Systematic Review Study of Decision Trees based Software Development Effort Estimation

A loss‐of‐field (LOF) detection scheme is proposed based on the decision tree (DT) technique. The proposed method is a response‐based scheme. Instead of direct detection of LOF the proposed scheme provide the LOF protection based on simple measurements at generator terminal. The trajectories of generator terminal voltage and generated active and reactive powers are used as new features in LOF detection. The proposed DT‐based technique is robust and adaptive and keeps its performance under different fault scenarios. This scheme automatically adapts to favourable conditions near decision boundary and detects relevant features by the concept of information gain. The proposed method is simulated for a dynamic system under various fault conditions and the results are compared with a multilayer perceptron network classifier for various classification features.

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

Human resource is one of the functions of a company that is considered as an asset. Therefo re, the theory of performance qualificat ion was adopted by the company in order to get an overview of employee performance. Furthermore, the company needs an effective method to predict the performance not only for the employees but also for the new applic ants. The goals of this research are to get a decision tree model of the employee performance. By learning employee data, the performance of the new applicants could be predicted. The study would provide the characteristic of new applicants who will give better performance than other applicants . The data from a company in Indonesia will have been used for this research. The data mining technique will be applied to the data of operators (such as admins, clerks, cashiers, machine operators, and security offi cers). The data mining technique was use d is decision tree. The decision tree technique was commonly used for a supervised learning data. The decision tree technique also has advantages compared others, because of its ability to produce information that is easy to understand. The result of this research shown the high dependency of employee performance with employment type (work contract). It also means that employees are encouraged to provide good performance to the company if those employees have become p ermanent employees. This research also showed that there is no relationship between employee performances with gender or position grade.

Heart failure is a complex condition with a significant impact on patients' lives. A few studies have identified risk factors associated with rehospitalization among telehomecare patients with heart failure using logistic regression or survival analysis models. To date, there are no published studies that have used data mining techniques to detect associations with rehospitalizations among telehomecare patients with heart failure. This study is a secondary analysis of the home healthcare electronic medical record called the Outcome and Assessment Information Set-C for 552 telemonitored heart failure patients. Bivariate analyses using SAS and a decision tree technique using Waikato Environment for Knowledge Analysis were used. From the decision tree technique, the presence of skin issues was identified as the top predictor of rehospitalization that could be identified during the start of care assessment, followed by patient's living situation, patient's overall health status, severe pain experiences, frequency of activity-limiting pain, and total number of anticipated therapy visits combined. Examining risk factors for rehospitalization from the Outcome and Assessment Information Set-C database using a decision tree approach among a cohort of telehomecare patients provided a broad understanding of the characteristics of patients who are appropriate for the use of telehomecare or who need additional supports.

A fuzzy decision tree method for fault classification in the steam generator of a pressurized water reactor

Decision trees are considered as one of the efficient classification techniques in data mining fields. But the standard decision trees are unfit to cope with data pervaded with uncertainty both at the construction and classification phase. Dempster-Shafer theory offers an alternative to traditional probabilistic theory for the mathematical representation of uncertainty. This paper added new aggregation combination operator and uncertainty measure operator into general framework for data mining based on evidence theory. Combining these two operators with decision tree and multidimensional cube, decision tree technique can be extended to uncertain environment. In the phase of node splitting, this algorithm can pre-prune the decision tree and generate a decision tree with fewer branches. Simulations have shown the effectiveness of this method.

Gene expression information from microarray experiments is a primary form of data for biological analysis and can offer insights into disease processes and cellular behaviour. Such datasets are particularly challenging to build classifiers for, due to their very high dimensional nature and small sample size. Decision trees are a seemingly attractive technique for this domain, due to their easily interpretable white box nature and noise resistance. However, existing decision tree methods tend to perform rather poorly for classifying gene expression data. To address this gap, we introduce a new technique for building decision trees that is better suited to this scenario. Our method is based on consideration of the area under the Receiver Operating Characteristics (ROC) curve, to help determine decision tree characteristics, such as node selection and stopping criteria. We experimentally compare our algorithm, called ROC-tree, against other well known decision tree techniques, on a number of gene expression datasets. The experimental results clearly demonstrate that ROC-tree can deliver better classification accuracy in a range of challenging situations.

Slope failure prediction using a decision tree: A case of engineered slopes in South Korea

<div>As pedestrians are among the most critical road users, this research analyzes their vulnerability characteristics and predicts the injury severity of pedestrian crashes through decision tree techniques, rather than using statistical regression models that have particular predefined causal relationships between dependent and independent variables. Five years have been studied in Nablus Governorate/Province (2012–2016), one of 16 governorates in Palestine, as a case study based on reported crash frequencies for developing countries. Tree techniques (CART [Classification and Regression Tree] and CHAID [Chi-Square Automatic Interaction Detector]) were applied to extract the main impacting factors on injury severity for pedestrian crashes. The main contributions considered a small regional context in developing countries and found differences between the results of various methods in injury severity. Fourteen independent variables have been analyzed. A CART model with Gini splitting has produced the most accurate model. The most important variables were the victim’s gender, followed by area classification as rural, and the age categories of pedestrians older than 65 and younger than 15 years. The least important variables were found to be the driver’s gender, land use, and pavement conditions. Results also showed that the proximity of crashes to schools is relatively high; therefore, some policies were suggested regarding children’s awareness, school zones, and driver behavior. It was found that the majority of factors influencing pedestrian crashes are related to human characteristics such as age, gender, or attitude whereas, in developed countries, they were related to vehicles and infrastructure. Based on the results of the study, tree techniques were considered effective in the analysis of injury severity of pedestrians in the context of developing countries to identify the main factors of vulnerability.</div>

Decision trees are versatile machine learning algorithms that are frequently used in classification and regression tasks. In this work, decision trees are employed as tools for sediment classification using sound waves propagating in the ocean and their behavior and features. We first analyze the structure of received time series at deployed hydrophones, extracting characteristic features (kurtosis and skewness, for example). Feature values then form vectors that are used as input patterns to the trees. A training step is the first stage of the machine learning approach with the trees trained to recognize sediment types based on feature values. The method is subsequently tested on feature vectors obtained from noise-corrupted time series. The performance depends on Signal-to-Noise Ratio values as expected and the method is found to be superior to conventional machine learning approaches. The addition of tools such as principal component analysis as well as spectrogram processing and time-frequency curve fitting further enhances the method. The decision tree technique provides an effective and efficient solution to the problem of sediment classification using acoustic data. [Work supported by ONR.]

A quantum machine is a human-made device whose collective motion follows the laws of quantum mechanics. Quantum machine learning (QML) is machine learning for quantum computers. The availability of quantum processors has led to practical applications of QML algorithms in the remote sensing field. Quantum machines can learn from fewer data than non-quantum machines, but because of their low processing speed, quantum machines cannot be applied to an image that has hundreds of thousands of pixels. Researchers around the world are exploring applications for QML and in this work, it is applied for pseudo-labelling of samples. Here, a PRISMA (PRecursore IperSpettrale della Missione Applicativa) hyperspectral dataset is prepared by quantum-based pseudo-labelling and 11 different machine learning algorithms viz., support vector machine (SVM), K-nearest neighbour (KNN), random forest (RF), light gradient boosting machine (LGBM), XGBoost, support vector classifier (SVC) + decision tree (DT), RF + SVC, RF + DT, XGBoost + SVC, XGBoost + DT, and XGBoost + RF with this dataset are evaluated. An accuracy of 86% was obtained for the classification of pine trees using the hybrid XGBoost + decision tree technique.

Software cost estimation (SCE) is one of the critical activities in software project management. During the past decades various models have been proposed for SCE. However, developing accurate and useful models is limited in practice despite the considerable financial gain they could offer to software stakeholders. Traditional techniques, such as regression, by-analogy and machine learning, face the difficulty of handling the dynamic nature of the software process and the problematic nature of the public data available. This paper addresses the issue of SCE proposing an alternative approach that combines robust decision tree structures with fuzzy logic. Fuzzy decision trees are generated using the CHAID and CART algorithms in a systematic manner, while development effort is treated as the dependent variable against two subsets of factors: The first contains selected attributes from the ISBSG, COCOMO and DESHARNAIS datasets and the second contains a subset of the available factors that can be measured early in the development cycle. The association rules obtained from the trees are then merged and defuzzified through a Fuzzy Implication System (FIS). The fuzzy framework is utilized to perform effort estimations. Experimental results indicate that the proposed approach is promising as it yields quite accurate estimations in most dataset cases considered. Finally, our evaluation suggests that accurate estimations may be produced, even when using only a small set of factors that can be measured early in the development cycle, thus increasing the practical value of the proposed cost model.

The use of credit cards for electronic commerce purposes has been on the increase in recent time. Credit card being the most acceptable and popular mode of payment, the number of fraud cases associated with it is also on the rise. As a result of the extensive nature of credit card transaction details, it is challenging to identify fraud in a credit card system in recent years, which implies that the identification of credit cards' fraud accurately, quickly, and effectively is a gray area of research. In this article, an automated template-based credit cards' fraud prediction (CCFP) model is developed using dynamic time warping (DTW) technique. This proposed CCFP technique is novel, as it has not been previously used to predict fraud in credit cards' systems. The performance of this proposed DTW-CCFP model is verified using the dataset that contains the credit card transactions of European cardholders. In addition, the performance of this proposed DTW-CCFP model is compared with three different machine learning (ML) prediction models: logistic regression (LR), decision tree (DT) and random forest (RF). The results were documented using two different performance metrics: sensitivity and false discovery rate (FDR). The proposed DTW-CCFP model outperforms the LR, DT and RF techniques. Of interest, the proposed DTW-CCFP model achieves this feat using a small portion (less than 5%) of the dataset to build the template in comparison to the LR, DT and RF techniques, which uses between 20%-30% of the dataset for training to achieve a fairly reasonable result

While decision tree techniques have been widely used in classification applications, a shortcoming of many decision tree inducers is that they do not learn intermediate concepts, i.e., at each node, only one of the original features is involved in the branching decision. Combining other classification methods, which learn intermediate concepts, with decision tree inducers can produce more flexible decision boundaries that separate different classes, potentially improving classification accuracy. We propose a generic algorithm for cascade generalization of decision tree inducers with the maximum cascading depth as a parameter to constrain the degree of cascading. Cascading methods proposed in the past, i.e., loose coupling and tight coupling, are strictly special cases of this new algorithm. We have empirically evaluated the proposed algorithm using logistic regression and C4.5 as base inducers on 32 UCI data sets and found that neither loose coupling nor tight coupling is always the best cascading strategy and that the maximum cascading depth in the proposed algorithm can be tuned for better classification accuracy. We have also empirically compared the proposed algorithm and ensemble methods such as bagging and boosting and found that the proposed algorithm performs marginally better than bagging and boosting on the average.

Data mining refers to the application of data analysis techniques with the aim of extracting hidden knowledge from data by performing the tasks of pattern recognition and predictive modeling. This article describes the application of data mining techniques on educational data of a higher education institution in Croatia. Data used for the analysis are event logs downloaded from an e-learning environment of a real e-course. Data mining techniques applied for the research are cluster analysis and decision tree. The cluster analysis was performed by organizing collections of patterns into groups based on student behavior similarity in using course materials. Decision tree was the method of interest for generating a representation of decision-making that allowed defining classes of objects for the purpose of deeper analysis about how students learned.