{"title":"利用非线性技术进行特征修正的模式识别","authors":"F. Mesa, R. Ospina-Ospina, D. M. Devia-Narvaez","doi":"10.18273/revuin.v22n1-2023002","DOIUrl":null,"url":null,"abstract":"Traditional data processing applications are unsuitable for handling large amounts of data. To achieve an efficient manipulation and extraction of characteristics or samples that the information represents, it is necessary to know aspects such as data collection and treatment. In this document, a database corresponding to the behavior of electrical energy consumption in a residential load was refined. The debugging and statistical analysis of the samples were carried out using the principal component analysis. The training of the smallest data set to the original database was made using vector support machine techniques and artificial neural networks. Finally, a proposal is presented for the analysis of samples that are within the operating limits or not using updating dynamic patterns for the unsupervised validation of new samples.","PeriodicalId":42183,"journal":{"name":"UIS Ingenierias","volume":"1 1","pages":""},"PeriodicalIF":0.3000,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pattern recognition for the modification of characteristics using non-linear techniques\",\"authors\":\"F. Mesa, R. Ospina-Ospina, D. M. Devia-Narvaez\",\"doi\":\"10.18273/revuin.v22n1-2023002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traditional data processing applications are unsuitable for handling large amounts of data. To achieve an efficient manipulation and extraction of characteristics or samples that the information represents, it is necessary to know aspects such as data collection and treatment. In this document, a database corresponding to the behavior of electrical energy consumption in a residential load was refined. The debugging and statistical analysis of the samples were carried out using the principal component analysis. The training of the smallest data set to the original database was made using vector support machine techniques and artificial neural networks. Finally, a proposal is presented for the analysis of samples that are within the operating limits or not using updating dynamic patterns for the unsupervised validation of new samples.\",\"PeriodicalId\":42183,\"journal\":{\"name\":\"UIS Ingenierias\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.3000,\"publicationDate\":\"2023-01-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"UIS Ingenierias\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18273/revuin.v22n1-2023002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"UIS Ingenierias","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18273/revuin.v22n1-2023002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
Pattern recognition for the modification of characteristics using non-linear techniques
Traditional data processing applications are unsuitable for handling large amounts of data. To achieve an efficient manipulation and extraction of characteristics or samples that the information represents, it is necessary to know aspects such as data collection and treatment. In this document, a database corresponding to the behavior of electrical energy consumption in a residential load was refined. The debugging and statistical analysis of the samples were carried out using the principal component analysis. The training of the smallest data set to the original database was made using vector support machine techniques and artificial neural networks. Finally, a proposal is presented for the analysis of samples that are within the operating limits or not using updating dynamic patterns for the unsupervised validation of new samples.