Data Mining - Concepts and Techniques.

Cardiovascular diseases (CVD) are among the most common serious illnesses affecting human health. CVDs may be prevented or mitigated by early diagnosis, and this may reduce mortality rates. Identifying risk factors using machine learning models is a promising approach. We would like to propose a model that incorporates different methods to achieve effective prediction of heart disease. For our proposed model to be successful, we have used efficient Data Collection, Data Pre-processing and Data Transformation methods to create accurate information for the training model. We have used a combined dataset (Cleveland, Long Beach VA, Switzerland, Hungarian and Stat log). Suitable features are selected by using the Relief, and Least Absolute Shrinkage and Selection Operator (LASSO) techniques. New hybrid classifiers like Decision Tree Bagging Method (DTBM), Random Forest Bagging Method (RFBM), K-Nearest Neighbors Bagging Method (KNNBM), AdaBoost Boosting Method (ABBM), and Gradient Boosting Boosting Method (GBBM) are developed by integrating the traditional classifiers with bagging and boosting methods, which are used in the training process. We have also instrumented some machine learning algorithms to calculate the Accuracy (ACC), Sensitivity (SEN), Error Rate, Precision (PRE) and F1 Score (F1) of our model, along with the Negative Predictive Value (NPR), False Positive Rate (FPR), and False Negative Rate (FNR). The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy while using RFBM and Relief feature selection methods (99.05%).

/pdf/efficient-prediction-of-cardiovascular-disease-using-machine-1g3efyu5h4.pdf

Efficient Prediction of Cardiovascular Disease Using Machine Learning Algorithms With Relief and LASSO Feature Selection Techniques

Cardio Vascular Disease (CVD) is, for the most part, alluding to conditions that include limited or blocked veins that can prompt a heart attack, chest torment (angina) or stroke. The machine learning classifier predicts the ailment dependent on the state of the side effect endured by the patient. This paper intends to look at the presentation of the Machine learning tree classifiers in anticipating Cardio Vascular Disease (CVD). Machine learning tree classifiers, for example, Random Forest, Decision Tree, Logistic Regression, Support vector machine (SVM), K-nearest neighbors (KNN) were broke down dependent on their precision and AUC ROC scores. In this investigation of foreseeing Cardiovascular Disease, the Random woodland Machine learning classifier accomplished a higher precision of 85%, ROC AUC score of 0.8675 and execution time of 1.09 sec.

Analysis and Prediction of Cardio Vascular Disease using Machine Learning Classifiers

A stroke is caused when blood flow to a part of the brain is stopped abruptly. Without the blood supply, the brain cells gradually die, and disability occurs depending on the area of the brain affected. Early recognition of symptoms can significantly carry valuable information for the prediction of stroke and promoting a healthy life. In this research work, with the aid of machine learning (ML), several models are developed and evaluated to design a robust framework for the long-term risk prediction of stroke occurrence. The main contribution of this study is a stacking method that achieves a high performance that is validated by various metrics, such as AUC, precision, recall, F-measure and accuracy. The experiment results showed that the stacking classification outperforms the other methods, with an AUC of 98.9%, F-measure, precision and recall of 97.4% and an accuracy of 98%.

/pdf/stroke-risk-prediction-with-machine-learning-techniques-35jz9bdz.pdf

Stroke Risk Prediction with Machine Learning Techniques

A comparative study on machine learning based heart disease prediction

Healthcare is an inevitable task to be done in human life. Cardiovascular disease is a broad category for a range of diseases that are affecting heart and blood vessels. The early methods of forecasting the cardiovascular diseases helped in making decisions about the changes to have occurred in high-risk patients which resulted in the reduction of their risks. The health care industry contains lots of medical data, therefore machine learning algorithms are required to make decisions effectively in the prediction of heart diseases. Recent research has delved into uniting these techniques to provide hybrid machine learning algorithms. In the proposed research, data pre-processing uses techniques like the removal of noisy data, removal of missing data, filling default values if applicable and classification of attributes for prediction and decision making at different levels. The performance of the diagnosis model is obtained by using methods like classification, accuracy, sensitivity and specificity analysis. This project proposes a prediction model to predict whether a people have a heart disease or not and to provide an awareness or diagnosis on that. This is done by comparing the accuracies of applying rules to the individual results of Support Vector Machine, Gradient Boosting, Random forest, Naive Bayes classifier and logistic regression on the dataset taken in a region to present an accurate model of predicting cardiovascular disease.

Prediction of Cardiovascular Disease Using Machine Learning Algorithms

Bitcoin is a decentralized digital currency without a central bank or single administrator sent from user to user on the peer-to-peer bitcoin blockchain network without intermediaries’ need. In this Bitcoin trend analysis work, initial attributes are considered from five sectors based on financial, social, token, network, and that count to thirteen attributes. The thirteen attributes considered are price, volume, market cap, a mean dollar invested age, social volume, social dominance, development activity, transaction volume, token age consumed, token velocity, token circulation, market value to realized value, and realized cap. We apply the attribute selection and trend analysis mapped with potential seven attributes: Price, Volume, Market Cap, Social Dominance, Development Activity, Market Value to Realized Value & Realized Cap. We have conducted Nonlinear Autoregressive with External Input analysis considering seven attributes. The work employed three training algorithms to train a neural network as Levenberg-Marquard, Bayesian Regularization, and Scaled Conjugate Gradient algorithm. The Error histogram and regression plots results indicate that the Bayesian Regularized Neural Network is showing good performance and thus provides a better forecast.

/pdf/a-bayesian-regularized-neural-network-for-analyzing-bitcoin-1s6ry2yvqn.pdf

A Bayesian Regularized Neural Network for Analyzing Bitcoin Trends

Machine learning is the worldwide recent research technique for various systems as they are intelligent enough to find the solution for classification and prediction problems. The proposed work is about a hybrid genetic fuzzy algorithm that performs an optimal search as well as classification upon uncertain data. The data which is uncertain is suitable for fuzzy classifiers to predict the disease. The hybrid genetic fuzzy system applied on the attributes selects relevant attributes. The selected attributes are fed into the fuzzy classifier. The fuzzy rules are again generated using genetic algorithms. This algorithm is applied on three of the important and bench marking data sets taken from the UCI machine learning repository. The heart disease, Wisconsin breast cancer and Pima Indian diabetes datasets produce classification accuracy as 89.65%, 99.5% and 88.93% respectively. In this article there is a comparative study on few of the feature selection and feature reduction techniques.

/pdf/comparative-study-on-dimensionality-reduction-for-disease-3ylqc4uh8y.pdf

Comparative study on dimensionality reduction for disease diagnosis using fuzzy classifier

Diabetes mellitus is one of the world’s major diseases Millions of people are affected by the disease The risk of diabetes is increasing day by day and is found mostly in women than men The diagnosis of diabetes is a tedious process So with improvement in science and technology it is made easy to predict the disease The purpose is to diagnose whether the person is affected by diabetes or not using K Nearest Neighbor classification technique The diabetes dataset is a taken as the training data and the details of the patient are taken as testing data The training data are classified by using the KNN classifier and secondly the target data is predicted KNN algorithm used here would be more efficient for both classification and prediction The results are analyzed with different values for the parameter k

Prediction of Diabetes Using Data Mining Techniques

Online communities will provide the trustworthiness of their services and also, recommendation systems to improve the commercial value in this competitive business world. Prediction is the greatest method to get people interested whatever offered. Traditional QoS based prediction approach, predicts the QoS value of web service when the incompletion QoS records. This proposed approach introduced cluster based PSO algorithm, which provides better scalability, simplicity, and efficiency. It uses the density-based clusters based on web service users' location and ranks the web services based on PSO algorithm. Here, top-K users are selecting based on web service preferences and weights are giving for experienced neighbors. To achieve the high-quality outcome of the ranking sequence by the control of fitness function and verified by AP correlation coefficient method. The experimental results discussed how this proposed approach provided better prediction accuracy and compared with other existing approaches.

V. Mareeswari

Papers

Prediction of Cardiovascular Disease Using Machine Learning Algorithms

A Bayesian Regularized Neural Network for Analyzing Bitcoin Trends

Comparative study on dimensionality reduction for disease diagnosis using fuzzy classifier

Prediction of Diabetes Using Data Mining Techniques

LocPSORank-Prediction of Ranking of Web Services Using Location-Based Clustering and PSO Algorithm