{"title":"贫困学生不完整数据分析的数据预处理方法","authors":"Haiyan Huang, Bizhong Wei, Jian Dai, Wenlong Ke","doi":"10.1109/CIS52066.2020.00060","DOIUrl":null,"url":null,"abstract":"Data mining is the focus of big data applications in various fields. Data pre-processing is a crucial step in the data mining process. With the development of the information society and the application of databases, the educational data has seen explosive growth, and the data on poor students has become informative. However, the actual student financial aid management system collects the data on poor students which generally has problems such as missing values, attributes redundancy, and noise. To solve this problem, we proposed a novel method called DPBP to preprocess data. The proposed DPBP approach consists of four stages: the preparation of data, the scoping of characteristics, the combination of characteristics, and the filtering of missing number. Firstly, we prepare the dataset by extracting data. Next, the characteristic range is limited by choosing experimental results of feature selection algorithm. Then, third stage performs feature combination to obtain the feature decomposition sets. Finally, based on accuracy and missing number, we gain the optimal dataset. Series of experiments result show that our proposed method significantly improves the data quality and stability.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data Preprocessing Method For The Analysis Of Incomplete Data On Students In Poverty\",\"authors\":\"Haiyan Huang, Bizhong Wei, Jian Dai, Wenlong Ke\",\"doi\":\"10.1109/CIS52066.2020.00060\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Data mining is the focus of big data applications in various fields. Data pre-processing is a crucial step in the data mining process. With the development of the information society and the application of databases, the educational data has seen explosive growth, and the data on poor students has become informative. However, the actual student financial aid management system collects the data on poor students which generally has problems such as missing values, attributes redundancy, and noise. To solve this problem, we proposed a novel method called DPBP to preprocess data. The proposed DPBP approach consists of four stages: the preparation of data, the scoping of characteristics, the combination of characteristics, and the filtering of missing number. Firstly, we prepare the dataset by extracting data. Next, the characteristic range is limited by choosing experimental results of feature selection algorithm. Then, third stage performs feature combination to obtain the feature decomposition sets. Finally, based on accuracy and missing number, we gain the optimal dataset. Series of experiments result show that our proposed method significantly improves the data quality and stability.\",\"PeriodicalId\":106959,\"journal\":{\"name\":\"2020 16th International Conference on Computational Intelligence and Security (CIS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 16th International Conference on Computational Intelligence and Security (CIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIS52066.2020.00060\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 16th International Conference on Computational Intelligence and Security (CIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIS52066.2020.00060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Data Preprocessing Method For The Analysis Of Incomplete Data On Students In Poverty
Data mining is the focus of big data applications in various fields. Data pre-processing is a crucial step in the data mining process. With the development of the information society and the application of databases, the educational data has seen explosive growth, and the data on poor students has become informative. However, the actual student financial aid management system collects the data on poor students which generally has problems such as missing values, attributes redundancy, and noise. To solve this problem, we proposed a novel method called DPBP to preprocess data. The proposed DPBP approach consists of four stages: the preparation of data, the scoping of characteristics, the combination of characteristics, and the filtering of missing number. Firstly, we prepare the dataset by extracting data. Next, the characteristic range is limited by choosing experimental results of feature selection algorithm. Then, third stage performs feature combination to obtain the feature decomposition sets. Finally, based on accuracy and missing number, we gain the optimal dataset. Series of experiments result show that our proposed method significantly improves the data quality and stability.