Data Mining Models Research Articles

Research on a Risk Early Warning Mathematical Model Based on Data Mining in China’s Coal Mine Management

The degree of informatization of coal mine safety management is becoming higher and higher, and a large amount of information is generated in this process. How to convert the existing information into useful data for risk control has become a challenge. To solve this challenge, this paper studies the mathematical model of coal mine risk early warning in China based on data mining. Firstly, the coal mine risk data was comprehensively analyzed to provide basic data for the risk prediction model of data mining. Then, the adaptive neuro-fuzzy inference system (ANFIS) was optimized twice to build the coal mine risk prediction model. By optimizing the calculation method of the control chart, the coal mine risk early warning system was proposed. Finally, based on the coal mine risk early warning model, the software platform was developed and applied to coal mines in China to control the risks at all levels. The results show that the error of the optimized ANFIS was reduced by 66%, and the early warning error was reduced by 57%. This study aimed to provide implementation methods and tools for coal mine risk management and control, and data collected has reference significance for other enterprises.

An Efficient Hybrid Feature Selection Method Using the Artificial Immune Algorithm for High-Dimensional Data.

Feature selection provides the optimal subset of features for data mining models. However, current feature selection methods for high-dimensional data also require a better balance between feature subset quality and computational cost. In this paper, an efficient hybrid feature selection method (HFIA) based on artificial immune algorithm optimization is proposed to solve the feature selection problem of high-dimensional data. The algorithm combines filter algorithms and improves clone selection algorithms to explore the feature space of high-dimensional data. According to the target requirements of feature selection, combined with biological research results, this method introduces the lethal mutation mechanism and the Cauchy operator to improve the search performance of the algorithm. Moreover, the adaptive adjustment factor is introduced in the mutation and update phases of the algorithm. The effective combination of these mechanisms enables the algorithm to obtain a better search ability and lower computational costs. Experimental comparisons with 19 state-of-the-art feature selection methods are conducted on 25 high-dimensional benchmark datasets. The results show that the feature reduction rate for all datasets is above 99%, and the performance improvement for the classifier is between 5% and 48.33%. Compared with the five classical filtering feature selection methods, the computational cost of HFIA is lower than the two of them, and it is far better than these five algorithms in terms of the feature reduction rate and classification accuracy improvement. Compared with the 14 hybrid feature selection methods reported in the latest literature, the average winning rates in terms of classification accuracy, feature reduction rate, and computational cost are 85.83%, 88.33%, and 96.67%, respectively.

Analysis of Data Mining Model for Successful Implementation of Data Warehouse in Tertiary Institutions (A Case Study of Irahim Badamasi Babangida University)

This research work with title “analysis of data mining model for successful implementation of data warehouse in tertiary institutions” is a proposal that provides a framework that is used to structure, plan, and control the process involved in information discovery for tertiary institutions. It equally deals with series of steps or procedures which governs the analysis and design of this particular Data Mining Model for Tertiary Institutions. The methods, techniques and procedures which are used to collect and analyze information were also provided and implemented. Object oriented Analysis and Design methodology (OOADM) was deployed to develop this model. The current system was analysed by using Use Case approach to identify the existing objects in the current system. Use Case diagrams were equally developed and the relationship between the objects was drawn. A diagram was drawn to represent the identified problems. Finally, the High-Level Model (HLM) that would be used to design the proposed system was drawn to enable the System Designer to develop a computer-based model that forecasts educational behaviours with little or no user intervention.

Intelligent Voice System Design for Optimizing E-Business Advertising Rhetoric Based on SVM Algorithm.

With the emergence and development of artificial intelligence, design is no longer a process that can be completed only by creativity and knowledge. This article introduces research based on voice data mining and further discusses the optimization and application of rhetorical methods for e-commerce advertising. This article is working from two main aspects: one is to use association rule models in speech data mining to obtain useful rule relationships between Chinese prosody parameters, and the other is to use neural networks and data items in speech data mining. Using computer technology can make online advertisements interact with users. In addition to clicking on advertisements to jump to product pages, online advertisements also have multichannel sensory feelings, which can provide rich information and stimulate interest through interaction with users. We need to optimize the rhetoric of the advertisement and pay attention to the combination of the beauty of speech and the content of the advertisement when designing the advertisement. At the same time, we must also pay attention to the accuracy and elegance of the advertising language and wording.

Prediction and Industrial Structure Analysis of Local GDP Economy Based on Machine Learning

The process of regional economic growth is a long-term evolutionary law. During this long evolutionary process, some regions may continue to grow, while others may fall into decline. It takes a long time. For example, from the perspective of our country’s regional economic growth since the turn of the century, the east coast has been in a relatively developed state, while the economy of some western regions is relatively backward. Therefore, how to promote the long-term growth of developed regions and revitalize the troubled regional economy by studying the long-term growth mechanism of the regional economy is an important topic of regional economic research. In this context, we can draw the following conclusions. (1) The employment structure of major industries has been declining year by year since 2000, and this trend is relatively obvious and the decline is relatively large. Despite some changes in industrial growth, the overall trend is upward. The employment structure of the service industry has increased year by year, and its proportion in total employment usually exceeds that of major industries, and it is the industry with the largest number of employees. (2) The accuracy under the machine learning model is 79.46%, the reliability is 89.27%, and it is feasible; the accuracy under the data mining model is 68.45%, the reliability is 75.43%, and the feasibility is 86.18%; the accuracy rate under the traditional statistical model is 60.14%, the feasibility is 68.24%, and the reliability is 75.12%. GDP not only is the core indicator of national economic accounting but also can be used to measure the economic status and development level of a country or region. The impact of industrial structure on GDP is huge, and a suitable industrial structure can promote a healthier growth of GDP. In order to analyze the relationship between our country’s GDP and industrial structure, the quantitative analysis method of grey correlation analysis is used to study it, and then according to the calculation results, suggestions for adjusting and optimizing the industrial structure will be put forward to the relevant ministries.

Predictive Data Mining in Clinical Medicine: Current Issues and Guidelines

The following study is based on the predictive data mining in clinical medicine where all data have been selected by focusing on the following topic. At the first the brief introduction of data mining, predictive data mining and its usage on the clinical medicines have been shared. Then the required materials and methods have been furnished up next. After that, the usages of predictive data mining in clinical medicines have been elaborated. The usages have been depicted within several parts of, such the use of predictive data mining in the clinical medicines. Also, the uses of different models of predictive data mining have been illustrated within an extensive manner. Later on, the benefits of predictive data mining for the healthcare sector and its profit making and advantages for using predictive data mining for a medical practitioner have been represented by gathering valid insights. Furthermore, the challenges and issues related to healthcare sectors and clinical medicines have ben flaunted in the following study and the strategies to mitigate the problems by using predictive data mining has been depicted within sheer elaboration.

Evaluation of Personalized Skincare Through in-silico Gene Interactive Networks and Cellular Responses to UVR and Oxidative Stress.

PurposePersonalized approaches in dermatology are designed to match the specific requirements based on the individual genetic makeup. One major factor accounting for the differences in skin phenotypes is single nucleotide polymorphism (SNP) within several genes with diverse roles that extend beyond skin tone and pigmentation. Therefore, the cellular sensitivities to the environmental stress and damage linked to extrinsic aging could also underlie the individual characteristics of the skin and dictate the unique skin care requirements. This study aimed to identify the likely biomarkers and molecular signatures expressed in skin cells of different ethnic backgrounds, which could aid further the design of personalized skin products based on specific demands.MethodsUsing data mining and in-silico modeling, the association of SNP-affected genes with three major skin types of European, Asian and African origin was analyzed and compared within the structure-function gene interaction networks. Cultured dermal fibroblasts were subsequently subjected to ultraviolet radiation and oxidative stress and analyzed for DNA damage and senescent markers. The protective applications of two cosmetic ingredients, Resveratrol and Quercetin, were validated in both cellular and in-silico models.ResultsEach skin type was characterized by the presence of SNPs in the genes controlling facultative and constitutive pigmentation, which could also underlie the major differences in responses to photodamage, such as oxidative stress, inflammation, and barrier homeostasis. Skin-type-specific dermal fibroblasts cultured in-vitro demonstrated distinctive sensitivities to ultraviolet radiation and oxidative stress, which could be modulated further by the bioactive compounds with the predicted capacities to interact with some of the genes in the in-silico models.ConclusionEvaluation of the SNP-affected gene networks and likely sensitivities of skin cells, defined as low threshold levels to extrinsic stress factors, can provide a valuable tool for the design and formulation of personalized skin products that match more accurately diverse ethnic backgrounds.

Verification of Covid-19 Social Assistance Recipients using Naïve Bayes Classifier

The Indonesian government launches the Covid-19 social assistance program to reduce the impacts of the economic downturn during the pandemic. The recipients of social assistance in Sukabumi Selatan District of Jakarta Province is collected form Neighborhood Association (RT/RW). However, this mechanism has limitations in terms of feasibility assessment through direct verification which is not optimal due to social restriction activities. At the same time, data is also collected through the regular recipients of social aid program, so there is a data discrepancy that causing a bias in determining the recipients’ feasibility. Therefore, a mechanism is required to assess the eligibility of the recipients. This study aims to assist Social Service Agency of Sukabumi Selatan district, in assessing the eligibility of the recipients using Naïve Bayes classifier and K-Nearest Neighbors (K-NN) classifier as comparison. Experiments using Cross-Industry Standard Process for Data Mining (CRISP-DM) model were carried out on a collected dataset, and the results show that Naïve Bayes classifier shows the best result with 93% accuracy, 86% precision and 100% recall, while K-NN has 90% accuracy, 82% precision and 98% recall. This research may assist the Social Service Agency of the district to determining more accurately the target recipients.

Application of Data Mining Model in Smart Chemistry Education

In order to solve the problem that the activities of teachers and students in traditional teaching methods are constrained by lesson plans, the teaching methods are aging, and they do not have the ability to expand students’ learning through big data; due to the problem of low self-learning and extracurricular communication ability of students after class, the author proposes the application of a data mining model in smart chemistry education. The author designs an educational wisdom platform based on big data, and its overall structure includes physical layer, virtual resource layer, logic layer, presentation layer, application layer, network layer, and user layer; the big data center module in the platform collects all business data through devices such as networks and sensors and stores the business data in mass data storage devices; the software design part uses the multi-feature fusion acquisition algorithm to collect student data and completes the early warning of student performance through the performance early warning algorithm based on correlation analysis technology. The results showed that only 5.15% and 4.49% of the students who designed the platform could not improve their after-class autonomous learning and extracurricular communication skills, and more than 95% of the students had good feedback after using the platform. Conclusion. It shows that the design platform can effectively improve the students’ ability of self-learning and extracurricular communication after class, and the application efficiency is high.

Intelligent Fuzzy Optimization Algorithm for Data Set Information Clustering Patterns Based on Data Mining and IoT

Social creation and life have become progressively unmistakable. Bunch examination is the reason for additional handling of the data. The ideas of data mining, as well as the use of neural networks in data mining, are examined. The two-layer perceptron, back engendering (BP) neural network, and RBF extended premise work network are totally depicted exhaustively in this article data mining, as demonstrated by the associated development of data mining and handling characterization issues, and self-sorting out map (SOM) is a self-assembling neural network for unaided grouping issues. As indicated by the qualities of self-versatile and self-arranging capacities, we learn, plan, and execute data mining grouping optimization techniques using these algorithms. This study isolates the neural network-based data mining technique into three phases: data course of action, rule extraction, and rule evaluation. This work centers around the teaching type and breaking down type rule extraction strategies. The connection approach is used to compute the association between the information and result neurons after researching the BP disintegration type method. After you have planned everything out, it is time to put it all together. The RBF neural network is utilized to pick center points in light of association levels. This can assist with diminishing the quantity of data centers in the neural network; further develop the network geography; decline the quantity of recursive segments in the subnet, in addition to other things; and further develop computation productivity. Accepting the model, for instance, the preparation mistake is determined through the use of data mining and a bunching algorithm. For the most part, the data mining grouping optimization method works on from two perspectives: better model planning and model pruning and rebuilding of the well-known neural network tests that duplicate model complexity, computational intricacy, and blunders. After that, the rate is calculated, and finally, the recreation investigation is carried out. The findings indicate that the proposed differential dispersed data mining algorithm is more exact and effective. More grounded combination capacity defeats the deficiencies and weaknesses of a few unique hereditary algorithms. It can truly work on the algorithm’s accessibility and search precision, as well as the usefulness of data mining employing neural network data mining models based on algorithm optimization. Precision and exactness are useful in a variety of situations. The rate is then computed, and ultimately, the reproduction study is conducted. The findings show that the proposed differential allocated data mining method works. The algorithm is more precise and more grounded in intermingling capacity and conquers the inadequacies and weaknesses of a few unique hereditary algorithms. It can successfully further improve the algorithm’s inquiry capacity and search precision, as well as work on the productivity of data mining, through algorithm optimization neural network data mining models. Precision and exactness have several applications.

A Cognitive Behavioral Computing Model Combined with DM’s Teaching Quality Improvement

There are more and more ideas of applying data research science to replace theoretical research science, including monitoring and evaluation of school teaching quality. In order to distinguish different types of learners through knowledge and behavior performance, so as to better improve the teaching quality of teachers, a data mining model based on knowledge expression and calculation mode is provided. According to all the key cognitive and behavioral input parameters and cognitive and behavioral index factors, through the collection of artificial neural networks, sensitivity analysis, data mining, and classification regression trees, they are divided into three types of differences, so as to better adopt differentiation strategies for learners with different types. The experimental results also show that the behavior parameters are far more critical than the knowledge parameters. The research results show that the model is effective in supporting teachers' work in the education system.

Using Decision Tree Classification and AdaBoost Classification to Build the Abnormal Data Monitoring System of Financial Accounting in Colleges and Universities.

In order to better solve the problems of low efficiency, large consumption of human resources, and relatively low degree of intelligence in the abnormal data monitoring system of financial accounting in colleges and universities under the background of current accounting computerization, this article takes data mining and neural network algorithm as the technical basis to build the abnormal data monitoring system of financial accounting in colleges and universities. This article uses data mining algorithm and neural network analysis technology to process the original accounting information of colleges and universities, effectively eliminate invalid data, retain valuable data, and improve the detection efficiency of abnormal accounting data. The system test results show that the accuracy of identifying 50 abnormal situations in the original accounting data of colleges and universities is more than 90% by using data mining and neural network model.

Improving mortality prediction in Acute Pancreatitis by machine learning and data augmentation

Acute Pancreatitis (AP) is the inflammation of the pancreas that can be fatal or lead to further complications based on the severity of the attack. Early detection of AP disease can help save lives by providing utmost care, rigorous treatment, and better resources. In this era of data and technology, instead of relying on manual scoring systems, scientists are employing advanced machine learning and data mining models for the early detection of patients with high chances of mortality. The current work on AP mortality prediction is negligible, and the few studies that exist have many shortcomings and are impractical for clinical deployment. In this research work, we tried to overcome the existing issues. One main issue is the lack of high-quality public datasets for AP, which are crucial for effectively training ML models. The available datasets are small in size, have many missing values, and suffer from high class imbalance. We augmented three public datasets, MIMIC-III, MIMIC-IV, and eICU, to obtain a larger dataset, and experiments proved that augmented data trained classifiers better than original small datasets. Moreover, we employed emerging advanced techniques to handle underlying issues in data. The results showed that iterative imputer is best for filling missing values in AP data. It beats not only the basic techniques but also the Knn-based imputation. Class imbalance is first addressed using data downsampling; apparently, it gave decent results on small test sets. However, we conducted numerous experiments on large test sets to prove that downsampling in the case of AP produced misleading and poor results. Next, we applied various techniques to upsample data in two different class splits, a 50 to 50 and a 70 to 30 majority–minority class split. Four different tabular generative adversarial networks, CTGAN, TGAN, CopulaGAN, and CTAB, and a variational autoencoder, TVAE, were deployed for synthetic data generation. SMOTE was also utilized for data upsampling. The computational results showed that the Random Forest (RF) classifier outperformed all other classifiers on a 50 to 50 class split data generated by CTGAN, with 0.702 Fβ and 0.833 recall. Results produced by RF on the TVAE dataset were also comparable, with 0.698 Fβ. In the case of SMOTE-based upsampling, DNN performed best with a 0.671 Fβ score.

Elucidating strategic patterns from target customers using multi-stage RFM analysis

ABSTRACT Predicting profitable customers is a strategic knowledge portfolio of retailer managers because some customers are better profitable than others in a business. The present work is an effort to demonstrate a better model of predicting profitable customers. We apply the k-means algorithm to identify customer patterns based on Recency, Frequency, and Monetary (RFM) attributes computed from a real-life dataset of UK-based and registered non-store online retail. Six data mining models have been applied to each identified pattern and overall data to predict whether each customer would purchase in the next six months or not. A comparative analysis of identified pattern characteristics and predictable performances and Type I and Type II errors have been performed to identify the target customer group in terms of better predictability and profitability. The identified patterns help to generate novel marketing strategies. Thus, the retailers may successfully target the most consistently profitable customer groups to apply diverse knowledge on marketing strategies for the specific pattern.

Fuzzy Data Mining and Bioinformatics Analysis in Methylation Analysis of M6A Gene Promoter Region in Esophageal Cancer

This work was aimed at analyzing the correlation between the methylation level of the M6A gene in esophageal cancer (EC) and the prognosis of patients based on bioinformatics technology and evaluating the prognostic predictive values of different data mining models. 80 EC patients and 80 healthy people were selected, and the serum of the patients was collected to detect the level of DNA methyltransferase. During the radical resection of EC, tumor tissues and adjacent normal tissues were collected from patients to detect the methylation level of the M6A gene. COX regression analysis was employed to analyze the independent risk factors (IRFs) of M6A gene methylation and other treatments affecting the prognosis of EC patients. The particle swarm optimization (PSO) algorithm was introduced to improve the fuzzy C -means clustering (FCM) algorithm. The differences in the prognostic prediction efficiency of logistic regression analysis (LRA), decision tree (DT) C5.0, artificial neural network (ANN), support vector machine (SVM), and improved FCM (IFCM) models were compared. The levels of DNA methyltransferase and human histone deacetylase 1 (HSD-1) in EC patients were increased greatly ( P < 0.05 ). The methylation rates and methylation levels of M6A methylation regulators (ALKBH5, HNRNPC, METTL3, WTAP, RBM15, YTHDC1, YTHDF1, and FTO) in EC tissues were obviously higher ( P < 0.05 ). The survival time of high-risk EC patients was much shorter than that of low-risk patients ( P < 0.05 ). Univariate and multivariate COX regression analysis showed that gender, tumor grade, TNM grade, degree of infiltration, and methylation of ALKBH5, HNRNPC, and METTL3 genes were IRFs for the prognosis of EC patients ( P < 0.05 ). The areas under the ROC curve (AUCs) of LRA, DT C5.0, ANN, SVM, and IFCM algorithms for predicting the prognosis of patients were 0.813, 0.857, 0.895, 0.926, and 0.958, respectively, and the IFCM model had the best diagnostic effect. In conclusion, the detection of bioinformatics technology showed no obvious DNA methylation in EC patients, and the elevated levels of M6A methylation regulators in patients were an IRF affecting the prognosis of patients. In addition, the fuzzy data mining model can be undertaken as the preferred method for prognosis prediction of EC patients.

Edge computing for vehicle battery management: Cloud-based online state estimation

The adoption of electric vehicles (EVs), including battery EVs and hybrid EVs, makes it possible to reduce fossil fuel consumption and greenhouse gas emission. However, an accurate battery model and an effective battery management system should be established to enable this benefit. This paper proposes a novel cloud-assisted online battery management method based on artificial intelligence and edge computing technologies. Integration of cloud computation and big data resources into real-time vehicle battery management is realized by establishing a novel cloud-edge battery management system (CEBMS). A deep learning algorithm-based cloud data mining and battery modeling method is developed to estimate the voltage and energy state of the battery. The accuracy of the established cloud battery model outperforms the onboard battery management system by utilizing multi-sources information from different EVs. Meanwhile, a cloud-assisted battery management method is established at edge nodes in the onboard battery management unit to realize real-time state estimation locally. By using precise battery state estimation provided by the cloud platform, vehicle battery model accuracy can be significantly improved. The performance of the proposed battery management method is verified by a vehicle big data platform and battery pack experimental test bench. Experimental results justify the effectiveness of the proposed method in battery state estimation, which can help the EVs use and manage the battery more effectively.

The Design of Academic Programs Using Rough Set Association Rule Mining

Program accreditation is important for determining whether or not a program or institution meets quality standards. It helps employers to evaluate the programs and qualifications of their graduates as well as to achieve its strategic goals and its continuous improvement plans. Preparing for accreditation requires extensive effort. One of the required documents is the program’s self-study report (SSR), which includes the PEO-SO map (which allocates the program’s educational objectives (PEOs) to student learning outcomes (SOs)). It influences program structure design, performance monitoring, assessment, and continuous improvement. Professionals in each academic engineering program have designed their PEO-SO maps in accordance with their experiences. The problem with the incorrect design of map design is that the SOs are either missing altogether or cannot be assigned to the correct PEOs. The objective of this work is to use a hybrid data mining approach to design the correct PEO-SO map. The proposed hybrid approach utilizes three different data mining techniques: classification to find the similarities between PEOs, crisp association rules to find the crisp rules for the PEO-SO map, and rough set association rules to find the coarse association rules for the PEO-SO map. The work collected 200 SSRs of accredited engineering programs by the ABET-EAC. The paper presents the different phases of the work, such as data collection and preprocessing, building of three data mining models (classification, crisp association rules, and rough set association rules), and analysis of the results and comparison with related work. The validation of the obtained results by different fifty specialists (from the academic engineering field) and their recommendations were also presented. The comparison with other related works proved the success of the proposed approach to discover the correct PEO-SO maps with higher performance.

Intelligent Application of Data Mining Model in Chinese International Education

In order to improve the effect of intelligentization of Chinese international education, this paper puts forward the application method of the data mining model. Through the collection, transformation, processing, mining, and analysis of a large number of random data generated in education and teaching, this method provides learning suggestions for learners, realizes evaluation and prediction, presents knowledge information for educators, realizes educational decision-making, and realizes the continuous optimization of the teaching process. The experimental results show that the relationship between teachers’ teaching and students’ scores is obtained through the analysis of association rules in data mining technology. The support and confidence of students’ scores taught by teacher B are 28.57% and 72%, respectively, and the support and confidence of students’ scores taught by teacher C are 19.05% and 70.59%, respectively. The two rules are established to a great extent through data association. Data mining technology can effectively optimize the effect of intelligentization of Chinese international education.

Accelerating the discovery of battery electrode materials through data mining and deep learning models

The availability of crystalline materials databases allows for building accurate machine learning (ML) models that can accelerate the exploration of materials chemical space for energy storage applications. In this work, we screen all inorganic materials included in the Materials Project and AFLOW databases as potential metal-ion battery electrodes. We develop an efficient protocol to mine and screen raw data in current databases and provide a new database of electrode materials by considering pairs of charged and discharged electrodes. This effort leads to a new database with over 190,000 instances, in contrast to the original battery database which contains about 5000. The expanded battery data set is then used to build regression-based deep neural network models for predicting average voltages and percentage volume changes upon charging and discharging, which present improvements of at least 28% for target properties with respect to previous models, and are now able to predict anode electrodes (low voltage region) as well as electrodes that will not work in electrochemical cells (negative voltages), overcoming the challenges identified in previous ML models for battery electrodes. Additionally, a further screening of the expanded database itself allowed us to identify 35 novel electrode candidates with excellent battery performance metrics.

Implementasi Sliding Window Algotihm pada Prediksi Kurs berbasis Neural Network

<p><em>Time series is sequential data based on time sequence.</em><em> </em><em>Time series data can be used for prediction topics, one of the prediction topics that is always interesting to study is exchange rate prediction. In the case of exchange rate prediction, an appropriate data preprocessing stage is required. The success of this preprocessing stage will have a major effect on the resulting RMSE value. There is an important technique in determining the best RMSE value, especially in time series data, one of which is the windowing technique. The windowing technique is the stage of transforming time series data into cross sectional. Window size has an important role in time series data. However, there is no standard in window size. The Window size experiment starts with a small value and then increases to a larger value until it reaches a certain point with the best RMSE. In this research, an experiment will be conducted on windows size on exchange rate data based on a neural network. The purpose of this research is to optimize the RMSE of a data mining model based on windows parameters. The implementation of sliding windows is carried out in the scenarios of window sizes 4, 6, and 28. Based on the experiments conducted, the best RMSE is on windows size 6 = 0.014 +/- 0.000. With a combination of neural network parameters in the form of training cycles = 1000, learning rate = 0.1 and momentum = 0.1.</em></p>