Non communicable diseases (NCDs), though not as dangerous as communicable diseases as far as proliferation is concerned, these are dangerous by themselves because of their root causes. In this article, our main focus is on predictive analysis of smoking, which is a non-communicable disease, using regression analysis. Regression analysis is a cornerstone of predictive based data mining techniques. We deploy Oracle Data Miner (ODM) which is a software mining tool for tracking smoking analysis report and Support Vector Machine (SVM) algorithm for experimental analysis using nonlinear regression. Risk factors for NCDs are obtained from Global Health Observatory (GHO) data of World Health Organization (WHO) and from reports on Tobacco control from National Tobacco Control Cell (NTCC) for detail survey. The datasets are carefully examined and different prevention methods or hazards to be faced thereof for different age groups are suggested. The treatments or precautions to be taken are dependent upon age groups. This study provides measures in reducing tobacco use and hence can be a key component in the concerned national or global plan.
Data mining provides versatile tools that automatically generate valuable information from data and transform that data into organized information. Today’s challenging task in many organizations is to explore predictive analytics using statistics, data mining and game theory to analyze current and historical facts in order to make predictions about future events. There are various approaches to predictive analytics, and most of them depend on clean databases and the ability to mine data for patterns or to create classifications. This paper mainly focuses on risk factors and datasets of Non Communicable Diseases (NCD)    which are ‘slow- moving catastrophe’. Predictive analysis  based data mining techniques are used to prevent the risk factors of NCD by using data obtained from GHO   and the reports generated by tobacco control in India. Non Communicable Diseases are known as chronic diseases which are not passed from person to person. These mining techniques are used to prevent the risk factors of NCD  by using data obtained from GHO and the reports generated by tobacco control in India. Non Communicable Diseases are known as chronic diseases which are not passed from person to person. These diseases are slow in progression and the main affecting areas in human body are cardiovascular i.e. heart attacks and stroke, chronic respiratory diseases (such as pulmonary disease and asthma), cancer and diabetes. Irrespective of the age group humans are affected with Non Communicable Diseases and are led to death.
The rise of Non Communicable Diseases in humans is propelled by some major risk factors  like; Tobacco use, Physical Inactivity, alcohol consumption, and taking unhealthy diet. The reasons for every risk factor are as follows:
As our main focus is on predictive analysis of smoking, which is a non-communicable disease it forecasts what might happen in the future with an acceptable level of reliability and includes what-if scenarios and risk assessment. Based on the age group different (treatments or cautions) are given for patients immediately or delayed. Thus reducing tobacco use must be a key component in national or global plan. This study provides measures in reducing tobacco use.
REFERENCEShttp://www.who.int/bulletin/volumes/90/1/11-091041/en/  http://www.who.int/gho/database/en/  http://apps.who.int/gho/data/node.home http://www.tobaccoatlas.org/topic/non-communicable-diseases/  http://ghdx.healthdata.org/series/steps-noncommunicable-disease-risk-factors-survey http://www.who.int/mediacentre/factsheets/fs355/en/  https://en.wikipedia.org/wiki/Tobacco_smoking  http://www.who.int/topics/tobacco/en/ http://www.who.int/mediacentre/factsheets/fs385/en/ http://www.healthline.com/health/alcoholism/basics#Overview1 http://www.healthline.com/health/alcoholism/basics#Overview1  Alberti, G.: Noncommunicable diseases: tomorrow’s pandemics,Bull World Health Organ vol.79 n.10 Genebra, Jan. 2001 http://www.wikihow.com/Run-Regression-Analysis-in-Microsoft-Excel https://docs.oracle.com/cd/B28359_01/datamine.111/b28129/regress.htm#DMCON005 Dumortier, A.,Beckjord, E.,Shiffman, S. and Sejdic,E.: Classifying smoking urges via machine learning, 2016 Elsevier Ireland ltd-Sep-2016  Moon, S. S., Kang,S. Y., Jitpitaklert, W. and Kim, S. B.: Decision tree models for characterizing smoking patterns of older adults,2001 Elsevier Ltd. Durmusoglu, Z. D.U.,Ciftci,P.K.: Classification of Smoking Status: The Case of Turkey,2016 IEEE Poynton, M. R., McDaniel,A. M.: Classification of smoking cessation status with a back propagation neural network,2006 ElsevierInc.  Tamilarasi,R. and Porkodi,R.: A study and Analysis of Disease prediction techniques in Data Mining for Healthcare,IJERMt-Marh-2015 Waghmare, K. J.: Prediction of occurrence of Non-communicable Diseases depending on Lifestyle Habits using Clustering Data Mining Technique,Elsevier publication-2013.  Kaur, S. and Bawa,R.K.: Future trends of Data mining in predicting the various diseases in Medical Healthcare sytem,IJEIC-2015 Alamdari, M. S.,Teimouri, M.,Farzadfar, F. and Meshkini, A. H.: Disease detection in Medical Prescriptions using data mining tools,2014 IEEE http://www.oracle.com/technetwork/database/options/advanced-analytics/odm/odmrinstallation-2080768.html http://www.oracle.com/webfolder/technetwork/tutorials/obe/db/11g/r2/prod/bidw/datamining/ODM11gR2-SetUp.htm http://www.predictiveanalyticstoday.com/what-is-predictive-analytics/ http://docs.opencv.org/2.4/doc/tutorials/ml/introduction_to_svm/introduction_to_svm.html https://en.wikipedia.org/wiki/Oracle_Data_Mining https://www.analyticsvidhya.com/blog/2015/10/understaing-support-vector-machine-example-code/  http://businessjargons.com/kiosk-banking.html  https://www.quora.com/What-is-Aadhaar-enabled-payment-system  https://upipayments.co.in/upi-payment-system/
DOWNLOAD THE COMPLETE RESEARCH PAPER PDF
20 total views, 0 views today