See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/315358903

Data analysis using Box and Whisker Plot for Lung Cancer

Conference Paper · April 2017

DOI: 10.1109/IPACT.2017.8245071

CITATIONS READS

32 22,046

3 authors, including:

Chandra Segar Thirumalai Vignesh Manickam

VIT University VIT University
64 PUBLICATIONS 2,719 CITATIONS 1 PUBLICATION 32 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Chandra Segar Thirumalai on 18 March 2017.

The user has requested enhancement of the downloaded file.

 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

Data analysis using Box and Whisker Plot for Lung

Cancer
Chandrasegar Thirumalai, IEEE Member,
School of Information Technology and Engineering,
VIT University, Vellore, India.
[email protected]

Vignesh M Balaji R
MS Software Engineering, MS Software Engineering,
School of Information Technology and Engineering School of Information Technology and Engineering,
VIT University, Vellore, India. VIT University, Vellore, India.
[email protected] [email protected]

Abstract— In statistical analysis, we have a collection of data, easily compare the different datasets. In other words, boxplot
with the use of these data, we have to do analysis based on our also called box and whisker plot method.
requirements. With the collection of data using Statistical
analysis, we deal collection, analysis, presentation and organizing TABLE II. DATA SET OF 2ND PART OF LUNG CANCER ATTRIBUTES.
the data. With the help of statistical analysis, we can find
Race Height Weight Family Copd Year Cancer
underlying patterns, relationships, and trends between data history
samples. The R system for statistical computing is an
environment for data analysis and graphics. Here we are going to Asian 175 85 No Yes 2000 Yes
implement boxplot method and control chart methods for Lung Asian 180 90 Yes Yes 2001 Yes
cancer dataset. With the help of boxplot, we can easily make Asian 182 57 Yes No 2002 No
relations between samples and we can find the outliers. American
Indian 170 80 Yes Yes 2003 Yes
African
Keywords-component; Data analysis, Lung Cancer, Decision
American 182 85 No Yes 2000 No
making White 170 60 Yes Yes 2002 No
Latin 175 65 No No 2003 No
I. INTRODUCTION Asian 178 59 Yes No 2004 No
We have taken lung cancer datasets of 12 primary American
Indian 187 70 No No 2005 No
attributes as shown in the following Table I and II. American
Indian 187 54 Yes Yes 2002 No
TABLE I. DATA SET OF 1ST PART OF LUNG CANCER ATTRIBUTES. American
Age Smoking status Years Average Gender Grade Indian 187 56 Yes Yes 2003 No
smoked per day Asian 187 58 Yes Yes 2001 Yes
Asian 185 89 Yes Yes 2003 Yes
68 Smoker 10 15 Male UG Asian 185 84 No Yes 2002 No
77 Former Smoker 15 10 Male PG Asian 185 74 No Yes 2004 Yes
68 Non Smoker 0 0 Male PG In boxplot method, the input data set is split to quartiles. In
71 Smoker 27 10 Male Nil a boxplot, it has a minimum value, lower quartile, median,
74 Smoker 10 5 Male Nil
51 Smoker 10 3 Female UG
upper quartile, maximum value. Boxplot, it contains one box, it
54 Former Smoker 14 6 Female PG goes from lower quartile to upper quartile. The difference
50 Non Smoker 0 0 Female Nil between upper quartile and lower quartile is the length of the
60 Smoker 5 5 Male UG box. Inside the box of boxplot, one vertical line is drawn, it is
54 Smoker 12 5 Male PG the median of the dataset. Median of the lower samples is
54 Non Smoker 0 0 Male UG called “Lower quartile” and Median of the higher samples is
56 Former Smoker 12 12 Male Nil called “Upper quartile”. In the outside of the box in a boxplot,
87 Smoker 10 10 Male PG two more vertical lines are drawn, one vertical near upper
45 Non Smoker 0 0 Male PG
76 Former Smoker 25 12 Male UG
quartile is called upper whisker and another one line near lower
quartile is called lower whisker is shown in the following Fig.
To analyze the relevant data of Lung cancer dataset we
1. The easiest way to find the quartiles have first sorted the
have an applied Box plot data analysis method which is shown
data and take the minimum and maximum values as lower
in Section 3. A boxplot is a data analysis method used to find
bound and upper bound respectively. Lower quartile, median
the output of the samples. With the use of boxplot, we can

978-1-5090-5682-8 /17/$31.00 ©2017 IEEE

1
 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

upper quartile is we can find using the following methods in

Section 2.

Fig. 1. Box Plot Attributes.

II. DATA ANALYSIS

A. Box Plot: Fig. 2. Smokers by Ages.
Step 1: Sort the data on a primary attribute.
Step 2: Calculate the Median. The above boxplot shows that when comparing to former
Step 3: Calculate the Quartiles. smoker and nonsmoker, the smoker is having higher chances
Quartiles: Q1 (25th percentile), Q3 (75th percentile) of getting affected by lung cancer, from the boxplot of a
smoker having a higher median, when comparing to age
Inter-quartile range: IQR = Q3 – Q1 attribute from people having age 25 to 40 are high chances for
cancer disease.
Five number summary: min, Q1, M, Q3, max

Boxplot: ends of the box are the quartiles, median is

marked, whiskers, and plot outlier individually

Step 4: Calculate the Outlier: More than 1.5 x IQR.

III. CALCULATION AND DISCUSSIONS

This is the sample dataset that we are going to know how

the boxplot method works.

TABLE III. SAMPLE DATASET OF 1ST PART BETWEEN AGE 25 TO 45.

Fig. 3. Cancer in Years (2003 – 2005).
Age Smoking status Years Average Gender Grade
smoked per day Above boxplot shows that when comparing the years 2004
25 Smoker 12 15 Male Nil to 2005, in year the boxplot for getting affected by cancer the
21 Non Smoker 0 0 Male Nil chances is very low, because the median is in the lower quartile
22 Former Smoker 5 2 Male Nil and people in 2005, having higher chances of getting cancer
28 Smoker 10 8 Female PG disease, because the median is near the upper quartile, we can
35 Smoker 7 3 Male PG understand this easily from the boxplot.
18 Former Smoker 8 2 Female PG
19 Non Smoker 0 0 Female PG IV. NUMERICAL RESULT ANALYSIS
40 Smoker 12 6 Male PG
45 Smoker 45 4 Female PG A. Boxplot for cancer in years
23 Smoker 2 5 Male PG

TABLE IV. SAMPLE DATASET OF 2ND PART BETWEEN AGE 25 TO 45.

Race Height Weight Family history Cancer Year
Asian 180 75 Yes Yes 2005
Asian 178 80 No No 2004
Asian 165 78 No No 2005
Asian 178 79 Yes No 2004
Asian 189 75 Yes Yes 2003
Asian 175 80 Yes No 2005
Asian 148 79 No Yes 2005
Asian 168 72 Yes No 2003
Fig. 4. Box plot for Cancer in Years.
Asian 189 85 No No 2004
Asian 168 69 No No 2005

2
 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

In the above Fig. 4, from the median, we can easily E. GG plot for Smoking Status vs Years Smoked
understand that the number of people affected by cancer is
increased with comparing to a nonsmoker.
B. Boxplot for all the attributes in the dataset

Fig. 8. GG plot for Smoking Status vs Years Smoked.

Fig. 5. Boxplot for Overall Attributes.
In Fig. 8 shows the average numbers of cigarette smokers
In the above Fig. 5 shows boxplot for all attributes with are high when compared to former smoker and nonsmoker.
outliers. Here, a maximum average of cigarette consumers per day is 20
C. Boxplot for Smoking status based on Age and least is 0.
F. 3D plot for Lung Cancer

Fig. 6. Boxplot for Smokers by Ages.

From the above Fig. 6, it shows that the age between 60 to

80, people those who are smokers and former smoker are
having higher chances to get cancer with comparing to a
nonsmoker.
D. Boxplot for Smoking status based on Year
Fig. 9. The 3D plot of Lung Cancer.

Fig 9 shows the cancer, years smoked and smoking status.

G. Scatterplot for Lung cancer

Fig. 7. Boxplot for Smoking Status of the Peoples (2000 – 2005).

The numbers of smokers are increased in 2004 when

compared to the year 2000 – 2005. Former smokers also
having fewer chances of getting lung cancer disease with
compared to nonsmoker and smoker. Fig. 10. Scatter plot of Year, Smoking Status, Years Smoked, and Age.

3
 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

I. Control chart

Fig. 11. Lung Cancer Causes Options.

From the above Fig. 11, scatterplot diagram we can easily

make the relationship between the attributes. Here we have
four attributes and four columns. The above scatterplot Fig. 14. C Chart for Cancer over a period of Years.
diagram first column for years, the second column for
smoking status, and the third column for year’s smoked and From the above Fig. 14, the upper control limit for age is
fourth one for age. 1563(15.63), control limit is 1448(14.48) and the lower
control limit is 1334(13.34). Cancer disease symptoms we can
H. 3D Scatterplot
mostly identify between the age 13 to 15.

J. Control Chart

Fig. 12. 3D Scatter plot of Year, Years Smoked, and Age.

Fig. 15. C Chart of 300 Samples of Smokers for Lung Cancer Cause.

From the above control chart, upper control limit is 18 and

control limit is 2.9. It is the control chart for all the data in the
dataset. In the dataset of 300 samples, someone have high
chances of getting lung cancer disease.
V. CONCLUSION
The purpose of this paper is to use “box and whisker plot”
Fig. 13. Lung Cancer Chances. method for visualizing the samples of the dataset and from
that results we can easily make relationships between the
In the above Fig 13 shows the getting chance for lung attributes. From the above boxplot method, we learned about
cancer for all the attributes in the datasets. In the above Fig. 13 which age of people mostly smoking people or farmer
first one age, shows that when the age between 55 to 90, this smoking people will have chances of getting lung cancer
aged people who are having smoking habits have high chances disease. we got some result with the help of these boxplot
of lung cancer disease. method results, we can make a system that gets some input
from the user, so that can predicate whether the person has any
chances to get cancer disease.

4
 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

REFERENCES [21] Chandrasegar Thirumalai, Viswanathan P, “Diophantine based

Asymmetric Cryptomata for Cloud Confidentiality and Blind Signature
[1] Kampstra, Peter. "Beanplot: A boxplot alternative for visual comparison applications,” JISA, Elsevier, 2017.
of distributions." Journal of statistical software 28, no. 1 (2008): 1-9.
[22] Avinash, S., K. Manjunath, and S. Senthil Kumar. "An improved image
[2] Frigge, Michael, David C. Hoaglin, and Boris Iglewicz. "Some processing analysis for the detection of lung cancer using Gabor filters
implementations of the boxplot." The American Statistician 43, no. 1 and watershed segmentation technique." Inventive Computation
(1989): 50-54. Technologies (ICICT), International Conference on. Vol. 3. IEEE, 2016.
[3] Benjamini, Yoav. "Opening the Box of a Boxplot." The American [23] Chandrasegar Thirumalai, Senthilkumar M, Silambarasan R, Carlos
Statistician 42, no. 4 (1988): 257-262. Becker Westphall, “Analyzing the strength of Pell’s RSA,” IJPT, Vol. 8
[4] Hubert, Mia, and Ellen Vandervieren. "An adjusted boxplot for skewed Issue 4, Dec. 2016, pp. 21869-21874.
distributions." Computational statistics & data analysis 52, no. 12 (2008): [24] Zhang, Wenbin, Jian Tang, and Nuo Wang. "Using the machine learning
5186-5201. approach to predict patient survival from high-dimensional survival
[5] Chandrasegar Thirumalai, Senthilkumar M, Vaishnavi B, “Physicians data." Bioinformatics and Biomedicine (BIBM), 2016 IEEE
Medicament using Linear Public Key Crypto System,” in International International Conference on. IEEE, 2016.
conference on Electrical, Electronics, and Optimization Techniques, [25] Chandrasegar Thirumalai, “Review on the memory efficient RSA
ICEEOT, IEEE & 978-1-4673-9939-5, March 2016. variants,” International Journal of Pharmacy and Technology, Vol. 8
[6] Thriumani, Reena, et al. "Cancer detection using an electronic nose: A Issue 4, Dec. 2016, pp. 4907-4916.
preliminary study on detection and discrimination of cancerous cells." [26] Rodriguez, Rafael, et al. "Low-order statistical analysis of 1-D diffuse
Biomedical Engineering and Sciences (IECBES), 2014 IEEE Conference reflectance signals from cancer cells using 2-D scalogram images."
on. IEEE, 2014. Imaging Systems and Techniques (IST), 2016 IEEE International
[7] P. Dhavachelvan, Chandra Segar T, K. Satheskumar, "Evaluation of Conference on. IEEE, 2016.
SOA Complexity Metrics Using Weyuker’s Axioms," IEEE International [27] Vinothini S, Chandra Segar Thirumalai, Vijayaragavan R, Senthil
Advance Computing (IACC), India, pp. 2325 – 2329, March 2009 Kumar M, “A Cubic based Set Associative Cache encoded mapping,”
[8] F. Fioravanti, P. Nesi, “A method and tool for assessing object-oriented International Research Journal of Engineering and Technology (IRJET),
projects and metrics management,” Journal of Systems and Software, Volume: 02 Issue: 02 May -2015
Volume 53, Issue 2, 31 August 2000, Pages 111-136 [28] Chandramowliswaran N, Srinivasan.S, and Chandra Segar.T, “A Note on
[9] Chandrasegar Thirumalai, “Physicians Drug encoding system using an Linear based Set Associative Cache address System” International J. of
Efficient and Secured Linear Public Key Cryptosystem (ESLPKC),” Computer Science and Engg. (IJCSE) & India, Engineering Journals &
International journal of pharmacy and technology, Vol. 8 Issue 3, Sep. 0975-3397, Vol. 4 No. 08 / pp. 1383-1386 / Aug. 2012.
2016, pp. 16296-16303 [29] Benezi, Sofia, et al. "Tract-Based Spatial Statistics analysis of diffusion-
[10] Software metric Numerical Data analysis using Box plot and control tensor imaging data in patients with Small Cell Lung Cancer." Wireless
chart methods, VIT University, DOI:10.13140/RG.2.2.27422.95041 Mobile Communication and Healthcare (Mobihealth), 2014 EAI 4th
[11] Chandrasegar Thirumalai, Rashad Manzoor, “Cost Optimization using International Conference on. IEEE, 2014.
Normal Linear Regression Method for Breast Cancer Type I Skin,” [30] Chandrasegar Thirumalai, Senthilkumar M, “Spanning Tree approach for
IEEE IPACT 2017. Error Detection and Correction,” IJPT, Vol. 8, Issue No. 4, Dec-2016,
[12] Halstead Metric for Intelligence, Effort, Time predictions, pp. 5009-5020
DOI:10.13140/RG.2.2.17988.42881 [31] Vinothini S, Chandra Segar Thirumalai, Vijayaragavan R, “Analyzing
[13] Chandramowliswaran N, Srinivasan.S, and Chandra Segar T, “A Novel the performance of AFRA with its traditional routing,” IRJET, Vol. 2 No.
scheme for Secured Associative Mapping” The International J. of 2, May 2015, pp.373-382
Computer Science and Applications (TIJCSA) & India, TIJCSA [32] Anderson, Paul E., et al. "Predictive modeling of lung cancer recurrence
Publishers & 2278-1080, Vol. 1, No 5 / pp. 1-7 / July 2012 using alternative splicing events versus differential expression data."
[14] McWilliams, Annette, et al. "Sex and smoking status effects on the early Computational Intelligence in Bioinformatics and Computational
detection of early lung cancer in high-risk smokers using an electronic Biology, 2014 IEEE Conference on. IEEE, 2014.
nose." IEEE Transactions on Biomedical Engineering 62.8 (2015): [33] Chandrasegar Thirumalai, Senthilkumar M, “Secured E-Mail System
2044-2054. using Base 128 Encoding Scheme,” International journal of pharmacy
[15] Vaishnavi B, Karthikeyan J, Kiran Yarrakula, Chandrasegar Thirumalai, and technology, Vol. 8 Issue 4, Dec. 2016, pp. 21797-21806.
“An Assessment Framework for Precipitation Decision Making Using [34] Amudhavel, J., et al. "Effective maintenance of replica in distributed
AHP”, International Conference on Electronics and Communication network environment using DST." Advances in Recent Technologies in
Systems (ICECS), IEEE & 978-1-4673-7832-1, Feb. 2016 Communication and Computing (ARTCom), 2010 International
[16] Bromis, Konstantinos, et al. "Analysis of resting state and task-related Conference on. IEEE, 2010.
fMRI data in small cell lung cancer patients before undertaking PCI."
Wireless Mobile Communication and Healthcare (Mobihealth), 2014
EAI 4th International Conference on. IEEE, 2014.
Chandra Segar Thirumalai was born in
[17] E Malathy, Chandra Segar Thirumalai, "Review on non-linear set
Pondicherry capital city, Indian union
associative cache design," IJPT, Dec-2016, Vol. 8, Issue No.4, pp. 5320- territory of Puducherry, in 1983. He received
5330 the Bachelor of Engineering in computer
[18] Dharmarajan, A., and T. Velmurugan. "Lung cancer data analysis by k- science and engineering from Dr. Paul’s
means and farthest first clustering algorithms." Indian Journal of Science Engineering College, Anna University,
and Technology 8.15 (2015).
Chennai, India, in 2005 and Master of Technology in
[19] Chandrasegar Thirumalai, Himanshu Kar, “Memory Efficient Multi Key
(MEMK) generation scheme for secure transportation of sensitive data computer science and engineering from Pondicherry Central
over Cloud and IoT devices,” IEEE IPACT 2017. University, Pondicherry, India, in 2009. He is currently doing
[20] Chandrasegar Thirumalai, Sathish Shanmugam, “Multi-key distribution his Doctorate of Philosophy in School of Information
scheme using Diophantine form for secure IoT communications,” IEEE Technology and Engineering at VIT University, Vellore,
IPACT 2017. India.

5
 International Conference on Innovations in Power and Advanced Computing Technologies [i-PACT2017]

He has been working as Assistant Professor Senior in the

Department of Digital Communications, School of
Information Technology and Engineering at VIT University,
Vellore, India. His area of specialization includes Public Key
Cryptography, and Networking. He is the author of more than
fifteen International journals and five IEEE conferences. He is
a professional member of IEEE and IDES. He received the
GATE score conducted by MHRD, India on 2009 with
87.28% in open general cadre and also qualified in SET
conducted by Tamil Nadu, India on 2016. He also received
VIT Most Active Researcher Award from the year 2011 to
2016.

Vignesh M Currently pursuing MS Software

Engineering at VIT University, School of
Information Technology, Vellore, India.

Balaji R Currently pursuing MS Software

Engineering at VIT University, School of
Information Technology, Vellore, India.

View publication stats