Search

Under the big data(BD) technology, colleges and universities pay more and more attention to educational technology, so as to follow up with modern information, digitization, and visualization. The courses of civil engineering teaching with traditional teaching methods and single knowledge of students are profit-only, applying data mining(DM) technology and BD technology to realize positive thinking mode. This article first gives a brief overview of DM technology and BD technology, and then discusses the strategy of applying BD technology in teaching of civil engineering professional courses, and finally applies BD DM technology to the construction of civil engineering teaching system, to realize the intelligent teaching mode. Based on DM technology and BD technology, this paper comprehensively studies the construction of two technologies in the civil engineering teaching system of colleges and universities. This article combines the new concept of constructing attention to teaching, expounds the advantages of DM algorithm in the construction of civil engineering teaching system, and briefly analyzes the composition and development of the networked civil engineering teaching system platform. At the same time, this article also in-depth research In the classification algorithm of the DM algorithm, the k-nearest algorithm is discussed, and for the efficiency of their construction in the civil engineering teaching system, the visualization research is carried out from the operation efficiency of the algorithm steps and other aspects and the organization of the data set. Based on the above research, the optimization schemes of particle swarm algorithm and ant colony algorithm are designed, and a parallelized early warning system model is realized using GPU based on CUDA platform. In the above research, the two algorithms were compared and tested, and the efficiency of the algorithm in the construction of civil engineering teaching system was verified. Experimental research results show that the cosine correlation analysis based on DM algorithms and the hybrid particle swarm algorithm can effectively integrate BD technology to construct a civil engineering teaching system and improve the operating efficiency of the system.

With the continuous progress of modern society, human rights are becoming more and more perfect, especially the medical system, because of the inevitability of development, at this stage has achieved a lot of proud results, but this can not meet the modern people’s pursuit of health. Because the use of resources in the industrial society has led to the emergence of many viruses that have not been seen many, so now more and more kinds of drugs, we are considering more and more things, one of which is about adverse reactions to drugs. Therefore, this paper is based on this data mining algorithm to monitor adverse drug reactions early warning method. Based on the security of the user’s personal privacy data, this paper proceeds to monitor the drug reaction in real time as the way, adopts the data mining algorithm as the main intelligent means used, compares it by consulting the domestic and foreign literature, and experiments with sandbox simulation as a modeling method, and finally results in the experimental results. The results show that if we can monitor drug reactions in real time, we can monitor adverse reactions early.

Due to the continuous dynamic changes of data in the current era, research on incremental association rules is necessary. Among them, frequent pattern mining has always been the subject of research. The research found that among the existing algorithms, Can Tree is very suitable for incremental mining because of its superior nature that it does not require adjustment, merging, and/or splitting of tree nodes during maintenance. In this paper, a new method of mining Can Tree is proposed to solve the problem of time consuming caused by repeatedly traversing paths when obtaining conditional mode basis. The path only needs to be traversed once to meet the requirements and verify it. Experimental results show that the performance of the algorithm is better than the traditional Can Tree algorithm, reducing time consumption to a certain extent.

With the intensification of the aging of our country’s population, research on how to better protect the living standards of the elderly, reduce the burden of the working population to support the elderly, and ensure the orderly and healthy development of the society, is currently the focus of attention. In order to prevent aging from bringing further negative impacts on our society or economy, this paper uses data mining algorithms as the research basis and uses time series models to make effective predictions. Therefore, this article first decomposes these data by analyzing the characteristics of elderly consumption data. The decomposed sequence has short correlation characteristics, and the prediction accuracy is significantly higher than that of the traditional time series model. However, this kind of time series model can only predict some offline data. In order to make it can be used for dynamic data prediction, this paper uses RBFNN online prediction algorithm. The RBF neural network is partially improved, and the parameters are calculated by improving the later SGD algorithm. The experimental conclusion shows that the prediction accuracy and efficiency of this algorithm are obviously more accurate than the neighbor clustering online training algorithm, and it achieves more effective online prediction. It can be concluded that the role of the elderly social security budget in economic management can fully reflect the income and expenditure of the elderly social security funds, improve the efficiency of fund use, and establish a unified national social security budget, thereby reducing the impact of aging on society Negative impact.

In recent years, Cross-border(CB) e-commerce(EC) has developed rapidly in our country, and the government has also introduced a series of measures to promote the development of CB EC. In the era of big data, recommendation systems are widely used in CB EC platforms, and more and more attention is paid to its personalized recommendation technology. Based on this, this paper studies the application of data mining algorithms in the construction of CB EC courses, which has certain guiding significance for the current market and enterprise development. By taking two CB EC companies as the research object, this paper uses data mining algorithms to mine and analyze the relevant data of these two EC companies, and find that a platform with a data mining system has more advantages in researching customer shopping preferences;comparing people’s satisfaction with EC companies with data mining systems and traditional companies, 83% of the participants in the experimental group were satisfied, of which 60% were very satisfied, while only 59% in the control group of people are satisfied.This shows that data mining algorithms are of great significance to the development of CB EC, and it also points out a new direction for the construction of CB EC courses, such as CB EC based on data mining algorithms. On the one hand, this will also play a positive role in the future development of CB EC.

With the rapid development of network, communication, and information technology, e-commerce has received widespread attention as a new business model. E-commerce has become a popular term, and e-commerce has become a popular mainstream in universities. However, as a comprehensive and free subject of art and science penetration, e-commerce puts forward more comprehensive requirements for teaching content, process and methods. Based on the above background, the purpose of this article is to study the professional practice teaching methods of e-commerce based on data mining algorithms. This article first analyzes the privacy issues caused by decentralized data mining under the condition of rapid development of e-commerce. How to build a more accurate model to complete data mining tasks without revealing personal privacy, mainly discussing data mining privacy protection algorithms. Next, through literary research method, questionnaire survey method, case research method, and interview method, explore the practical teaching method of e-commerce professional based on data mining algorithm. The role is to study the problems and solutions that blended learning needs to solve in specific applications. The experimental results show that, compared with the previous guidance method, the new teaching method can improve students’ initiative, enthusiasm and creativity by about 10% in the learning process.

Traditional association rule mining does not consider the importance of each item, so the actual process lacks certain pertinence. Based on the New-Apriori algorithm and the Fp-growth algorithm idea, this paper proposes an improved association rule algorithm based on Fp-tree, Constructs the general process of personalized recommendation of association rules. And uses the Web log file to use the frequency of web pages being selected by users as the weight value, and realizes the algorithm of the personalized recommendation system. The experimental results show that the algorithm has high accuracy and effectiveness.

The decline of air quality seriously affects human life and ecological environment. The blind allocation of governance resources leads to poor improvement. In order to allocate resources reasonably and improve treatment efficiency, a new key nodes mining algorithm for air quality system based on network structure and the characteristics of pollutant transmission is proposed, aiming at resource investing guidance. Firstly, the air quality network is established and its structural characteristics are analyzed. Secondly, according to the diffusion and attenuation mechanism of air pollutants in the network, a bidirectional transmission key node mining algorithm is proposed which takes both the in-links and out-links into consideration. Thirdly, a dynamic independent threshold propagation model in directed weighted network is proposed, and the number of activated nodes is used as evaluation criterion for key node mining results. Finally, experiment is executed on Jing-Jin-Ji PM2.5 air quality network. Experiment results show that the bidirectional transmission key node mining algorithm can get accurate results and good applicability in air quality network.

Until now, the association rule mining algorithm is still one of the core issues in the field of big data research. At present, there are many research related to association rule mining algorithms, mainly focusing on how to find frequent item sets and how to tailor rules, and based on this direction, there have been many classic algorithms, such as Apriori and FP-growth algorithms. However, most of the above algorithms process and analyze the entire data set, so that although related algorithms can be used to obtain the results, the results are not meticulous. To solve this problem, this paper proposes an algorithm, which first uses the k-means algorithm to perform cluster analysis on the data set to generate a specific number of clusters. Then, in different clusters, the association rules in each cluster are found by the improved Top-k algorithm combined with the correlation coefficient. By integrating clustering and the improved Top-k algorithm, the data set can be analyzed directionally to improve the accuracy and efficiency of the whole algorithm. And the final experiment shows that compared with the original algorithm, the running time is shortened by 14%.

Premature birth is still a big problem in Indonesia, in general, 15 million babies are born prematurely every year, more than 1 million babies die from complications due to premature birth. The main purpose of this study is to compare the Artificial Neural Network and Naive Bayes datamining algorithm models to predict preterm birth so as to obtain clinical evidence in preterm birth long before confinement so that sudden preterm birth can be converted to normal nativity. The model proposed in research on the prediction of preterm birth is by applying an Artificial Neural Network (ANN) algorithm and Naive Bayes algorithm. Where the two algorithms will be compared the level of accuracy and the value of the AUC against the prediction of preterm birth The results obtained that the prediction of preterm birth using the Artificial Neural Network (ANN) algorithm produces an accuracy value of 90.67% and an ROC value of 0.954. While the Naive Bayes algorithm produces an accuracy value of 84.53% and an ROC value of 0.929. For this reason, it can be concluded that the Artificial Neural Network (ANN) algorithm has a superior accuracy of 6.14% and 0.025 for its ROC value in predicting preterm birth.

Corona virus disease (COVID-19) is an infectious caused by a new virus, the virus causes respiratory disease with symptoms such as coughing and fever, causes pneumonia in more severe cases. problem statement: The new Corona virus, or what has become known as “COVID-19”, has spread to more than 79 countries outside China, where the Wuhan region is the epicenter of the virus. Until now researchers not discovered vaccine COVID-19. For prevalence observation there are countries has spread the virus significantly, others in an average and other less, with countries until now where the virus hasn’t spread. proposed solution: This research based on studying the impact geographical latitude on knowing the spread of the COVID 19 in confirmed cases. result: To help scientists and researchers whom still to work on discovery the vaccine, taking importance of the zones the spread of the Covid-19. Using Dataset from Kaggle by classification algorithms linear regression data mining to extract a knowledge from data beneficial.

In the analysis of power market economic evaluation indicators, it is more common to use technical data mining for data calculation based on technology maturity analysis. This paper is based on a distributed computing platform for data mining, and parallelizes the traditional FP-Growth algorithm, so that the FP-Growth algorithm can be applied to the mining of big data association rules. Experimental results show that the algorithm can greatly improve the efficiency of mining association rules for massive data. The model is trained and tested on a distributed cluster built into the laboratory using customer electricity data, and then the predictions are validated to determine whether the difference between the predicted values and historical data for the same period exceeded the set threshold.

Sabilillah Educational Cash Unit is a unit within the sabilillah educational foundation which is engaged in education. The stored cash processing data will be utilized using data mining so that it can be used as a decision support for finding information that is useful in evaluating the data used. Various methods contained in the data mining, the authors will make a comparison of the method techniques from the data mining. The use of the decision tree and, K-means method is implemented using the Rapid Miner application, which will later be analysed of each of these methods to determine the strategy to look for students who have the potential to save the hajj savings. This research was conducted with a group of data to determine the percentage value of precision, recall and accuracy. The results of this study that the C.4.5 method has a better value than other methods on the recall and accuracy, while the K-Means method has a precision value better than the other methods.

One of the major diseases in the world is liver disease. The liver is an important part of the large organs in the human body and is also considered a gland. This is because it creates and bites bile. Liver disease is a liver problem that causes the disease. The objective of this study is to propose a rule-based classification model with basic decision making techniques to predict various types of heart disease. To get better results the experiment was done using a different data mining algorithm compared with previous liver disease predictions. All experiments have been implemented at Azure Machine Learning tool. This paper is about to study the prediction of liver disease to produce better performance accuracy by comparing various mining data classification algorithms.

Nowadays, computer networks are widely used to exchange valuable and confidential data information between servers to computers or cellular devices. Access to user control and use of software or hardware as a firewall often experience security problems. Unauthorized access to information through computer networks continues to occur and tends to increase. This study examines the attack detection mechanism by using three data mining algorithms based on particle swarm optimization (PSO), namely PSO-K Nearest Neighbor, PSO-Random Forest, and PSO-Decision Tree in the Canadian Institute for Cybersecurity Dataset (CICIDS2017). The initial experiment showed that the approach using the PSO-RF method was able to produce the highest accuracy of attack detection. Accuracy values generated using the PSO-RF algorithm with a combination of the number of trees and maximal depth = 20 in the CICIDS2017 dataset are intact higher than other proposed algorithms. The highest accuracy of attack detection in the CICIDS2017 dataset is intact, which is 99.76%. In the CICIDS2017 dataset 50% Benign and 50% Attack it turns out that the PSO-RF algorithm with a combination of the number of trees and maximal depth = 20 also gets the highest accuracy value of 99.67%.

FP-growth algorithm is a classic algorithm of mining frequent item sets, but there exist certain disadvantages for mining the weighted frequent item sets. Based on the weighted downward closure property of the weighted model, this paper proposed that the weighted support was recorded in the two-dimensional table. This method has saved the process to search for the first conditional pattern base by traversing the weighted FP-tree, improved the efficiency of the weighted frequent item sets generated.

Data mining is a study that uses statistical knowledge, mathematical calculations, artificial intelligence methods, machine learning by extracting and identifying useful information and related knowledge from various large databases.. One of them is looking for itemsets combination from the data stack, the search process can be done using the Apriori Association Rules algorithm, the FPGrowth Association Rule and Closed Association rule. The three algorithms are some of the implementations of frequent itemsets search methods. Two datasets will be tested, namely retail datasets and accidents datasets derived from fimi datasets, with the aim of knowing the behavior of the three algorithms against the dataset model we tested. Each algorithm will test both datasets, with minimum support values for retail datasets ranging from 0.01-0.05 and min-conf 0.01-0.05. Likewise on the accident min-sup and min-conf 0.6-1 datasets. For retail algorithm data with the fastest processing time, the FP-Growth AR algorithm is more than 85% compared to Apriori-AR, followed by AR-Apriori and Apriori-Close-AR. For detailed memory usage results the Apriori-AR algorithm is lighter and outperforms. Accident data the experimental results show that FP-Growth-AR is a little more memory efficient and the fastest process is Apriori-Close, while the Apriori-AR with the longest processing time.

Cervical cancer becomes a major cause of cancer deaths in women around the world. The objective of this study is to provide a comprehensive analysis of different data mining methods to diagnose the malignant cancer samples. Different data mining algorithms (SVM, Naïve Bayes, and KNN) has been applied on four different medical tests (Biopsy, Cytology, Hinselmann, and Schiller) as four different target variables. The attributes influence the disease most is extracted since the disease has no symptoms in the early stage. The extraction involved over 32 attributes and two different algorithms such as Correlation-based Filter (CFS) and Random Forest. The results showed that the performance of Naïve Bayes classifier outperforms other classifiers after evaluation using 10-fold cross-validation method in R environment. In addition, the use of attribute selection has been proved not only can select the highly important attributes but also to increase the performance of all classifiers on cervical cancer dataset. In this study, the work reveals the classifiers can effectively achieve the best performance with the least number of highly important attributes.

The association rules mining algorithm is always one of the specialists most concerned topics in the research of database knowledge. It is widely used in many fields in society. This article is based on association rule mining algorithm to put forward the relevant strategies for the majorization to make the mining algorithm get better application. With the development of the society, social information becomes richer and richer, people also become more and more interested in the unknown world. Sustainably improve the automation and intelligentization of the tools for processing information can continually improve the abilities in many ways and get more useful information from the huge database. So the appearance of the data mining makes it possible. It can fetch some hidden, unknown and useful information and knowledge from the huge practical application data. And the association rule is a main mode in research of data mining. It can fetch target data by finding the dependency between fields of a given condition from different data fields. As a result, the optimization of association rules mining algorithm is of quite importance in fetching target data.