Online Rule-Based Classifier Learning on Dynamic Unlabeled Multivariate Time Series Data

Traditional classification learning algorithms have several limitations: 1) they are time consuming for the large-scale training multivariate time-series (MTS) data, and unsuitable for the dynamically added training data; 2) as the number of the training MTS data becomes larger, they could not achieve the desired classification accuracy; 3) most of them do not consider how to make use of the unlabeled samples to enhance the classifier performance; and 4) due to the high dimension of MTS and complex relationship among variables, existing online learning algorithms are not effective to update shapelet-based association rules. Up to now, few work touched online classification learning for dynamically added unlabeled examples. To efficiently address these issues, we propose an online rule-based classifier learning framework on dynamically added unlabeled MTS data (ORCL-U). This framework integrates a confidence-based labeling strategy (CLS) and an online rule-based classifier learning approach (ORBCL). Extensive experiments on ten datasets show the effectiveness and efficiency of our proposed approach.

Automated summary

Traditional classification learning algorithms have limitations in terms of time consumption for large-scale training multivariate time-series (MTS) data, inability to achieve desired classification accuracy with increasing training MTS data, lack of consideration for utilizing unlabeled samples to enhance classifier performance, and inefficiency in updating shapelet-based association rules. Few studies have addressed online classification learning for dynamically added unlabeled examples. To address these issues, this study proposes an online rule-based classifier learning framework that integrates a confidence-based labeling strategy and an online rule-based classifier learning approach. Extensive experiments on ten datasets demonstrate the effectiveness and efficiency of the proposed approach.