No abstract

Humans are able to localize the source of a sound. This enables them to direct attention to a particular speaker in a cocktail party. Psycho-acoustic studies show that the sensory cortices of the human brain respond to the location of sound sources differently, and the auditory attention itself is a dynamic and temporally based brain activity. In this work, we seek to build a computational model which uses both spatial and temporal information manifested in EEG signals for auditory spatial attention detection (ASAD). Methods: We propose an endto-end spatiotemporal attention network, denoted as STAnet, to detect auditory spatial attention from EEG. The STAnet is designed to assign differentiated weights dynamically to EEG channels through a spatial attention mechanism, and to temporal patterns in EEG signals through a temporal attention mechanism. Results: We report the ASAD experiments on two publicly available datasets. The STAnet outperforms other competitive models by a large margin under various experimental conditions. Its attention decision for 1-second decision window outperforms that of the state-ofthe-art techniques for 10-second decision window. Experimental results also demonstrate that the STAnet achieves competitive performance on EEG signals ranging from 64 to as few as 16 channels. Conclusion: This study provides evidence suggesting that efficient low-density EEG online decoding is within reach. Significance: This study also marks an important step towards the practical implementation of ASAD in real life applications.

Background Compensations are commonly observed in patients with stroke when they engage in reaching without supervision; these behaviors may be detrimental to long-term functional improvement. Automatic detection and reduction of compensation cab help patients perform tasks correctly and promote better upper extremity recovery. Objective Our first objective is to verify the feasibility of detecting compensation online using machine learning methods and pressure distribution data. Second objective was to investigate whether compensations of stroke survivors can be reduced by audiovisual or force feedback. The third objective was to compare the effectiveness of audiovisual and force feedback in reducing compensation. Methods Eight patients with stroke performed reaching tasks while pressure distribution data were recorded. Both the offline and online recognition accuracy were investigated to assess the feasibility of applying a support vector machine (SVM) based compensation detection system. During reduction of compensation, audiovisual feedback was delivered using virtual reality technology, and force feedback was delivered through a rehabilitation robot. Results Good classification performance was obtained in online compensation recognition, with an average F1-score of over 0.95. Based on accurate online detection, real-time feedback significantly decreased compensations of patients with stroke in comparison with no-feedback condition (p < 0.001). Meanwhile, the difference between audiovisual and force feedback was also significant (p < 0.001) and force feedback was more effective in reducing compensation in patients with stroke. Conclusions Accurate online recognition validated the feasibility of monitoring compensations using machine learning algorithms and pressure distribution data. Reliable online detection also paved the way for reducing compensations by providing feedback to patients with stroke. Our findings suggested that real-time feedback could be an effective approach to reducing compensatory patterns and force feedback demonstrated a more enviable potential compared with audiovisual feedback.

Objectives: Compensations are commonly employed by patients with stroke during rehabilitation without therapist supervision, leading to suboptimal recovery outcomes. This study investigated the feasibility of the realtime monitoring of compensation in patients with stroke by using pressure distribution data and machine learning algorithms. Whether trunk compensation can be reduced by combining the online detection of compensation and haptic feedback of a rehabilitation robot was also investigated. Methods: Six patients with stroke did three forms of reaching movements while pressure distribution data were recorded as Dataset1. A support vector machine (SVM) classifier was trained with features extracted from Dataset1. Then, two other patients with stroke performed reaching tasks, and the SVM classifier trained by Dataset1 was employed to classify the compensatory patterns online. Based on the real-time monitoring of compensation, a rehabilitation robot provided an assistive force to patients with stroke to reduce compensations. Results: Good classification performance (F1 score > 0.95) was obtained in both offline and online compensation analysis using the SVM classifier and pressure distribution data of patients with stroke. Based on the real-time detection of compensatory patterns, the angles of trunk rotation, trunk lean-forward and trunk-scapula elevation decreased by 46.95%, 32.35% and 23.75%, respectively. Conclusion: High classification accuracies verified the feasibility of detecting compensation in patients with stroke based on pressure distribution data. Since the validity and reliability of the online detection of compensation has been verified, this classifier can Manuscript

No abstract