An outlier mining algorithm based on constrained concept lattice

AbstractTraditional outlier mining methods identify outliers from a global point of view. These methods are inefficient to find locally biased data points (outliers) in low dimensional subspaces. Constrained concept lattices can be used as an effective formal tool for data analysis because constrained concept lattices have the characteristics of high constructing efficiency, practicability and pertinency. In this paper, we propose an outlier mining algorithm that treats the intent of any constrained concept lattice node as a subspace. We introduce sparsity and density coefficients to measure outliers in low dimensional subspaces. The intent of any constrained concept lattice node is regarded as a subspace, and sparsity subspaces are searched by traversing the constrained concept lattice according to a sparsity coefficient threshold. If the intent of any father node of the sparsity subspace is a density subspace according to a density coefficient threshold, then objects contained in the extent of the sparsity subspace node are considered as bias data points or outliers. Our experimental results show that the proposed algorithm performs very well for high red-shift spectral data sets.Keywords: constrained concept latticeoutlierssparsity subspacedensity coefficient AcknowledgementsThis work is partially supported by the National Natural Science Foundation of P.R. China (61073145), the Natural Science Foundation of Shanxi Province, P.R. China (2010011021-2) and the Returning Students and Scholars Research Project of Shanxi Province, P.R.China (2009-77). Xiao Qin's work was made possible thanks to NSF awards CCF-0845257 (CAREER), CNS-0757778 (CSR), CCF-0742187 (CPA), CNS-0831502 (CyberTrust), OCI-0753305 (CI-TEAM), DUE-0837341 (CCLI) and DUE-0830831 (SFS).Additional informationNotes on contributorsJifu ZhangJifu Zhang is a Professor in School of Computer Science and Technology, Taiyuan University of Science and Technology, China. He received his PhD degree in Pattern Recognition and Intelligence Systems from Beijing Institute of Technology, China in 2005, and has published more than 100 papers. His current research interests include concept lattice, data mining and artificial intelligence. An outlier mining algorithm based on constrained concept latticeAll authorsJifu Zhang, Sulan Zhang, Kai H. Chang & Xiao Qinhttps://doi.org/10.1080/00207721.2012.745029Published online:21 January 2014Display full size Sulan ZhangSulan Zhang is an Associate Professor in School of Computer Science and Technology, University of Science and Technology, China. Her current research interests include concept lattice, data mining, granular computing, image processing and pattern recognition. An outlier mining algorithm based on constrained concept latticeAll authorsJifu Zhang, Sulan Zhang, Kai H. Chang & Xiao Qinhttps://doi.org/10.1080/00207721.2012.745029Published online:21 January 2014Display full size Kai H. ChangKai H. Chang is a Professor and the chair of Computer Science and Software Engineering Department, Auburn University. He received his PhD degree in Electrical and Computer Engineering from University of Cincinnati in 1986. His research and educational interests are in the area of software testing, software quality assurance, artificial intelligence and computer science education. He is also recognised for his contributions to the software engineering education program by serving as an IEEE-Computer Society/ACM Curriculum Committee for Software Engineering (CCSE) member. An outlier mining algorithm based on constrained concept latticeAll authorsJifu Zhang, Sulan Zhang, Kai H. Chang & Xiao Qinhttps://doi.org/10.1080/00207721.2012.745029Published online:21 January 2014Display full size Xiao QinXiao Qin is an Associate Professor with the Department of Computer Science and Software Engineering, Auburn University. He received his PhD degree in Computer Science from the University of Nebraska-Lincoln in 2004. His research interests include data-intensive computing, parallel and distributed systems, storage systems and performance evaluation. He also has been on the program committees of various international conferences, including IEEE Cluster, IEEE International Performance, Computing and Communications Conference and International Conference on Parallel Processing. An outlier mining algorithm based on constrained concept latticeAll authorsJifu Zhang, Sulan Zhang, Kai H. Chang & Xiao Qinhttps://doi.org/10.1080/00207721.2012.745029Published online:21 January 2014Display full size