of small samples. Thus, this paper proposes to apply classification techniques under Bootstrap approach for classifying objects in case of small samples. INTRODUCTION Classification is perhaps the most familiar and most popular data mining technique (M. H. Dunham) [1]. Examples of classification applications include image and pattern recognition, medical diagnosis, loan approval, detecting faults in industry applications, and classifying financial market trends. Estimation and prediction may be viewed as types of classification. When someone estimates your age or guesses the number of marbles in a jar, these are actually classification problems. Before the use of current data mining techniques, classification was frequently performed by simply applying knowledge of the data. Statistical classification is a procedure in which individual items are placed into groups based on quantitative information on one or more characteristics inherent in the items (referred to as traits, variables, characters, etc) and based on a training set of previously labeled items. We still do not have single classifier that can reliably outperform all others on a given data set. The accuracy of a particular parametric classifier on a given data set will clearly depend on the relationship between the classifier and the data (C. M. Van Der Walt and E. Barnard) [2]. By developing statistical classification methods we can asses the performance of the assignment rule, the relative sizes of the classes can be measured formally the differences between classes can also be tested (D. J. Hand) [3].},\n bibtype = {article},\n author = {Rahman, M M and Hossain, M M and Majumder, A K},\n journal = {International Journal of Advanced Scientific and Technical Research Issue},\n number = {1}\n}","author_short":["Rahman, M., M.","Hossain, M., M.","Majumder, A., K."],"urls":{"Paper":"https://bibbase.org/service/mendeley/3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f/file/3b636309-06d8-f983-74e1-363069ade6ec/Classification_Rule_for_Small_Samples___A_Bootstrap_Approach.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","bibbaseid":"rahman-hossain-majumder-classificationruleforsmallsamplesabootstrapapproach-2013","role":"author","keyword":["Bootstrap Approach","Fisher's Linear Classification","Neural Network Classification","Quadratic Classification","Small Sample"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/3d6b17c2-7de8-3a82-bf4f-ddb0e3081e5f","dataSources":["2252seNhipfTmjEBQ"],"keywords":["bootstrap approach","fisher's linear classification","neural network classification","quadratic classification","small sample"],"search_terms":["classification","rule","small","samples","bootstrap","approach","rahman","hossain","majumder"],"title":"Classification Rule for Small Samples: A Bootstrap Approach","year":2013}