Supervised Data Mining Techniques Research Articles

Are the best higher education institutions also more sustainable?

Purpose The purpose of this study is to analyze the integration of sustainable practices in the strategies and operations of world-class higher education institutions (HEIs) under the theoretical guidance of Max Weber's instrumental and value rationalities. Design/methodology/approach The results of the Quacquarelli-Symonds World University Ranking, Times Higher Education World University Rankings, THE Impact Rankings and GreenMetric World University Ranking rankings from 2019 to 2022 were paired, and the correlation between them was verified. Institutions with simultaneous occurrence in the four rankings in at least one of the years were also classified. A quantitative and qualitative methodology was used to explore how elite HEIs integrate sustainable practices into their operations and strategies, under the theoretical guidance of Max Weber's instrumental and value rationalities. Furthermore, multivariate regression models with supervised data mining techniques were applied, using the SMOReg algorithm on 368 instances with multiple attributes, to predict the numerical value of sustainability in the rankings. Coefficients were assigned to variables to determine their relative importance in predicting rankings. Findings The results of this study suggest that although many HEIs demonstrate a commitment to sustainability, this rarely translates into improvements in traditional rankings, indicating a disconnect between sustainable practices and global academic recognition. Research limitations/implications The research has limitations, including the analysis being restricted to data from specific rankings between 2019 and 2022, which may limit generalization to future editions or rankings. The predictive models used selected data and, therefore, cannot cover the full complexity of metrics from other rankings. Furthermore, internal factors of HEIs were not considered, and the correlations identified do not imply direct causality. The limited sample and potential methodological biases, together with the heterogeneity of the rankings, restrict the generalization of the results. These limitations should be considered in future studies. Practical implications The theoretical contributions of this study include an in-depth understanding of the intersection between academic excellence and environmental and social responsibility. From a management perspective, guidance is provided on integrating sustainability into HEI strategies to enhance visibility and classification in global rankings, while maintaining academic integrity and commitment to sustainability. Social implications This highlights the importance of reassessing academic rankings criteria to include sustainability assessments, thereby encouraging institutions to adopt practices that genuinely contribute to global sustainable development. Originality/value The originality lies in the predictive analysis between these rankings, examining the link between the level of sustainability of an HEI and its classification as a World Class University. Furthermore, it combines theories of rationality with the analysis of sustainability integration in elite HEIs, introducing new analytical perspectives that can influence future educational policies and institutional practices.

A scalable, distributed framework for significant subgroup discovery

Subgroup discovery is a supervised data mining technique having many applications in medical domains, market basket analysis, and social media analysis. It helps in mining subgroups (or patterns) with a high association to a target property, measured using a quality function. However, the process is computationally intensive as it is necessary to go through the search space of all subgroups to find the top-k interesting ones w.r.t. the quality function. Further, as we verify many associations, it is quite possible that a certain level of association might be achieved by chance. To address this issue, the state-of-the-art TopKWY algorithm employs permutation testing to control false discoveries. Still, testing multiple subgroups against thousands of permuted target labels further increases computational complexity. Additionally, TopKWY is limited to a specific quality function and lacks a parallel/distributed implementation to handle scalability challenges. In this paper, we propose a parallel and distributed framework for subgroup discovery named ParaDiS that extends permutation testing to a broader class of quality functions. ParaDiS scales to large datasets while effectively controlling the false discovery rate. It features different optimizations to reduce communication/computation overheads and a distributed best-first search strategy to improve pruning across different workers. We compare its performance for several real-world datasets and achieve an order of magnitude reduction in the execution time compared to the sequential approach.

Data mining model for predicting the quality level and classification of construction projects

Project managers supervise projects to ensure their smooth completion within a stipulated time frame and budget while guaranteeing construction quality. The relationships of various attributes with quality can be quantified and classified to facilitate such supervision. Therefore, this study used a data mining algorithm to analyze the relationships between defects, quality levels, contract sums, project categories, and progress in 1,015 inspection projects. In the first part, association rule mining (ARM), an unsupervised data mining approach, was used to obtain 11 rules relating two defect types (i.e., quality management system and construction quality) and determine the relationships between the four attributes (i.e., quality level, contract sum, project category, and progress). The resulting association rule may be beneficial for construction management because project managers can use it to determine the correlations between defects and attributes. In the second part, supervised data mining techniques, namely neural network (NN), support vector machine (SVM), and decision tree (C5.0 and QUEST) algorithms, were applied to develop a classification model for quality prediction. The target variable was quality, which was divided into four levels, and the decision variables comprised 499 defects, 3 contract sums, 7 project categories, and 2 progress variables. The results indicated that five defects were important. Finally, the four indicators of gain chart, break-even point (BEP), accuracy, and area under the curve (AUC) were calculated to evaluate the model. For the SVM model, the actual value predicted by the gain chart was 96.04%, the BEP was 0.95, and the AUC was 0.935. The SVM yielded optimal classification efficiency and effectively predicted the quality level. The data mining model developed in this study can serve as a reference for effective construction management.

Multi-objectives TLBO hybrid method to select the related risk features with rheumatism disease

Features subset selection was commonly used in data mining and artificial intelligence techniques to produce a model with a minimal set of features that enhances the performance of the classifier. The essential motive for selecting features is to avoid the problem of a number of dimensions trap. This paper introduces a new technique of selection of features dependent on the modified of binary teaching–learning-based optimization and the suggested method called MBTLBO. This algorithm (teaching learning-based optimization TLBO) is one of the present metaheuristic that is been widely utilized to a several of intractable optimization issues in recent times. Such algorithm has been combined with supervised data mining technique (support vector machine) for the implementation of feature subset selection problem in binary identification. The collection of specific risk features with the rheumatic disease was implemented. The findings revealed that the new approach (MBTLBO) increases the accuracy of classification.

Developing machine-learning regression model with Logical Analysis of Data (LAD)

This paper proposes a regression model based on Logical Analysis of Data (LAD). LAD is known as a combinatorial Boolean supervised data mining technique for pattern generation. It is used mainly for classification problems, and has demonstrated high accuracy compared to other classification techniques. In this paper, we extend the use of LAD to deal with supervised data with continuous responses. We derive a LAD regression model (LADR). Three discretization methods that transform the values of the response into a set of thresholds are tested. At each threshold, LAD analyzes the data as a two-class classification problem and extracts the prescriptive patterns for each class. LADR regression uses the generated patterns from the original data by using cbmLAD software to fit a numerical continuous dependent response. Therefore, a normalized regression model with only binary independent variables is obtained. LADR has been applied for six datasets and obtains better results compared with the linear regression (LR), support vector regression (SVR), Decision Tree Regression (DTR), Random Forest (RF), and Polynomial Regression (PolyR). The performance is evaluated by the Mean Square Error (MSE), Coefficient of Determination (R2), and Mean Absolute Error (MAE) based on a 10-fold cross validation.

A new predictive medical approach based on data mining and Symbiotic Organisms Search algorithm

Handling very large data, in order to make the best decision, is only possible through an extraction of knowledge. Data mining has become a widely used process in data analytics to extract the most important knowledge for predictive decision making. One of the important types of data mining is clustering mechanism; its purpose is dividing data into a set of clusters with very large data, the numbers of parameters are very high, and the clustering problem is more difficult. Metaheuristics have been widely used in clustering; they can provide satisfactory solutions for complex problems. The main objective of this paper is to propose a new clustering algorithm based on a metaheuristic technique called Symbiotic Organisms Search (SOS), it was inspired from a biological process, and it simulates the symbiotic interaction between organisms of the same population. The SOS method is used to find the optimal centers of a number of clusters, as a supervised data mining technique. Experimental results have been performed through two phases. Firstly, the SOS technique is benchmarked with six well-known test functions. Secondly, different medical datasets have been used to test our proposed clustering method based on SOS, and show its credibility of treatment.

Investigation and comparative analysis of data mining techniques for the prediction of crop yield

Crop yield is affected by climatic, management, geographical, biological and other such factors. Data mining techniques can be used to analyse the effect of these factors on crop yield and to predict crop yield based on these factors. The current paper focuses on the sequence of steps to be followed in data mining process for prediction of crop yield - starting from the determination of research goals to the application of the data mining techniques to build a model. The study applies the defined data mining process to build a model for the prediction of paddy yield based on different climatic factors. The current research also provides an insight to the different metrics that can be used to evaluate various supervised data mining techniques. The metrics have been divided into three categories - threshold evaluation metrics, numerical evaluation metric, and built time and size metrics. Comparative analysis of five supervised data mining techniques has been carried out on the basis of their performance in these three categories of metrics.

An overview and comparison of supervised data mining techniques for student exam performance prediction

Recent increase in the availability of learning data has given educational data mining an importance and momentum, in order to better understand and optimize the learning process and environments in which it occurs. The aim of this paper is to provide a comprehensive analysis and comparison of state of the art supervised machine learning techniques applied for solving the task of student exam performance prediction, i.e. discovering students at a “high risk” of dropping out from the course, and predicting their future achievements, such as for instance, the final exam scores. For both classification and regression tasks, the overall highest precision was obtained with artificial neural networks by feeding the student engagement data and past performance data, while the usage of demographic data did not show significant influence on the precision of predictions. To exploit the full potential of the student exam performance prediction, it was concluded that adequate data acquisition functionalities and the student interaction with the learning environment is a prerequisite to ensure sufficient amount of data for analysis.

Application of support vector regression analysis to estimate total organic carbon content of Cambay shale in Cambay basin, India – a case study

The objective of the present study is to estimate total organic carbon (TOC) content over the entire thickness of Cambay Shale, in the boreholes of Jambusar–Broach block of Cambay Basin, India. To achieve this objective, support vector regression (SVR), a supervised data mining technique, has been utilized using five basic wireline logs as input variables. Suitable SVR model has been developed by selecting epsilon-SVR algorithm and varying three different kernel functions and parameters like gamma and cost on a sample dataset. The best result is obtained when the radial-basis kernel function with gamma = 1 and cost = 1, are used. Finally, the performance of developed SVR model is compared with the ΔlogR method. The TOC computed by SVR method is found to be more precise than the ΔlogR method, as it has better agreement with the core-TOC. Thus, in the present study area, the SVR method is found to be a powerful tool for estimating TOC of Cambay Shale in a continuous and rapid manner.

Using Data Mining Techniques to Investigate the Correlation between Surface Cracks and Flange Lengths in Deep Drawn Sheet Metals

Abstract A problem during manufacturing of body parts in the automobile industry is the frequent occurrence of surface cracks in sheet metal cold forming processes. In this paper, we compare different supervised data mining techniques to predict cracks in deep-drawn sheet metals using their flange lengths as correlating features. Inline images of sheet metals are taken during the deep drawing process through cameras that are installed in every stage of a six-stage press line. A commercial software is used to label the images as defective and non-defective. Additionally, flange lengths, which generally correlate with forces set at the machines, are measured along the periphery of the sheets. The results are promising, as the models achieved satisfactory accuracy rates, albeit with some margin for improvement. This paper aims to choose a binary classification algorithm that is best suitable for the given dataset. Furthermore, the results provide an insight on the correlation of flange lengths with the occurrence of cracks, which can be used for online parameter adjustments of the machines in the future.

Introducing a new method for the fusion of fraud evidence in banking transactions with regards to uncertainty

Detection of fraudulent transactions is a vital factor for financial institutions, and finding more effective and accurate methods is of tremendous importance. The use of supervised data mining techniques is not feasible in many cases due to the lack of access to labeled data. Fraud detection is a complex task, and unsupervised methods like clustering and outlier detection techniques employed alone do not yield satisfactory results. Another issue is epistemic uncertainty due to the absence of sufficient information on the behavioral aspects of different customers, which also leads to poorer results for fraud detection and makes the fraud detection system inapplicable in real world environment. In this paper, using multi criteria decision method, intuitionistic fuzzy set, and evidential reasoning, a new method for detection of fraud was introduced, which infuses several behavioral evidence of a transaction concerning the effect of uncertainty for them. Transactional behavior was modeled by considering the trends of different main and aggregated variables at different periods and the extent of deviation of the new arrived transaction from each of these trends were considered as behavioral evidence. The final belief, which is the result of the combination of much evidence using the proposed method, will determine the originality of a newly arrived transaction. Finally, using a real world dataset, the results of the new method were compared with the results of Dempster–Shafer method in terms of the number of frauds discovered and the number of erroneous alerts they issued. The findings showed that the method introduced in this study has higher accuracy and lower false alarms compared to Dempster–Shafer method while the computational complexity of this method makes its implementation time longer.

A predictive method for hepatitis disease diagnosis using ensembles of neuro-fuzzy technique.

Hepatitis is an inflammation of the liver, most commonly caused by a viral infection. Supervised data mining techniques have been successful in hepatitis disease diagnosis through a set of datasets. Many methods have been developed by the aids of data mining techniques for hepatitis disease diagnosis. The majority of these methods are developed by single learning techniques. In addition, these methods do not support the ensemble learning of the data. Combining the outputs of several predictors can result in improved accuracy in classification problems. This study aims to propose an accurate method for the hepatitis disease diagnosis by taking the advantages of ensemble learning. We use Non-linear Iterative Partial Least Squares to perform the data dimensionality reduction, Self-Organizing Map technique for clustering task and ensembles of Neuro-Fuzzy Inference System for predicting the hepatitis disease. We also use decision trees for the selection of most important features in the experimental dataset. We test our method on a real-world dataset and present our results in comparison with the latest results of previous studies. The results of our analyses on the dataset demonstrated that our method performance is superior to the Neural Network, ANFIS, K-Nearest Neighbors and Support Vector Machine. The method has potential to be used as an intelligent learning system for hepatitis disease diagnosis in the healthcare.

Financial Fraud Detection using Radial Basis Network

The ubiquitous cases of abnormal transactions with intent to defraud is a global phenomenon. An architecture that enhances fraud detection using a radial basis function network was designed using a supervised data mining technique― radial basis function (RBF) network, a multivariate interpolation approximation method. Several base models were thus created, and in turn used in aggregation to select the optimum model using the misclassification error rate (MER), accuracy, sensitivity, specificity and receiver operating characteristics (ROC) metrics. The results shows that the model has a zero-tolerance for fraud with better prediction especially in cases where there were no fraud incidents doubtful cases were rather flagged than to allow a fraud incident to pass undetected. Expectedly, the model’s computations converge faster at 200 iterations. This study is generic with similar characteristics with other classification methods but distinct parameters thereby minimizing the time and cost of fraud detection by adopting computationally efficient algorithm.

Network Intrusion Detection in Big Dataset Using Spark

Nowadays, huge amount of data is flowing every second; hence intrusion detection task became tedious. Hence, Intrusion detection systems require efficient and improved detection mechanism which could detect intrusive activities and serious threat to network security. Nowadays, huge amount of data is flowing every second; hence intrusion detection task became tedious. In our research work, we have proposed a framework in which a feature reduction algorithm is used for reducing the less important features and then applied the supervised data mining techniques on UNSW-NB15network dataset for fast, efficient and accurate detection of intrusion in the Netflow records using Spark. In this paper, we have used two feature reduction algorithms, namely, Canonical Correlation Analysis (CCA) and Linear Discriminant Analysis (LDA) and seven well known classification algorithms. In order to compare the performance of the proposed framework, five performance matrices such as accuracy, Specificity, Kappa, Mean Abs. Error, FPR, Precision, Recall, ROC Area and Training Time are used.

An analytics approach to exploring the link between ICT development and affordability

Despite the rapid development in information and communications technologies (ICTs), the disparity in the ICT affordability, adoption, and utilization between developed and developing countries is still a subject of discussion among academics, researchers, and policy makers. Recent initiatives by the UN in developing a comprehensive ICT development index (IDI) and other accompanying data collection efforts have created a fertile ground for researchers in applying various methods to measure the magnitude of the digital divide and monitor how the disparity will evolve over time. This paper contributes towards this objective by extending existing research in the measurement and understanding of the global digital divide issue. Using unsupervised and supervised data mining techniques, we explore the countries' ICT development and affordability profiles, their evolution over time, and the link between ICT pricing and the ICT development stages of countries. Our analyses, based on ICT pricing and development data of 120 countries from 2008 to 2012, provide valuable insights into the global digital divide and the evolution of countries over time. In addition, it demonstrates the potential for predicting a country's future ICT development stage using its past or current ICT pricing information. This provides policy making opportunities for governments through continuous monitoring, reporting, and benchmarking of their ICT development and pricing information.

A MULTIVARIATE TIME SERIES CLASSIFICATION METHOD FOR STREAMING DATA USING TEMPORAL METAFEATURE ABSTRACTIONS

In this paper we demonstrate a new approach to the classification of multivariate time series streaming data by utilizing a temporal metafeature abstractions method. The technique extracts global features and metafeatures in order to capture the necessary time-lapse information in the streams of data. The features are then used to create a static, intermediate stream representation that includes all the important time-varying information, and is suitable for analysis using the standard supervised data mining techniques. The capability of the new algorithm called MineTool-TS2 was demonstrated through its application to three datasets: UCSD Microgrid energy usage data, a space physics dataset and synthetic data.

Analysis of meal patterns with the use of supervised data mining techniques—artificial neural networks and decision trees

Background:At present, the analysis of dietary patterns is based on the intake of individual foods. This article demonstrates how a coding system at the meal level might be analyzed by using data mining techniques. Objective:The objective was to evaluate the usability of supervised data mining methods to predict an aspect of dietary quality based on dietary intake with a food-based coding system and a novel meal-based coding system. Design:Food consumption databases from the North-South Ireland Food Consumption Survey 1997–1999 were used. This was a randomized cross-sectional study of 7-d recorded food and nutrient intakes of a representative sample of 1379 Irish adults. Meal definitions were recorded by the respondent. A healthy eating index (HEI) score was developed. Artificial neural networks (ANNs) and decision trees were used to predict quintiles of the HEI based on combinations of foods consumed at breakfast and main meals. Results:This study applied both data mining techniques to the food and meal-based coding systems. The ANN had a slightly higher accuracy than did the decision tree in relation to its ability to predict HEI quintiles 1 and 5 based on the food coding system (78.7% compared with 76.9% and 71.9% compared with 70.1%, respectively). However, the decision tree had higher accuracies than did the ANN on the basis of the meal coding system (67.5% compared with 54.6% and 75.1% compared with 72.4%, respectively). Conclusions:ANNs and decision trees were successfully used to predict an aspect of dietary quality. However, further exploration of the use of ANNs and decision trees in dietary pattern analysis is warranted.