An Improved Self-Training Method for Positive Unlabeled Time Series Classification Using DTW Barycenter Averaging

A Novel Classification Method: Neighborhood-Based Positive Unlabeled Learning Using Decision Tree (NPULUD)

In a standard binary supervised classification task, the existence of both negative and positive samples in the training dataset are required to construct a classification model. However, this condition is not met in certain applications where only one class of samples is obtainable. To overcome this problem, a different classification method, which learns from positive and unlabeled (PU) data, must be incorporated. In this study, a novel method is presented: neighborhood-based positive unlabeled learning using decision tree (NPULUD). First, NPULUD uses the nearest neighborhood approach for the PU strategy and then employs a decision tree algorithm for the classification task by utilizing the entropy measure. Entropy played a pivotal role in assessing the level of uncertainty in the training dataset, as a decision tree was developed with the purpose of classification. Through experiments, we validated our method over 24 real-world datasets. The proposed method attained an average accuracy of 87.24%, while the traditional supervised learning approach obtained an average accuracy of 83.99% on the datasets. Additionally, it is also demonstrated that our method obtained a statistically notable enhancement (7.74%), with respect to state-of-the-art peers, on average.

Improved LDTW Algorithm Based on the Alternating Matrix and the Evolutionary Chain Tree

Dynamic time warping under limited warping path length (LDTW) is a state-of-the-art time series similarity evaluation method. However, it suffers from high space-time complexity, which makes some large-scale series evaluations impossible. In this paper, an alternating matrix with a concise structure is proposed to replace the complex three-dimensional matrix in LDTW and reduce the high complexity. Furthermore, an evolutionary chain tree is proposed to represent the warping paths and ensure an effective retrieval of the optimal one. Experiments using the benchmark platform offered by the University of California-Riverside show that our method uses 1.33% of the space, 82.7% of the time used by LDTW on average, which proves the efficiency of the proposed method.