Data Mining Models Research Articles

Validation of data mining models by comparing with conventional methods for dental age estimation in Korean juveniles and young adults

Teeth are known to be the most accurate age indicators of human body and are frequently applied in forensic age estimation. We aimed to validate data mining-based dental age estimation, by comparing the accuracy of the estimation and classification performance of 18-year thresholds with conventional methods and with data mining-based age estimation. A total of 2657 panoramic radiographs were collected from Koreans and Japanese populations aged 15 to 23 years. They were subdivided into a training and internal test set of 900 radiographs each from Koreans, and an external test set of 857 radiographs from Japanese. We compared the accuracy and classification performance of the test sets from conventional methods with those from the data mining models. The accuracy of the conventional method with the internal test set was slightly higher than that of the data mining models, with a slight difference (mean absolute error < 0.21 years, root mean square error < 0.24 years). The classification performance of the 18-year threshold was also similar between the conventional method and the data mining models. Thus, conventional methods can be replaced by data mining models in forensic age estimation using second and third molar maturity of Korean juveniles and young adults.

Early Warning Model of College Students' Psychological Crises Based on Big Data Mining and SEM

In recent years, the psychological problems of college students could not be ignored, as they have seriously affected the growth of students and the normal teaching order of colleges and universities. However, there exists a strong noise in college students' psychological sample data set and a strong correlation between its data. Aiming to solve this problem, this paper proposes a psychological crisis warning method for college students based on big data mining and structural equation model (SEM). This method is oriented to massive user data in social networks. Particle swarm optimization is introduced to improve the random forest algorithm, and the original data is labeled to alleviate the impact of data noise on the recognition accuracy. The simulation example comes from an efficient actual data set in the southern China. The experimental results show that the proposed method can achieve an efficient analysis of actual complex data, and can provide reliable psychological auxiliary diagnosis for practitioners.

Agile neural expert system for managing basic education

Inadequate experts in managing resources at the lower level of education to enhance effective teaching and learning for quality education is a significant challenge in developing nations. Many basic schools lack basic educational resources such as sitting places and writing places for learners. Inadequate teaching and learning resources negatively affect the educational policies in a country. It is common to see the media projecting the challenges of a school lacking these resources. The use of an Expert System (ES) in Artificial Intelligence (AI) to assist in effective management is a necessity. In this paper, an agile neural expert system is proposed using differential equations with an initial value problem. The technique combines both rule-based and neural networks in handling the problem. The expertise of the Human Expert (HE) is used in a knowledge-based to assist in managing the resources in schools. This has been possible with the use of Data Mining (DM) techniques and modeling of projected population growth, affecting enrolment in schools and necessitating the provision of resources to cater to the growing population. For efficiency and effectiveness in planning, provision, and management of the resources, smart notification has been embedded in the system to monitor the availability and provision of the resources by prompting the various actors in the requisition, verification, validation, and approval of resources to be supplied to schools. The system proves a higher efficiency demonstrating speed in decision-making, accuracy in decisions and ease to use.

Comparative Analysis of Various Techniques used for Predicting Student’s Performance

Research in higher education is beginning to explore the potential of data mining in analysing data to give quality service and needs of their graduates. Thus, educational data mining emerges as one tools to study academic tool data to identify patterns and help for decision making with affecting education. Data mining applications are becoming a more common tool in understanding and solving educational and administrative problems in higher education. Generally, research in educational mining focuses on modelling students’ performance instead of instructors’ performance. One of the common tools to evaluate instructors’ performance is the course evaluation questionnaire to evaluate based on students’ perceptions. In this study, four different classification techniques, decision tree algorithms, support vector machines, artificial neural networks, and discriminant analysis– are used to build classifier models. Their performances are compared over a dataset composed of responses of students to a real course evaluation questionnaire using accuracy, precision, recall, and specificity performance metrics. Although all the classifier models show comparably high classification performances, accordingly, it is shown that many of the questions in the course evaluation questionnaire appear to be irrelevant. Furthermore, the analysis shows that the instructors’ success based on the students’ perception mainly depends on the interest of the students in the course. The finding of the study indicate the effectiveness and expressiveness of data mining models in course evaluation and higher education mining. Moreover these findings may be used to improve measurement instruments.

Reciprocal analysis of groundwater potentiality and vulnerability modeling in the Bahabad Plain, Iran.

Heuristic and statistical groundwater quality assessment models are efficient tools in the zoning of groundwater vulnerability to contamination. An important reciprocal methodology, yet neglected in Iran, was conducted to assess the performance of three groundwater vulnerability models, namely GODS, SI, and DRASTIC, and a data mining model for groundwater potential, maximum entropy (MaxEnt). For both the training and validation stages for the MaxEnt model, the Mahalanobis distance technique was adopted. The vulnerability rates obtained from the DRASTIC model with a coefficient of determination (R2) value of 0.76 had a statistically significant correlation with nitrate concentrations in the 21 wells, compared to SI and GODS. The DRASTIC model can better reflect the vulnerability of groundwater resources to contamination. The impact of the vadose zone with an average effective weight of 33 is more important than other parameters, followed by depth than groundwater (D) (32.01), net recharge (R) (28.95), and the aquifer media (A) (18.1). These weights may not be changed. MaxEnt showed significant performance in both the training and validation stages with the respective area under the receiver operating characteristic curve (AUROC) values of 0.907 and 0.901. A reciprocal analysis between the vulnerability map in the superior model and the groundwater potential map derived from MaxEnt revealed that areas with high groundwater potential are still in safe state but require more attention as the top priority for amendment practices. In addition, approximately 8.7% of the entire study area has a high vulnerability to contamination, which requires immediate pragmatic actions.

Extracting decision models for ski injury prediction from data

AbstractCreating decision models for risk assessment of ski injuries is a challenging task. Ski injuries are rare events, but they carry a high cost, that is, can cause working or movement disabilities. Usually, ski risk assessment is performed on small‐scale, case‐controlled studies where the effect of a single factor is evaluated. Recently, data mining and machine learning algorithms are being employed for ski risk assessment and injury prediction. However, these models do not generally satisfy the need for interpretation of the decision model, do not provide explanations for the predictions, and in general do not ensure the completeness and consistency of decision rules. To make data mining and machine learning models useful, one needs to implement the aforementioned properties. Decision support systems are expected to have these properties; however, the process of building such decision support systems is still tedious: it has to consider human biases, assumptions, and subjective values, as well as focus on the decision problem being solved. We propose a method for extraction of decision models from data at hand. Our method DIDEX, Data Induced DEcision eXpert, builds models that have desirable properties for inclusion in decision support systems. The proposed method is used to build a decision model for ski injury prediction based on data from Mt. Kopaonik ski resort, Serbia. The results show that DIDEX generates up to a five times simpler model compared to the existing domain expert DEX models while having a 6% better predictive accuracy. Additionally, its predictive accuracy is comparable to similar machine learning algorithms, such as decision tree classifiers, random forest, and logistic regression.

Haptic and Biometric Sensor Technologies, Spatial Data Mining and Simulation Modeling Algorithms, and Virtual Navigation and Decision Intelligence Tools across Web3-powered Metaverse Worlds

Haptic and Biometric Sensor Technologies, Spatial Data Mining and Simulation Modeling Algorithms, and Virtual Navigation and Decision Intelligence Tools across Web3-powered Metaverse Worlds

A Text Mining and Statistical Approach for Assessment of Pedagogical Impact of Students’ Evaluation of Teaching and Learning Outcome in Education

Technology-enhanced learning (TEL) is now at the heart of teaching and learning process in many higher education institutions (HEIs). Today, educators are faced with the challenges of pedagogically specifying what tools, methods, and technologies are used to support the teachers and students, and to help maintain/sustain a continuous education and practices. This study shows that there is an opportunity in the use of (educational) datasets derived about the teaching and learning processes to provide insights for fostering the education process. To this effect, it analyzed the students’ evaluation of teaching (SET) dataset ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n=471968$ </tex-math></inline-formula> ) collected within a higher education setting to determine prominent factors that influences the students’ performance or the way (TEL-based) education is being delivered, including its didactical impact and implications for practice. Theoretically, the study employed a mixed methodology grounded on integration of the Data-structure approach and Descriptive decision theory to study the rationality behind the students’ evaluation of the teaching and performance. This was done through the Textual data quantification (qualitative) and Statistical (quantitative) analysis. Qualitatively, the study applied the Educational Process and Data Mining (EPDM) model (a text mining method) to extract the different sentiments and emotional valence expressed by the students in the SET, and how those characteristically differ based on the period and type of evaluation they have completed (between 2019 to 2021). For the quantitative analysis, the study used a multivariate analysis of covariance (MANCOVA) and multiple pairwise comparisons post-hoc tests to analyze the quantified information (average sentiment and emotional valence) extracted from the SET data to determine the marginal means of effect the different SET types and evaluation period have on the students’ learning outcomes/perception about the teaching-learning process. In addition, the study empirically discussed and shed light on the implications of the main findings for TEL-based Education, particularly implemented by the HEI during the analyzed periods. The scholastic indicator from the study shows that while the flexible digital models or instructional methods are effective for continuous education, innovative pedagogies, and teaching transformations. It also, on the other hand, serve as an incentive for more robust research that idiosyncratically look into their implications for the students’ learning outcomes and assessment done in this study.

Development of a Data Mining Model to Detect Cardiovascular Disease

In the previous publication on Volume 15 No 9, September 30, 2022 of IJCN, we analyzed “Data Mining as a Technique for Healthcare Approach”. In this edition, emphasis has been made on the “Development of Data Mining Model to Detect Cardiovascular Diseases (CVD)”. A Software was developed using the internationally accepted Software Engineering Methodology (SSADM), coding by OOP and packing by prototyping methodologies. Among others, this paper discusses; Cardiovascular diseases, Data Mining Algorithm, Analysis and Information flow of the Present System, Data flow and High level flow of the Proposed System, Modulating, System Design and Development, Hardware and Software Specifications, System Testing, Evaluation and Documentation.

Consistency preserving database watermarking algorithm for decision trees

Database watermarking technologies provide an effective solution to data security problems by embedding the watermark in the database to prove copyright or trace the source of data leakage. However, when the watermarked database is used for data mining model building, such as decision trees, it may cause a different mining result in comparison with the result from the original database caused by the distortion of watermark embedding. Traditional watermarking algorithms mainly consider the statistical distortion of data, such as the mean square error, but very few consider the effect of the watermark on database mining. Therefore, in this paper, a consistency preserving database watermarking algorithm is proposed for decision trees. First, label classification statistics and label state transfer methods are proposed to adjust the watermarked data so that the model structure of the watermarked decision tree is the same as that of the original decision tree. Then, the splitting values of the decision tree are adjusted according to the defined constraint equations. Finally, the adjusted database can obtain a decision tree consistent with the original decision tree. The experimental results demonstrated that the proposed algorithm does not corrupt the watermarks, and makes the watermarked decision tree consistent with the original decision tree with a small distortion.

Quantitative Study of Traffic Accident Prediction Models: A Case Study of Virginia Accidents

Traffic accidents are a serious problem that threatens people's lives, health, and properties. Thus, decreasing traffic accidents is a crucial demand for public safety. This paper proposes two data mining models to predict accident risks based on the decision tree and the naive Bayes algorithms. The purpose of the classifiers is to predict the potential severity of a traffic accident based on a set of data attributes related to the weather factors, accident timing, and properties of the road. The models are developed using data on accidents in Virginia between 2016 and 2021. Several metrics are considered to measure the performance of each model such as accuracy, precision, recall, and F1-score. Furthermore, to statistically compare the performance of the prediction models, the study employs three quantitative analysis tools, approximate visual test, paired observations, and ANOVA. The experimental results revealed that the decision tree outperforms naive Bayes in terms of prediction accuracy.

Data Mining Approach Based on Hierarchical Gaussian Mixture Representation Model

Infinite Gaussian mixture process is a model that computes the Gaussian mixture parameters with order. This process is a probability density distribution with adequate training data that can converge to the input density curve. In this paper, we propose a data mining model namely Beta hierarchical distribution that can solve axial data modeling. A novel hierarchical Two-Hyper-Parameter Poisson stochastic process is developed to solve grouped data modelling. The solution uses data mining techniques to link datum in groups by linking their components. The learning techniques are novel presentations of Gaussian modelling that use prior knowledge of the representation hyper-parameters and approximate them in a closed form. Experiments are performed on axial data modeling of Arabic Script classification and depict the effectiveness of the proposed method using a hand written benchmark dataset which contains complex handwritten Arabic patterns. Experiments are also performed on the application of facial expression recognition and prove the accuracy of the proposed method using a benchmark dataset which contains eight different facial expressions.

Using Data Mining Techniques to Predict Chronic Kidney Disease: A Review Study.

One of the growing global health problems is chronic kidney disease (CKD). Early diagnosis, control, and management of chronic kidney disease are very important. This study considers articles published in English between 2016 and 2021 that use classification methods to predict kidney disease. Data mining models play a vital role in predicting disease. Through our study, data mining techniques of support vector machine, Naive Bayes, and k-nearest neighbor had the highest frequency. After that, random forest, neural network, and decision tree were the most common data mining techniques. Among the risk factors associated with chronic kidney disease, respectively, risk factors of albumin, age, red blood cells, pus cells, and serum creatinine had the highest frequency in these studies. The highest number of best yields was allocated to random forest technique. Reviewing larger databases in the field of kidney disease can help to better analyze the disease and ensure the risk factors extracted.

Correlating driving behavior with safety performance: from the heart to the pedals with a driving simulator

Driving behavior significantly affects road safety, pollutant emissions, and fuel consumption, and an in-depth analysis is crucial for any accurate evaluation of a transport system. To develop a comprehensive study, it is important to consider different variables and traffic conditions, the presence of vulnerable road users, road singularities, as well as driving behavior profiles (e.g., gear-shift strategy, acceleration style). In this research, fixed-based driving simulation tests were carried out to allow a global evaluation of driving behavior under two different traffic conditions (urban and highway). The main objective is to understand driver-road interaction and associated impacts in terms of the adopted gear-shift strategy, vehicle dynamics profile, driving volatility profile (a safety-related indicator), driver's heart rate monitoring (a driving comfort-related variable), and pollutant emissions modeling. Drivers’ performance was assessed for each case study and a database was created for different segment types and considering different drivers, using statistical data mining models. This work is relevant for a better understanding of driving behavior both from the viewpoint of policymaking as well as for driver awareness about the relative impact associated with his/her driving behavior.

Penerapan Feature Selection Pada Algoritma Decision Tree Untuk Menentukan Pola Rekomendasi Dini Konseling

Early detection in providing recommendations for student counseling is very important, therefore you can assess the student's potential, beliefs, and attitude as early as possible. The problem that arises in this case is how to detect a student early so that he or she needs counseling assistance or not so that it can be identified early to minimize the risk of further psychological conditions. This article proposes a data mining model using a decision tree to classify counseling recommendations for students. In addition, to improve the resulting accuracy performance, a feature selection method is proposed using forward selection and genetic algorithms. The stages of the research were carried out by pre-processing the data, implementing algorithms, validating data, and optimizing the model. The experimental results show that the best level of accuracy using the decision tree model is 95.64%. It increases to 96.91% after optimization using the genetic algorithm.

Proposed framework for applying data mining techniques to detect key performance indicators for food deterioration

One of the most prosperous domains that Data mining accomplished a great progress is Food Security and safety. Some of Data mining techniques studies applied several machine learning algorithms to enhance and traceability of food supply chain safety procedures and some of them applying machine learning methodologies with several feature selection methods for detecting and predicting the most significant key performance indicators affect food safety. In this research we proposed an adaptive data mining model applying nine machine learning algorithms (Naive Bayes, Bayes Net Key -Nearest Neighbor (KNN), Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), J48, Hoeffding tree, Logistic Model Tree) with feature selection wrapper methods (forward and backward techniques) for detecting food deterioration’s key performance indicators. Therefore, results before and after applying wrapper feature selection methods have been compared, analyzed, and interpreted. In conclusion the proposed model applied effectively and successfully detected the most significant indicators for meat safety and quality with the aim of helping farmers and suppliers for being sure of delivering safety meat for consumer and diminishing the cost of monitoring meat safety.

Impact of Digital Transformation of Engineering Enterprises on Enterprise Performance Based on Data Mining and Credible Bayesian Neural Network Model

Enterprise performance’s path choice is impacted by DT (digital transformation). However, from the standpoint of the digital economy, there is currently a dearth of research studying the effect of DT on company performance. The rise of big data technologies makes it feasible to collect comprehensive and objective information. In order to do this, we suggest a new forecasting technology that fully utilises DM (data mining) technology to implement the forecasting process, processes the enterprise’s quantitative financial index data, and creates a model. The enterprise performance is forecasted by the reliable Bayesian neural network model of the innovative project portfolio, and the logic of the model architecture is demonstrated. The findings demonstrate that as sample numbers rise, the average accuracy of training samples gradually drops while the average accuracy of test samples gradually rises. The average accuracy of training samples is 0.726, while the average accuracy of validation samples is 0.652 when there are 150 samples. The analysis of the results demonstrates that this study successfully integrates DM into the corporate performance prediction model.

Sphere Gap Breakdown Voltage Prediction Based on ISSA Optimized BP Neural Network and Effective Electric Field Feature Set

Electric field distribution is a determinant factor of air gap breakdown voltage. This paper defined an effective electric field zone between the sphere gaps for feature extraction, and 29 parameters were extracted from this zone to reflect the electric field distribution. A data mining model was established by back propagation neural network (BPNN) for sphere gap breakdown voltage prediction, taking the electric field features as inputs. The maximum information coefficient (MIC) method was used to select features strongly correlated to the breakdown voltage, and a multi‐strategy improved salp swarm algorithm (ISSA) was applied to optimize the BPNN parameters to enhance the prediction performance. The standard sphere gaps provided in IEC 60052 were taken as training set and test set, which were divided according to the electric field nonuniform coefficients. The breakdown voltage prediction results of test sample sphere gaps demonstrate good agreements with the experimental values. With input features selected by the MIC method, the ISSA optimized BPNN model has a mean absolute percentage error of only 0.83% and a maximum relative error of 5.86%. By constructing the nonlinear mapping relationship between the effective electric field features and the insulation strength, this study provides a new approach to predict air gap breakdown voltage. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Challenges of using Data Mining Techniques to Analyze and Forecast COVID-19 Pandemic in Zambia

COVID-19 is a highly infectious respiratory disease that belongs to the SARS group of viruses that has presented a global challenge to almost everyone world-wide. During the early stages of the pandemic in Zambia, a major challenge was the limited data and datasets for COVID-19. This challenge restricted research, especially in data mining. The challenge of data and datasets is currently improving. This paper presents the challenges of using data mining techniques and models to analyze and forecast the COVID-19 pandemic in Zambia. The analysis initially presents the methodology used for creating a dataset that focuses on the pandemic at provincial scope and uses the Zambia National Public Health Institute (ZNPHI) and Ministry of Health Zambia daily situation reports. The analysis of the pandemic at country level used the COVID-19 datasets from the Humanitarian Data Exchange (HDX) and the European Center for Disease Prevention and Control (ECDC). The study finally discusses the development and evaluation of the forecasting model. The forecasting model is based on the COVID_SEIRD Python package. To evaluate the forecasting model, the research utilized a combination of correlation and the max-function from basic statistics. The analysis focuses on finding the provincial area with the most COVID-19 cases in Zambia, while the forecasting process manages to forecast the trend of the pandemic for recoveries and fatalities.

IMPLEMENTATION OF WEB-BASED NAIVE BAYES ALGORITHM FOR DETERMINING DEPARTMENTS AT SMK 10 MUHAMMADIYAH KISARAN

Determination of majors is very important for the convenience of prospective students in the process and continuation of education so that they do not experience difficulties in the teaching and learning process in the future. SMK 10 Muhammadiyah Kisaran is one of the private vocational schools in Asahan that provides 3 majors including Audio Video Engineering (TAV), Computer and Network Engineering (TKJ), and Motorcycle Engineering and Business (TBSM). SMK 10 Muhammadiyah Kisaran does not yet have a special system for selecting majors so that prospective students are welcome to choose majors according to their own wishes, not a few students find it difficult because the students themselves do not understand their abilities.so that it’s not uncommon for students to choose majors in a random way or follow their friends' choices. Therefore we need a system that can help prospective students in selecting majors that match their interests and talents and reduce mistakes in choosing majors. The technique used for the classification data mining model in this study is the Naïve Bayes Algorithm. The dataset that will be used as training data and test data is data for new students for the 2021/2022 school year, to be precise, for class X SMK 10 Muhammadiyah Kisaran obtained from the results of documentation and questionnaires. The criteria used were school origin, gender, interests, major, influence of friends, parental suggestions, math scores, English grades, and science grades. The results of the classification modeling with the Naïve Bayes Algorithm produce an accuracy value of 89%.