Search

Background: Acute rheumatic fever (ARF) is an important disease that is frequently seen in Turkey, it is necessary to develop solutions to cure the disease. It is believed that new data analysis methods may be applied to this disease, and this may be useful to discover previously unrecognized patterns. Data mining of existing records and data repositories may improve knowledge on the diagnosis and management of ARF. In this regard, we planned to make a contribution to the development of new solutions by approaching the problem from a different standpoint., Objectives: The aim of this study is to analyse the effects of ARF undergone during childhood on the basis of cardiac diseases by using data mining methods., Materials and Methods: Classification methods of data mining were used, and experiments were conducted on five algorithms. The records of the patients diagnosed with ARF were analysed by setting models with naive Bayes classifier, decision trees (CART, C4.5, C5.0, C5.0 boosted) and random forest algorithms. The performances of the algorithms that were derived were then compared. Among model performance evaluation techniques, the hold-out, cross-validation and bootstrap methods were tested in diverse ways in an applied manner. Within the scope of the research, the dataset comprising records of 297 patients was utilised in cooperation with İstanbul Medeniyet University Göztepe Training and Research Hospital's Pediatric Cardiology Clinic (İstanbul Medeniyet Üniversitesi Göztepe Eğitim ve Araştırma Hastanesi Çocuk Kardiyolojisi Kliniği). Data analysis was carried out with the data of the remaining 201 patients following pre-processing., Results: The results that were obtained from different algorithms were compared based on the model performance evaluation criteria. The best result was shown under the CART model by using the hold-out technique (80% training, 20% testing). According to this model, the importance values of the predictive attributes were listed, and it was found that the "teleNormal" and "cardiomegaly" attributes were not required for ARF diagnosis and treatment. In compliance with this result, it was thought that it should not be necessary for patients have a chest x-ray which is needed for diagnosis of "teleNormal" and "cardiomegaly". This will help reduce costs and thus contribute to the health economy while preventing patients from having unnecessary x-rays., Discussion and Conclusion: The results of this study showed that data mining techniques may be used to analyse diseases such as ARF. The important attributes that affect the disease were obtained in accordance with the results. The results of the best model (CART) may be broadened in numerous ways and provide information for both experienced and inexperienced physicians. This study is considered to be significant as it helps data mining methods become more prevalently used for data analysis in fields of medicine and healthcare., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Data mining is a data analysis process using software to find certain patterns or rules in a large amount of data, which is expected to provide knowledge to support decisions. However, missing value in data mining often leads to a loss of information. The purpose of this study is to improve the performance of data classification with missing values, precisely and accurately. The test method is carried out using the Car Evaluation dataset from the UCI Machine Learning Repository. RStudio and RapidMiner tools were used for testing the algorithm. This study will result in a data analysis of the tested parameters to measure the performance of the algorithm. Using test variations: performance at C5.0, C4.5, and k-NN at 0% missing rate, performance at C5.0, C4.5, and k-NN at 5–50% missing rate, performance at C5.0 + k-NNI, C4.5 + k-NNI, and k-NN + k-NNI classifier at 5–50% missing rate, and performance at C5.0 + CMI, C4.5 + CMI, and k-NN + CMI classifier at 5–50% missing rate, The results show that C5.0 with k-NNI produces better classification accuracy than other tested imputation and classification algorithms. For example, with 35% of the dataset missing, this method obtains 93.40% validation accuracy and 92% test accuracy. C5.0 with k-NNI also offers fast processing times compared with other methods. [ABSTRACT FROM AUTHOR]

The adoption of Big Data Analysis (BDA) has become popular among firms since it creates evidence for decision-making by managers. However, the adoption of BDA continues to be poor among small and medium enterprises (SMEs). Therefore, this study adopted the Technology-Organization-Environment (TOE) framework to identify the drivers of readiness to adopt BDA among SMEs. Chi-square automatic interaction detection (CHAID), Bayesian network, neural network, and C5.0 algorithms of data mining were utilized to analyze data collected from 240 Vietnamese managers of SMEs. The evaluation model identified the C5.0 algorithm as the best model, with accurate results for the prediction of factors influencing the readiness to adopt BDA among SMEs. The findings revealed management support, data quality, firm size, data security and cost to be the fundamental factors influencing BDA adoption readiness. Moreover, the results identified the service sector as having a higher level of readiness toward the adoption of BDA compared to the manufacturing sector. The findings are imperative for the enhancement of the decision-making process and advancement of comprehension of the determinants of BDA adoption among SMEs by researchers, managers, providers and policymakers.

Objectives Machine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset. Methods Our study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18. Results We studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively. Conclusions Our findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.

Human Development Index (HDI) is an indicator that ranks nations by their development in health, welfare and success of their citizens. Using national income alone is not sufficient to determine the level of development of a nation. HDI, published by United Nations Development Plan (UNDP), is calculated based on nation's income, education and health indicators. Hence, HDI became a metric to rank the quality of human life between countries. This study contains decision trees that are generated using C5.0 and GINI Algorithms based on UNDP data for 79 countries dating from 2010 till 2017 In addition to the decision trees, the factors that affect HDI also were determined and rules were produced by grouping countries as highly developed, developed, developing and under developed countries. Based the analyses, C5.0 and GINI algorithms produced 97.94% and 91.93% ranking accuracy respectively. Additionally, sensitivity and determinability statistics were also calculated, and the variables in education, employment and health were determined to be the most significant. [ABSTRACT FROM AUTHOR]

Data mining approaches are designed for classification problems in which each observation is a member of one and only one class. In this study, a non-deterministic approach based on C5.0 data mining algorithm has been employed for discriminating the phenological stages of maize from emergence to dough, in a field located in Karaj, Iran. Two readily-available predictors i.e. accumulated growing degree days (AGDD) and multi-temporal LANDSAT7-extracted normalized difference vegetation index (NDVI) was used to build the decision tree. The AGDD was calculated based on three cardinal thresholds of temperature i.e. effective minimum, optimum, effective maximum. The NDVI was compared with two recently developed indices namely, enhanced vegetation index2 (EVI2) and optimized soil adjusted vegetation index (OSAVI) using the signal to noise ratio (SNR) criterion. Findings confirmed that these three remotely sensed indices do not have significant differences, therefore, the smoothed time series of NDVI was used in the C5.0 algorithm. The precisions of classification by C5.0 data mining algorithm in partitioning of training and testing data were approximately 90.51 and 81.77%, respectively. The mean absolute error (MAE) values of the onset of maize phenological stages were estimated about 2.6-5.3 days for various stages by C5.0 model. While corresponding values for the classical AGDD model were 3.9-10.7 days. This confirms the skill of data mining approach in comparison with commonly-used the classical AGDD model in applications of real time monitoring. [ABSTRACT FROM AUTHOR]

Abstract Global burned are algorithms provide valuable information for climate modellers since fire disturbance is responsible of a significant part of the emissions and their related impact on humans. The aim of this work is to explore how four different classification algorithms, widely used in remote sensing, such as Random Forest (RF), Support Vector Machine (SVM), Neural Networks (NN) and a well-known decision tree algorithm (C5.0), for classifying burned areas at global scale through a data mining methodology using 2008 MODIS data. A training database consisting of burned and unburned pixels was created from 130 Landsat scenes. The resulting database was highly unbalanced with the burned class representing less than one percent of the total. Therefore, the ability of the algorithms to cope with this problem was evaluated. Attribute selection was performed using three filters to remove potential noise and to reduce the dimensionality of the data: Random Forest, entropy-based filter, and logistic regression. Eight out of fifty-two attributes were selected, most of them related to the temporal difference of the reflectance of the bands. Models were trained using an 80% of the database following a ten-fold approach to reduce possible overfitting and to select the optimum parameters. Finally, the performance of the algorithms was evaluated over six different regions using official statistics where they were available and benchmark burned area products, namely MCD45 (V5.1) and MCD64 (V6). Compared to official statistics, the best agreement was obtained by MCD64 (OE = 0.15, CE = 0.29) followed by RF (OE = 0.27, CE = 0.21). For the remaining three areas (Angola, Sudan and South Africa), RF (OE = 0.47, CE = 0.45) yielded the best results when compared to the reference data. NN and SVM showed the worst performance with omission and commission error reaching 0.81 and 0.17 respectively. SVM and NN showed higher sensitivity to unbalanced datasets, as in the case of burned area, with a clear bias towards the majority class. On the other hand, tree based algorithms are more robust to this issue given their own mechanisms to deal with big and unbalanced databases. [ABSTRACT FROM AUTHOR]

The expenses for attracting new customers are much higher compared to the ones needed to maintain old customers due to the increasing competition and business saturation. So customer retention is one of the leading factors in companies' marketing. Customer retention requires a churn management, and an effective management requires an exact and effective model for churn prediction. A variety of techniques and methodologies have been used for churn prediction, such as logistic regression, neural networks, genetic algorithm, decision tree etc.. In this article, a hybrid method is presented that predicts customers churn more accurately, using data fusion and feature extraction techniques. After data preparation and feature selection, two algorithms, LOLIMOT and C5.0, were trained with different size of features and performed on test data. Then the outputs of the individual classifiers were combined with weighted voting. The results of applying this method on real data of a telecommunication company proved the effectiveness of the method. [ABSTRACT FROM AUTHOR]

The use of data mining approaches for analyzing patients trace in different medical databases has become an important research field especially with the evolution of these methods and their contributions in medical decision support. In this paper, we develop a new clinical decision support system (CDSS) to diagnose Coronary Artery Diseases (CAD). According to CAD experts, Angiography is most accurate CAD diagnosis technique. However, it has many aftereffects and is very costly. Existing studies showed that CAD diagnosis requires heterogeneous patients traces from medical history while applying data mining techniques to achieve high accuracy. In this paper, an automatic approach to design CDSS for CAD assessment is proposed. The proposed diagnosis model is based on Random Forest algorithm, C5.0 decision tree algorithm and Fuzzy modeling. It consists of two stages: first, Random Forest algorithm is used to rank the features and a C5.0 decision tree based approach for crisp rule generation is developed. Then, we created the fuzzy inference system. The generation of fuzzy weighted rules is carried out automatically from the previous crisp rules. Moreover, a critical issue about the CDSS is that some values of the features are missing in most cases. A new method to deal with the problem of missing data, which allows evaluating the similarity despite the missing information, was proposed. Finally, experimental results underscore very promising classification accuracy of 90.50% while optimizing training time using UCI (the University of California at Irvine) heart diseases datasets compared to the previously reported results. [ABSTRACT FROM AUTHOR]

This study aims to establish a rigorous and effective model to detect enterprises’ financial statements fraud for the sustainable development of enterprises and financial markets. The research period is 2004–2014 and the sample is companies listed on either the Taiwan Stock Exchange or the Taipei Exchange, with a total of 160 companies (including 40 companies reporting financial statements fraud). This study adopts multiple data mining techniques. In the first stage, an artificial neural network (ANN) and a support vector machine (SVM) are deployed to screen out important variables. In the second stage, four types of decision trees (classification and regression tree (CART), chi-square automatic interaction detector (CHAID), C5.0, and quick unbiased efficient statistical tree (QUEST)) are constructed for classification. Both financial and non-financial variables are selected, in order to build a highly accurate model to detect fraudulent financial reporting. The empirical findings show that the variables screened with ANN and processed by CART (the ANN + CART model) yields the best classification results, with an accuracy of 90.83% in the detection of financial statements fraud. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) is set to revolutionize all aspects of our lives. The number of objects connected to IoT is expected to reach 50 billion by 2020, giving rise to an enormous amounts of valuable data. The data collected from the IoT devices will be used to understand and control complex environments around us, enabling better decision making, greater automation, higher efficiencies, productivity, accuracy, and wealth generation. Data mining and other artificial intelligence methods would play a critical role in creating smarter IoTs, albeit with many challenges. In this paper, we examine the applicability of eight well-known data mining algorithms for IoT data. These include, among others, the deep learning artificial neural networks (DLANNs), which build a feed forward multi-layer artificial neural network (ANN) for modelling high-level data abstractions. Our preliminary results on three real IoT datasets show that C4.5 and C5.0 have better accuracy, are memory efficient and have relatively higher processing speeds. ANNs and DLANNs can provide highly accurate results but are computationally expensive. [ABSTRACT FROM AUTHOR]

This study attempts to diagnose the detecting electronic industries' earnings management by integrating suitable soft computing methods. Accounting earnings information is a very crucial element for corporate stakeholders to determine their stock prices and evaluate their supervision and management authority's performance, while it is also essential information for measuring corporate value. Hence, whether an enterprise can faithfully express its true economic meaning over its financial statements and how the management handles its earnings have turned out to be a popular issue widely discussed by researchers. Detecting public companies' earnings management is an important and challenging issue that has served as the impetus in many academic studies over the last few decades. Data mining technique and machine learning methods have also been commonly applied by accounting and financial personnel to other fields of studies. The study used the stepwise regression and random forest techniques to screen the variables in the first place, followed by adopting three kinds of decision trees including Chi-squared automatic interaction detector, classification and regression trees and C5.0 to establish a model and find out if the tested enterprise had extreme earnings manipulation. The results show that the proposed hybrid approach (RF+C5.0) has the optimal classification rate (the accuracy rate is 91.24 %) and the lowest occurrence of Type I error and Type II error. Also, as discovered from the rules set of the final additional testing, an enterprise's operating cash flow, times interest earned ratio and previous period's discretionary accruals play a decisive role in affecting its extreme earnings management. [ABSTRACT FROM AUTHOR]

Retinopathy or blindness due to diabetes is one of the most common complications among diabetics worldwide. Due to its high prevalence, early detections are necessary so as to avoid vision loss. This paper aims to discuss the design and development of a retinopathy predictive system which is based on data mining and case based reasoning (CBR). To be specific, C5.0 was used to produce the decision tree whereas k-nearest neighbour and Hamming distance algorithms were used to select the three most similar cases for every new case entered into the system. Then a voting mechanism makes the final prediction. Results show that the hybrid system has a better accuracy prediction rate (85%) compared to C5.0 (76%) and CBR (73%) implemented solely. [ABSTRACT FROM AUTHOR]

Data plays a vital role as a source of information to organizations, especially in times of information and technology. One encounters a not-so-perfect database from which data is missing, and the results obtained from such a database may provide biased or misleading solutions. Therefore, imputing missing data to a database has been regarded as one of the major steps in data mining. The present research used different methods of data mining to construct imputative models in accordance with different types of missing data. When the missing data is continuous, regression models and Neural Networks are used to build imputative models. For the categorical missing data, the logistic regression model, neural network, C5.0 and CART are employed to construct imputative models. The results showed that the regression model was found to provide the best estimate of continuous missing data; but for categorical missing data, the C5.0 model proved the best method. [ABSTRACT FROM AUTHOR]