Patterns of time-interval based patterns for improved multivariate time series data classification

In recent years, computational advancements have contributed to a significant increase in the volume and availability of multivariate time series data (MTSD). The ability to make use of MTSD is challenging, as it often suffers from missing values, random noise, varied sampling rates, and temporal granularities. In the modern era of machine learning, learning frameworks must accurately capture the data's temporal structure and have high generalization capabilities, as well as provide interpretability and explainability regarding its decisions. The use of temporal abstractions (TAs) and interval-based temporal patterns (TPs) has been proposed for learning from MTSD, overcoming existing challenges, and achieving state-of-the-art results on various tasks, however, improvements are needed in terms of the generalization capabilities and decision explainability. In this paper, we propose a novel interval-based method, Inter-Rel, which provides an additional layer of learning that exploits the temporal relations among the discovered interval-based TPs, enhances the feature space, and improves explanatory capabilities by shedding light on the relations between the TPs over time. To evaluate the effectiveness and additional benefits provided by Inter-Rel, we evaluate our method on various learning tasks and domains such as early sepsis detection; electroencephalogram-based (EEG-based) subject classification; and the categorization of malicious portable executables based on dynamic analysis. The experimental results demonstrate that Inter-Rel's use enhances classification performance by up to 16% in terms of area under the curve (AUC) or accuracy (depending on the task) while providing additional explanatory capabilities that can be leveraged by a domain expert.