{"title":"具有聚类边界适应度的质心稳定性有效评价的永续模糊离群值研究","authors":"S. Rajalakshmi, P. Madhubala","doi":"10.46632/daai/3/2/4","DOIUrl":null,"url":null,"abstract":"This paper aims to investigate certain factors that hide outliers in two dimensions such as boundary partitioning and space angular parameters. In this proposed algorithm, boundary representation of clusters, the data points that lie on the cluster boundary is stored geometrically as coordinate values such as i_bound (inliers) and o_bound(outliers). Outliers that present in dataset are investigated by boundary fitness over centroid stability. In this paper we focus to examine whether the data point lie on the boundary is treated as inliers or outliers. Several iterations are manipulated to fix the outlier point deeply. Using fuzzy clustering, data points are clustered and boundary is fixed. If the space occupied by the cluster varies for every iteration, the distance from inlier to outlier between the boundaries is calculated. After calculation, if the data point is below the threshold value, it is treated as outlier. Our proposed method shows efficiency over evaluation metrics of outlier detection performance.","PeriodicalId":226827,"journal":{"name":"Data Analytics and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Certain Investigation on Perpetualistic Fuzzy Outlier Data for Efficiency Evaluation of Centroid Stability with Cluster Boundary Fitness\",\"authors\":\"S. Rajalakshmi, P. Madhubala\",\"doi\":\"10.46632/daai/3/2/4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper aims to investigate certain factors that hide outliers in two dimensions such as boundary partitioning and space angular parameters. In this proposed algorithm, boundary representation of clusters, the data points that lie on the cluster boundary is stored geometrically as coordinate values such as i_bound (inliers) and o_bound(outliers). Outliers that present in dataset are investigated by boundary fitness over centroid stability. In this paper we focus to examine whether the data point lie on the boundary is treated as inliers or outliers. Several iterations are manipulated to fix the outlier point deeply. Using fuzzy clustering, data points are clustered and boundary is fixed. If the space occupied by the cluster varies for every iteration, the distance from inlier to outlier between the boundaries is calculated. After calculation, if the data point is below the threshold value, it is treated as outlier. Our proposed method shows efficiency over evaluation metrics of outlier detection performance.\",\"PeriodicalId\":226827,\"journal\":{\"name\":\"Data Analytics and Artificial Intelligence\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Data Analytics and Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.46632/daai/3/2/4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Data Analytics and Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.46632/daai/3/2/4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Certain Investigation on Perpetualistic Fuzzy Outlier Data for Efficiency Evaluation of Centroid Stability with Cluster Boundary Fitness
This paper aims to investigate certain factors that hide outliers in two dimensions such as boundary partitioning and space angular parameters. In this proposed algorithm, boundary representation of clusters, the data points that lie on the cluster boundary is stored geometrically as coordinate values such as i_bound (inliers) and o_bound(outliers). Outliers that present in dataset are investigated by boundary fitness over centroid stability. In this paper we focus to examine whether the data point lie on the boundary is treated as inliers or outliers. Several iterations are manipulated to fix the outlier point deeply. Using fuzzy clustering, data points are clustered and boundary is fixed. If the space occupied by the cluster varies for every iteration, the distance from inlier to outlier between the boundaries is calculated. After calculation, if the data point is below the threshold value, it is treated as outlier. Our proposed method shows efficiency over evaluation metrics of outlier detection performance.