Classification of multivariate weakly-labelled time-series with attention
This addresses a gap in weakly-labelled time-series classification for applications like EEG analysis, but it appears incremental as it adapts existing attention and CNN methods to this specific domain.
The paper tackles the problem of classifying weakly-labelled multivariate time-series, which are noisy and redundant, by proposing an approach that exploits context relevance of subsequences to improve accuracy. It experiments with attention algorithms combined with CNN models (FCN and ResNet) in a CNN-LSTM architecture, evaluating on a multivariate EEG dataset from driving activities.
This research identifies a gap in weakly-labelled multivariate time-series classification (TSC), where state-of-the-art TSC models do not per-form well. Weakly labelled time-series are time-series containing noise and significant redundancies. In response to this gap, this paper proposes an approach of exploiting context relevance of subsequences from previous subsequences to improve classification accuracy. To achieve this, state-of-the-art Attention algorithms are experimented in combination with the top CNN models for TSC (FCN and ResNet), in an CNN-LSTM architecture. Attention is a popular strategy for context extraction with exceptional performance in modern sequence-to-sequence tasks. This paper shows how attention algorithms can be used for improved weakly labelledTSC by evaluating models on a multivariate EEG time-series dataset obtained using a commercial Emotiv headsets from participants performing various activities while driving. These time-series are segmented into sub-sequences and labelled to allow supervised TSC.