KEMBAR78
Algo | PDF | Cluster Analysis | Outlier
Scribd
Upload
60 views3 pages

Algo

Outlier analysis is used for data reliability, event reporting, and secure network functioning. It identifies outliers which helps control data quality, improves robustness under noise/faults, and reduces communication overhead of erroneous data. Outlier detection also efficiently finds abnormal sensor values. The detected outliers likely indicate events of interest. Additionally, outlier detection identifies malicious sensors, detects potential network attacks, and ensures security. Our proposal employs distance-based outlier analysis for clustering nodes to obtain energy efficiency. We use k-means clustering and select cluster heads based on distances to other nodes and neighboring clusters.

Uploaded by

jashmine15
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
60 views3 pages

Algo

Outlier analysis is used for data reliability, event reporting, and secure network functioning. It identifies outliers which helps control data quality, improves robustness under noise/faults, and reduces communication overhead of erroneous data. Outlier detection also efficiently finds abnormal sensor values. The detected outliers likely indicate events of interest. Additionally, outlier detection identifies malicious sensors, detects potential network attacks, and ensures security. Our proposal employs distance-based outlier analysis for clustering nodes to obtain energy efficiency. We use k-means clustering and select cluster heads based on distances to other nodes and neighboring clusters.

Uploaded by

jashmine15
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 3

Outlier analysis:

The identifcation of outliers provides data reliability, event


reporting, and secure functioning of the net-work. Specifcally,
outlier detection controls the quality of measured data, improves
robustness of the data analysis under the presence of noise and
faulty sensors so that the communication overhead of erroneous
data is reduced and the aggregated results are prevented to be
afected. utlier detection also provides an e!cient way to search
for values that do not follow the normal pattern of sensor data in
the network. The detected values consequently are treated as
events indicating change of phenomenon that are of interest.
"urthermore, outlier detection identifes malicious sensors that
always generate outlier values, detects potential network attacks
by adversaries, and further ensures the security of the network.
The previous researches aim at using outlier detection for
malicious node detection and fault detection. #ut for our proposal,
we employ distance based outlier analysis for clustering the
nodes so as to obtain energy e!ciency. The clustering
methodology employs k-means algorithm for forming clusters.
Our proposed Algorithm for CH Selection
$epresent the nodes as a graph
%ertices& The sensor nodes
'dges & Sensor nodes that are within range of one
node are connected by an 'dge.
"ind dominating set.
(o)of)clusters * dominating number
cluster)head+, * dominating set
"or each node i in cluster)head+,
id)src * id of base station
id)dest * id of node i
data * + -.luster /ead0 1 id)src ,
S'(23data4 to id)dest
'nd "or
dominating set:
5ist all nodes in the graph with the distances to other
nodes.
"ind the largest sets of nodes which cover its neighboring
nodes. 5et it be S.
'ach node ni S is chosen as 5eader..
'ach leader node forms cluster.
5eader node gets position information from all nodes in
cluster.
The node with highest distance from each node and is
closer to neighbouring cluster is chosen as ./.
K-means algorithm for CH selection:
5ist all nodes in the graph with the distances to
other nodes.
"ind the set of nodes which cover its neighboring
nodes. 5et it be S.
'ach node in S is assigned the leader.
5eader forms cluster.
./ checks if is at mean distance from all nodes in the
cluster.
6f not the node at mean distance is found and is
chosen as ./.
7dv of k-means algorithm&
+8, 9niform energy drainage at all nodes.
2isadvantage&
+8, nly intra-cluster distance is reduced.
7dvantage of our approach&
+8, ./ spends little energy since inter-cluster distance is reduced.
2isadv&
+8, 9nuniform energy drainage.

You might also like