Data Mining Techniques for the Detection of the Risk in Cardiovascular Diseases

2019 ◽  
pp. 313-330
Author(s):  
Karunakaran Dinakaran ◽  
Vishnu Priya ◽  
Palanisamy Valarmathie
Keyword(s):  
Data Mining ◽  
Cardiovascular Diseases ◽  
Data Mining Techniques

Cardiovascular Disease Prediction Using Data Mining Techniques

2019 ◽  
pp. 246-264
Author(s):  
Kalyani Kadam ◽  
Pooja Vinayak Kamat ◽  
Amita P. Malav
Keyword(s):  
Data Mining ◽  
Cardiovascular Disease ◽  
Big Data ◽  
Cardiovascular Diseases ◽  
Primary Objective ◽  
Disease Prediction ◽  
Data Mining Techniques ◽  
Data Architecture ◽  
Life Threatening ◽  
Using Data

Cardiovascular diseases (CVDs) have turned out to be one of the life-threatening diseases in recent times. The key to effectively managing this is to analyze a huge amount of datasets and effectively mine it to predict and further prevent heart-related diseases. The primary objective of this chapter is to understand and survey various information mining strategies to efficiently determine occurrence of CVDs and also propose a big data architecture for the same. The authors make use of Apache Spark for the implementation.

Cardiovascular Disease Prediction Using Data Mining Techniques

2019 ◽  
pp. 159-179
Author(s):  
Kalyani Kadam ◽  
Pooja Vinayak Kamat ◽  
Amita P. Malav
Keyword(s):  
Data Mining ◽  
Cardiovascular Disease ◽  
Big Data ◽  
Cardiovascular Diseases ◽  
Primary Objective ◽  
Disease Prediction ◽  
Data Mining Techniques ◽  
Data Architecture ◽  
Life Threatening ◽  
Using Data

Cardiovascular diseases (CVDs) have turned out to be one of the life-threatening diseases in recent times. The key to effectively managing this is to analyze a huge amount of datasets and effectively mine it to predict and further prevent heart-related diseases. The primary objective of this chapter is to understand and survey various information mining strategies to efficiently determine occurrence of CVDs and also propose a big data architecture for the same. The authors make use of Apache Spark for the implementation.

A Diagnostic Model for Cardiovascular Diseases Using Feature Selection and Data Clustering

2020 ◽  
Vol 17 (6) ◽  
pp. 2859-2865
Author(s):  
Shima Farahbakhsh
Keyword(s):  
Data Mining ◽  
Feature Selection ◽  
Cardiovascular Diseases ◽  
Data Clustering ◽  
Information Gain ◽  
Pearson Correlation ◽  
Large Body ◽  
Diagnostic Model ◽  
Target Feature ◽  
Data Mining Techniques

Cardiovascular diseases are one of the most common diseases and currently, the number of people with cardiovascular diseases is increasing. However, if necessary treatment is not provided for the patient at the right time, it might lead to patient death. Therefore, accurate diagnosis of cardiac problems during the first examination along with suitable treatment can decrease the rate of mortality due to cardiovascular diseases. To this end, data mining techniques can be used. Data mining extracts the necessary data from a large body of information. This data is then is used for data classification and prediction through clustering, classification and/or identification of hidden patterns. Many studies so far have focused on using data mining techniques to diagnose cardiovascular diseases. The present study aims to provide a diagnostic model for cardiovascular diseases using an approach based on feature selection and data clustering as pre-processing steps. The proposed model involves 4 main phases: (1) Pre-processing the data to eliminate null and outlier values from data sets; (2) Choosing effective features by using three methods of Pearson correlation coefficient, Information Gain algorithm, and analysis of the main components which try to remove the features that do not have a special relationship with target feature and the behavior of this feature is independent of the target feature; at the end of this phase, 5 features of 13 initial features are removed. (3) Using the KMeans algorithm in data clustering and developing pre-processes before creating the final cluster and developing a model for predicting the type of cardiovascular diseases. The results obtained from the proposed solution show that am4 algorithms of ID3, Naïve Bayes, SVM, and IBK used, IBK algorithm was the most accurate algorithm with 0.97 accuracy.

KLASIFIKASI SMS SPAM MENGGUNAKAN SUPPORT VECTOR MACHINE

2019 ◽  
Vol 15 (2) ◽  
pp. 275-280
Author(s):  
Agus Setiyono ◽  
Hilman F Pardede
Keyword(s):  
Data Mining ◽  
Support Vector Machine ◽  
Decision Tree ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Spam Detection ◽  
Support Vector Machine Algorithm ◽  
Data Mining Techniques ◽  
To Receive

It is now common for a cellphone to receive spam messages. Great number of received messages making it difficult for human to classify those messages to Spam or no Spam.  One way to overcome this problem is to use Data Mining for automatic classifications. In this paper, we investigate various data mining techniques, named Support Vector Machine, Multinomial Naïve Bayes and Decision Tree for automatic spam detection. Our experimental results show that Support Vector Machine algorithm is the best algorithm over three evaluated algorithms. Support Vector Machine achieves 98.33%, while Multinomial Naïve Bayes achieves 98.13% and Decision Tree is at 97.10 % accuracy.

How Sweet and Ripe are the Fruits? Data Mining Techniques for Classifying and Predicting ‘Quick-Wins’ Direct Capital Investment in Indonesia as One Approach to Business intelligence Orientation and Knowledge Management Scenarios of Indonesian Enterprises

2019 ◽  
Vol 1 (1) ◽  
pp. 121-131
Author(s):  
Ali Fauzi
Keyword(s):  
Data Mining ◽  
Business Intelligence ◽  
Direct Investment ◽  
Capital Investment ◽  
Export Market ◽  
Added Value ◽  
Knowledge Generation ◽  
Management Scenarios ◽  
Data Mining Techniques ◽  
Knowledge Based Economy

The existence of big data of Indonesian FDI (foreign direct investment)/ CDI (capital direct investment) has not been exploited somehow to give further ideas and decision making basis. Example of data exploitation by data mining techniques are for clustering/labeling using K-Mean and classification/prediction using Naïve Bayesian of such DCI categories. One of DCI form is the ‘Quick-Wins’, a.k.a. ‘Low-Hanging-Fruits’ Direct Capital Investment (DCI), or named shortly as QWDI. Despite its mentioned unfavorable factors, i.e. exploitation of natural resources, low added-value creation, low skill-low wages employment, environmental impacts, etc., QWDI , to have great contribution for quick and high job creation, export market penetration and advancement of technology potential. By using some basic data mining techniques as complements to usual statistical/query analysis, or analysis by similar studies or researches, this study has been intended to enable government planners, starting-up companies or financial institutions for further CDI development. The idea of business intelligence orientation and knowledge generation scenarios is also one of precious basis. At its turn, Information and Communication Technology (ICT)’s enablement will have strategic role for Indonesian enterprises growth and as a fundamental for ‘knowledge based economy’ in Indonesia.

Sign in / Sign up

Export Citation Format

Share Document