Performance Analysis of K-mean Clustering Map for Different Nodes

International Journal of Trend in

International Open Access Journal

ISSN No: 2456

@ IJTSRD | Available Online @ www.ijtsrd.com

Performance Analysis of KSubham Bhawsar, Aastha Hajari

Embedded System and VLSI DesignShiv Kumar Singh Institute of Technology

ABSTRACT WSNs is a group of inexpensive and autonomous sensor nodes interconnected and work together to monitor various environmental conditions such as humidity, temperature, pressure, and other climate changes. Wireless sensor nodes are randomly installed and communicate themselves through the wireless communication medium. In this paper we compared the simulation results of the K-mean techniques for different numbers of nodes like 50, 100 and 150. Keyword: K-mean, Nodes, Clusters. I. INTRODUCTION The Wireless sensor networks (WSN) are highly distributed networks of small, lightweight nodes and deployed in large numbers to monitor the environment parameters or system by the measurement of physical parameters such as temperature, pressure, or relative humidity [2]. Each node of the network consists of three subsystems: the sensor subsystem which senses the environment, the processing subsystem which performs local computation on the sensed data, and the communication subsystem which is responsible formessage exchange with neighbour sensor nodes. While individual sensors have limited sensing region, processing power, and energy, networking a large numbers of sensors gives rise to robust, reliable, and accurate sensor network covering a wider region [2]Wireless Sensor Networks (WSNs) typically consist of a large number of low-cost, lowmultifunctional wireless sensor nodes. Nodes are equipped with sensing, communication and computation capabilities, where they communicate via a wireless medium and work collaboratively to accomplish a common task.

International Journal of Trend in Scientific Research and Development (IJTSRD)

International Open Access Journal | www.ijtsrd.com

ISSN No: 2456 - 6470 | Volume - 2 | Issue – 6 | Sep

www.ijtsrd.com | Volume – 2 | Issue – 6 | Sep-Oct 2018

Performance Analysis of K-mean Clustering Map for Different Nodes

Subham Bhawsar, Aastha Hajari edded System and VLSI Design, Department of Electronics and Communication Engineering

Shiv Kumar Singh Institute of Technology & Science (SKSITS), Indore, Madhya Pradesh

WSNs is a group of inexpensive and autonomous sensor nodes interconnected and work together to monitor various environmental conditions such as

pressure, and other climate changes. Wireless sensor nodes are randomly installed and communicate themselves through the wireless communication medium. In this paper we compared

mean techniques for s like 50, 100 and 150.

The Wireless sensor networks (WSN) are highly distributed networks of small, lightweight nodes and deployed in large numbers to monitor the environment parameters or system by the measurement of physical parameters such as

e humidity [2]. Each node of the network consists of three subsystems: the sensor subsystem which senses the environment, the processing subsystem which performs local computation on the sensed data, and the communication subsystem which is responsible for message exchange with neighbour sensor nodes. While individual sensors have limited sensing region, processing power, and energy, networking a large numbers of sensors gives rise to robust, reliable, and accurate sensor network covering a wider region [2]. Wireless Sensor Networks (WSNs) typically consist

cost, low-power and multifunctional wireless sensor nodes. Nodes are equipped with sensing, communication and computation capabilities, where they communicate via

m and work collaboratively to

To get more efficient and effective result of Kalgorithm there have been a lot of research happened in previous day. All researchers worked on different view and with different idea. Krishnaproposed the genetic K-means(GKA) algorithm which integrate a genetic algorithm with Kachieve a global search and fast convergence. Components of sensor node Wireless sensor networks (WSNs) have gained worldwide consideration in recent years, particularly with the proliferation in Micro-Electro(MEMS) technology which has facilitated the development of intelligent sensors. Sensor node as shown in Figure 1 may also have additional application dependent components such as a location finding system, power generator and mobilize [1]. The analog signals produced by the sensors based on the observed phenomenon are transformed to digital signals by ADC, and then fed into the processing unit. The processing unit, which is generally associated with a small storage unit, manages the events that make the sensor node collaborate with other nodes to carry out the assigned sensing tasks. A transceiver unit connects the node to the network [1]. The main job of sensor node in a sensor field is to detect the events, perform quick local data processing, and broadcast the data. Energy consumption is a key issue in wireless sensor networks (WSNs). In a sensor node, energy is consumed by the power supply, the sensor, the computation unit and the broadcasting unit. The wireless sensor node, being a microelectronics device, can only be equipped with a limited power source (≤0.5 Ah, 1.2 V) [1].

Research and Development (IJTSRD)

www.ijtsrd.com

6 | Sep – Oct 2018

Oct 2018 Page: 1215

mean Clustering Map for Different Nodes

nd Communication Engineering Madhya Pradesh, India

and effective result of K-mean algorithm there have been a lot of research happened in previous day. All researchers worked on different view and with different idea. Krishna and Murty[4]

means(GKA) algorithm which integrate a genetic algorithm with K-means in order to achieve a global search and fast convergence.

Wireless sensor networks (WSNs) have gained world-

ation in recent years, particularly with Electro-Mechanical systems

(MEMS) technology which has facilitated the development of intelligent sensors. Sensor node as shown in Figure 1 may also have additional

components such as a location finding system, power generator and mobilize [1]. The analog signals produced by the sensors based on the observed phenomenon are transformed to digital signals by ADC, and then fed into the processing unit.

t, which is generally associated with a small storage unit, manages the events that make the sensor node collaborate with other nodes to carry out the assigned sensing tasks. A transceiver unit connects the node to the network [1]. The main

ode in a sensor field is to detect the events, perform quick local data processing, and broadcast the data. Energy consumption is a key issue in wireless sensor networks (WSNs). In a sensor node, energy is consumed by the power supply, the sensor,

utation unit and the broadcasting unit. The wireless sensor node, being a microelectronics device, can only be equipped with a limited power source

International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456


Fig 1: Components of a sensor node [1] Density based Clustering algorithms: Data ocategorized into core points, border points and noise points. All the core points are connected together based on the densities to form cluster. Arbitrary shaped clusters are formed by various clustering algorithms such as DBSCAN, OPTICS, DBCLASGDBSCAN, DENCLU and SUBCLU [3]. II. K-MEANS CLUSTERING There are many algorithms for partition clustering category, such as kmeans clustering (MacQueen 1967), k-medoid clustering, genetic kalgorithm (GKA), Self-Organizing Map (SOM) and also graph-theoretical methods (CLICK, CAST) [6]. k-means is one of the simplest unsupervisedlearning algorithms that solve the wellclustering problem, in the procedure follows a simple and easy way to classify a given data setcertain number of clusters (assume k clusters) fixed apriority. There are main idea is to define k centre’s, one for each cluster. These centers shoulda cunning way because of different location causes different result. So results, the better choicethem as much as possible far away from each other.For the next step is to take each point belonging to a given data set and associate it to the nearest centre. When no point is pending, the first step is completed and an early group age is done. After we have these k new cancroids, a new binding has to be done between the same data set points and the nearest new centre. A loop has been generated. As a result of this loop wethat the k canters change their location step by step until no more changes are done or incanters do not move any more. A. The process of k-means algorithm: This part briefly describes the standard kalgorithm. K-means is a typical clustering algorithm in data mining and which is widely used for clustering large set of data’s.



Fig 1: Components of a sensor node [1]

Density based Clustering algorithms: Data objects are categorized into core points, border points and noise points. All the core points are connected together based on the densities to form cluster. Arbitrary shaped clusters are formed by various clustering algorithms such as DBSCAN, OPTICS, DBCLASD, GDBSCAN, DENCLU and SUBCLU [3].

There are many algorithms for partition clustering category, such as kmeans clustering (MacQueen

medoid clustering, genetic k-means Organizing Map (SOM) and

theoretical methods (CLICK, CAST) [6]. the simplest unsupervised

the well known clustering problem, in the procedure follows a simple

to classify a given data set through a clusters (assume k clusters) fixed

is to define k centre’s, should be placed in

because of different location causes choice is to place

far away from each other. step is to take each point belonging to

given data set and associate it to the nearest centre. the first step is completed

After we have these k new cancroids, a new binding the same data set

the nearest new centre. A loop has been this loop we may notice

that the k canters change their location step by step in other words

means algorithm: This part briefly describes the standard k-means

means is a typical clustering algorithm in data mining and which is widely used for clustering

Fig. 2: K-Means Algorithm [5, 6] A.1 K-mean Algorithm Process1. Select K points as initial centroid. 2. Repeat. 3. Form k clusters by assigning all points to the

closest centroid. 4. Recomputed the centroid of each cluster Until the

centroid do not change. III. Result Analysis of K-k-means techniques is one ofunsupervised learning algorithmswell known clustering problem. We consider access points of K-means technique for 150, 50 and 100 Nodes as shown in Figure 3, Figure 4, and Figure 5, respectively.

Fig. 3: K-means clustering map for 150 Nodes

International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456-6470

Oct 2018 Page: 1216

Algorithm [5, 6]

mean Algorithm Process Select K points as initial centroid.

Form k clusters by assigning all points to the

Recomputed the centroid of each cluster Until the

Means Technique one of the simplest

algorithms that solve the known clustering problem. We consider five

means technique for 150, 50 and Figure 3, Figure 4, and Figure

means clustering map for 150 Nodes



Fig. 4: K-means clustering map for 50 Nodes

Fig. 5: K-means clustering map for 150 Nodes IV. CONCLUSION The K-means algorithm is a popular clustering algorithm. Distance measure plays a important rule on the performance of this algorithm. Also, we will try to extend future this work for another partition clustering algorithms like K-Medoids, CLARA and CLARANS. REFERENCES 1. Vibhav Kumar Sachan, Syed Akht

“Energy-efficient Communication Methods in Wireless Sensor Networks: A Critical Review” International Journal of Computer Applications (0975 – 8887) Volume 39– No.17, February 2012.

2. Shweta Bhatele and Lalita Bargadiya “Evaluation of Communication Overhead and Energy

0 100 200 300 400 500 600 7000

100

200

300

400

500

600

700

800

900

1000

2

3

4

7

8

10

11

14

15

16

19

21

22

24

25

26

27

28

29

30

31

32

33

35

36

38

39

40

42

43

44

46

47

48

49

50

0 100 200 300 400 500 600 7000

100

200

300

400

500

600

700

800

900

1000

2 3

4

7

8

10 11

14

15

16

19

21

22

24

25

2627

28

29

30

31

32

33

35

36

38

39

40

42

4344

46

47

4849

50

51

5253

5455

56

57

60

61

64

66

67

68

69

70

71

72

74

7576

77

78 7980

8385 87

88

90

91

92

94

95

96

97

98

99

101

102

103

104105

106

107

109

110

111

112

114

115

116

118

119

120

121

122

124

129130

131

132

133

135

136

137

138

139

141

142

144

145

146

147

148149

150





means algorithm is a popular clustering algorithm. Distance measure plays a important rule on the performance of this algorithm. Also, we will try to extend future this work for another partition clustering

Medoids, CLARA and CLARANS.

Vibhav Kumar Sachan, Syed Akhtar Imam efficient Communication Methods in

Wireless Sensor Networks: A Critical Review” International Journal of Computer Applications

No.17, February 2012. Shweta Bhatele and Lalita Bargadiya “Evaluation

Overhead and Energy

Consumption in Wireless Sensor Network using Different Clustering Techniques” IJSHRE, Vol. 2(1), 2014.

3. T. Mohana Priya, Dr. A.Saradh “An Improved Kmeans Cluster algorithm using Map Reduce Techniques to mining of inter and intra clusterdatain Big Data analytics” International Journal of Pure and Applied Mathematics, Volume 119 No. 7 2018, pp. 679-690.

4. Nidhi Singh, Divakar Singh “Performance Evaluation of K-Means and Heirarichal Clustering in Terms of Accuracy and Running Time” International Journal of Computer Science and Information Technologies, Vol. 3 (3) , 2012, pp. 4119-4121

5. Dibya Jyoti Bora, Dr. Anil Kumar Gupta “Effect of Different Distance Measures on the Performance of K-Means Algorithm: An Experimental Study in Matlab” Dibya Jyet al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (2) , 2014, pp. 2501-2506.

6. Shaeela Ayesha, Tasleem Mustafa, Ahsan Raza Sattar & M.Inayat Khan, “Data Mining Model for Higher Education System “,EuropeScientific Research, ISSN 1450No.1 ,2010, pp.27.

7. Amrinder Kaur, “Simulation of Low Energy Adaptive Clustering Hierarchy Protocol for Wireless Sensor Network”, Volume 3, Issue 7, July 2013.

8. Amitabh Basu , Jie Gao, Joseph S. B. MitGirishkumar Sabhnani , “Distributed localization using noisy distance and angle information” 7th AC Minternational symposium on Mobile ad hoc networking and computing, 2006,pp. 262

9. Rui Zhang, Myung J. “Mobile sink update local information through these Aps”, 2008.

10. Shiv Prasad Kori, “Performance Comparison in Terms of Communication Overhead for Wireless Sensor Network Based on Clustering Technique”, Volume 4, Issue 3, ISSN (Online): 2249ISSN (Print): 2278–4209.

11. Labisha R. V, Baburaj E, “Energy Efficient Clustering Algorithms in Wireless Sensor Networks-An Analytical View”, Volume9, Number3, May 2014.

12. E. Ekici , S. Vural, J. McNair, D. Alprobabilistic location verification in randomly deployed wireless sensor networks “ Elsevier Science Publishers B. V, 2006 ,pp.,195

800 900 1000

15

6

912

13

14

1718

20

23

32

34

37

41

45

800 900 1000

1

5

6

912 13

14

17

18

20

2332

3437

41

45

58

59

62

63

65

7381

8284

86

89

90

93100

108

113

117

123

125

126

127128

134

135

137

140

143

International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456-6470

Oct 2018 Page: 1217

Consumption in Wireless Sensor Network using Different Clustering Techniques” IJSHRE, Vol.

A.Saradh “An Improved K-means Cluster algorithm using Map Reduce Techniques to mining of inter and intra cluster datain Big Data analytics” International Journal of Pure and Applied Mathematics, Volume 119 No.

Nidhi Singh, Divakar Singh “Performance Means and Heirarichal Clustering

in Terms of Accuracy and Running Time” onal Journal of Computer Science and

Information Technologies, Vol. 3 (3) , 2012, pp.

Dibya Jyoti Bora, Dr. Anil Kumar Gupta “Effect of Different Distance Measures on the

Means Algorithm: An Experimental Study in Matlab” Dibya Jyoti Bora et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (2)

Shaeela Ayesha, Tasleem Mustafa, Ahsan Raza Sattar & M.Inayat Khan, “Data Mining Model for Higher Education System “,European Journal of Scientific Research, ISSN 1450-216X Vol.43

Amrinder Kaur, “Simulation of Low Energy Adaptive Clustering Hierarchy Protocol for Wireless Sensor Network”, Volume 3, Issue 7,

Amitabh Basu , Jie Gao, Joseph S. B. Mitchell, Girishkumar Sabhnani , “Distributed localization using noisy distance and angle information” 7th AC Minternational symposium on Mobile ad hoc networking and computing, 2006,pp. 262 – 273.

Lee, Seong-Soon Joo, local information through

Performance Comparison in Terms of Communication Overhead for Wireless Sensor Network Based on Clustering Technique”, Volume 4, Issue 3, ISSN (Online): 2249–071X,

V, Baburaj E, “Energy Efficient

Clustering Algorithms in Wireless Sensor An Analytical View”, Volume9,

E. Ekici , S. Vural, J. McNair, D. Al-Abri “Secure probabilistic location verification in randomly

ss sensor networks “ Elsevier Science Publishers B. V, 2006 ,pp.,195-209