Apriori Sets And Sequences - Keith's MS Thesis
Apriori Sets And Sequences
About
Code
Performance Data Collection
·
Data Sets
Documents
Results
·
                                          
Printer Friendly Version
Thesis Report Latex

Intro ] Fast Algorithms for Mining Association Rules.tex ] Mining Association Rules between Sets of Items in Large Databases.tex ]
Mining Association Rules from Set Valued Data.tex ] abstract.tex ] algorithmic.sty ]
appendix-log-metrics.tex ] appendix-performance-data.tex ] appendix-performance-metrics.tex ]
appendix-readme.tex ] appendix-sleep-data.tex ] appendix-stock-data.tex ]
asas-1-candidate.tex ] asas-1-support.tex ] asas-2-candidate.tex ]
asas-2-support.tex ] asas-3-candidate.tex ] asas-algorithm.tex ]
asas-confidence.tex ] asas-details.tex ] asas-duplicate-item-sets.tex ]
asas-general.tex ] asas-implementation-filters.tex ] asas-implementation-other-features.tex ]
asas-implementation-rule-generation.tex ] asas-implementation-support-counting-prune.tex ] asas-implementation.tex ]
asas-input.tex ] asas-multiple-events.tex ] asas.bib ]
asas.tex ] background-apriori-sets.tex ] background-apriori.tex ]
background-association-rules.tex ] background-pattern-matching.tex ] background-weka-arff.tex ]
background.tex ] conclusions-future-work.tex ] contribution.tex ]
data-representation.tex ] event-attributes.tex ] experimental-evaluation.tex ]
future-work.tex ] intro-context.tex ] intro-definition.tex ]
intro-motivation.tex ] intro.tex ] itemset-data-structures.tex ]
kap.bib ] perf-experiments-data-collection.tex ] perf-experiments.tex ]
performance-evaluation.tex ] related-work.tex ] sleep-experiments-old.tex ]
sleep-experiments.tex ] stock-experiments.tex ] thesis-2-2column.tex ]
thesis.aux ] thesis.bbl ] thesis.blg ]
thesis.dvi ] thesis.lof ] thesis.log ]
thesis.lot ] thesis.pdf ] thesis.ps ]
thesis.tex ] [ thesis.toc ]

ASAS Thesis ] Solution ] WPI-CSGSO-thesis-template ]
algorithm-example ] figures ] financial-events ]
old ] other-bib-files ] Up: Documents ]

\contentsline {chapter}{\numberline {1}Introduction}{1} \contentsline {section}{\numberline {1.1}Context of This Research}{1} \contentsline {section}{\numberline {1.2}Motivation}{1} \contentsline {section}{\numberline {1.3}Problem Definition}{3} \contentsline {section}{\numberline {1.4}Contributions of This Work}{4} \contentsline {chapter}{\numberline {2}Background}{6} \contentsline {section}{\numberline {2.1}Association Rules}{6} \contentsline {section}{\numberline {2.2}Apriori Algorithm}{7} \contentsline {section}{\numberline {2.3}Pattern Matching}{8} \contentsline {section}{\numberline {2.4}Weka and ARFF}{8} \contentsline {section}{\numberline {2.5}Apriori Sets Algorithm}{9} \contentsline {chapter}{\numberline {3}Related Work}{10} \contentsline {chapter}{\numberline {4}Event Attributes and Event Identification}{14} \contentsline {section}{\numberline {4.1}Description of Sequence Attributes}{14} \contentsline {section}{\numberline {4.2}Description of Event Attributes}{15} \contentsline {section}{\numberline {4.3}Event Identification}{16} \contentsline {chapter}{\numberline {5}Data Representation}{19} \contentsline {section}{\numberline {5.1}Extension of ARFF}{19} \contentsline {section}{\numberline {5.2}ASAS Item Sets}{20} \contentsline {section}{\numberline {5.3}Item Set Data Structures}{23} \contentsline {chapter}{\numberline {6}ASAS Algorithm}{26} \contentsline {section}{\numberline {6.1}Input}{26} \contentsline {section}{\numberline {6.2}Frequent Item Set Generation}{26} \contentsline {subsection}{\numberline {6.2.1}Level 1 Candidate Generation}{28} \contentsline {subsection}{\numberline {6.2.2}Level 1 Counting Support}{29} \contentsline {subsection}{\numberline {6.2.3}Level 2 Candidate Generation}{30} \contentsline {subsection}{\numberline {6.2.4}Level 2 (and up) Counting Support}{31} \contentsline {subsection}{\numberline {6.2.5}Level 3 (and up) Candidate Generation}{33} \contentsline {subsection}{\numberline {6.2.6}Multiple Events of The Same Type}{35} \contentsline {subsection}{\numberline {6.2.7}Duplicate Item Sets}{36} \contentsline {section}{\numberline {6.3}Rule Generation: Calculating Confidence}{39} \contentsline {chapter}{\numberline {7}ASAS Implementation}{44} \contentsline {section}{\numberline {7.1}Data Preprocessing Filters}{44} \contentsline {section}{\numberline {7.2}Implementing Rule Generation}{46} \contentsline {section}{\numberline {7.3}Support Counting Prune}{46} \contentsline {section}{\numberline {7.4}Other Features}{47} \contentsline {chapter}{\numberline {8}Experimental Evaluation of ASAS}{49} \contentsline {section}{\numberline {8.1}Evaluation on The Computer Performance Domain}{49} \contentsline {subsection}{\numberline {8.1.1}Data Collection}{49} \contentsline {subsection}{\numberline {8.1.2}Rules}{50} \contentsline {subsection}{\numberline {8.1.3}Summary of Results}{52} \contentsline {section}{\numberline {8.2}Evaluation on The Stock Market Domain}{53} \contentsline {subsection}{\numberline {8.2.1}Stock Market Data}{53} \contentsline {subsection}{\numberline {8.2.2}Rules}{54} \contentsline {subsubsection}{Multiple Occurrences of Event Type}{58} \contentsline {subsection}{\numberline {8.2.3}Summary of Results}{60} \contentsline {section}{\numberline {8.3}Evaluation on The Human Sleep Domain}{60} \contentsline {subsection}{\numberline {8.3.1}Clinical Sleep Data}{60} \contentsline {subsection}{\numberline {8.3.2}Rules}{61} \contentsline {subsection}{\numberline {8.3.3}Summary of Results}{63} \contentsline {section}{\numberline {8.4}Performance Evaluation of ASAS}{63} \contentsline {subsection}{\numberline {8.4.1}Time to Mine}{64} \contentsline {subsubsection}{Total Time to Mine}{64} \contentsline {subsubsection}{Time to Mine per Frequent Item Set}{66} \contentsline {subsection}{\numberline {8.4.2}Effect of Increasing Maximum Number of Same Type Events Allowed in a Rule}{67} \contentsline {chapter}{\numberline {9}Conclusions and Future Work}{71} \contentsline {section}{\numberline {9.1}Conclusions}{71} \contentsline {section}{\numberline {9.2}Future Work}{72} \contentsline {subsection}{\numberline {9.2.1}ASAS Extensions}{72} \contentsline {subsection}{\numberline {9.2.2}Improve Candidate Generation}{72} \contentsline {subsubsection}{Improve Candidate Generation: Memory Consumption}{73} \contentsline {subsubsection}{Improve Candidate Generation: Intelligent Same Type Event Handling}{73} \contentsline {subsection}{\numberline {9.2.3}Improve Support Counting}{76} \contentsline {subsection}{\numberline {9.2.4}System Features}{77} \contentsline {chapter}{\numberline {A}Appendix Readme File}{86} \contentsline {chapter}{\numberline {B}Appendix ASAS Log Metrics}{94} \contentsline {chapter}{\numberline {C}Appendix Computer Performance Metrics}{97} \contentsline {chapter}{\numberline {D}Appendix Computer Performance Data}{100} \contentsline {chapter}{\numberline {E}Appendix Stock Market Data}{105} \contentsline {chapter}{\numberline {F}Appendix Sleep Data}{113}

by: Keith A. Pray
Last Modified: July 4, 2004 7:47 AM
© 2004 - 1975 Keith A. Pray.
All rights reserved.

Current Theme: