Dalin Zhang

TL;DR: This study presents a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition and proposes a new taxonomy to structure the deep methods by challenges.

TL;DR: This paper proposes a pattern-balanced semisupervised framework to extract and preserve diverse latent patterns of activities from multimodal wearable sensory data, and exploits the independence of multi-modalities of sensory data and attentively identify salient regions that are indicative of human activities from inputs by the authors' recurrent convolutional attention networks.

TL;DR: Two deep learning-based frameworks with novel spatio-temporal preserving representations of raw EEG streams to precisely identify human intentions are introduced with high accuracy and outperform a set of state-of-the-art and baseline models.

TL;DR: A convolutional recurrent attention model (CRAM) that utilizes a convolutionAL neural network to encode the high-level representation of EEG signals and a recurrent attention mechanism to explore the temporal dynamics of the EEG signals as well as to focus on the most discriminative temporal periods is presented.

TL;DR: Both cascade and parallel convolutional recurrent neural network models for precisely identifying human intended movements and instructions by effectively learning the compositional spatio-temporal representations of raw EEG streams are introduced.