Biomedical Engineering Reference
In-Depth Information
rules using deviation method. Then, we generate fuzzy rule in accordance with the
definite rule by fuzzifying it in such a way that we obtain a set of fuzzy if-then
rules with consequent parts that represent whether it is a normal data or an
abnormal data. These rules are given to the fuzzy rule base to effectively learn the
fuzzy system. In the testing phase, the test data is matched with fuzzy rules to
detect whether the test data is an abnormal data or a normal data. We apply
KNN classification and DS theory of evidence to classify data. Through these,
we devised a new pattern of intrusion and classifieds category of pattern and apply
event evidence logic with the help of DS theory. Finned pattern of intrusion is
compared with the existing pattern of intrusion which generates a new schema of
pattern and updates a list of pattern of intrusion detection and improves the true
rate of intrusion detection. We used the concept of DS theory in this work on event
evidence to find the validity of data and reduce the rate of intrusion. We also used
the patterns of design of schema and data conversion in data conversion first-type
intrusion detection in MATLAB, but for data of intrusion data in overall string
format, now we have used the classification method. We faced various difficulties
in classification of data conversion string through numeric format for suitability of
classification. In the process of data conversion, we used the ratio mapping concept
used by the machine learning (ML) receptory organization for mapping of data
string to numeric format.
The rest of the chapter is organized as follows: In
Literature Survey,
some
related works are reviewed,
KNN (Known Nearest Neighbor)
deals with KNN
classifier,
The Dempster-Shafer Theory
overviews the DS theory,
KDD Data Set
99
KDD data set,
Method
describes our method,
Experimental Results and
Performance Analysis
shows performance and results, and
Conclusion
draws the
conclusions.
Literature Survey
Classification Method by Fuzzy GNP-Based Class
Association Rules
The work of Han and Kamber [
1
] in the field of intrusion detection with regard to
the fuzzy GNP-based class association approach is designed for databases con-
taining both discrete and continuous attribute as Network Connection Database.
A specific classification method is described as follows: The definition of the
matching degree between the continuous attribute A
i
in rule r with q
i
and testing
data connection with value a
i
is:
MatchDegree q
i
;
a
i
ð
Þ ¼
Fq
i
a
ðÞ
ð
1
Þ
where, Fq
i
represents the membership function for linguistic term q
i
.
and the matching between rule r (p continuous and q discrete attributes) and
new unlabeled connection d is defined as:
Search WWH ::
Custom Search