Developing a Software for Diagnosing Heart Disease via Data Mining Techniques

In modern society, mortality and morbidity are caused majorly by heart disease (HD), and in world, deaths are mainly caused by heart disease (HD). The detection of HD and prevention against death is a challenging task. Medical diagnosis is highly complicated and it is very important. It must be performed efficiently with high accuracy. The professionals in healthcare in heart disease diagnosis are assisted by using various techniques in data mining. In this work, heart disease prediction method with following steps is introduced. The steps are preprocessing technique, feature selection, and learning algorithm. Before that important features are selected via the use of the updated frequency-based bat algorithm (UFBBA). In the UFBBA algorithm, the frequency values are computed via the use of the features. If the features are most important, then the frequency is higher else the frequency is lower. A selected feature from the UFBBA is used for better accuracy results than the other classifiers. A feature selected from the algorithm is applied for classification (Vote). Experimentation dataset of the proposed system is collected from Irvine (UCI) Cleveland dataset, University of California dataset. The results are measured with respect to accuracy, f-measure, precision, and recall.

In the present state of affairs, the motive behind every educational organization is to uplift the academic achievement of students. Educational data mining (EDM) is an upward field of research, and it is very helpful for academic institutions to predict the academic performance of the students. Educational datasets are the basis of various predictive models. Quality of these models can be improved by using feature selection (FS). To get the required benefits from the available data, there must be some tools for analysis and prediction. In lieu of the above, machine learning/data mining are most suitable. In educational data mining, for better accuracy of prediction models’ and quality of various educational datasets, feature selection (FS) plays a vital role. Feature selection (FS) algorithms abolish inappropriate information from the repositories of educational background so that performance of classifier in terms of accuracy could be increased and the same could be used for better decision. In lieu of the above, a best feature selection algorithm must be selected. In this paper, two filter selection approaches namely correlation feature selection (CFS) and wrapper-based feature selection have been used to demonstrate the importance of selection of a feature subset for a classification problem. The present paper aims to find the detailed investigation of filter feature selection algorithms along with the classification algorithms on a given dataset. We found result with numerous numbers of features from various Feature selection algorithms and classifiers which will help the researcher to discover the most excellent mixture of filter feature selection algorithms and its associated classifiers. The result indicates that SMO and J48 have the highest accuracy measures with the correlation feature selection algorithms, while Naïve Bayes has the highest accuracy measures with the wrapper subset feature selection algorithms for predicting high, medium and low grade for the students.

Irrelevant feature in heart disease dataset affects the performance of binary classification model. Consequently, eliminating irrelevant and redundant feature (s) from training set with feature selection algorithm significantly improves the performance of classification model on heart disease detection. Sequential feature selection (SFS) is successful algorithm to improve the performance of classification model on heart disease detection and reduces the computational time complexity. In this study, sequential feature selection (SFS) algorithm is implemented for improving the classifier performance on heart disease detection by removing irrelevant features and training a model on optimal features. Furthermore, exhaustive and permutation based feature selection algorithm are implemented and compared with SFS algorithm. The implemented and existing feature selection algorithms are evaluated using real world Pima Indian heart disease dataset and result appears to prove that the SFS algorithm outperforms as compared to exhaustive and permutation based feature selection algorithm. Overall, the result looks promising and more effective heart disease detection model is developed with accuracy of 99.3%.

The purpose of this study was to determine the incidence of missed congenital heart disease in neonates in the state of Wisconsin leading to death or readmission during the first 2 weeks of life. Wisconsin hospitalization and death records were reviewed from 2002 to 2006. Only those neonates discharged home after birth without a cardiac or major non-cardiac diagnosis were considered. Wisconsin hospital records identified those neonates readmitted during the first 2 weeks of life with a diagnosis of heart disease using International Classification of Diseases, 9th Revision (ICD-9) codes. Wisconsin death records also identified patients who died within the first 14 days of life who had a diagnosis of heart disease using International Classification of Diseases, 10th Revision (ICD-10) codes. Adverse events were attributed to congenital heart disease if the diagnosis was a left-sided obstructive lesion or a cyanotic heart defect. Other adverse events were attributed to heart disease if no other major diagnosis was present and the data suggested an intention to treat. The 114 Wisconsin hospitals, which delivered 340 203 babies during 2002-2006, were stratified into quartiles based on the total number of deliveries to determine if there was a difference in incidence of missed congenital heart disease based on hospital birth size. Congenital heart disease led to death or rehospitalization during the first 2 weeks of life in 14 out of 345 573 births (1 : 24 684) in Wisconsin between 2002 and 2006. Coarctation of the aorta and hypoplastic left heart syndrome were the most common diagnoses. There did not appear to be a difference in the incidence of missed diagnosis of congenital heart disease based on the number of deliveries performed at the birth hospital. Death or readmission events in neonates under 2 weeks of age because of a missed diagnosis of congenital heart disease occurred in 1 : 24 684 neonates in the state of Wisconsin between 2002 and 2006. Critical left sided obstructive lesions were the most common cause of these events.

New hybrid data mining model for credit scoring based on feature selection algorithm and ensemble classifiers

With the growth of Internet, there has been a tremendous increases in the number of attacks and therefore Intrusion Detection Systems (IDS’s) has become a main stream of information security. The purpose of IDS is to help the computer systems to deal with attacks. This anomaly detection system creates a database of normal behaviour and deviations from the normal behaviour to trigger during the occurrence of intrusions. Based on the source of data, IDS is classified into Host based IDS and Network based IDS. In network based IDS, the individual packets flowing through the network are analyzed where as in host based IDS the activities on the single computer or host are analyzed. The feature selection used in IDS helps to reduce the classification time. In this paper, the IDS for detecting the attacks effectively has been proposed and implemented. For this purpose, a new feature selection algorithm called Optimal Feature Selection algorithm based on Information Gain Ratio has been proposed and implemented. This feature selection algorithm selects optimal number of features from KDD Cup dataset. In addition, two classification techniques namely Support Vector Machine and Rule Based Classification have been used for effective classification of the data set. This system is very efficient in detecting DoS attacks and effectively reduces the false alarm rate. The proposed feature selection and classification algorithms enhance the performance of the IDS in detecting the attacks.

Moxa floss is the primary material used in moxibustion, an important traditional Chinese medicine therapy that uses ignited moxa floss to apply heat to the body for disease treatment. Till date, there is no available data regarding quality control of different grades of moxa floss. The objectives of this study were to explore the probative value of the electronic nose (e-nose) in differentiating different quality grades of commercial moxa floss sold in China, and to investigate if data mining techniques could be used to optimize the sensor array while retaining classification accuracy of the samples. The e-nose with 12 metal oxide semiconductor type sensors was used to analyze the odor profiles of 15 commercial moxa floss samples of different quality grades. Feature selection algorithms using principal component analysis (PCA) and BestFirst (BC) coupled with correlation-based feature subset selection (CfsSubsetEval) method were used to obtain the most efficient feature subsets. Results for the BC feature selection method identified 3 optimized sensors (S2, S6, and S11), suggesting that aromatic compounds relate more to the identification of the samples. Radial basis function (RBF), multilayer perceptron (MLP), and random forests (RF) performed well in discriminating the samples, retaining prediction accuracies above 85%, which achieved cost-effectiveness and operational simplicity, while retaining prediction accuracy. The e-nose could be a rapid and nondestructive method for objective preliminary classification of quality grades of moxa floss and may be used for future studies related to moxa products safety and quality.

Discrete learning-based intelligent methodology for heart disease diagnosis

Remote sensing images obtained by remote sensing are a key source of data for studying large-scale geographic areas. From 2013 onwards, a new generation of land remote sensing satellites from USA, China, Brazil, India and Europe will produce in 1year as much data as 5 years of the Landsat-7 satellite. Thus, the research community needs new ways to analyze large data sets of remote sensing imagery. To address this need, this paper describes a toolbox for combing land remote sensing image analysis with data mining techniques. Data mining methods are being extensively used for statistical analysis, but up to now have had limited use in remote sensing image interpretation due to the lack of appropriate tools. The toolbox described in this paper is the Geographic Data Mining Analyst (GeoDMA). It has algorithms for segmentation, feature extraction, feature selection, classification, landscape metrics and multi-temporal methods for change detection and analysis. GeoDMA uses decision-tree strategies adapted for spatial data mining. It connects remotely sensed imagery with other geographic data types using access to local or remote database. GeoDMA has methods to assess the accuracy of simulation models, as well as tools for spatio-temporal analysis, including a visualization of time-series that helps users to find patterns in cyclic events. The software includes a new approach for analyzing spatio-temporal data based on polar coordinates transformation. This method creates a set of descriptive features that improves the classification accuracy of multi-temporal image databases. GeoDMA is tightly integrated with TerraView GIS, so its users have access to all traditional GIS features. To demonstrate GeoDMA, we show two case studies on land use and land cover change.

In recent years, the incidence of cardiovascular disease has been on the rise, and the causes have gradually become more complex, so it is urgent to intervene in the diagnosis and treatment of heart disease. In this paper, 251,505 survey responses from BRFSS were selected to analyze the cardiology dataset using the Logistic model and the C5.0 decision tree model. The results show that the occurrence of heart disease has a strong relationship with hypertension, smoking, stroke history, gender, and age, which has certain practical significance for the prediction and diagnosis of heart disease.

Heart disease is one of the major causes of life complicacies and subsequently leading to death. The heart disease diagnosis and treatment are very complex, especially in the developing countries, due to the rare availability of efficient diagnostic tools and shortage of medical professionals and other resources which affect proper prediction and treatment of patients. Inadequate preventive measures, lack of experienced or unskilled medical professionals in the field are the leading contributing factors. Although, large proportion of heart diseases is preventable but they continue to rise mainly because preventive measures are inadequate. In today’s digital world, several clinical decision support systems on heart disease prediction have been developed by different scholars to simplify and ensure efficient diagnosis. This paper investigates the state of the art of various clinical decision support systems for heart disease prediction, proposed by various researchers using data mining and machine learning techniques. Classification algorithms such as the Naïve Bayes (NB), Decision Tree (DT), and Artificial Neural Network (ANN) have been widely employed to predict heart diseases, where various accuracies were obtained. Hence, only a marginal success is achieved in the creation of such predictive models for heart disease patients therefore, there is need for more complex models that incorporate multiple geographically diverse data sources to increase the accuracy of predicting the early onset of the disease.

In this paper, we address the oscillations in the signals of both motion capture and inertial measurement sensors. This characteristic is often observed when the range of motion reaches or exceeds approximately 85 degrees. Elimination of oscillation in the filtered output signal is of significance as it means the filtered signal can be applied directly by applications such as visualization, motion tracking, clinical report, etc. This paper proposed a system model using feature selection and machine learning algorithm to automatically detect and post-filter the oscillation. Feature selection aims to derive the most impactful wearable sensor data gathered from the accelerometer, magnetometer and gyroscope, using well-known classifiers such as Logistic Regression, Support Vector Machine and Multilayer Perceptron. The features and classification method that are most suited for the detection model are selected. Experimental results show that we can on average achieve up to 76% accuracy and are able to filter out the fluctuation; the latter is more efficient than manually post-processing the data. The trained detection model has thus proven its effectiveness in eliminating the noisy fluctuations and its potential to be used in real-time.

The majority of deaths today are due to heart diseases. Early diagnosis of heart diseases will lead to early initiation of the treatment process. Therefore, computer-aided systems are of great importance. In this study, heart sounds were used for the early diagnosis and treatment of heart diseases. Diagnosing heart sounds provides important information about heart diseases. Therefore, a hybrid model was developed in the study. In the developed model, first of all, spectrograms were obtained from audio signals with the Mel-spectrogram method. Then, the interpolation method was used to train the developed model more accurately and with more data. Unlike other data augmentation methods, the interpolation method produces new data. The feature maps of the data were obtained using the Darknet53 architecture. In order for the developed model to work faster and more effectively, the feature map obtained using the Darknet53 architecture has been optimized using the Relief feature selection method. Finally, the obtained feature map was classified in different classifiers. While the accuracy value of the developed model in the first dataset was 99.63%, the accuracy rate in the second dataset was 97.19%. These values show that the developed model can be used to classify heart sounds.

Data mining techniques have been widely used in clinical decision support systems for prediction and diagnosis of various diseases with good accuracy. These techniques have been very effective in designing clinical support systems because of their ability to discover hidden patterns and relationships in medical data. One of the most important applications of such systems is in diagnosis of heart diseases because it is one of the leading causes of deaths all over the world. Almost all systems that predict heart diseases use clinical dataset having parameters and inputs from complex tests conducted in labs. None of the system predicts heart diseases based on risk factors such as age, blood pressure, fasting blood sugar, chest pain etc. Heart disease patients have lot of these visible risk factors in common which can be used very effectively for diagnosis. System based on such risk factors would not only help medical professionals but it would give patients a warning about the probable presence of heart disease even before he visits a hospital or goes for costly medical check-ups. Hence this paper presents a technique for prediction of heart disease using major risk factors. This technique involves two most successful data mining tools, Support vector machine and Principal component analysis. The hybrid system implemented uses the global optimization advantage PCA for initialization of neural network weights. The learning is fast, more stable and accurate as compared to back propagation.

In feature selection, we are concerned with finding out those features that produces result similar to those of the original entire set of features. We concern ourselves with efficiency and effectiveness while evaluating Feature selection algorithms. Efficiency deals with the time required to find a subset of features and effectiveness, with the quality of subset of features. On these criteria, a FAST clustering-based feature selection algorithm (FAST) has been proposed and experimentally evaluated and implemented in this paper. The dimensionality reduction of data is the most important feature of FAST. First, we use graph-theoretic clustering method to divide features into clusters. Next, we form a subset of features by selecting the feature which is most representative and strongly related to the target classes. Due to features in different clusters being relatively independent; the clustering-based strategy of FAST has a high probability of providing us with a subset of features which are both useful and independent. Efficiency of FAST is ensured by using the concept of minimum spanning tree (MST) along with kruskal’s algorithm.