Information Technology Reference
In-Depth Information
Table 3.
The obtained classification accuracies, sensitivity and specifity values for AIRS
classifier algorithm using 10-fold cross validation
Number of Resources
Classification Accuracy
(%)
Sensitivity
Specificity
50
75
100
66.67
100
58.33
100
54.54
150
50
0
50
200
75
100
66.67
250
58.33
100
54.54
300
58.33
66.67
55.55
58.33
350
100
54.54
400
66.67
100
60
450
75
100
66.67
500
66.67
100
66.67
Table 4.
The obtained classification accuracies, sensitivity and specifity values for Fuzzy-AIRS
classifier algorithm using 10-fold cross validation
Number of Resources
Classification Accuracy
(%)
Sensitivity
Specificity
50
75
100
66.67
100
91.66
85.71
100
150
100
100
100
200
100
100
100
250
91.66
100
85.71
100
100
300
100
100
100
100
350
100
100
100
400
100
100
100
450
100
100
100
500
5 Conclusions and Future Work
With the improvements in expert systems and ML tools, the effects of these innova-
tions are entering to more application domains day-by-day and medical field is one of
them. Decision-making in medical field can sometimes be a trouble. Classification
systems that are used in medical decision-making provide medical data to be exam-
ined in shorter time and more detailed.
In this study, the resource allocation mechanism of AIRS that is among the most
important classification systems of Artificial Immune Systems was changed with a
new one that was formed using fuzzy-logic rules.
In the application phase of this study, Carotid Artery Doppler Signals were used. In
the classifications of Atherosclerosis disease, the analyses were conducted to see the
effects of the new resource allocation mechanism.
According to the application results, Fuzzy-AIRS showed a considerably high per-
formance with regard to the classification accuracy especially for diagnosis of
Atherosclerosis disease. The reached classification accuracy of Fuzzy-AIRS for
Atherosclerosis disease is 100%.
