Copyright: © the author(s), publisher and licensee Technoscience Academy. This is an open-access article distributed under the
terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use,
distribution, and reproduction in any medium, provided the original work is properly cited
International Journal of Scientific Research in Science and Technology
Print ISSN: 2395-6011 | Online ISSN: 2395-602X (www.ijsrst.com)
doi : https://doi.org/10.32628/IJSRST229212
103
An Applied Mean Substitutions Technique for Detection of
Anomalous Value in Data Mining
Dr. Darshanaben Dipakkumar Pandya
1
, Dr. Abhijeetsinh Jadeja
2
, Dr. Sheshang D. Degadwala
3
1
Assistant Professor, Department of Computer Science, Shri C.J Patel College of Computer Studies (BCA),
Visnagar, Gujarat, India
2
Principal(I/C), Department of Computer Science, Shri C.J Patel College of Computer Studies (BCA), Visnagar,
Gujarat, India
3
Head of Computer Department, Sigma Institute of Engineering, Vadodara, Gujarat, India
Article Info
Volume 9, Issue 2
Page Number : 103-108
Publication Issue
March-April-2022
Article History
Accepted : 01 April 2022
Published : 05 April 2022
ABSTRACT
In the numerical value database, inliers in a database are subset of observations
adequately small enough compared to the rest of the observations, which
appears to be inconsistent with the remaining data set. They are the result of
instant failures or early failures, experienced in many life-test experiments. The
problem is how to handle Inliers in a dataset, and how to evaluate the Inliers.
This paper describes a revolutionary of approach that uses Inliers detection as a
pre-processing step to detect the Inliers and then applies Mean Substitution
technique algorithm, hence to analyze the effects of the Inliers on the analysis
of dataset.
Keywords: Data Mining, Attribute, Inliers Detection Approach Algorithm,
Mean Substitution Technique Algorithm
I. INTRODUCTION
An anomalous value in database is solitary of the
principle problems featured in data analysis and in
the prediction. The belongings of these anomalous
values are highly reflected on the final results. Our
chief goal is to achieve the final result without error
in the consolidated form, which is use to take
decisions. Now let us consider the following example
as a natural occurrence of a physical phenomenon: 0,
0, 0, 0, 0.01, 0.03, 0.08, 1.50, 1.96, 1.21, 1.75, 2.53,
3.90 and 4.10. Here, the first four observations may be
treated as instantaneous failures, next three
observations may be treated as early failures and
other observations may be treated as coming from any
failure time distribution.
In this study, a method of Inliers detection is
introduced and discussed which provides an approach
to treat anomalous values. This step treats the
anomalous block of values from a real-world
imbalanced database.