Scribd
Upload
13 views12 pages

Age Detection

Uploaded by

chandanahk775
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
13 views12 pages

Age Detection

Uploaded by

chandanahk775
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“JNANA SANGAMA”, BELAGAVI - 590018

K.R PET KRISHNA GOVERNMENT ENGINEERING COLLEGE, K.R PET -571426


Department of Computer Science & Engineering
5th Semester
“DB SCAN CLUSTERING ALGORITHM”
Presented by
MADHUSHREE C K 4GK21CS020

Under the Supervision of

Head of the Department


Under the Guidence Dr Harresh K
Dr Devika G
Assistant Professor
Department of CSE
2023-2024
CONTENTS

• DB scan clustering
• Algorithm
• Numerical Problem
• Advantages
• Drawbacks
• Application
Reference
DB SCAN CLUSTERING

• DBSCAN (Density-Based Spatial Clustering of


Applications with Noise) is a clustering algorithm
commonly used in Data Mining and Machine Learning.
• It was proposed by Martin Ester, Hans-Peter Krieger,
Jorge Sander, and Xiaowei Xu in 1996.
• Density-based: It defines clusters as areas in data space.
• Spatial: It considers the special distribution of data points.
• Clustering with Noise: It identifying noise(outliers) in the
dataset.
ALGORITHM
Initialization:

Assign each point in the dataset as unvisited. For each point p in the dataset:

If p is already visited, continue to the next point. Mark p as visited.

Find all points within distance Eps of p (including p itself).

If the size of Nε​( p) is less than MinPts, mark p as noise and continue to the next point.

Otherwise, assign p as a core point and create a new cluster Add p to the current cluster.

For each point q in Nε​(p):

If q is not visited: Mark q as visited.Find all points within distance Eps of q.

If the size of Nε​(q) is greater than or equal to MinPts, add all points inNε​(q) to the

current cluster.

If q is not already a member of any cluster, add q to the current cluster as a border
NUMERICAL EXAMPLE

Apply the DBSCAN algorithm to the given data points


Create the clusters with minPts=4
Epsilon(€)=1.9

? Data points:
P1(3,7) P2(4,6) P3(5,5)P4(6,4)
P5(7,3) P6(6,2)P7(7,2)P8(8,4)
P9(3,3)P10(2,6)P11(3,5)P12(2,4)

Solution: Use Euclidian distance and calculate between each


points.
Distance(A(x1,y1),B(x2,y2))=
Distances Calculation
minPts=4 and epsilon()=1.9
p1 p2 p3 p4 p5 p6 p7 p8 p9 p10 p11 p12 points status
P1(3,7) 0 P1:p2,p10
Noise Border
P2(4,6) 1.41 0 P2:p1,p3,p11
Core
P3(5,5) 2.83 1.41 0 P3:p2,p4
Noise Border
P4(6,4) 4.24 2.83 1.41 0 P4:p3,p5
Noise Border
P5(7,3) 5.66 4.24 2.83 1.41 0 P5:p4,p6,p7,p8
Core
P6(6,2) 5.83 4.47 3.16 2.00 1.41 0 P6:p5,p7
Noise Border
P7(7,2) 6.40 5.00 3.61 2.24 1.00 1.00 0 P7:p5,p6
Noise Border
P8(8,4) 5.83 4.47 2.83 2.00 1.41 2.83 2.24 0 P8:p5
Noise Border
P9(3,3) 4.00 3.16 3.16 3.16 4.00 3.16 4.12 5.10 0 P9:p12
Noise
P10(2,6) 1.41 2.00 4.47 4.47 5.83 5.66 6.40 6.32 3.16 0 P10:p1,p11
Noise Border
P11(3,5) 2.00 1.41 3.16 3.16 4.47 4.24 5.00 5.10 2.00 1.41 0 P11:p2,p10,p1
2 Core
P12(2,4) 3.16 2.83 4.00 4.00 5.10 4.47 5.39 6.00 1.41 2.00 1.41 0 P12:p9,p11
Noise Border
Table: Distances calculation and Status
8

5
Y-axis

0
0 1 2 3 4 5 6 7 8 9
X-axis

Graph: Clustering
ADVANTAGES

• No Need for Distance Metrics

• Efficient for Large Dataset

• Ability to Handle Noise

• Automatic Determination of Clusters

• Robust to Density Variations ext


DRAWBACKS

• Sensitive to Parameters:
• Difficulty with Varying Density
• Computational Complexity
• Non-Euclidean Spaces
• Cluster Shape Sensitivity
• Handling noise and Outliers
APPLICATION

 Anomaly Detection
 Spatial Data Analysis:
 Image Segmentation
 Customer Segmentation
 Genomics and Bioinformatics
 Recommendation System
 Healthcare Data Analysis
 Environmental Monitoring
REFERENCE

• https://www.geeksforgeeks.org/self-organising-maps-kohonen-maps/
• https://www.simplilearn.com/self-organizing-kohonen-maps-article
• https://en.wikipedia.org/wiki/Self-organizing_map
THANK YOU

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy