Local Subspace Classifier Research Articles

Anomaly Detection Method Based on Fast Local Subspace Classifier

SUMMARYAn anomaly detection method based on multidimensional time‐series sensor data and using normal state models has been developed. The local subspace classifier (LSC) method is employed to handle the various normal states and the fast LSC method is proposed to reduce the computation time. Clustering is utilized to reduce the amount of data when searching in the fast LSC (FLSC) method. The effectiveness of the FLSC method is confirmed against data from real equipment. The FLSC method is 1 to 10 times as fast as the LSC method.

Constrained subspace classifier for high dimensional datasets

Datasets with significantly larger number of features, compared to samples, pose a serious challenge in supervised learning. Such datasets arise in various areas including business analytics. In this paper, a new binary classification method called constrained subspace classifier (CSC) is proposed for such high dimensional datasets. CSC improves on an earlier proposed classification method called local subspace classifier (LSC) by accounting for the relative angle between subspaces while approximating the classes with individual subspaces. CSC is formulated as an optimization problem and can be solved by an efficient alternating optimization technique. Classification performance is tested in publicly available datasets. The improvement in classification accuracy over LSC shows the importance of considering the relative angle between the subspaces while approximating the classes. Additionally, CSC appears to be a robust classifier, compared to traditional two step methods that perform feature selection and classification in two distinct steps.

Anomaly Detection Method Based on Fast Local Subspace Classifier

An anomaly detection method based on multidimensional time-series sensor data and using normal state models has been developed. The local subspace classifier LSC method is employed to handle the various normal states and the fast LSC method is proposed to reduce the computation time. Clustering is utilized to reduce the amount of data when searching in the fast LSC FLSC method. The effectiveness of the FLSC method is confirmed against data from real equipment. The FLSC method is 1 to 10 times as fast as the LSC method.

Local Subspace Classifier with Transform-Invariance for Image Classification

A family of linear subspace classifiers called local subspace classifier (LSC) outperforms the k-nearest neighbor rule (kNN) and conventional subspace classifiers in handwritten digit classification. However, LSC suffers very high sensitivity to image transformations because it uses projection and the Euclidean distances for classification. In this paper, I present a combination of a local subspace classifier (LSC) and a tangent distance (TD) for improving accuracy of handwritten digit recognition. In this classification rule, we can deal with transform-invariance easily because we are able to use tangent vectors for approximation of transformations. However, we cannot use tangent vectors in other type of images such as color images. Hence, kernel LSC (KLSC) is proposed for incorporating transform-invariance into LSC via kernel mapping. The performance of the proposed methods is verified with the experiments on handwritten digit and color image classification.

Rough sets for enhancements of local subspace classifier

Developed recently local subspace classifier (LSC) based on local principal component analysis (LPCA) though has high performance (99.4% on NIST database of handwritten digits) lacks a mechanism of recovery from errors. Having confidence levels associated with the decision function in the classifier could help in creation of such procedure. In this paper it is shown how rough set idea can be used to incorporate confidence mechanism. In this way we make the algorithm more adequate to practical use as human actions are now possible at low confidence decisions. Besides main goal of the paper the necessary algorithmic tools for LPCA and their theoretical base are presented, too.

Introducing Locality and Softness in Subspace Classification

Subspace classifiers classify a pattern based on its distance from different vector subspaces. Earlier models of subspace classification were based on the assumption that individual classes lie in unique subspaces. In later extensions, locality was introduced into subspace classification allowing for a class to be associated with more than one sub manifold. The local subspace classifier is thus a piecewise linear classifier, and is more powerful when compared to the linear classification performed by global subspace methods. We present extensions to the basic subspace method of classification based on introducing locality and softness in the classification process. Locality is introduced by (subspace) clustering the patterns into clusters, and softness is introduced by allowing a pattern to be associated with more than one cluster. Our motivation for introducing both locality and softness is based on the premise that by introducing locality, it is possible to reduce the bias though at the cost of a possible increase in variance. By introducing softness (or aggregation), the variance can be reduced. Consequently, by introducing both locality and softness, we avoid the possibility of high variance that locality typically introduces. We derive appropriate algorithms to construct a local and soft model of subspace classifiers and present results obtained with the proposed algorithm.