You are on page 1of 3

Numerical Similarity

Numerical similarity measures how much a number X is similar to a number Y. On the other
hand, it determines which of two number Y and Z is more similar to number X.

Example: X=5, Y=3 and Z=6.

Its very clear that Z is similar to X than Y similar to X, because the distance between X and Z is
Smaller them the distance between X and Y.

How to calculate the distance similarity as a percent:

1- Based on the min and max distance [1]

- Determine a min and max value for attribute a


- Find the min and max distance as shown in figure
| |
-

Disadvantage:

- Finding max and min value is not an easy task in all domain
- Execution time

|X-Y|
Min a X Y Max a

x- min a Max a - x

2- Based on the min and max value [2]

- Determine a min and max value for attribute a


- Find the distance between min and max value
| |
-
Advantages:

- Faster than 1

Disadvantages

- Depending on external values min a and max a


- Execution time.

3- Based on the max value [3]

- Determines the max value for attribute a


- Find the distance between min and max value
| |
-

Advantages:

- Faster than 1 and 2

Disadvantages

- Depending on external values max a


- Execution time.

4- Percent Distance Similarity [4]

This algorithm is independent of any external attribute.

| |
{

Advantages:

- Faster than 1, 2 and 3


- Depending on external values max a
References:

[1] J. Kang, K. M. Sim, Towards Agents and Ontology for Cloud Service Discovery,
International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery,
2011.

[2] M. Barati, R. St-Denis, An Architecture for Semantic Service Discovery and Realizability in
Cloud Computing, 2015 6th International Conference on the Network of the Future (NOF), 2015,
pp.1-6.
[3] S. Hasan, V. V. Kumari Numerical Similarity Algorithms for Cloud Service Discovery and
Selection System, International Journal of Intelligent Engineering and Systems, Vol.10,
No.4, 2017, pp.226-234 DOI: 10.22266/ijies2017.0831.24 (Scopus)

[4] S Hasan, VV Kumari , Generic-distributed framework for cloud services marketplace based
on unified ontology - Journal of Advanced Research, Volume 8, Issue 6, November 2017, Pages
569-576 Elsevie. https://doi.org/10.1016/j.jare.2017.07.003

You might also like