Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
40456.pdf (4.95 MB)
ETD Abstract Container
Abstract Header
Detection of Similarly-structured Anomalous sets of nodes in Graphs
Author Info
Sharma, Nikita
ORCID® Identifier
http://orcid.org/0000-0002-6057-6920
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1627665644265336
Abstract Details
Year and Degree
2021, MS, University of Cincinnati, Engineering and Applied Science: Computer Science.
Abstract
Detecting anomalies in a given data set has been a vital task always with various applications in the areas of healthcare, banking, security and law enforcement. While there have been numerous methods and algorithms being developed in the past for anomaly detection, the technique of biclustering numerical data with the help of Triadic Concept Analysis (TCA) as an extension of FCA (Formal Concept Analysis) for ternary relations have started surfacing only recently. We have used this idea along with a very efficient algorithm called as 'TRIMAX Biclustering Algorithm' to find out anomalous biclusters in our data set for a given 'Theta' parameter. This Theta parameter is the condition under which a given node-attribute pair is identied as being similar. The technique of biclustering helps in overcoming the limitation of standard clustering techniques where distance function producing partitions of objects takes into consideration all attributes as this method may be ineffective or difficult to interpret. A Bicluster shows a strong association between a subset of objects and a subset of attributes in a numerical object/attribute data set up which when combined with the statistical concept of Z-Score helps in finding anomalous biclusters in a given data set. This method is flexible and can be scaled to an n-dimensional numerical data set. We go a step further to verify whether the identied biclusters are persistent or not with the change in the 'Theta' parameter. Finally, we present three real-world applications of graph-based anomaly detection of a varying domain, size, shape and density.
Committee
Raj Bhatnagar, Ph.D. (Committee Chair)
Yizong Cheng, Ph.D. (Committee Member)
Nan Niu, Ph.D. (Committee Member)
Pages
92 p.
Subject Headings
Computer Science
Keywords
Anomaly Detection
;
Biclustering
;
TRIMAX Biclustering
;
Graph attributes
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Sharma, N. (2021).
Detection of Similarly-structured Anomalous sets of nodes in Graphs
[Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1627665644265336
APA Style (7th edition)
Sharma, Nikita.
Detection of Similarly-structured Anomalous sets of nodes in Graphs.
2021. University of Cincinnati, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1627665644265336.
MLA Style (8th edition)
Sharma, Nikita. "Detection of Similarly-structured Anomalous sets of nodes in Graphs." Master's thesis, University of Cincinnati, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1627665644265336
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
ucin1627665644265336
Download Count:
99
Copyright Info
© 2021, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.