期刊
IEEE SENSORS LETTERS
卷 6, 期 4, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSENS.2022.3156158
关键词
Sensor signal processing; Arduino Due microcontroller; cognitive activity prediction (CAP)/cognitive activity classification; convolutional neural network (CNN); electroencephalogram (EEG); TensorFlow lite
资金
- Indian Council of Medical Research (ICMR) [ICMR/ISRM/12(89)/2020/2020-3701]
In this study, a lightweight 1-D convolutional neural network method is proposed for predicting cognitive activity from electroencephalogram signals. The real-time recorded results demonstrate high prediction accuracy and low power consumption on resource-constrained edge devices.
Cognitive activity prediction (CAP) from electroencephalogram (EEG) signals is progressively utilized in the field of brain-computer interface (BCI) and mental health management. Various machine and deep learning methods have been proposed recently for CAP. However, since Internet-of-Things-based real-time BCI systems demand low latency, power, and portability, these methods need to be deployable on resource-constrained edge devices. Towards this aspect, we propose a real-time implementation of a lightweight 1-D convolutional neural network on an Arduino Due microcontroller for CAP from EEG signals. The performance evaluation on two public datasets and one real-time recorded dataset indicates that the proposed work achieves subject-independent prediction accuracies of 99.30%, 82.50%, and 99.02% in these datasets. Furthermore, the prediction of real-time recorded EEG signals is accurate for majority of the subjects. The proposed work outperforms the existing techniques and achieves low power consumption of 0.63 W in real-time on-device implementation with an average latency of 455.12 ms in model deployment, test output prediction, and activity-based transmission.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据