An Intergrated Data Mining and Survival Analysis Model for Customer Segmentation

Objective Training monitoring is an important part of scientific training, and also accumulated a large amount of data, but the analysis and evaluation of biochemical indicators are mostly concentrated on the level of experience and the general, phased and individualized research application of statistical methods. The data mining technology is applied to the analysis and evaluation of the biochemical indexes of competitive sports, the analysis of the data is carried out in the deep level, the potential, new and useful information and knowledge are extracted, and the new exploration ideas are carried out for the analysis of the biochemical indexes of competitive sports, and a more reliable and more powerful data branch is provided for the scientific and efficient training support.
 Methods Using the literature data method, logic analysis method and expert interview method, the application of the current data mining technology in the analysis of biochemical indicators is summarized.
 Results The scientific analysis and evaluation of athletes' physical function status has been the focus of domestic and foreign coaches and sports researchers. The application of data mining technology in sports biochemical indicators is also becoming more and more extensive. For example, Mao Jie and others applied the gray ART clustering model analysis method to the monitoring of competitive sports biochemical indicators. Through this data mining model, the coach can easily judge the athlete's competitive physical condition, and can provide a scientific basis for correct training according to the different competitive conditions of each athlete, using different training guidance programs and training methods. Ma Jing et al. explored the feasibility of applying decision tree algorithm and association rules in volleyball biochemical analysis. It was found that C5.0 decision tree and Apriori association rule algorithm can be used to predict and analyze the technical level of women's volleyball players. Li Guangjun and others successfully applied the association rule data mining to the biochemical data analysis of canoeists, and provided a basis for scientific decision-making and analysis of sports training and athlete selection. Zhang Hui designed a data mining system for sports biochemical index based on association rules. The results show that the system has fast data mining rate, short time consuming and high reliability. It provides a more scientific evaluation standard for the data mining of sports biochemical index, and also provides a basis for the future training program.
 Conclusions With the development of competitive sports, in order to achieve new heights, the application of data mining technology to vast biochemical data is of great significance for the establishment of scientific training evaluation methods and standards, and is also the inevitable development of future sports scientific research.

With the wide application of computer technology, the position of computer technology in various fields is gradually higher. Accordingly, the amount of data generated by people’s activities on the Internet is also increasing. With the continuous progress of information technology, the data that originally belonged to chicken ribs in people’s eyes has more value. At this time, the era of big data is coming. Firstly, this paper analyzes the main methods and advantages of data mining. Then, this paper analyzes the function of data mining technology. Finally, the main application of data mining technology is proposed.

Based on the wireless sensor network unmanned driving infringement identification system, this paper focuses on the application of data mining technology and state machine technology and designs and implements a set of practical and effective. Self‐driving cars can reduce the frequency of traffic accidents, alleviate urban traffic congestion, improve people’s travel efficiency, and lower the threshold of driving and other social values. The data processing program and a number of algorithms are given, and a complete set of data processing procedures and algorithms are proposed, including the collection of raw sensor data, the preprocessing of the collected data, and the feature extraction of the processed data. In the experiment, the unmanned driving infringement monitoring network was first designed to conduct real‐time monitoring of unmanned driving infringements during transportation and application. Aiming at the characteristics of unmanned driving infringements, a monitoring network platform was designed for remote control and large‐scale monitoring. Secondly, according to the characteristics of the unmanned driving infringement monitoring sensor network, the unmanned driving infringement node monitoring terminal is designed. The monitoring terminal part mainly designs the sensor module, the wireless communication module, the display warning module power module, and the data mining processing module. The sensor modules, respectively, include temperature, humidity, and concentration sensors, and the communication mode in the communication module mainly adopts Wi‐Fi. At the same time, the research is based on wireless sensor network, combined with data mining technology, puts forward a sensory data display system model based on data mining technology, and conducts an in‐depth analysis of the sensory data display system model, including the logical level of the system, system architecture, and functional modules. Finally, it focuses on the specific application of data mining technology in environmental information analysis and prediction, uses JAVA programming and realizes a data analysis and display system based on wireless sensor network, and verifies the accuracy of the data mining algorithm. The experimental results analyze the application of data mining technology in the driverless infringement determination system and use a large number of unmanned driving infringements to analyze the determination rules, so as to realize the interaction between active people and driverless cars.

Data mining technology has changed the way people understand data and analyze data to a large extent. The technology belongs to a new kind of information processing technology, which can provide information support to the decision makers and make for promotion of integrated development of educational reform. At present, the educational management system in colleges and universities mainly centers on the handling of daily routines, and the mass data merely realized the storage instead of exerting its function, besides, the significance hidden in the mass data often has not been discovered. Therefore, starting from the definition of data mining, the paper analyzed the necessity of application of data mining technology in the educational management system, and then studied the application of data mining technology in the educational management system. Keywords: Data Mining; Colleges and Universities; Educational Management System; Application DOI: 10.7176/JEP/11-8-14 Publication date: March 31 st 2020

Transitioning from a mining to meaning perspective in organization data mining can be a crucial step in the successful application of data mining technologies. The purpose of this paper is to examine more fully the implications of that shift. The use of data mining technology was part of our cycle time study of the Poplar County Criminal Justice System (a fictitious name). In this paper we will report on the use of data mining in the Poplar County Criminal Justice System (PCCJS) study in an attempt to speed up their case handling processes. Marketing and finance researchers are more involved with “simple” (i.e., direct) relationships, whereas BPR researchers are more concerned with long chains of interacting processes. This difference appears in the tools these researchers use: marketing and finance researchers are more interested in set-theoretic problems, BPR researchers, in graph-theoretic problems. Yet data mining technologies incorporate graph-theoretic algorithms. Consequently, they should be able to support hypothesis generation in BPR activities. We were able to come up with relevant and meaningful hypotheses for BPR in the PCCJS system by using data mining technology, specifically sequential pattern analysis: “Which areas we should look into in order to speed up the case handling process?” This valuable outcome would have not been possible without data mining technology, considering the large volume of data on hand. It is hoped that this study will contribute to broadening the scope of applicability of data mining technology.

With the continuous expansion of college enrollment, education has become flexible and diverse. Most colleges and universities are facing the contradiction between the sharp increase in the number of students and the increasing shortage of teaching resources, which has brought unprecedented challenges to education management. More and more teaching resources are pouring into higher education, and at the same time, strict requirements are put forward for higher education management. Data mining technology improves the application of data from low-level query operation to higher-level applications such as decision support, analysis and prediction. How to use information technology to serve the school management and decision-making better and more effectively has become an important symbol to measure the teaching management level and school strength of colleges and universities. The popularization and application of data mining technology is an exploration of informationization of teaching management in colleges and universities under the new situation. This paper summarizes the definition of data mining technology, analyzes its application methods and key points, and further studies and discusses the application of data mining technology in the informationization of teaching management in colleges and universities, in order to promote the development of education.

Data extraction methods have been widely used in different departments and achieved good results. The most typical example is the combination of data extraction technology and economics, which plays an important role in product classification, customer classification and market segmentation. This paper discusses the application of data mining technology in physical training. First, collect a large amount of data from sports training, and then use the data extraction method to extract useful information. On the one hand, in order to improve the performance of athletes, on the other hand, we can organize scientific training on the physical status indicators of athletes to prevent injuries. This paper discusses several common motion data extraction algorithms.KeywordsData miningPhysical trainingApplication countermeasures

However with China entering into the WTO, the big clearance in national seaport will soon realize, immigration traveler's number will be fast increasing, at the same time, anti-illegal immigrant conflict would also be more intense and complicated. Under such condition the analysis of anti-illegal immigrant intelligence has many difficulties. So data mining technology will be introduced in anti-illegal immigrant intelligence to detect new illegal immigrant trends. This article states the process of data mining in anti-illegal immigrant consulting relevancy data mining algorithm, including data processing in advance, association rule digging out, and so forth. Mining on time sequence rule will be the important way in data mining. Through this way, the objective law of anti-illegal immigrant intelligence will be found to support decision-making.

Badminton is one of the traditional competitive sports in China. However, with more and more information science and technology being applied in the field of sports, especially the application of decision support system based on data mining technology is becoming more and more popular, which poses a new challenge to whether our badminton can continue to defend its title in the international high-level competitions. At present, the information level of badminton in China is limited, and the analysis of a large number of game related data is only limited in the field of statistics. Therefore, it is necessary to introduce association rule mining to conduct in-depth analysis of the existing data, and find the rules related to the winning factors of athletes. At the same time, because of the disadvantages of traditional association rule algorithm, such as time-consuming, redundant rules and so on, it can not adapt to the fast-paced badminton game in efficiency. Aiming at this problem, this paper makes an exploratory research on the application of data mining technology in badminton field. This paper is selected from the research project of General Administration of sport of China, which is “the development and application of the software for monitoring the quality of badminton technical training and statistics of on-the-spot tactics based on tablet computer". It designs and implements the on-the-spot tactics analysis system of badminton, including data collection, data preprocessing and data mining, which can provide auxiliary support for coaches to make targeted training plans and on-the-spot tactics decisions hold on.

In the era of big data, the identification of financial fraud has changed from the traditional case analysis stage to the data mining stage. The application of data mining technology is helpful in identifying the company's fraud in massive data. In the process of fraud identification, a variety of data mining methods can be used, such as statistical methods, classification, clustering and neural network construction. This paper analyzes the application of several kinds of data mining methods in the field of financial fraud, and finds that due to the different model building methods and sample selection in empirical research, the accuracy of each method has not yet been determined. In the future, with the development of accounting information system, the combination of data mining and text mining will become the inevitable trend of financial fraud identification.

Recent developments in computing, communications, digital storage technologies, and high-throughput data-acquisition technologies, make it possible to gather and store incredible volumes of data. It creates unprecedented opportunities for knowledge discovery large-scale database. Data mining technology is a useful tool for this task. It is an emerging area of computational intelligence that offers new theories, techniques, and tools for processing large volumes of data, such as data analysis, decision making, etc. There are countless researchers working on designing efficient data mining techniques, methods, and algorithms. Unfortunately,most data mining researchers pay much attention to technique problems for developing data mining models and methods, while little to basic issues of data mining. What is data mining? What is the product of a data mining process? What are we doing in a data mining process? What is the rule we would obey in a data mining process? What is the relationship between the prior knowledge of domain experts and the knowledgemind from data? In this paper, we will address these basic issues of data mining from the viewpoint of informatics [1]. Data is taken as a manmade format for encoding knowledge about the natural world. We take data mining as a process of knowledge transformation. A domain-oriented data-driven data mining (3DM) model based on a conceptual data mining model is proposed. Some data-driven data mining algorithms are also proposed to show the validity of this model, e.g., the data-driven default rule generation algorithm, data-driven decision tree pre-pruning algorithm and data-driven knowledge acquisition from concept lattice.

Research on the application of data mining technology in software engineering

With the wider application of data mining technology, new media has been accepted by people for its high communication efficiency, good communication quality, and strong interaction. The city is an important factor of modernization, and the use of new media to spread the image of the city can promote the rapid development of the city. Based on this, the purpose of this article is to research and analyze the optimization path of new media city image communication strategy based on data mining technology. This article first summarizes the status quo of urban image communication, and then extends the theory of urban image communication and analyzes it in detail. Then through the analysis of new media communication methods and their advantages in urban communication. This article elaborates on the new media communication based on data mining technology, and uses questionnaire survey method, field survey method and other research methods to carry out experimental research on the theme of this article. Research shows that new media has become an important channel for city image communication.

The healthcare big data industry is rapidly developing globally, and data mining and knowledge services in the healthcare field have become one of the core demands for its development. Data mining in healthcare is beneficial to improve the efficiency of diagnosis and treatment of patients, which is helpful to formulate more effective treatment plans and reduce medical costs. In this paper, we searched the core journals on China Knowledge Network and web of science by subject terms, and eliminated the irrelevant articles for literature counting. In this paper, the commonly used models and algorithms of data mining in healthcare are firstly elaborated; then the progress of the application of this technology in assisting medical tasks, optimizing resource allocation and improving health information services are respectively reviewed, summarizing the segmentation, classic algorithms and representative studies implied by each application. However, the application of data mining technology in healthcare also faces some problems, from data collection, to data cleaning, preprocessing, visualization, to the selection of algorithms and evaluation of results, each link is full of difficulties and challenges. Finally, this paper proposes future research directions such as diversifying data sources, strengthening security and privacy protection, developing visualization and analysis tools, accurately using big data to improve the service level of healthcare institutions, semanticizing electronic medical records mining, and improving cancer prevention. At the same time, data mining is deeply integrated with cloud computing, artificial intelligence and other fields to jointly promote scientific and technological progress in the field of health care.

Hybridization of cognitive computing for food services